CN111860146B

CN111860146B - Ocean front region acquisition method and device, computer equipment and storage medium

Info

Publication number: CN111860146B
Application number: CN202010528843.4A
Authority: CN
Inventors: 任磊; 姬进财; 潘广维; 杨清书
Original assignee: Sun Yat Sen University
Current assignee: Sun Yat Sen University
Priority date: 2020-06-11
Filing date: 2020-06-11
Publication date: 2023-06-09
Anticipated expiration: 2040-06-11
Also published as: CN111860146A

Abstract

The application relates to a method, a device, computer equipment and a storage medium for acquiring a ocean front area. The method comprises the following steps: determining a rough estimated ocean front area, target paths of a plurality of unmanned ships reaching the rough estimated ocean front area and target time lengths reaching the rough estimated ocean front area along the target paths according to the acquired satellite remote sensing observation data; determining each initial position of each unmanned ship in the roughly estimated ocean front area according to the received confirmation arrival information sent when each unmanned ship arrives at the roughly estimated ocean front area; outputting an adjustment instruction according to the region change information of the roughly estimated ocean front region determined by the received multiple groups of satellite remote sensing observation data in the target time length to instruct each unmanned ship to adjust based on the corresponding initial position, so as to obtain the adjusted position of each unmanned ship; and determining the target ocean front area according to the received adjusted positions. By adopting the method, the identification accuracy of the ocean front area in the sea area can be improved.

Description

Ocean front region acquisition method and device, computer equipment and storage medium

Technical Field

The present disclosure relates to the field of ocean front identification technologies, and in particular, to a method and an apparatus for acquiring an ocean front area, a computer device, and a storage medium.

Background

The narrow junction zone between two or more water bodies with obviously different properties in the ocean is called an ocean front, and the ocean front is a transition zone of ocean environment parameters and can be described by elements such as seawater temperature, salinity, density, speed, color, chlorophyll and the like; the scale of the ocean front can reach hundreds of kilometers, the ocean front exists in the surface layer, the middle layer and the bottom layer of the ocean, and the strong turbulence mixed exchange, the horizontal irradiance (irradiance) and the vertical movement existing in the frontal area of the ocean front not only affect shipping and fishery, but also affect activities such as underwater communication, ship safety, maritime search and rescue and the like, so that the accurate identification of the ocean front is one of the problems to be solved in the current urgent need.

In the conventional technology, when a gradient threshold method is used for identifying a ocean front area in a sea area, reasonable thresholds are set according to different standards of different parameters (such as temperature and salinity) in the sea area, so that the ocean front area is identified according to the reasonable thresholds.

However, the current traditional method is difficult to set reasonable threshold values for different sea areas and different seasons, so that the identification accuracy of the ocean front area in the sea area is not high.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a method, an apparatus, a computer device, and a storage medium for acquiring a ocean front area capable of improving the accuracy of identifying the ocean front area in a sea area.

A method of acquiring a ocean front region, the method comprising:

acquiring satellite remote sensing observation data, and determining a rough estimated ocean front area according to the satellite remote sensing observation data; the satellite remote sensing observation data comprise at least one of a water color value, a temperature value, a salinity value, a chlorophyll concentration value and a suspended sediment concentration value of a sea area to be identified;

determining target paths of a plurality of unmanned ships to be dispatched to reach the roughly estimated ocean front area and target time lengths of the unmanned ships to reach the roughly estimated ocean front area along the target paths according to the satellite remote sensing observation data; the target path is used for representing the shortest path of the unmanned ships to reach the roughly estimated ocean front area;

determining each initial position of each unmanned ship in the roughly estimated ocean front area according to the received confirmation arrival information sent when each unmanned ship arrives at the roughly estimated ocean front area;

Determining the regional variation information of the roughly estimated ocean front region according to a plurality of groups of satellite remote sensing observation data received in the target duration;

outputting an adjustment instruction according to the region change information to instruct each unmanned ship to adjust based on the corresponding initial position, so as to obtain an adjusted position of each unmanned ship;

and determining a target ocean front area according to the received adjusted positions.

In one embodiment, the method further comprises:

acquiring a plurality of groups of satellite remote sensing observation data at different moments in the target duration;

determining a plurality of rough estimation ocean front areas according to the plurality of groups of satellite remote sensing observation data;

and carrying out interpolation fitting processing on the plurality of rough estimation ocean frontal areas according to the plurality of different moments to obtain the area change information.

In one embodiment, the method further comprises:

determining the area estimation value and the frontal line length of the roughly estimated ocean frontal area according to the satellite remote sensing observation data;

determining the number of unmanned ships to be dispatched according to the area estimated value and the first ratio result of the frontal surface line length;

determining a plurality of linear distances between each unmanned ship and each preset vertex position of the rough estimated ocean front area, and selecting the smallest linear distance among the plurality of linear distances corresponding to each unmanned ship as a target path for the unmanned ship to reach the rough estimated ocean front area;

And obtaining the maximum speed per hour of the unmanned ships and warships, and taking the second ratio result of the target path of the unmanned ships reaching the roughly estimated ocean front area to the maximum speed per hour as the target duration.

In one embodiment, further comprising:

according to the satellite remote sensing observation data, determining a visual area distribution map of the roughly estimated ocean front area;

according to the position coordinates of each vertex of the visual area distribution diagram, carrying out calibration processing of a regular graph on the visual area distribution diagram to obtain a target rectangular frame containing the visual area distribution diagram;

determining an area estimation value of the roughly estimated ocean front area corresponding to the target rectangular frame;

and dividing the contour line of the visual regional distribution map into a plurality of contour points, and linearly superposing the distances between two adjacent contour points to obtain the length of the frontal surface line.

In one embodiment, further comprising:

inversion processing is carried out on the satellite remote sensing observation data to obtain a sea area distribution diagram of the sea area to be identified;

if the sea area distribution diagram meets a prestored interface determination condition, determining that an interface existing in the sea area distribution diagram is the roughly estimated sea front area;

And carrying out visual treatment on the roughly estimated ocean front area to obtain a visual area distribution map of the roughly estimated ocean front area.

A method of predicting a marine front region, the method comprising:

outputting instrument layout instructions according to the target ocean front area; the instrument layout instruction is used for indicating that a plurality of detection instruments are arranged in a crossing mode according to a preset distance interval;

acquiring sea area observation elements detected by the detecting instrument, and performing cleaning treatment operation on the acquired sea area observation elements to obtain cleaned observation elements; the sea area observation elements comprise humidity, salinity, temperature, wind speed, wind direction, flow speed, wave height, wave direction, wave period, water depth and navigational speed of the sea area to be observed;

performing feature selection processing on the observation elements after the cleaning processing by using a support vector machine recursion feature elimination method to obtain target features;

inputting the target characteristics and the set time into a preset ocean front prediction model to obtain a predicted ocean front region of the target ocean front region at the preset time; the preset ocean front prediction model comprises a model which is used for training a random forest model by using the target characteristics and is well trained;

And carrying out visualization processing on the predicted ocean front area to obtain a predicted area visualization image of the predicted ocean front area.

In one embodiment, further comprising:

taking the target features as the input of a random forest model, and carrying out model training by combining with the sensitive parameter initial values of the random forest model to obtain a preliminary result after model training;

determining different groups of values of the sensitive parameters according to the preliminary result, and determining different root mean square errors between the predicted value and the actual observed value of the random forest model after the different groups of values and the target feature verification;

and sequencing the different root mean square errors, and taking a random forest model corresponding to the smallest root mean square error as the preset ocean front prediction model.

A system for acquiring a region of a ocean front, the system comprising: the system comprises a processor and an unmanned ship formation controller, wherein the processor and the unmanned ship formation controller are respectively arranged in a land base station of a sea area to be identified, and the processor is electrically connected with the unmanned ship formation controller;

the processor is used for acquiring satellite remote sensing observation data and determining a rough estimated ocean front area according to the satellite remote sensing observation data; determining target paths of a plurality of unmanned ships to be dispatched to reach the roughly estimated ocean front area and target time lengths of the unmanned ships to reach the roughly estimated ocean front area along the target paths according to the satellite remote sensing observation data; determining each initial position of each unmanned ship in the roughly estimated ocean front area according to the received confirmation arrival information sent when each unmanned ship arrives at the roughly estimated ocean front area; determining the regional variation information of the roughly estimated ocean front region according to a plurality of groups of satellite remote sensing observation data received in the target duration; outputting an adjustment instruction according to the region change information to instruct each unmanned ship to adjust based on the corresponding initial position, so as to obtain an adjusted position of each unmanned ship; determining a target ocean front area according to the received adjusted positions; the satellite remote sensing observation data comprises at least one of a water color value, a temperature value, a salinity value, a chlorophyll concentration value and a suspended sediment concentration value of a sea area to be identified, and the target path is used for representing the shortest path of the unmanned ships to the roughly estimated ocean front area;

And the unmanned naval vessel formation controller is used for controlling the unmanned naval vessels with corresponding quantity to run according to the quantity of the unmanned naval vessels to be dispatched.

