CN113298311A - Forest fire danger level prediction method, device, equipment and readable storage medium - Google Patents
Forest fire danger level prediction method, device, equipment and readable storage medium Download PDFInfo
- Publication number
- CN113298311A CN113298311A CN202110636930.6A CN202110636930A CN113298311A CN 113298311 A CN113298311 A CN 113298311A CN 202110636930 A CN202110636930 A CN 202110636930A CN 113298311 A CN113298311 A CN 113298311A
- Authority
- CN
- China
- Prior art keywords
- fire
- time phase
- data
- current time
- data corresponding
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000007613 environmental effect Effects 0.000 claims abstract description 56
- 238000012549 training Methods 0.000 claims abstract description 40
- 238000004590 computer program Methods 0.000 claims description 17
- 238000012706 support-vector machine Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 230000002265 prevention Effects 0.000 abstract description 3
- 230000002349 favourable effect Effects 0.000 abstract 1
- 230000005855 radiation Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000012952 Resampling Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000002485 combustion reaction Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000003331 infrared imaging Methods 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Abstract
The application belongs to the technical field of intelligent decision making, and provides a forest fire hazard level prediction method, a forest fire hazard level prediction device, forest fire hazard level prediction equipment and a readable storage medium, wherein the forest fire hazard level prediction method comprises the following steps: when it is monitored that a forest is on fire, acquiring environmental data corresponding to a previous time of a current time phase, acquiring environmental data corresponding to the current time phase, and acquiring fire data corresponding to the current time phase; training a model for predicting the fire hazard level according to the environmental data corresponding to the previous time and the fire data corresponding to the current time to obtain a fire hazard level prediction model; and predicting a danger level result corresponding to the forest fire in the later time phase by combining the fire data corresponding to the later time phase of the current time phase according to the environment data corresponding to the current time phase and the fire danger level prediction model. The method and the device can improve the foresight, convenience, high efficiency and accuracy of the forest fire hazard level assessment, reduce the hazard, and are favorable for guiding the prevention and control of forest fires.
Description
Technical Field
The application relates to the technical field of intelligent decision, in particular to a forest fire hazard level prediction method, a forest fire hazard level prediction device, forest fire hazard level prediction equipment and a readable storage medium.
Background
The forest is a natural 'dispatcher', can adjust the circulation of air and water in the nature, influences the change of climate, is one of the areas which are most easily damaged on the earth, and each forest fire occurrence is great loss of ecological environment and human society. The assessment of the danger level of the forest fire has very important significance on forest management, forest protection and fire rescue.
The traditional method for evaluating the danger level of the forest fire is also used for extracting the fired forest fire, manual evaluation is carried out based on the combination of the forest fire and artificial experience, the method is subjective, and the accuracy is difficult to guarantee, and the extraction of the fired forest fire is that under the condition of fire, fire fighters and forest keepers are used as main forces to carry out manual point-point search, so that the danger is high, the labor intensity is high, the time period is long, and the convenience is low.
Disclosure of Invention
The application mainly aims to provide a forest fire danger level prediction method, a forest fire danger level prediction device, forest fire danger level prediction equipment and a readable storage medium, and aims to solve the technical problems that the danger level of a forest fire is evaluated manually in the traditional mode, and the accuracy and the convenience are high.
In a first aspect, the present application provides a forest fire risk level prediction method, including:
when it is monitored that a forest is on fire, acquiring environmental data corresponding to a previous time of a current time phase, acquiring environmental data corresponding to the current time phase, and acquiring fire data corresponding to the current time phase;
training a model for predicting the fire hazard level according to the environmental data corresponding to the previous time and the fire data corresponding to the current time to obtain a fire hazard level prediction model;
and predicting a danger level result corresponding to the forest fire in the later time phase by combining the fire data corresponding to the later time phase of the current time phase according to the environment data corresponding to the current time phase and the fire danger level prediction model.
In a second aspect, the present application also provides a forest fire risk level prediction apparatus, the apparatus comprising:
the acquisition module is used for acquiring environmental data corresponding to the previous time of the current time phase, acquiring environmental data corresponding to the current time phase and acquiring fire data corresponding to the current time phase when the forest is monitored to be on fire;
the training module is used for training a model for predicting the fire hazard level according to the environmental data corresponding to the previous time and the fire data corresponding to the current time to obtain a fire hazard level prediction model;
and the prediction module is used for predicting a danger level result corresponding to the forest fire in the later time phase by combining the fire data corresponding to the later time of the current time phase according to the environment data corresponding to the current time phase and the fire danger level prediction model.
In a third aspect, the present application further provides a computer device comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program, when executed by the processor, implements the steps of the forest fire risk level prediction method as described above.
In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, where the computer program, when executed by a processor, implements the forest fire risk level prediction method as described above.
