CN115796366A - Forest pest prediction method and forest pest prediction map system - Google Patents
Forest pest prediction method and forest pest prediction map system Download PDFInfo
- Publication number
- CN115796366A CN115796366A CN202211537475.5A CN202211537475A CN115796366A CN 115796366 A CN115796366 A CN 115796366A CN 202211537475 A CN202211537475 A CN 202211537475A CN 115796366 A CN115796366 A CN 115796366A
- Authority
- CN
- China
- Prior art keywords
- pest
- forest
- data
- layer
- information
- 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.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of image data processing, in particular to a forest pest prediction method and a pest prediction forest map system, wherein the method comprises the following steps: acquiring and displaying geographic information data based on the forest geographic information layer; acquiring and displaying environmental characteristic data based on the environmental characteristic information layer; acquiring and displaying pest characteristic data based on the pest characteristic information map layer; based on the sensing node distribution layer, carrying out initialization global monitoring and displaying on a forest pest monitoring area, carrying out key monitoring and displaying on a pest high-incidence area, and acquiring and displaying the mobile information of the mobile sensing nodes and the acquired data; predicting a development trend and a geographic position of the insect pest based on an insect pest trend prediction layer and an improved deep confidence model; and storing geographic information data, environmental characteristic data and insect pest characteristic data based on the data storage module. By adopting the invention, the forest health diagnosis and the monitoring and early warning of ecological diversity change can be realized.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to a forest pest prediction method and a forest pest prediction map system.
Background
Forest pest control work is highly valued by the nation all the time, and fine management of the forest can greatly improve effective circulation of forest resources and effectively guarantee ecological safety. Therefore, the realization of the accurate prediction of forest insect pests according to sensing results such as climate change, forest growth speed, insect pest reproduction process and the like is widely concerned. The method aims to accurately predict the insect pest development trend by means of modern high technologies such as a geographic information system and a sensor sensing technology, give full play to the efficiency, improve the fine management of the forest and comprehensively solve a plurality of problems existing in the forest insect pest management at present. The requirements on the existing insect pest prediction technical means are higher and higher due to the change of natural climate, the diversity of forest species and the increase of insect pest types, and the accuracy of forest insect pest prediction can be ensured only on the premise of comprehensively mastering forest basic information, climate change trend and insect pest evolution process.
Natural climate assessment, insect pest reproduction processes and the like involved in modern insect pest prediction systems all rely on data acquisition by sensors. However, due to the diversification of forest resources and the rapid diffusion of plant diseases and insect pests, the traditional complicated insect pest prediction means cannot meet the requirement of forest accurate control. Therefore, the integration of the perception of the ecosystem in the form of an internet of things with digital twinning techniques is being studied extensively.
The enhanced type twin map for forest pest prediction is a novel pest twin map which has higher precision and richer data information relative to a common forest pest distribution system, and natural climate change, ecological diversity change, larva reproduction process, pest monitoring modes and the like can be presented in the digital twin system so as to meet the requirement of accurate pest prediction. A perfect insect pest prediction enhanced forest twin map is constructed, and the reasonable design of an insect pest prediction model is not negligible.
However, most of the current pest forecast data are relatively isolated and not perfect enough, and have the problems of data structure redundancy, low precision, poor applicability and the like, and even the information quantity of some pest sensing data is less. The defects seriously restrict the improvement of insect pest prediction precision, further form serious threat to ecological environment and influence the quality of forest resources.
Disclosure of Invention
The embodiment of the invention provides a forest pest prediction method and a pest prediction forest map system. The technical scheme is as follows:
on one hand, the method is realized based on a pest prediction forest map system, and the pest prediction forest map system comprises a forest geographic information map layer, an environment characteristic information map layer, a pest characteristic information map layer, a sensing node distribution map layer, a pest trend prediction map layer and a data storage module;
the method comprises the following steps:
acquiring and displaying geographic information data based on the forest geographic information layer;
acquiring and displaying environmental characteristic data based on the environmental characteristic information map layer, wherein the environmental characteristic data comprises natural climate information and soil information;
acquiring and displaying pest characteristic data based on the pest characteristic information map layer, wherein the pest characteristic data comprises pest period and pest species;
based on the sensing node distribution layer, carrying out initialized global monitoring and displaying on a forest pest monitoring area, carrying out key monitoring and displaying on a pest high-incidence area, and acquiring and displaying the mobile information of the mobile sensing node and the acquired data;
based on the pest trend prediction layer and an improved deep confidence model, predicting pest development trend and geographic position through geographic information data, environmental characteristic data, pest characteristic data and data acquired by a mobile sensing node, and forming a visual pest prediction map;
and storing geographic information data, environmental characteristic data, insect pest characteristic data and data acquired by the mobile sensing node based on the data storage module.
Optionally, the natural climate information includes relevant information of temperature, humidity, atmospheric pollution, acid rain, climate warming, illumination, and rain of the environment;
the soil information comprises desertification land data and wetland data.
Optionally, the pest period pitch refers to the time interval of each pest period of the pest, namely the days of the pest larva period developing to the later period;
the insect pest species include pathogenic organisms that harm forest trees, such as bacteria, fungi, and mycoplasma-like organisms.