An acquisition device for a marine front region, the device comprising:

the first determining module is used for acquiring satellite remote sensing observation data and determining a rough estimated ocean front area according to the satellite remote sensing observation data; the satellite remote sensing observation data comprise at least one of a water color value, a temperature value, a salinity value, a chlorophyll concentration value and a suspended sediment concentration value of a sea area to be identified;

the second determining module is used for determining target paths of a plurality of unmanned ships to be dispatched to reach the roughly estimated ocean front area and target time lengths of the unmanned ships to reach the roughly estimated ocean front area along the target paths according to the satellite remote sensing observation data; the target path is used for representing the shortest path of the unmanned ships to reach the roughly estimated ocean front area;

the third determining module is used for determining each initial position of each unmanned ship in the rough estimated ocean front area according to the received confirmation arrival information sent when each unmanned ship arrives at the rough estimated ocean front area;

The fourth determining module is used for determining the region change information of the roughly estimated ocean front region according to a plurality of groups of satellite remote sensing observation data received in the target time length;

the adjusting module is used for outputting an adjusting instruction according to the region change information so as to instruct each unmanned ship to adjust based on the corresponding initial position, and the adjusted position of each unmanned ship is obtained;

and a fifth determining module, configured to determine a target ocean front area according to the received adjusted positions.

A prediction apparatus for a marine front region, the apparatus comprising:

the instruction output module is used for outputting instrument layout instructions according to the target ocean front area in the ocean front area acquisition method; the instrument layout instruction is used for indicating that a plurality of detection instruments are arranged in a crossing mode according to a preset distance interval;

the cleaning processing module is used for acquiring the sea area observation elements detected by the detecting instrument, and performing cleaning processing operation on the acquired sea area observation elements to obtain the observation elements after cleaning processing; the sea area observation elements comprise humidity, salinity, temperature, wind speed, wind direction, flow speed, wave height, wave direction, wave period, water depth and navigational speed of the sea area to be observed;

The feature selection module is used for performing feature selection processing on the observation elements after the cleaning processing by using a support vector machine recursion feature elimination method to obtain target features;

the prediction module is used for inputting the target characteristics and the set time into a preset ocean front prediction model to obtain a predicted ocean front area of the target ocean front area at the preset time; the preset ocean front prediction model comprises a model which is used for training a random forest model by using the target characteristics and is well trained;

and the visualization processing module is used for carrying out visualization processing on the predicted ocean front area to obtain a predicted area visualization image of the predicted ocean front area.

A computer device comprising a memory storing a computer program and a processor which when executing the computer program performs the steps of:

A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:

The method for acquiring the ocean front region comprises the steps of firstly determining the rough estimated ocean front region according to the acquired satellite remote sensing observation data, wherein the satellite remote sensing observation data comprise at least one index data of a water color value, a temperature value, a salinity value, a chlorophyll concentration value and a suspended sediment concentration value of a sea area to be identified, so that the purpose of determining the rough estimated ocean front region according to two or more index data in the satellite remote sensing observation data can be realized, and the defects of large identification difficulty and single mode caused by the fact that the ocean front region can be identified only after threshold values are set according to different index numbers in the traditional technology are avoided, and the flexibility and timeliness of determining the rough estimated ocean front region are improved; further, according to the satellite remote sensing observation data, determining target paths of a plurality of unmanned ships to be dispatched to the rough estimated ocean front area and target time lengths of the unmanned ships to reach the rough estimated ocean front area along the target paths, so that the problem that the identification accuracy of the ocean front area is low due to the fact that the traditional technology can only judge whether the ocean front exists in the sea area or not is solved, and a foundation is laid for obtaining the accurate ocean front area subsequently; then determining each initial position of each unmanned ship in the roughly estimated ocean front area according to the received confirmation arrival information sent when each unmanned ship arrives at the roughly estimated ocean front area; determining the regional variation information of the roughly estimated ocean front region according to a plurality of groups of satellite remote sensing observation data received in the target time length, so as to achieve the purpose of capturing the development variation of the roughly estimated ocean front region in real time in the target time length, and providing a basis for the follow-up determination of an accurate ocean front region; outputting an adjustment instruction according to the region change information to instruct each unmanned ship to adjust based on the corresponding initial position, so as to obtain an adjusted position of each unmanned ship; and determining a target ocean front area according to the received adjusted positions. The method has the advantages that the purposes that the initial positions of the unmanned ships can be adjusted in real time according to the region change information when the unmanned ships arrive at the roughly estimated ocean front region and the ocean front region can be accurately positioned according to the adjusted positions are achieved, the defect that the identification method for identifying the ocean front region by taking a large amount of ocean front identification priori information about the sea region as reference information in the traditional technology does not have low reusability and universality is overcome, and the reusability and universality of identifying the ocean front region are improved; and further, the initial positions of the unmanned ships are adjusted according to the region change information of the roughly estimated ocean front region in the target duration, so that the roughly estimated ocean front region is repositioned according to the adjusted positions to obtain an accurate ocean front region, and the accuracy and the reliability of determining the target ocean front region are improved.

Drawings

FIG. 1 is a schematic view of a ocean front;

FIG. 2 is a flow chart of a method of acquiring ocean front area in one embodiment;

FIG. 3 is a flow chart of a method for acquiring ocean front area in another embodiment;

FIG. 4 is a flow chart of a method of acquiring ocean front area according to yet another embodiment;

FIG. 5 is a flow chart of a method of acquiring ocean front area in yet another embodiment;

FIG. 6 is a flow chart of a method of predicting ocean front area in one embodiment;

FIG. 7 is a block diagram of an acquisition device of the ocean front area in one embodiment;

FIG. 8 is a block diagram of a prediction apparatus for ocean front area in one embodiment;

FIG. 9 is an internal block diagram of the ocean front area acquisition system in one embodiment;

fig. 10 is an internal structural view of a computer device in one embodiment.

Detailed Description

The narrow zone of intersection between two or more bodies of water of substantially different properties in the ocean is known as the ocean front, as shown in figure 1, and the ocean front is the zone of jump in the ocean environment parameters, which can be described by elements such as sea water temperature, salinity, density, velocity, colour, chlorophyll, etc. The ocean front can reach hundreds of kilometers in scale and exists on the surface layer, the middle layer and the bottom layer of the ocean. The strong turbulent mixing exchanges, horizontal irradiance (irradiance) and vertical movement present in the frontal region. The ocean front motions not only affect shipping and fishery, but also are used for activities such as underwater communication, ship safety, maritime search and rescue and the like; the accurate real-time identification of the ocean front is a key for coping with the problems, the traditional ocean front identification method is a gradient threshold method, and as different parameters (such as temperature, salinity and the like) have different standards, even if the parameters are the same, different sea areas and different seasons, the dividing and defining standards have differences, so that the gradient threshold method is difficult to determine reasonable thresholds; the current method can only judge whether the ocean front exists in the target sea area, and can not identify the morphological details of the ocean front; in addition, the existing ocean front identification method can be used for carrying out ocean front identification of local sea areas, but the problem that the identification standards of non-local sea areas are not uniform exists. In the prior art, a great deal of experience is summarized to provide reference information for sea area division, and the methods have no reusable property for different sea areas, so the methods have no good universality; moreover, the current knowledge of the ocean front is mostly limited to its identification, but there are fewer prediction methods established based on the identification features.

Aiming at the problems in the prior art, the application provides a method, a device, computer equipment and a storage medium for acquiring a ocean front area. In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

According to the ocean front region acquiring method, an execution main body can be an ocean front region acquiring device, and the ocean front region acquiring device can be realized to be part or all of computer equipment in a mode of software, hardware or combination of software and hardware. Optionally, the computer device may be an electronic device with a processor function, such as a personal computer (Persodal Computer, PC), a portable device, a notebook computer, a smart phone, a tablet computer, a portable wearable device, etc., for example, a tablet computer, a mobile phone, etc., and the embodiment of the present application does not limit a specific form of the computer device.