The application discloses a forest fire hazard grade prediction method, a device, equipment and a readable storage medium. According to the multi-temporal environmental data and the fire data, the prediction of the danger level of the forest fire at the later temporal is realized based on the fire danger level prediction model, the foresight, convenience, high efficiency and accuracy are improved, the system has wide applicability, the scheduling of fire fighters and personnel evacuation decision can be assisted, the danger is reduced, and the guidance of the prevention and control of the forest fire is facilitated.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow chart illustrating an embodiment of a forest fire risk level prediction method according to the present application;
FIG. 2 is an exemplary diagram of wind field data related to an embodiment of a forest fire risk level prediction method according to the present application;
FIG. 3 is a schematic flow chart illustrating another embodiment of the forest fire risk level prediction method according to the present application;
fig. 4 is a schematic block diagram of a forest fire risk level prediction apparatus according to an embodiment of the present application;
fig. 5 is a block diagram schematically illustrating a structure of a computer device according to an embodiment of the present application.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The flow diagrams depicted in the figures are merely illustrative and do not necessarily include all of the elements and operations/steps, nor do they necessarily have to be performed in the order depicted. For example, some operations/steps may be decomposed, combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
It is to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should also be understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
The embodiment of the application provides a forest fire danger level prediction method, a forest fire danger level prediction device, forest fire danger level prediction equipment and a readable storage medium. The forest fire danger level prediction method is mainly applied to forest fire danger level prediction equipment, and the forest fire danger level prediction equipment can be equipment with a data processing function, such as a mobile terminal, a Personal Computer (PC), a portable computer and a server.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a schematic flow chart of a forest fire risk level prediction method according to an embodiment of the present disclosure.
As shown in fig. 1, the forest fire risk level prediction method includes steps S101 to S104.
Step S101, when it is monitored that a forest is on fire, acquiring environmental data corresponding to a previous time of a current time phase, acquiring environmental data corresponding to the current time phase, and acquiring fire data corresponding to the current time phase.
The environmental data represent data corresponding to the ecological environment of the forest, and comprise vegetation coverage data, population distribution data and terrain data. The fire data represents data corresponding to main factors for determining the danger degree of the forest fire, and comprises wind field data corresponding to climate and thermal infrared ortho-image data corresponding to combustion temperature.
The method for predicting the forest fire danger level dynamically monitors the forest fire by using a remote sensing technology and an aerial photography technology, so that a satellite remote sensing system (comprising a satellite and a remote sensor carried by the satellite) and an unmanned aerial vehicle aerial photography system (comprising an unmanned aerial vehicle and a thermal infrared sensor and a multispectral imager carried by the unmanned aerial vehicle) are built in advance, and communication connection between the satellite remote sensing system and the unmanned aerial vehicle aerial photography system and forest fire danger level prediction equipment is respectively built.
It should be noted that after the monitoring of the forest becomes effective (the monitoring is started when the default forest is not on fire), the forest fire hazard level prediction device controls the satellite remote sensing system to acquire the remote sensing images of the forest regularly according to the phases, wherein the length of the time phase can be flexibly set according to actual needs, for example, 1 day, and the remote sensing image acquired by each time phase and the corresponding acquisition time phase are stored in an associated manner. It will be appreciated that the remote sensing images of the forest are acquired a plurality of times within each time phase, so that a plurality of remote sensing images are associated with each time phase. For example, to improve the accuracy of forest monitoring, the remote sensing image may be a high-resolution remote sensing image.
The method comprises the steps of firstly, obtaining environmental data corresponding to the previous time of the current time phase of the forest, obtaining environmental data corresponding to the current time phase, and obtaining fire data corresponding to the current time phase. Illustratively, for example, when the current time phase is Tn, the previous time phase is Tn-1, and a forest fires in the Tn time phase, the environmental data corresponding to the Tn-1 time phase and the environmental data corresponding to the Tn time phase are acquired, and the fire data corresponding to the Tn time phase is acquired.
In some embodiments, the environment data includes vegetation coverage data, population distribution data, and terrain data, and the obtaining of the environment data corresponding to the previous time of the current time phase specifically includes: acquiring the remote sensing image of the previous time phase, and determining vegetation coverage data of the previous time phase according to the remote sensing image of the previous time phase; acquiring population distribution data in a preset range around a forest; acquiring elevation data, and determining terrain data according to the elevation data; and taking the vegetation coverage data, the population distribution data and the terrain data of the previous time phase as the corresponding environmental data of the previous time.
For example, the vegetation coverage data corresponding to the previous time is obtained by querying a pre-stored associated remote sensing image and a time phase, searching the previous time phase of the current time phase from the pre-stored time phase, and then searching the pre-stored remote sensing image matched with the previous time phase of the current time phase as the remote sensing image of the previous time phase. And then, acquiring vegetation coverage data according to the spectral characteristics of the vegetation, which are different from other ground features and are shown on the remote sensing image of the previous time phase.
Illustratively, this can be achieved by normalizing the Vegetation index NDVI (normalized Difference Vegetation index), which is an important index reflecting the Vegetation coverage status:
NDVI＝(NIR-Red)/(NIR+Red)
wherein NIR represents a near infrared band and Red represents a Red light band.
Because the reflectivity of the vegetation is generally strongest in the near-infrared band, the ratio of the red light band to the near-infrared band can be adopted to highlight the information of the vegetation to the maximum extent, so that the vegetation coverage data of the previous time phase can be obtained.
For example, the population distribution data is obtained by downloading population density data within a preset range of a square circle around a forest from a national population density data open platform as population distribution data, wherein the preset range can be set according to practical flexibility, such as within 10 kilometers of the square circle with the forest as the center.
For example, the topographic data may be obtained by Downloading Elevation (DEM) data from a national elevation data open platform in forest areas and then calculating topographic data from the elevation data.
In some embodiments, the terrain data includes slope data and slope data, and the determining of the terrain data from the elevation data, in particular, taking into account that slope and slope influence the ignition speed and the tendency, comprises: dividing the forest area into a plurality of orthogonal grid units according to the elevation data to obtain the elevation of each grid unit; calculating a slope of each grid cell to obtain slope data and a slope of each grid cell to obtain slope data according to the elevation in each grid cell; and taking the calculated gradient data and the slope data as terrain data.
The method comprises the steps of dividing a forest area into a plurality of orthogonal grid units according to elevation data of the forest area to obtain an elevation in each grid unit, so as to obtain elevation grids of the forest area, calculating the gradient of each grid unit according to the elevation in each grid unit, summing the gradients of all the grid units to obtain gradient data of the forest, calculating the gradient of each grid unit, summing the gradients of all the grid units to obtain gradient data of the forest, and calculating the gradient of each grid unit to obtain gradient data of the forest.
Illustratively, for example, for the grid cell h shown:
| H1 | H2 | H3 |
| H4 | h | H5 |
| H6 | H7 | H8 |
let the elevation of the grid cell h be SizeDEMThen, the gradient and the slope direction of the grid cell h can be calculated by the calculation formula shown below:
Slopesn＝(H7-H2)/(2*SizeDEM)
Slopewe＝(H4-H5)/(2*SizeDEM)
Aspect＝Slopesn/Slopewe
wherein Slope represents the gradient, Aspect represents the Slope direction, and Slope representssnSlope, representing north-south (Y-axis)weIndicating a slope in the east-west direction (X-axis).
After the slope and the slope direction of each grid unit are obtained through calculation in the mode, the slope and the slope direction of each grid unit are respectively summarized, so that slope data and slope direction data of a forest region can be obtained, and the obtained slope data and slope direction data group are used as terrain data.
In some embodiments, the fire data includes wind field data, and the acquiring the fire data corresponding to the current time phase specifically includes: acquiring wind field data of the current time phase and acquiring thermal infrared ortho-image data of the current time phase; and taking the wind field data and the thermal infrared orthographic image data of the current time phase as fire data corresponding to the current time phase.
Considering that a wind field is one of real-time elements for determining the danger level of the forest fire, the wind field data of the current time phase is acquired, and the wind field data comprises wind power data and wind direction data. For example, the current time phase of the wind farm data may be obtained from a meteorological platform based on the geographic location of the forest. Of course, in the safe area where the forest is not on fire, the wind field data of the current time phase and the wind direction data can be measured by using a wind field measuring tool to obtain the wind field data, the wind field data is vector data, only the wind field distribution on the plane 360 degrees is considered, the measurement is carried out according to the clockwise direction, the angle range is between 0 degrees (positive east) and 360 degrees (still positive east), namely a complete circle, and the example graph is shown in fig. 2.
In some embodiments, the fire data includes thermal infrared ortho image data, and the acquiring thermal infrared ortho image data of the current time phase includes: collecting a thermal infrared image and a multispectral image of a current time phase; fusing the collected thermal infrared image and the multispectral image to obtain a fused image; and carrying out coordinate conversion on the fused image to obtain thermal infrared ortho-image data of the current time phase.