It should be noted that, the execution subject of the method embodiments described below may be part or all of the above-mentioned computer device. The following method embodiments are described taking an execution subject as a computer device as an example.

In one embodiment, as shown in fig. 2, a method for acquiring a ocean front area is provided, which includes the following steps:

s11, acquiring satellite remote sensing observation data, and determining a rough estimated ocean front area according to the satellite remote sensing observation data; the satellite remote sensing observation data comprise at least one of a water color value, a temperature value, a salinity value, a chlorophyll concentration value, a suspended sediment concentration value and the like of a sea area to be identified.

The water color value of the sea area to be identified can be determined by the optical property of the sea water, suspended matters contained in the sea water, the depth of the sea water, the characteristics of cloud layers and other factors; the salinity value may comprise the ratio of total dissolved solids in the seawater to the weight of the seawater, typically expressed in grams per kilogram of seawater; the chlorophyll concentration values may include chlorophyll concentration values of different layers of the sea area to be identified, such as a surface layer, a subsurface layer, a middle layer, and a bottom layer, and the chlorophyll concentration values may be determined together by factors such as ocean water temperature environment, nutrient salt distribution, and phytoplankton species; the suspended sediment concentration value can represent the sediment content in sea areas generated by a plurality of factors such as sediment sources, flow system growth, flow velocity strength, stormy waves and the like, and can change along with at least one of season, big tide and rising and falling tide, for example, the sediment content in small tide is higher than that in big tide, the sediment content in falling tide is higher than that in rising tide, the sediment content in winter and spring is relatively high, and the sediment content in summer and autumn is relatively low.

Specifically, when the satellite remote sensing observation data is obtained, the computer equipment can set that the water color value, the temperature value, the salinity value, the chlorophyll concentration value and the suspended sediment concentration value included in the satellite remote sensing observation data are respectively different index data, then select one of the index data (such as the salinity value) in the remote sensing observation data to perform inversion processing and/or visualization processing to obtain a salinity visual distribution map, compare the salinity visual distribution map with a prestored interface determination condition, determine the first target interface as a rough estimated ocean front area when a first target interface matched with the interface determination condition exists in the salinity visual distribution map, for example, determine that a narrow band is the first target interface when the salinity difference of the seawater on two sides of a narrow band in the salinity visual distribution map is greater than or equal to a preset salinity difference threshold, and determine that no area to be identified exists if the salinity difference of the seawater on two sides of the narrow band is smaller than the preset difference threshold.

Then, selecting another index data (such as a suspended sediment concentration value) from the satellite remote sensing observation data, performing inversion processing and/or visualization processing to obtain a suspended sediment concentration visualization distribution map, performing the same matching operation on the suspended sediment concentration visualization distribution map and a prestored interface determination condition, determining a second target interface existing in the suspended sediment concentration visualization distribution map, comparing the first target interface with the second target interface, judging that the first target interface is reasonable if the coincidence degree of the first target interface and the second target interface is higher than a preset coincidence degree threshold value, selecting a third index data (such as a water color value) in the satellite remote sensing observation data, performing inversion processing and/or visualization processing on the basis of a difference point or area of the first two index data (such as a salinity value and a suspended sediment concentration value) to obtain a water color visualization distribution map, and judging that whether the coincidence degree of the first target interface and the second target interface is higher than the preset coincidence degree threshold value or not through the same operation; and determining that the first target interface is a rough estimated ocean front area at the moment until the coincidence degree of the target interface determined based on the previous index data and the target interface determined based on the current index data is higher than a preset coincidence degree threshold value. Wherein the rough estimate ocean front area may comprise an area formed by at least two contour lines. Alternatively, the fitness threshold may be 80%.

Step S12, determining target paths of a plurality of unmanned ships to be dispatched reaching the rough estimated ocean front area and target time lengths reaching the rough estimated ocean front area along the target paths according to the satellite remote sensing observation data; wherein the target path is used to characterize a shortest path for the plurality of unmanned vessels to reach the rough estimate ocean front area.

Specifically, as shown in fig. 3, the computer device may determine the target path and the target duration by the sub-steps of:

and step S121, determining the area estimation value and the frontal line length of the roughly estimated ocean front area according to the satellite remote sensing observation data.

Wherein, as shown in fig. 4, the process of determining the area estimation value and the frontal line length by the computer device may comprise:

step S1211, determining a visual area distribution map of the rough estimated ocean front area according to the satellite remote sensing observation data.

In particular, the process of the computer device determining the visual zone profile of the rough estimate of the ocean front zone may comprise: firstly, carrying out inversion processing on the satellite remote sensing observation data to obtain a sea area distribution map of the sea area to be identified; if the sea area distribution diagram meets a prestored interface determination condition, determining that an interface existing in the sea area distribution diagram is the roughly estimated sea front area; and carrying out visual treatment on the roughly estimated ocean front area to obtain a visual area distribution map of the roughly estimated ocean front area.

In the actual processing process, the process of determining the rough estimated ocean front area by the computer device according to the satellite remote sensing observation data is the same as the determining process of the rough estimated ocean front area in step S11, and will not be described in detail here. And, the visual zone profile of the rough estimate ocean front zone determined by the computer device may include visual contours forming at least two contours of the rough estimate ocean front zone.

And S1212, performing regular graph calibration processing on the visual regional distribution map according to the position coordinates of each vertex of the visual regional distribution map to obtain a target rectangular frame containing the visual regional distribution map.

Specifically, when determining the visual area distribution diagram of the roughly estimated ocean front area, the computer device may first obtain a topographic map of the visual area distribution diagram, then determine, according to the topographic map, each vertex position coordinate of the roughly estimated ocean front area, where each vertex position coordinate may include M coordinate positions of M vertices of the roughly estimated ocean front area, then select M vertices of the roughly estimated ocean front area, and determine, in a calibration manner (such as a rectangular frame calibration manner) of a regular image, a target rectangular frame including the visual area distribution diagram, where the target rectangular frame may also be a rectangular frame including the roughly estimated ocean front area. Wherein M is a positive integer. Alternatively, the value of M may be 4.

And step S1213, determining an area estimation value of the roughly estimated ocean front area corresponding to the target rectangular frame.

Specifically, when determining the target rectangular frame containing the visual area distribution diagram, the computer device may further determine an area value of the target rectangular frame, and use the area value of the target rectangular frame as the area estimation value of the rough estimated ocean front area.

And step S1214, dividing the contour line of the visual area distribution map into a plurality of contour points, and linearly superposing the distances between two adjacent contour points to obtain the frontal surface line length.

Specifically, when determining the visual area distribution diagram of the rough estimated ocean front area, that is, the visual contour lines forming at least two contour lines of the rough estimated ocean front area included in the visual area distribution diagram of the rough estimated ocean front area, the computer device may further uniformly divide each visual contour line into a plurality of contour points according to a preset distance interval, calculate a distance between every two adjacent contour points, and then linearly superimpose the calculated distances to obtain a frontal surface line length of the rough estimated ocean front area.

And step S122, determining the number of unmanned ships to be dispatched according to the area estimated value and the first ratio result of the frontal surface line length.

Specifically, when determining the area estimated value and the frontal surface line length of the roughly estimated ocean front area, the computer device may further determine a first ratio result of the area estimated value and the frontal surface line length, and determine the number of unmanned ships to be dispatched according to the first ratio result, that is, a first target ratio obtained by rounding the first ratio result, as the number of unmanned ships to be dispatched. Alternatively, when the first target ratio obtained by rounding the first ratio result is smaller than 2, it may be determined that 2 unmanned ships are to be dispatched.

Step S123, determining a plurality of linear distances between each unmanned ship and each preset vertex position of the rough estimated ocean front area, and selecting a smallest linear distance among the plurality of linear distances corresponding to each unmanned ship as a target path for the unmanned ship to reach the rough estimated ocean front area.