Considering that the combustion temperature of the forest in fire is one of real-time elements reflecting the forest fire, the thermal infrared imaging technology can be used for knowing the forest fire. The thermal infrared imaging technology is formed according to the characteristic that an object is heated to emit infrared rays, the thermal infrared image contains temperature distribution information, the higher the temperature is, the stronger the thermal radiation emitted by the object is, the lower the temperature is, and the weaker the thermal radiation of the object is, so that the thermal infrared remote sensing image of the forest region at the current time phase is obtained to know the forest fire condition at the current time phase. Considering the complexity of forest ground features, the quality of the thermal infrared image is not ideal, in order to improve the quality of the thermal infrared image, the multispectral image of the forest region at the current time phase is also acquired, and the multispectral image of the forest region at the current time phase is fused with the thermal infrared image so as to combine the advantages of the thermal infrared image and the multispectral image and realize the quality enhancement of the thermal infrared image.
Specifically, an unmanned aerial vehicle aerial photography system (comprising an unmanned aerial vehicle and a thermal infrared sensor and a multispectral imager carried by the unmanned aerial vehicle) is controlled to collect a thermal infrared image and a multispectral image of a current time phase, and then the thermal infrared image and the multispectral image of the current time phase are fused. Illustratively, because the imaging principle of the thermal infrared image is different from that of the multispectral image, the thermal infrared image contains radiation intensity information of thermal infrared radiation emitted by a forest ground object, the multispectral image records solar radiation intensity information reflected by the ground object including visible light, near infrared and intermediate infrared bands, the two types of radiation are generated by different radiation sources, but the radiation magnitude of the ground object is the same as that of the solar radiation reflected by the ground object, and is finally determined by the geometry and physical properties of the ground object, so that strong internal correlation is inevitably existed between the two types of radiation information, and therefore, a regression relationship between the thermal infrared image and the multispectral image can be established by using a preset forward neural network, the fusion of the thermal infrared image and the multispectral image at the current time phase is realized, and a fused image with improved quality is obtained. And then, performing coordinate conversion on the fused image to obtain the thermal infrared ortho-image data of the current time phase.
And finally, taking the wind field data and the thermal infrared orthographic image data of the current time phase as fire data corresponding to the current time phase.
And S102, training a model for predicting the fire hazard level according to the environment data corresponding to the previous moment and the fire data corresponding to the current moment to obtain a fire hazard level prediction model.
And then, taking the environmental data of the previous time phase and the fire data of the current time phase as training data, and training a model for predicting the fire danger level so as to obtain a fire danger level prediction model.
In some embodiments, step S102 specifically includes: preprocessing the environmental data of the previous time phase and the fire data of the current time phase to obtain training data; and training a support vector machine according to the training data to obtain a fire hazard grade prediction model.
For example, the model for predicting the fire hazard level may be a Support Vector Machine (SVM). Before the support vector machine is trained by using the environmental data of the previous time phase and the fire data of the current time phase, the environmental data of the previous time phase and the fire data of the current time phase need to be preprocessed. Specifically, the environmental data of the previous time phase is resampled to a uniform preset resolution; resampling the fire data of the current time phase to the preset resolution, and then calculating the average value, the maximum value, the minimum value and the entropy of the gray scale of the thermal infrared ortho-image data in the resampled fire data of the current time phase to obtain the gray scale data corresponding to the thermal infrared ortho-image data; and then respectively converting the environment data of the previous time phase after resampling and the gray data corresponding to the thermal infrared ortho-image data into raster data, finishing preprocessing and obtaining training data.
And then, training the support vector machine according to the obtained training data. Specifically, the raster data corresponding to the thermal infrared ortho-image data in the training data is labeled, that is, data respectively belonging to three dangerous grade ranges of high risk, medium risk and low risk are selected from the raster data corresponding to the thermal infrared ortho-image data, and the corresponding high risk grade, medium risk grade and low risk grade are labeled. And then, according to the training data, in combination with the labeling of the danger level corresponding to the grid data of the thermal infrared ortho-image data, establishing a training set for training a support vector machine, wherein the training set is { (training data 1, danger level label 1), (training data 2, danger level label 2), }.
And further training the support vector machine according to the training set, wherein the danger levels to be distinguished comprise three conditions of high danger, medium danger and low danger, the task of the support vector machine is to summarize the rule of the training set, the three conditions are divided into three types, and the probability that the training data in the training set belong to the three types of danger levels is used as an output item of the danger levels to obtain a fire danger level prediction model so as to realize the function of automatically predicting the forest fire danger levels.
And step S103, predicting a danger level result corresponding to the forest fire in the later time phase by combining the fire data corresponding to the later time phase of the current time phase according to the environment data corresponding to the current time phase and the fire danger level prediction model.
When the danger level of the forest fire at the time phase later than the current time phase is predicted, the danger level result corresponding to the forest fire at the later time phase can be predicted according to the environment data and the fire danger level prediction model corresponding to the current time phase and by combining the fire data corresponding to the later time phase at the current time phase. The environmental data corresponding to the current time phase includes vegetation coverage data, population distribution data and terrain data of the current time phase. The vegetation coverage data corresponding to the current time phase can be obtained by obtaining a remote sensing image of the current time phase and calculating.
Illustratively, for example, the current time phase is Tn, and the latter time phase is Tn +1, then a forest fires in the Tn time phase, then the environmental data of the Tn time phase is acquired, and the fire data of the Tn +1 time phase is acquired, and the environmental data of the Tn time phase and the fire data of the Tn +1 time phase are analyzed by the fire risk level prediction model to predict the fire risk level of the Tn +1 time phase.
In some embodiments, step S103 includes sub-steps S1031 to S1032.
And a substep S1031 of preprocessing the environmental data corresponding to the current time phase and the fire data corresponding to the latter time phase.
Namely, resampling the environment data corresponding to the current time phase to a uniform preset resolution; resampling the fire data of the later time phase to the preset resolution, and then calculating the average value, the maximum value, the minimum value and the entropy of the gray scale of the thermal infrared ortho-image data in the resampled fire data of the later time phase to obtain the gray scale data corresponding to the thermal infrared ortho-image data; and then respectively converting the resampled environment data of the next time phase and the gray data corresponding to the thermal infrared ortho-image data into raster data to finish preprocessing.
And a substep S1032 of substituting the preprocessed environmental data corresponding to the current time phase and the fire data corresponding to the later time into the fire danger level prediction model for analysis to obtain the probability that the forest fire belongs to each danger level at the later time.
And substituting the preprocessed environmental data corresponding to the current time phase and the preprocessed fire data of the later time phase into a fire hazard grade prediction model for analysis to obtain the probability that the forest fire of the later time phase belongs to each hazard grade.
And a substep S1033 of comparing the probabilities belonging to the respective danger levels and determining a danger level result corresponding to the forest fire in the later time phase according to the comparison result.
And comparing the probability of the forest fire of the later time phase belonging to each danger level, determining the danger level of the forest fire of the later time phase according to the comparison result, and specifically determining the danger level with the highest probability as the danger level result corresponding to the forest fire of the later time phase.
According to the method for predicting the forest fire hazard level, when a forest is monitored to be on fire, a fire hazard level prediction model is obtained through training by selecting the environmental data of the previous time phase of the current time phase and the fire data of the current time phase as training data, and then the hazard level of the forest fire in the next time phase of the current time phase is predicted according to the environmental data and the fire hazard level prediction model corresponding to the current time phase and by combining the fire data corresponding to the next time phase of the current time phase. According to the multi-temporal environmental data and the fire data, the prediction of the danger level of the forest fire at the later temporal is realized based on the fire danger level prediction model, the foresight, convenience, high efficiency and accuracy are improved, the system has wide applicability, the scheduling of fire fighters and personnel evacuation decision can be assisted, the danger is reduced, and the guidance of the prevention and control of the forest fire is facilitated.
Referring to fig. 4, fig. 4 is a schematic block diagram of a forest fire risk level prediction apparatus according to an embodiment of the present disclosure.
As shown in fig. 4, the forest fire risk level prediction apparatus 400 includes: an acquisition module 401, a training module 402, and a prediction module 403.
An obtaining module 401, configured to obtain, when it is monitored that a forest is on fire, environment data corresponding to a previous time of a current time phase, obtain environment data corresponding to the current time phase, and obtain fire data corresponding to the current time phase;
a training module 402, configured to train a model for predicting a fire risk level according to the environmental data corresponding to the previous time and the fire data corresponding to the current time, so as to obtain a fire risk level prediction model;
and a predicting module 403, configured to predict, according to the environment data and the fire risk level prediction model corresponding to the current time phase, a risk level result corresponding to the later-time phase forest fire by combining with the fire data corresponding to the later time of the current time phase.
It should be noted that, as will be clear to those skilled in the art, for convenience and brevity of description, the specific working processes of the apparatus and the modules and units described above may refer to the corresponding processes in the foregoing forest fire risk level prediction method embodiments, and are not described herein again.
The apparatus provided by the above embodiments may be implemented in the form of a computer program that can be run on a computer device as shown in fig. 5.
Referring to fig. 5, fig. 5 is a schematic block diagram of a computer device according to an embodiment of the present disclosure. The computer device may be a Personal Computer (PC), a server, or the like having a data processing function.
As shown in fig. 5, the computer device includes a processor, a memory, and a network interface connected by a system bus, wherein the memory may include a nonvolatile storage medium and an internal memory.
The non-volatile storage medium may store an operating system and a computer program. The computer program comprises program instructions which, when executed, cause a processor to perform any one of the forest fire risk level prediction methods.
The processor is used for providing calculation and control capability and supporting the operation of the whole computer equipment.
The internal memory provides an environment for running a computer program in the non-volatile storage medium, and the computer program, when executed by the processor, causes the processor to perform any one of the forest fire risk level prediction methods.