Specifically, when the number of unmanned ships to be dispatched is determined, for example, when the number of unmanned ships to be dispatched is P, the computer device may set the P unmanned ships to be at the same starting point, set each vertex coordinate position of the roughly estimated ocean front area as each preset vertex position, for example, the number of preset vertex positions of the device is T, calculate the straight line distance between the starting point and each preset vertex position, thereby obtaining T straight line distances, at this time, rank the T straight line distances according to different distance values, select the straight line distance with the smallest distance value from the T straight line distances after the ranking, and use the straight line distance with the smallest selected distance value as the target path of the unmanned ships to reach the roughly estimated ocean front area. For example, when the P unmanned ships are at the same starting point O and the preset vertex positions include the coordinate positions of A, B, C, D, calculating OA, OB, OC, OD a linear distance, and taking the linear distance with the smallest distance value in the linear distances of OA, OB, OC, OD as the target path of the unmanned ship to the rough estimate ocean front area.

Step S124, obtaining the maximum speed of the unmanned ships and warships, and taking the second ratio result of the target path of the unmanned ships reaching the roughly estimated ocean front area to the maximum speed as the target duration.

Specifically, when the computer device determines that the number of unmanned ships to be dispatched is P, it may further determine, according to the number of unmanned ships to be dispatched and the weight of each unmanned ship, a target carrier device that may carry P unmanned ships, for example, the target carrier device may be a large ship, and the carrier time speed of the target carrier device may be greater than the maximum ship time speed in the P unmanned ships. And then taking the carrier speed per hour of the target carrier equipment as the maximum speed per hour of the unmanned ships and warships, and further determining a second ratio result of the target path of the unmanned ships to the roughly estimated ocean front area to the maximum speed per hour, so as to take the second ratio result as the target time length of the plurality of unmanned ships to the roughly estimated ocean front area.

And S13, determining each initial position of each unmanned ship in the roughly estimated ocean front area according to the received confirmation arrival information sent when each unmanned ship arrives at the roughly estimated ocean front area.

Specifically, when the number of unmanned ships to be dispatched is determined to be P by the computer device, a marine front area detection instruction may be sent to the unmanned ship formation controller, and the marine front area detection instruction carries the number of unmanned ships to be dispatched, the target carrier device carrying the P unmanned ships, the maximum speed of the target carrier device, the target path of the plurality of unmanned ships to be dispatched reaching the rough estimated marine front area, and the target time length of reaching the rough estimated marine front area along the target path, where the unmanned ship formation controller may control the target carrier device carrying the P unmanned ships to reach the rough estimated marine front area along the target path when the target time length, and send acknowledgement arrival information to the marine computer device, where the acknowledgement arrival information may be used to characterize that the P unmanned ships have reached a vertex position in the rough estimated marine front area.

When the computer equipment receives the confirmation arrival information sent by the unmanned ship formation controller, each initial position of each unmanned ship in the rough estimated ocean front area can be determined, namely when the number of unmanned ships to be dispatched is P, each initial position of each unmanned ship in the rough estimated ocean front area can be determined at equal intervals according to the frontal line length of the rough estimated ocean front area, and position instruction information carrying the P unmanned ships in each initial position of the rough estimated ocean front area is sent to the unmanned ship formation controller, so that the unmanned ship formation controller controls each unmanned ship to travel to the corresponding initial position in the rough estimated ocean front area.

In the actual processing process, the land base station of the sea area to be identified can comprise a remote controller, a carrier PC (personal computer) of a control platform and a communication tool, a plurality of unmanned ships can be stored in the land base station, and each unmanned ship can comprise the unmanned ship, a GPS (global positioning system), an inertial navigation unit and other sensors carried on the unmanned ship, a radio station and other communication transmission equipment.

And S14, determining the regional variation information of the roughly estimated ocean front region according to the plurality of groups of satellite remote sensing observation data received in the target time.

Specifically, as shown in fig. 5, the computer device may determine the region variation information of the roughly estimated ocean front region by the following substeps:

step S141, obtaining a plurality of groups of satellite remote sensing observation data at different moments in the target duration.

Specifically, in the process that the plurality of unmanned ships travel to the rough estimated ocean front area along the target path, the computer equipment can acquire satellite remote sensing observation data in real time so as to realize a plurality of groups of satellite remote sensing observation data acquired at different moments when the plurality of unmanned ships reach the target duration of the rough estimated ocean front area along the target path, wherein each group of satellite remote sensing observation data comprises at least one of a water color value, a temperature value, a salinity value, a chlorophyll concentration value and a suspended sediment concentration value of a sea area to be identified, which are acquired at corresponding moments.

Step S142, determining a plurality of rough estimation ocean front areas according to the plurality of groups of satellite remote sensing observation data.

Specifically, when the computer device obtains the plurality of sets of satellite remote sensing observation data, a rough estimated ocean front area can be correspondingly determined for each set of satellite remote sensing observation data, so that a plurality of rough estimated ocean front areas are determined, and the distribution of the plurality of rough estimated ocean front areas corresponds to different obtaining moments. The process of determining the rough estimated ocean front area corresponding to the acquisition time according to each set of satellite remote sensing observation data is the same as the process of determining the rough estimated ocean front area in step S11, and will not be described herein.

And S143, carrying out interpolation fitting processing on the plurality of rough estimation ocean frontal areas according to the plurality of different moments to obtain the area change information.

Specifically, when determining the plurality of rough estimated ocean front areas, the computer device may further perform interpolation fitting processing on the plurality of rough estimated ocean front areas according to different acquisition moments corresponding to the plurality of rough estimated ocean front areas, to obtain post-interpolation fitting ocean front area information, where the post-interpolation fitting ocean front area information may be used to characterize a development change path of the rough estimated ocean front area within the target duration, such as left and/or right movement. Therefore, the information of the ocean front area after the interpolation fitting process can be used as the area change information of the roughly estimated ocean front area.

And S15, outputting an adjustment instruction according to the region change information to instruct each unmanned ship to adjust based on the corresponding initial position, and obtaining the adjusted position of each unmanned ship.

Specifically, when the computer device determines the region change information of the roughly estimated ocean front region, the corresponding relation between the roughly estimated ocean front region and the region change information can be obtained first, then according to the corresponding relation, according to the region change information and the P initial positions of the P unmanned ships in the roughly estimated ocean front region, an adjustment instruction carrying the region change information is sent to the unmanned ships at each initial position respectively, so that the unmanned ships at each initial position are instructed to be adjusted based on the corresponding initial positions, P adjusted positions of the P unmanned ships are obtained, and the P adjusted positions are sent to the computer device. Each adjusted position can be used for representing the development change of the initial position of the corresponding unmanned ship within the target duration.

In the actual processing process, when the computer equipment determines the region change information of the roughly estimated ocean front region, a position adjustment instruction can be sent to the unmanned ship formation controller according to the obtained corresponding relation between the roughly estimated ocean front region and the region change information, the position adjustment instruction carries the region change information and the corresponding relation, so that the unmanned ship formation controller can control and adjust P initial positions of P unmanned ships according to the region change information and the corresponding relation, P adjusted positions of the P unmanned ships are obtained, and the P adjusted positions are sent to the computer equipment.

And S16, determining a target ocean front area according to the received adjusted positions.

Specifically, when the computer device receives each adjusted position sent by each unmanned ship or the unmanned ship formation controller, the computer device can be redetermined as the ocean front area according to each adjusted position, so that the target ocean front area is determined. Wherein the target ocean front area may comprise a precisely identified final ocean front area.