The network interface is used for network communication, such as sending assigned tasks and the like. Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
It should be understood that the Processor may be a Central Processing Unit (CPU), and the Processor may be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, etc. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Wherein, in one embodiment, the processor is configured to execute a computer program stored in the memory to implement the steps of:
when it is monitored that a forest is on fire, acquiring environmental data corresponding to a previous time of a current time phase, acquiring environmental data corresponding to the current time phase, and acquiring fire data corresponding to the current time phase; training a model for predicting the fire hazard level according to the environmental data corresponding to the previous time and the fire data corresponding to the current time to obtain a fire hazard level prediction model; and predicting a danger level result corresponding to the forest fire in the later time phase by combining the fire data corresponding to the later time phase of the current time phase according to the environment data corresponding to the current time phase and the fire danger level prediction model.
In some embodiments, the processor, when implementing the obtaining of the environmental data corresponding to the previous time of the current time phase, is configured to implement:
acquiring a remote sensing image of a previous time phase of a current time phase, and determining vegetation coverage data of the previous time phase according to the remote sensing image of the previous time phase;
acquiring population distribution data in a preset range around a forest;
acquiring elevation data, and determining terrain data according to the elevation data;
and taking the vegetation coverage data, the population distribution data and the terrain data of the previous time phase as the corresponding environmental data of the previous time.
In some embodiments, the processor, when carrying out said determining terrain data from said elevation data, is operable to carry out:
dividing the forest area into a plurality of orthogonal grid units according to the elevation data to obtain the elevation of each grid unit;
calculating a slope of each grid cell to obtain slope data and a slope of each grid cell to obtain slope data according to the elevation in each grid cell;
and taking the calculated gradient data and the slope data as terrain data.
In some embodiments, the processor is configured to train a model for predicting a fire risk level according to the environmental data corresponding to the previous time and the fire data corresponding to the current time, and when obtaining the fire risk level prediction model, the processor is configured to:
preprocessing the environmental data corresponding to the previous time and the fire data corresponding to the current time to obtain training data;
and training a support vector machine according to the training data to obtain a fire hazard grade prediction model.
In some embodiments, the processor is configured to, when predicting a risk level result corresponding to the forest fire in a later time phase according to the environmental data corresponding to the current time phase and the fire risk level prediction model and by combining fire data corresponding to the later time phase in the current time phase, perform:
preprocessing the environmental data corresponding to the current time phase and the fire data corresponding to the later time;
substituting the preprocessed environmental data corresponding to the current time phase and the preprocessed fire data corresponding to the later time phase into the fire hazard level prediction model for analysis to obtain the probability that the forest fire belongs to each hazard level at the later time phase;
and comparing the probabilities belonging to the danger levels, and determining a danger level result corresponding to the forest fire in the later time phase according to a comparison result.
In some embodiments, the processor, when obtaining the fire data corresponding to the current time, is configured to:
acquiring wind field data of the current time phase and acquiring thermal infrared ortho-image data of the current time phase;
and taking the wind field data and the thermal infrared orthographic image data of the current time phase as fire data corresponding to the current time phase.
In some embodiments, the processor, when being configured to acquire thermal infrared ortho image data of a current phase, is configured to:
collecting the thermal infrared image and the multispectral image of the current time phase;
fusing the collected thermal infrared image and the multispectral image to obtain a fused image;
and carrying out coordinate conversion on the fused image to obtain the thermal infrared ortho-image data of the current time phase.
Embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, where the computer program includes program instructions, and when the program instructions are executed, a method implemented by the computer program instructions may refer to the various embodiments of the forest fire risk level prediction method of the present application.
The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, for example, a hard disk or a memory of the computer device. The computer readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the computer device.
Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments. While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A forest fire hazard level prediction method is characterized by comprising the following steps:
when it is monitored that a forest is on fire, acquiring environmental data corresponding to a previous time of a current time phase, acquiring environmental data corresponding to the current time phase, and acquiring fire data corresponding to the current time phase;
training a model for predicting the fire hazard level according to the environmental data corresponding to the previous time and the fire data corresponding to the current time to obtain a fire hazard level prediction model;
and predicting a danger level result corresponding to the forest fire in the later time phase by combining the fire data corresponding to the later time phase of the current time phase according to the environment data corresponding to the current time phase and the fire danger level prediction model.
2. The forest fire risk level prediction method according to claim 1, wherein the obtaining of the environmental data corresponding to the previous time of the current time phase comprises:
acquiring the remote sensing image of the previous time phase, and determining vegetation coverage data of the previous time phase according to the remote sensing image of the previous time phase;
acquiring population distribution data in a preset range around a forest;
acquiring elevation data, and determining terrain data according to the elevation data;
and taking the vegetation coverage data, the population distribution data and the terrain data of the previous time phase as the corresponding environmental data of the previous time.
3. A forest fire risk class prediction method as claimed in claim 2, wherein said determining terrain data from said elevation data comprises:
dividing the forest area into a plurality of orthogonal grid units according to the elevation data to obtain the elevation of each grid unit;
calculating a slope of each grid cell to obtain slope data and a slope of each grid cell to obtain slope data according to the elevation in each grid cell;
and taking the calculated gradient data and the slope data as terrain data.
4. The forest fire risk level prediction method according to claim 1, wherein the training of a model for predicting a fire risk level according to the environmental data corresponding to the previous time and the fire data corresponding to the current time obtains a fire risk level prediction model, and the method comprises:
preprocessing the environmental data corresponding to the previous time and the fire data corresponding to the current time to obtain training data;
and training a support vector machine according to the training data to obtain a fire hazard grade prediction model.
5. The method for predicting the forest fire risk level according to claim 1, wherein predicting the risk level result corresponding to the forest fire in the later time phase by combining the environmental data corresponding to the current time phase and the fire risk level prediction model with the fire data corresponding to the later time phase in the current time phase comprises:
preprocessing the environmental data corresponding to the current time phase and the fire data corresponding to the later time;
substituting the preprocessed environmental data corresponding to the current time phase and the preprocessed fire data corresponding to the later time phase into the fire hazard level prediction model for analysis to obtain the probability that the forest fire belongs to each hazard level at the later time phase;
and comparing the probabilities belonging to the danger levels, and determining a danger level result corresponding to the forest fire in the later time phase according to a comparison result.
6. The forest fire risk level prediction method according to claim 1, wherein the obtaining of the fire data corresponding to the current time phase comprises:
acquiring wind field data of the current time phase and acquiring thermal infrared ortho-image data of the current time phase;
and taking the wind field data and the thermal infrared orthographic image data of the current time phase as fire data corresponding to the current time phase.
7. The forest fire risk level prediction method according to claim 6, wherein the acquiring thermal infrared ortho image data of the current time phase comprises:
collecting the thermal infrared image and the multispectral image of the current time phase;
fusing the collected thermal infrared image and the multispectral image to obtain a fused image;
and carrying out coordinate conversion on the fused image to obtain the thermal infrared ortho-image data of the current time phase.
8. A forest fire risk level prediction apparatus, characterized by comprising:
the acquisition module is used for acquiring environmental data corresponding to the previous time of the current time phase, acquiring environmental data corresponding to the current time phase and acquiring fire data corresponding to the current time phase when the forest is monitored to be on fire;
the training module is used for training a model for predicting the fire hazard level according to the environmental data corresponding to the previous time and the fire data corresponding to the current time to obtain a fire hazard level prediction model;
and the prediction module is used for predicting a danger level result corresponding to the forest fire in the later time phase by combining the fire data corresponding to the later time of the current time phase according to the environment data corresponding to the current time phase and the fire danger level prediction model.
9. A computer arrangement, characterized in that the computer arrangement comprises a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program, when executed by the processor, carries out the steps of the forest fire risk level prediction method according to any one of claims 1 to 7.
10. A computer-readable storage medium, having a computer program stored thereon, wherein the computer program, when being executed by a processor, carries out the steps of the forest fire risk level prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110636930.6A CN113298311A (en) | 2021-06-08 | 2021-06-08 | Forest fire danger level prediction method, device, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110636930.6A CN113298311A (en) | 2021-06-08 | 2021-06-08 | Forest fire danger level prediction method, device, equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113298311A true CN113298311A (en) | 2021-08-24 |
Family
ID=77327545
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110636930.6A Pending CN113298311A (en) | 2021-06-08 | 2021-06-08 | Forest fire danger level prediction method, device, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113298311A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114664048A (en) * | 2022-05-26 | 2022-06-24 | 环球数科集团有限公司 | Fire monitoring and fire early warning method based on satellite remote sensing monitoring |