In the method for acquiring the ocean front area, firstly, the rough estimated ocean front area is determined according to the acquired satellite remote sensing observation data, and the satellite remote sensing observation data comprise at least one index data of a water color value, a temperature value, a salinity value, a chlorophyll concentration value and a suspended sediment concentration value of a sea area to be identified, so that the purpose of determining the rough estimated ocean front area according to two or more index data in the satellite remote sensing observation data can be realized, the defects that the identification difficulty is high and the mode is single because the ocean front area can be identified only after the threshold value is set according to different index numbers in the traditional technology are avoided, and the flexibility and the timeliness of determining the rough estimated ocean front area are improved; further, according to the satellite remote sensing observation data, determining target paths of a plurality of unmanned ships to be dispatched to the rough estimated ocean front area and target time lengths of the unmanned ships to reach the rough estimated ocean front area along the target paths, so that the problem that the identification accuracy of the ocean front area is low due to the fact that the traditional technology can only judge whether the ocean front exists in the sea area or not is solved, and a foundation is laid for obtaining the accurate ocean front area subsequently; then determining each initial position of each unmanned ship in the roughly estimated ocean front area according to the received confirmation arrival information sent when each unmanned ship arrives at the roughly estimated ocean front area; determining the regional variation information of the roughly estimated ocean front region according to a plurality of groups of satellite remote sensing observation data received in the target time length, so as to achieve the purpose of capturing the development variation of the roughly estimated ocean front region in real time in the target time length, and providing a basis for the follow-up determination of an accurate ocean front region; outputting an adjustment instruction according to the region change information to instruct each unmanned ship to adjust based on the corresponding initial position, so as to obtain an adjusted position of each unmanned ship; and determining a target ocean front area according to the received adjusted positions. The method has the advantages that the purposes that the initial positions of the unmanned ships can be adjusted in real time according to the region change information when the unmanned ships arrive at the roughly estimated ocean front region and the ocean front region can be accurately positioned according to the adjusted positions are achieved, the defect that the identification method for identifying the ocean front region by taking a large amount of ocean front identification priori information about the sea region as reference information in the traditional technology does not have low reusability and universality is overcome, and the reusability and universality of identifying the ocean front region are improved; and further, the initial positions of the unmanned ships are adjusted according to the region change information of the roughly estimated ocean front region in the target duration, so that the roughly estimated ocean front region is repositioned according to the adjusted positions to obtain an accurate ocean front region, and the accuracy and the reliability of determining the target ocean front region are improved.

In one embodiment, as shown in fig. 6, there is provided a prediction method of a ocean front region, comprising the steps of:

s21, outputting instrument layout instructions according to the target ocean front area in the ocean front area prediction method; the instrument layout instruction is used for indicating that a plurality of detection instruments are arranged in a crossing mode according to a preset distance interval.

Specifically, the instrument layout instruction may carry instrument attribute information to be laid, where the attribute information includes the type of instruments to be laid and the number of each instrument. Alternatively, the instruments to be deployed may include a thermal salt depth profiler (CTD), an acoustic doppler flow profiler (ADCP), an optical back scattering turbidity meter (OBS), an acoustic back scattering meter (acoustic backscattering, ABS), etc., where CTD is a water body detection instrument for measuring the temperature, salinity of seawater at different depths, ADCP is a hydroacoustic flow meter for measuring the water velocity, OBS is an optical instrument for measuring the turbidity of the water body, and ABS is an acoustic instrument for measuring the concentration, particle size, and sediment flux of sediment particles.

In the actual processing process, in order to improve the acquisition accuracy of the information of the ocean frontal area, the computer equipment can arrange a plurality of detection instruments according to the following process:

(1) Firstly, the computer equipment preliminarily judges an initial contour line of a target ocean front area according to received satellite remote sensing observation data, and outputs first initial layout information to indicate that unmanned ships are respectively laid on two sides of the initial contour line, and each unmanned ship is carried with the following instruments of the same kind, including CTD, ADCP, OBS, ABS and the like.

(2) And then the computer equipment transmits the initial layout information to the water through control instructions on instruments on each unmanned ship so as to control the instruments to observe dynamic environment information on two sides of the initial contour line of the ocean front area at the same time interval (for example, 5-10 minutes), wherein the dynamic environment information comprises flow velocity, temperature, salinity, turbidity, sand particle concentration, particle size, sediment flux and the like, and transmits the observed dynamic environment information to a terminal monitoring centralized control system.

(3) And then the computer equipment receives the power environment information sent by the terminal monitoring centralized control system, analyzes and compares the power environment information of two unmanned ships at two sides of the initial contour line, and if the turbidity, the sand particle concentration, the particle size and the sediment flux index difference at two sides are obvious (for example, the difference of at least one data value is more than 10 times), the initial contour line is judged to be correct and reasonable, and at the moment, a distance reduction instruction is sent to an unmanned ship formation controller to instruct to reduce the distance between the two unmanned ships at two sides of the initial contour line.

(4) Enabling the distance between two unmanned ships after the distance reduction to be a new initial route profile, repeatedly executing the steps of analyzing and comparing the dynamic environment information of the two unmanned ships at the two sides of the initial route profile until the turbidity, the sand particle concentration, the particle size and the sediment flux index difference at the two sides of the initial route profile are not obvious (for example, at least one data magnitude difference is more than 10 times), stopping sending a distance reduction instruction, and taking the relative positions of the unmanned ships at the two sides of the current target ocean frontal area as the optimal positions; if the turbidity, the sand particle concentration, the particle size and the sediment flux index difference on the two sides are not obvious (for example, the data magnitude difference is more than 10 times), sending a distance enlarging instruction to an unmanned ship formation controller so as to instruct to enlarge the distance between the two unmanned ships on the two sides of the initial contour line; stopping sending the distance expansion instruction until the indexes of turbidity, sand particle concentration, particle size and sediment flux on two sides are obviously different, and taking the relative positions of two unmanned ships on two sides of the current ocean front area as the optimal positions.

(5) Making the other two positions at two sides of the initial contour line be new positions of two unmanned ships, and returning to the step (1) for executing to obtain the optimal position; and judging that the relative positions of every two unmanned ships arranged on the two sides of the initial contour line are optimal positions. And determining a plurality of detection instruments distributed in the target ocean frontal area at the moment.

Step S22, obtaining sea area observation elements detected by the detecting instrument, and performing cleaning treatment operation on the obtained sea area observation elements to obtain cleaned observation elements; the cleaning operation comprises a missing value filling operation and/or an abnormal value deleting operation, and the sea area observation elements comprise humidity, salinity, temperature, wind speed, wind direction, flow speed, wave height, wave direction, wave period, water depth and navigational speed of the sea area to be observed.

Specifically, the computer device may receive the sea observation elements detected by the detecting instrument in real time, and may perform a missing value filling operation on the obtained sea observation elements, for example, the observation elements obtained at the time t are complete (that is, include humidity, salinity, temperature, wind speed, wind direction, flow velocity, wave height, wave direction, wave period, water depth, and speed), the observation elements other than salinity are obtained at the time t+1, the observation materials obtained at the time t+2 and t+3 are complete, and at this time, the salinity information missing at the time t+1 may be subjected to a linear difference value processing according to the observation elements obtained at the time t, t+2, and t+3, so as to fill the missing value, thereby obtaining the observation elements after the missing value filling operation. For example, when the wind speed in the observation element obtained at the time t 'exceeds a wind speed threshold value, deleting the wind speed obtained at the time t' as an abnormal value, wherein the wind speed threshold value is the maximum wind speed in the history observation element; the computer device may also perform an outlier deletion operation on the obtained sea area observation element, for example, when the wind speed in the observation element obtained at the time t 'exceeds a wind speed threshold value, delete the wind speed obtained at the time t' as an outlier, where the wind speed threshold value may be a maximum wind speed in the historical observation element, so as to obtain an outlier post-operation observation element, so that it may be determined that the post-cleaning-treatment observation element may include a missing-value filling-operation observation element and/or the outlier post-operation observation element.

And S23, performing feature selection processing on the observation elements after the cleaning processing by using a support vector machine recursion feature elimination method to obtain target features.

Specifically, the computer device may use a support vector machine (SVM-RFE) recursive feature elimination algorithm to perform feature selection on the observation element after the cleaning process, so as to obtain the target feature. The SVM-RFE is a gene selection method proposed by Guyon et al in classifying cancers, and higher classification accuracy can be obtained by using the SVM-RFE.

The feature extraction process using SVM-RFE algorithm is: the core of the SVM-RFE algorithm is that all the features are modeled and ordered in descending order according to the influence weight of each feature on the result variable, the features with smaller influence weights are deleted earliest, the remaining features of the remaining influence weights are used for re-modeling and ordering in descending order, and the iteration cycle is continued until only one of the remaining features of the remaining influence weights exists.

The SVM-RFE algorithm can effectively reduce the number of features and has better robustness, and is a cyclic process, each step comprises the following substeps:

1) The classifier is trained with the current dataset to obtain individual features related to the classifier features. For example, in a linear kernel support vector machine, the relevant information may include weights for each feature.

2) And calculating the ranking criterion score of each feature according to a preset rule.

3) The feature corresponding to the smallest ranking criterion score is removed from the current dataset.

And the process is circularly executed until the circulation process is finished when the last variable in the feature set is executed, the corresponding execution result at the end of the circulation process is an obtained list of feature sequence numbers ordered according to the feature importance, and each feature sequence number corresponds to a target feature.

S24, inputting the target characteristics and the set time into a preset ocean front prediction model to obtain a predicted ocean front area of the target ocean front area at the preset time; the preset ocean front prediction model comprises a model which is used for training a random forest model by using the target characteristics and is well trained.

The set time may include any time after the target time of the target ocean front area is determined.

Specifically, the process of determining the preset ocean front prediction model by the computer equipment comprises the following steps: firstly, taking the target features as the input of a random forest model, and carrying out model training by combining with the sensitive parameter initial values of the random forest model to obtain a preliminary result after model training; then determining different groups of values of the sensitive parameters according to the preliminary result, and determining different root mean square errors between the predicted value and the actual observed value of the random forest model after the different groups of values and the target feature verification; and finally, sorting the sizes of the different root mean square errors, and taking a random forest model corresponding to the smallest root mean square error as the preset ocean front prediction model.

In the actual processing, the training process of the random forest model comprises the following substeps:

(1) There are N samples randomly selected for placement in the plurality of target features, and the N samples selected are used to train a decision tree, and the N samples may be samples at a root node of the decision tree. Wherein each sample is a corresponding one of the target features, and each time one sample is selected, the replaced random selection may include replacing the selected sample with a second random selection of the plurality of target features.

(2) When each sample is detected to comprise M attributes, and the ith node of the decision tree needs to be split, randomly selecting M attributes from the M attributes, wherein M < < M. And then adopting a preset strategy (such as an information gain strategy) to select 1 attribute from m attributes as a splitting attribute of the ith node.

(3) And (3) taking the i+1 as a new i, returning to (2) and continuing to execute the step of obtaining the splitting attribute of the ith node until the splitting attribute of the ith node is the attribute corresponding to the splitting of the parent node, and determining that the ith node reaches the leaf node without continuing splitting.

(4) Establishing a large number of decision trees according to the steps (1) - (3) to form a random forest, wherein the random forest has 2 parameters, and one is the number of trees in the forest, and a larger value is usually taken; the other is M, and the value of M is generally the same as the root mean square of M. The predicted value of the target variable in the random forest model is the average value of all the decision trees.

(5) Based on the random forest established in the step (4), comparing the average value output by the random forest with the observed value of the target variable, and calculating the correlation coefficient and the root mean square error.

(6) And (3) repeating the steps (1) - (5) by considering different input variable structures (namely the number of variables used, the same variable data type and the like), obtaining statistical values (namely the correlation coefficient and the root mean square error) of the model training period when the different input variable structures are considered, comparing and analyzing the statistical values, and selecting a model with the most remarkable correlation coefficient and the minimum root mean square error as an optimal model.

And S25, carrying out visualization processing on the predicted ocean front area to obtain a predicted area visualization image of the predicted ocean front area.

Specifically, when the computer device determines the predicted ocean front area, the predicted ocean front area may be further subjected to visualization processing to obtain a predicted area visualized image of the predicted ocean front area, where the predicted area visualized image of the predicted ocean front area may include visualized contours forming at least two contours of the predicted ocean front area.

In this embodiment, the objective of acquiring the sea area observation elements in real time through the various deployed detection instruments is achieved by the target sea area output instrument deployment instruction determined in the sea area prediction method, and the objective of extracting the feature elements influencing the sea area distribution change based on the multiple observation information is achieved by performing a cleaning processing operation including a missing value filling operation and/or an abnormal value deleting operation on the acquired sea area observation elements and performing feature selection processing on the observation elements after the cleaning processing by using a support vector machine recursion feature elimination method to determine target features, so that the prediction accuracy of the development path of the target sea area is guaranteed to be improved subsequently; further, the target feature and the set time are input into the preset ocean front prediction model which is used for training a random forest model and is trained, the predicted ocean front area of the target ocean front area at the preset time is determined, and the predicted area visual image of the predicted ocean front area is determined by performing visual processing on the predicted ocean front area, so that the purpose of predicting elements influencing ocean front distribution change by adopting an integrated decision tree random forest machine learning method is achieved, and the accuracy and the prediction precision of predicting the ocean front area are effectively improved.

It should be understood that, although the steps in the flowcharts of fig. 2-6 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2-6 may include multiple steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the steps or stages in other steps or other steps.

In one embodiment, as shown in fig. 7, there is provided an acquisition device for a ocean front area, comprising: a first determination module 11, a second determination module 12, a third determination module 13, a fourth determination module 14, an adjustment module 15, and a fifth determination module 16, wherein:

the first determining module 11 is used for acquiring satellite remote sensing observation data and determining a rough estimated ocean front area according to the satellite remote sensing observation data; the satellite remote sensing observation data comprise at least one of a water color value, a temperature value, a salinity value, a chlorophyll concentration value and a suspended sediment concentration value of a sea area to be identified.

A second determining module 12, configured to determine, according to the satellite remote sensing observation data, a target path of the plurality of unmanned vessels to be dispatched reaching the rough estimated ocean front area and a target duration of reaching the rough estimated ocean front area along the target path; wherein the target path is used to characterize a shortest path for the plurality of unmanned vessels to reach the rough estimate ocean front area.

And the third determining module 13 is configured to determine each initial position of each unmanned ship in the rough estimated ocean front area according to the received acknowledgement arrival information sent when each unmanned ship arrives at the rough estimated ocean front area.

And a fourth determining module 14, configured to determine the region variation information of the rough estimated ocean front region according to the multiple sets of satellite remote sensing observation data received in the target duration.

And the adjusting module 15 is configured to output an adjusting instruction according to the region change information, so as to instruct each unmanned ship to adjust based on the corresponding initial position, and obtain an adjusted position of each unmanned ship.

A fifth determination module 16 is configured to determine a target ocean front area based on each of the received adjusted positions.

The second determining module 12 may include: the first, second, third and fourth determination sub-modules.

Specifically, the first determining submodule can be used for determining an area estimated value and a frontal line length of the roughly estimated ocean front area according to the satellite remote sensing observation data; the second determining submodule can be used for determining the number of the unmanned ships to be dispatched according to the first ratio result of the area estimated value and the frontal surface line length; the third determining submodule can be used for determining a plurality of linear distances between each unmanned ship and each preset vertex position of the rough estimated ocean front area, and selecting the smallest linear distance among the plurality of linear distances corresponding to each unmanned ship as a target path for the unmanned ship to reach the rough estimated ocean front area; and the fourth determination submodule can be used for obtaining the maximum speed of the unmanned ships and taking a second ratio result of the target path of the unmanned ships reaching the roughly estimated ocean front area to the maximum speed as the target duration.

The first determining sub-module may include: the device comprises a first determining unit, a calibration processing unit, a second determining unit and a third determining unit.

Specifically, the first determining unit may be configured to determine a visualized area distribution map of the roughly estimated ocean front area according to the satellite remote sensing observation data; the calibration processing unit can be used for carrying out regular graph calibration processing on the visual regional distribution map according to the position coordinates of each vertex of the visual regional distribution map to obtain a target rectangular frame containing the visual regional distribution map; the second determining unit can be used for determining an area estimation value of the roughly estimated ocean front area corresponding to the target rectangular frame; and the third determining unit can be used for dividing the contour line of the visual regional distribution diagram into a plurality of contour points and linearly superposing the distances between two adjacent contour points to obtain the length of the frontal surface line.

The first determining unit may include: the first determining subunit, the second determining subunit, and the third determining subunit.

Specifically, the first determining subunit may be configured to perform inversion processing on the satellite remote sensing observation data to obtain a sea area distribution diagram of the sea area to be identified; the second determining subunit may be configured to determine that an interface where the sea area distribution map exists is the rough estimated sea front area if the sea area distribution map meets a pre-stored interface determining condition; and the third determination subunit is used for carrying out visualization processing on the roughly estimated ocean front area to obtain a visualized area distribution diagram of the roughly estimated ocean front area.

The fourth determination module 14 may include: the method comprises the steps of obtaining a sub-module, a fifth determining sub-module and a fitting processing sub-module.

Specifically, the acquisition sub-module can be used for acquiring a plurality of groups of satellite remote sensing observation data at different moments in the target duration; the fifth determining submodule can be used for determining a plurality of rough estimated ocean front areas according to the plurality of groups of satellite remote sensing observation data; and the fitting processing sub-module can be used for carrying out interpolation fitting processing on the plurality of rough estimated ocean frontal areas according to the plurality of different moments to obtain the area change information.