| CN116307739A (en) * | 2023-05-15 | 2023-06-23 | 安徽省赛达科技有限责任公司 | Forest fire prevention intelligent monitoring early warning system |
| CN116701409A (en) * | 2023-08-07 | 2023-09-05 | 湖南永蓝检测技术股份有限公司 | Sensor data storage method for intelligent on-line detection of environment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678419A (en) * | 2016-01-05 | 2016-06-15 | 天津大学 | Fine grit-based forest fire hazard probability forecasting system |
| CN107085904A (en) * | 2017-03-31 | 2017-08-22 | 上海事凡物联网科技有限公司 | Forest fire danger class decision method and system based on single classification SVM |
| CN108520363A (en) * | 2018-04-18 | 2018-09-11 | 电子科技大学 | A kind of appraisal procedure for predicting the following phase forest fire occurrence risk |
| CN110047241A (en) * | 2019-04-27 | 2019-07-23 | 刘秀萍 | A kind of forest fire unmanned plane cruise monitoring system |
-
2021
- 2021-06-08 CN CN202110636930.6A patent/CN113298311A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678419A (en) * | 2016-01-05 | 2016-06-15 | 天津大学 | Fine grit-based forest fire hazard probability forecasting system |
| CN107085904A (en) * | 2017-03-31 | 2017-08-22 | 上海事凡物联网科技有限公司 | Forest fire danger class decision method and system based on single classification SVM |
| CN108520363A (en) * | 2018-04-18 | 2018-09-11 | 电子科技大学 | A kind of appraisal procedure for predicting the following phase forest fire occurrence risk |
| CN110047241A (en) * | 2019-04-27 | 2019-07-23 | 刘秀萍 | A kind of forest fire unmanned plane cruise monitoring system |
Non-Patent Citations (1)
| Title |
|---|
| 邵振鲁主编: "《煤田火灾地球物理探测技术研究与应用》", 中国矿业大学出版社, pages: 9 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114664048A (en) * | 2022-05-26 | 2022-06-24 | 环球数科集团有限公司 | Fire monitoring and fire early warning method based on satellite remote sensing monitoring |
| CN116307739A (en) * | 2023-05-15 | 2023-06-23 | 安徽省赛达科技有限责任公司 | Forest fire prevention intelligent monitoring early warning system |
| CN116701409A (en) * | 2023-08-07 | 2023-09-05 | 湖南永蓝检测技术股份有限公司 | Sensor data storage method for intelligent on-line detection of environment |
| CN116701409B (en) * | 2023-08-07 | 2023-11-03 | 湖南永蓝检测技术股份有限公司 | Sensor data storage method for intelligent on-line detection of environment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113298311A (en) | Forest fire danger level prediction method, device, equipment and readable storage medium | |
| Kamadinata et al. | Sky image-based solar irradiance prediction methodologies using artificial neural networks | |
| Chu et al. | Hybrid intra-hour DNI forecasts with sky image processing enhanced by stochastic learning | |
| US10103548B2 (en) | Operating a solar power generating system | |
| Escrig et al. | Cloud detection, classification and motion estimation using geostationary satellite imagery for cloud cover forecast | |
| Bouzgou et al. | Minimum redundancy–maximum relevance with extreme learning machines for global solar radiation forecasting: Toward an optimized dimensionality reduction for solar time series | |
| Pereira et al. | Development of an ANN based corrective algorithm of the operational ECMWF global horizontal irradiation forecasts | |
| El Alani et al. | Short term solar irradiance forecasting using sky images based on a hybrid CNN–MLP model | |
| Arslan et al. | Application of Long Short-Term Memory neural network model for the reconstruction of MODIS Land Surface Temperature images | |
| Romaguera et al. | Detecting geothermal anomalies and evaluating LST geothermal component by combining thermal remote sensing time series and land surface model data | |
| US20160097679A1 (en) | Method for estimating land surface termperature lapse rate using infrared image | |
| US10509868B2 (en) | Operating a solar power generating system | |
| Carneiro et al. | Review on photovoltaic power and solar resource forecasting: current status and trends | |
| CN106803128B (en) | Photovoltaic power generation prediction method and device | |
| Voyant et al. | Time series modeling and large scale global solar radiation forecasting from geostationary satellites data | |
| Rocha et al. | Global horizontal and direct normal solar irradiance modeling by the machine learning methods XGBoost and deep neural networks with CNN-LSTM layers: A case study using the GOES-16 satellite imagery | |
| Moosavi et al. | Estimation of spatially enhanced soil moisture combining remote sensing and artificial intelligence approaches | |
| Munkhammar et al. | An autocorrelation-based copula model for generating realistic clear-sky index time-series | |
| Huertas-Tato et al. | Using a multi-view convolutional neural network to monitor solar irradiance | |
| Zhao et al. | Fuzzy inference systems based on multi-type features fusion for intra-hour solar irradiance forecasts | |
| Rojas-Campos et al. | Postprocessing of NWP precipitation forecasts using deep learning | |
| Choi et al. | Short-term solar irradiance forecasting using convolutional neural networks and cloud imagery | |
| Ying et al. | Net surface shortwave radiation retrieval using random forest method with MODIS/Aqua data | |
| CN117057497A (en) | Forest fire risk assessment method and model construction method and device thereof | |
| Perez-Mora et al. | Short-term Spanish aggregated solar energy forecast |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210824 |
|
| RJ01 | Rejection of invention patent application after publication |