In one embodiment, as shown in fig. 8, there is provided a prediction apparatus of a ocean front region, including: the device comprises an instruction output module 21, a cleaning processing module 22, a feature selection module 23, a prediction module 24 and a visualization processing module 25, wherein:

the instruction output module 21 may be configured to output an instrument layout instruction according to the target ocean front area in the ocean front area acquiring device; the instrument layout instruction is used for indicating that a plurality of detection instruments are arranged in a crossing mode according to a preset distance interval;

the cleaning processing module 22 may be configured to obtain the sea area observation element detected by the detecting instrument, and perform a cleaning processing operation on the obtained sea area observation element to obtain a cleaned observation element; the sea area observation elements comprise humidity, salinity, temperature, wind speed, wind direction, flow speed, wave height, wave direction, wave period, water depth and navigational speed of the sea area to be observed;

The feature selection module 23 may be configured to perform feature selection processing on the observation element after the cleaning processing by using a support vector machine recursive feature elimination method to obtain a target feature;

the prediction module 24 may be configured to input the target feature and the set time into a preset ocean front prediction model, to obtain a predicted ocean front area of the target ocean front area at the preset time; the preset ocean front prediction model comprises a model which is used for training a random forest model by using the target characteristics and is well trained;

the visualization processing module 25 may be configured to perform visualization processing on the predicted ocean front area, to obtain a predicted area visualization image of the predicted ocean front area.

Prediction module 24 may include: the system comprises a model training sub-module, a first processing sub-module and a second processing sub-module.

Specifically, the model training sub-module can be used for taking the target feature as the input of a random forest model, and combining the initial value of the sensitive parameter of the random forest model to perform model training to obtain a preliminary result after model training; the first processing sub-module can be used for determining different groups of values of the sensitive parameters according to the preliminary result and determining different root mean square errors between the predicted value and the actual observed value of the random forest model after the different groups of values and the target feature verification; and the second processing submodule can be used for sequencing the different root mean square errors in size and taking a random forest model corresponding to the smallest root mean square error as the preset ocean front prediction model.

The specific definition of the marine front region acquiring device may be referred to the definition of the marine front region acquiring method hereinabove, and the specific definition of the marine front region predicting device may be referred to the definition of the marine front region predicting method hereinabove, which will not be described herein. The above-mentioned ocean front area obtaining device the above-mentioned ocean front area predicting device and each module in the above-mentioned ocean front area predicting device may be implemented in whole or in part by software, hardware and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, as shown in fig. 9, there is provided an acquisition system for a ocean front area, the system comprising: the unmanned naval vessel formation controller, treater, unmanned naval vessel formation controller set up respectively in the land basic station of waiting to discern the sea area, contain remote controller and control platform's carrier PC and communication tool in the land basic station, the treater with unmanned naval vessel formation controller electricity is connected, wherein:

The processor is used for acquiring satellite remote sensing observation data and determining a rough estimated ocean front area according to the satellite remote sensing observation data; determining target paths of a plurality of unmanned ships to be dispatched to reach the roughly estimated ocean front area and target time lengths of the unmanned ships to reach the roughly estimated ocean front area along the target paths according to the satellite remote sensing observation data; determining each initial position of each unmanned ship in the roughly estimated ocean front area according to the received confirmation arrival information sent when each unmanned ship arrives at the roughly estimated ocean front area; determining the regional variation information of the roughly estimated ocean front region according to a plurality of groups of satellite remote sensing observation data received in the target duration; outputting an adjustment instruction according to the region change information to instruct each unmanned ship to adjust based on the corresponding initial position, so as to obtain an adjusted position of each unmanned ship; determining a target ocean front area according to the received adjusted positions; the satellite remote sensing observation data comprises at least one of a water color value, a temperature value, a salinity value, a chlorophyll concentration value and a suspended sediment concentration value of a sea area to be identified, and the target path is used for representing the shortest path of the unmanned ships to the rough estimated ocean front area.

The processor is also used for acquiring a plurality of groups of satellite remote sensing observation data at different moments in the target duration; determining a plurality of rough estimation ocean front areas according to the plurality of groups of satellite remote sensing observation data; and carrying out interpolation fitting processing on the plurality of rough estimation ocean frontal areas according to the plurality of different moments to obtain the area change information.

The processor is further used for determining an area estimation value and a frontal line length of the roughly estimated ocean front area according to the satellite remote sensing observation data; determining the number of unmanned ships to be dispatched according to the area estimated value and the first ratio result of the frontal surface line length; determining a plurality of linear distances between each unmanned ship and each preset vertex position of the rough estimated ocean front area, and selecting the smallest linear distance among the plurality of linear distances corresponding to each unmanned ship as a target path for the unmanned ship to reach the rough estimated ocean front area; and obtaining the maximum speed per hour of the unmanned ships and warships, and taking the second ratio result of the target path of the unmanned ships reaching the roughly estimated ocean front area to the maximum speed per hour as the target duration.

The processor is further used for determining a visual area distribution map of the roughly estimated ocean front area according to the satellite remote sensing observation data; according to the position coordinates of each vertex of the visual area distribution diagram, carrying out calibration processing of a regular graph on the visual area distribution diagram to obtain a target rectangular frame containing the visual area distribution diagram; determining an area estimation value of the roughly estimated ocean front area corresponding to the target rectangular frame; and dividing the contour line of the visual regional distribution map into a plurality of contour points, and linearly superposing the distances between two adjacent contour points to obtain the length of the frontal surface line.

The processor is further used for carrying out inversion processing on the satellite remote sensing observation data to obtain a sea area distribution diagram of the sea area to be identified; if the sea area distribution diagram meets a prestored interface determination condition, determining that an interface existing in the sea area distribution diagram is the roughly estimated sea front area; and carrying out visual treatment on the roughly estimated ocean front area to obtain a visual area distribution map of the roughly estimated ocean front area.

The processor is also used for outputting instrument layout instructions according to the target ocean front area; the instrument layout instruction is used for indicating that a plurality of detection instruments are arranged in a crossing mode according to a preset distance interval; acquiring sea area observation elements detected by the detecting instrument, and performing cleaning treatment operation on the acquired sea area observation elements to obtain cleaned observation elements; the sea area observation elements comprise humidity, salinity, temperature, wind speed, wind direction, flow speed, wave height, wave direction, wave period, water depth and navigational speed of the sea area to be observed; performing feature selection processing on the observation elements after the cleaning processing by using a support vector machine recursion feature elimination method to obtain target features; inputting the target characteristics and the set time into a preset ocean front prediction model to obtain a predicted ocean front region of the target ocean front region at the preset time; the preset ocean front prediction model comprises a model which is used for training a random forest model by using the target characteristics and is well trained; and carrying out visualization processing on the predicted ocean front area to obtain a predicted area visualization image of the predicted ocean front area.

The processor is also used for taking the target characteristics as the input of a random forest model, and carrying out model training by combining with the initial value of the sensitive parameter of the random forest model to obtain a preliminary result after model training; determining different groups of values of the sensitive parameters according to the preliminary result, and determining different root mean square errors between the predicted value and the actual observed value of the random forest model after the different groups of values and the target feature verification; and sequencing the different root mean square errors, and taking a random forest model corresponding to the smallest root mean square error as the preset ocean front prediction model.

In the actual processing process, as shown in fig. 9, the ocean front area acquisition system comprises a water surface unmanned ship formation controller and a terminal monitoring centralized control system, wherein the water surface unmanned ship formation controller comprises a water surface unmanned ship formation formed by a plurality of unmanned ships, observation equipment (such as an ADCP\CTD\meteorological sensor and the like), a control system comprising a basic motion controller and a sensor data processor, a power supply system (such as normal emergency standby power supply and abnormal emergency standby power supply) and an information receiving and transmitting system. The terminal monitoring centralized control system may include: a display, a communication system, a data storage system (e.g., storing sensor data, track information, ocean front size information), a remote control system, a parameter setting system (e.g., setting formation shape, desired path, etc.).

In one embodiment, a computer device is provided, which may be a terminal, and an internal structure diagram thereof may be as shown in fig. 10. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program, when executed by a processor, implements a method of acquiring a marine front region. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.

It will be appreciated by those skilled in the art that the structure shown in fig. 10 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:

In one embodiment, the processor when executing the computer program further performs the steps of:

acquiring a plurality of groups of satellite remote sensing observation data at different moments in the target duration; determining a plurality of rough estimation ocean front areas according to the plurality of groups of satellite remote sensing observation data; and carrying out interpolation fitting processing on the plurality of rough estimation ocean frontal areas according to the plurality of different moments to obtain the area change information.

Determining the area estimation value and the frontal line length of the roughly estimated ocean frontal area according to the satellite remote sensing observation data; determining the number of unmanned ships to be dispatched according to the area estimated value and the first ratio result of the frontal surface line length; determining a plurality of linear distances between each unmanned ship and each preset vertex position of the rough estimated ocean front area, and selecting the smallest linear distance among the plurality of linear distances corresponding to each unmanned ship as a target path for the unmanned ship to reach the rough estimated ocean front area; and obtaining the maximum speed per hour of the unmanned ships and warships, and taking the second ratio result of the target path of the unmanned ships reaching the roughly estimated ocean front area to the maximum speed per hour as the target duration.

according to the satellite remote sensing observation data, determining a visual area distribution map of the roughly estimated ocean front area; according to the position coordinates of each vertex of the visual area distribution diagram, carrying out calibration processing of a regular graph on the visual area distribution diagram to obtain a target rectangular frame containing the visual area distribution diagram; determining an area estimation value of the roughly estimated ocean front area corresponding to the target rectangular frame; and dividing the contour line of the visual regional distribution map into a plurality of contour points, and linearly superposing the distances between two adjacent contour points to obtain the length of the frontal surface line.

inversion processing is carried out on the satellite remote sensing observation data to obtain a sea area distribution diagram of the sea area to be identified; if the sea area distribution diagram meets a prestored interface determination condition, determining that an interface existing in the sea area distribution diagram is the roughly estimated sea front area; and carrying out visual treatment on the roughly estimated ocean front area to obtain a visual area distribution map of the roughly estimated ocean front area.

outputting instrument layout instructions according to the target ocean front area; the instrument layout instruction is used for indicating that a plurality of detection instruments are arranged in a crossing mode according to a preset distance interval; acquiring sea area observation elements detected by the detecting instrument, and performing cleaning treatment operation on the acquired sea area observation elements to obtain cleaned observation elements; the sea area observation elements comprise humidity, salinity, temperature, wind speed, wind direction, flow speed, wave height, wave direction, wave period, water depth and navigational speed of the sea area to be observed; performing feature selection processing on the observation elements after the cleaning processing by using a support vector machine recursion feature elimination method to obtain target features; inputting the target characteristics and the set time into a preset ocean front prediction model to obtain a predicted ocean front region of the target ocean front region at the preset time; the preset ocean front prediction model comprises a model which is used for training a random forest model by using the target characteristics and is well trained; and carrying out visualization processing on the predicted ocean front area to obtain a predicted area visualization image of the predicted ocean front area.

taking the target features as the input of a random forest model, and carrying out model training by combining with the sensitive parameter initial values of the random forest model to obtain a preliminary result after model training; determining different groups of values of the sensitive parameters according to the preliminary result, and determining different root mean square errors between the predicted value and the actual observed value of the random forest model after the different groups of values and the target feature verification; and sequencing the different root mean square errors, and taking a random forest model corresponding to the smallest root mean square error as the preset ocean front prediction model.

In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:

In one embodiment, the computer program when executed by the processor further performs the steps of:

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include Random access memory (Random AccessMemory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.

Claims

1. A method of acquiring a ocean front region, the method comprising:

determining a target ocean front area according to the received adjusted positions;

the determining the region change information of the roughly estimated ocean front region according to the plurality of groups of satellite remote sensing observation data received in the target duration comprises the following steps:

performing interpolation fitting processing on the plurality of rough estimation ocean frontal areas according to the plurality of different moments to obtain the area change information;

the determining, according to the satellite remote sensing observation data, a target path of a plurality of unmanned ships to be dispatched to reach the rough estimated ocean front area and a target time length of reaching the rough estimated ocean front area along the target path includes:

2. The method of claim 1, wherein determining the area estimate and the frontal line length of the roughly estimated ocean front area from the satellite remote sensing observations comprises:

3. The method of claim 2, wherein said determining a visual zone profile of said rough estimate of ocean front zone from said satellite remote sensing observations comprises:

4. A method of predicting a ocean front region, the method comprising:

a method according to any one of claims 1 to 3, wherein the target ocean front area outputs instrument deployment instructions; the instrument layout instruction is used for indicating that a plurality of detection instruments are arranged in a crossing mode according to a preset distance interval;

acquiring sea area observation elements detected by the detecting instrument, and performing cleaning treatment operation on the acquired sea area observation elements to obtain cleaned observation elements; the cleaning operation comprises a missing value filling operation and/or an abnormal value deleting operation, and the sea area observation elements comprise humidity, salinity, temperature, wind speed, wind direction, flow speed, wave height, wave direction, wave period, water depth and navigational speed of a sea area to be observed;

inputting the target characteristics and the set time into a preset ocean front prediction model to obtain a predicted ocean front area of the target ocean front area at the set time; the preset ocean front prediction model comprises a model which is used for training a random forest model by using the target characteristics and is well trained;

5. The method of claim 4, wherein the predetermined ocean front prediction model comprises:

6. A marine front region acquisition system, the system comprising: the system comprises a processor and an unmanned ship formation controller, wherein the processor and the unmanned ship formation controller are respectively arranged in a land base station of a sea area to be identified, and the processor is electrically connected with the unmanned ship formation controller;

The unmanned naval vessel formation controller is used for controlling the corresponding number of unmanned naval vessels to run according to the number of the unmanned naval vessels to be dispatched;

the processor is also used for acquiring a plurality of groups of satellite remote sensing observation data at different moments in the target duration; determining a plurality of rough estimation ocean front areas according to the plurality of groups of satellite remote sensing observation data; performing interpolation fitting processing on the plurality of rough estimation ocean frontal areas according to the plurality of different moments to obtain the area change information;

7. An apparatus for acquiring a region of a ocean front, the apparatus comprising:

a fifth determining module, configured to determine a target ocean front area according to the received adjusted positions;

the fourth determining module is specifically configured to obtain multiple sets of satellite remote sensing observation data at different moments in the target duration; determining a plurality of rough estimation ocean front areas according to the plurality of groups of satellite remote sensing observation data; performing interpolation fitting processing on the plurality of rough estimation ocean frontal areas according to the plurality of different moments to obtain the area change information;

the second determining module is specifically configured to determine an area estimation value and a frontal line length of the roughly estimated ocean front area according to the satellite remote sensing observation data; determining the number of unmanned ships to be dispatched according to the area estimated value and the first ratio result of the frontal surface line length; determining a plurality of linear distances between each unmanned ship and each preset vertex position of the rough estimated ocean front area, and selecting the smallest linear distance among the plurality of linear distances corresponding to each unmanned ship as a target path for the unmanned ship to reach the rough estimated ocean front area; and obtaining the maximum speed per hour of the unmanned ships and warships, and taking the second ratio result of the target path of the unmanned ships reaching the roughly estimated ocean front area to the maximum speed per hour as the target duration.

8. A marine front region prediction apparatus, the apparatus comprising:

an output module for outputting instrument layout instructions according to the target ocean front area in any one of the methods of claims 1 to 3; the instrument layout instruction is used for indicating that a plurality of detection instruments are arranged in a crossing mode according to a preset distance interval;

the cleaning module is used for acquiring the sea area observation elements detected by the detecting instrument, and performing cleaning treatment operation on the acquired sea area observation elements to obtain cleaned observation elements; the cleaning operation comprises a missing value filling operation and/or an abnormal value deleting operation, and the sea area observation elements comprise humidity, salinity, temperature, wind speed, wind direction, flow speed, wave height, wave direction, wave period, water depth and navigational speed of a sea area to be observed;

the processing module is used for carrying out feature selection processing on the observation elements after the cleaning processing by using a support vector machine recursion feature elimination method to obtain target features;

the prediction module is used for inputting the target characteristics and the set time into a preset ocean front prediction model to obtain a predicted ocean front area of the target ocean front area at the set time; the preset ocean front prediction model comprises a model which is used for training a random forest model by using the target characteristics and is well trained;

And the visualization module is used for carrying out visualization processing on the predicted ocean front area to obtain a predicted area visualization image of the predicted ocean front area.

9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 5 when the computer program is executed.

10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 5.