Optionally, the initializing global monitoring and displaying of the forest pest monitoring area includes:
and deploying mobile sensing nodes according to a space division coverage algorithm, and acquiring current pest distribution information in a forest pest monitoring area.
Optionally, deploying the mobile sensing node according to a space division coverage algorithm, and acquiring current pest distribution information in a forest pest monitoring area, including:
s51, initializing the coverage radius, the communication radius and the insect pest monitoring area size of the mobile sensing node;
s52, randomly deploying a plurality of mobile sensing nodes in a forest pest monitoring area;
s53, constructing a plurality of polyhedrons based on a space division algorithm, and calculating the gravity center point (x) of each polyhedron i ,y i ,z i )；
S54, controlling the mobile sensing nodes to move towards the gravity center point of each polyhedron;
s55, calculating the coverage rate of the mobile sensing nodes, and executing the step S56 if the coverage of the whole forest pest monitoring area is preliminarily finished; otherwise, executing the step S53;
and S56, outputting a result to complete the insect pest initialization universe monitoring.
Optionally, the monitoring and displaying of the high pest incidence area includes:
simulating the superposition effect of a plurality of insect damage sources by a Gaussian basis function based on a Gaussian estimation method to obtain an insect damage degree distribution map;
and determining a high pest occurrence area according to the pest damage degree distribution map, controlling the mobile sensing node to perform key coverage on the high pest occurrence area, and acquiring detailed data of a severe pest area.
Optionally, the method for estimating pest damage degree based on gaussian includes simulating superposition effect of multiple pest damage sources by using gaussian basis function to obtain a pest damage degree distribution map, and includes:
s71, using a bounded and continuous density function
Estimating a value of each point in the forest pest monitoring area, wherein,
beta represents a first weight coefficient for a bounded continuous basis function;
s72, adopting a group of three-dimensional Gaussian functions evenly distributed in the task area as basis functions, wherein each basis function is represented by the following formula (1):
wherein the content of the first and second substances,
indicating the range of influence of the source of the pest,
indicating the lateral distance of the source of the infestation,
indicating the longitudinal distance of the source of the infestation,
vertical distance, x, representing insect pest source 0 Abscissa, y, representing the spatial center of the basis function 0 Ordinate, z, representing the spatial centre of the basis functions 0 The vertical coordinate of the spatial central point of the basis function is represented, x represents the abscissa of the insect pest source, y represents the ordinate of the insect pest source, and z represents the vertical coordinate of the insect pest source;
s73, obtaining an estimation result of the density function by adopting the following formula (2) through a self-adaptive parameter adjusting method:
wherein, the first and the second end of the pipe are connected with each other,
represents the result of the estimation of the density function, T represents the matrix transposition,
represents a second weight coefficient;
s74, if the estimation result of the density function of each point in the forest pest monitoring area meets the requirement
Determining the estimation result as a global optimal estimation;
and S75, determining a pest damage degree distribution map according to the global optimal estimation.
Optionally, the predicting pest development trend and the geographic location by using the improved deep confidence model and the geographic information data, the environmental characteristic data, the pest characteristic data and the data collected by the mobile sensing node, and forming a visual pest prediction map includes:
forming an original data set from the environment characteristic data;
establishing a forest environment information database of pest occurrence rules according to the original data set, and carrying out normalization processing on data in the forest environment information database to form a training data set and a test data set;
constructing an initial improved depth confidence model, wherein the initial improved depth confidence model consists of three layers of unsupervised limited Boltzmann machines and 1 back propagation neural network;
training the initial improved deep confidence model based on the training data set to obtain a trained improved deep confidence model;
inputting the test data set into a trained improved deep confidence model, and calculating a prediction result of the insect pest development trend;
and forming a visual pest prediction map according to the pest prediction result.
Optionally, the training the initial improved depth confidence model based on the training data set to obtain a trained improved depth confidence model includes:
inputting the training data set into a first layer of unsupervised limited Boltzmann machine for unsupervised training, and adding pest prior knowledge P in the training process i If the value is not equal to { i =1,2 and 3}, acquiring weight parameters, using the acquired weight parameters as the input of the next layer of unsupervised limited Boltzmann machine, and repeating the steps, extracting pest depth characteristics layer by layer, and acquiring an initialized parameter model;
adding a label layer on the top layer through forward propagation, obtaining model parameters through unsupervised learning, using backward propagation to propagate errors from top to bottom to each layer of unsupervised limited Boltzmann machine, and obtaining second insect pest characteristics from the training data set;
acquiring output characteristics corresponding to the training data set through a back propagation neural network arranged behind a third layer of unsupervised limited Boltzmann machine;
adjusting parameters in the initial improved depth confidence model according to the output characteristics corresponding to the training data set, and performing iteration;
and when the iteration times reach the preset times, stopping the iteration and determining the trained improved depth confidence model.
On the other hand, a pest damage prediction forest map system is provided, and the system comprises a forest geographic information map layer, an environment characteristic information map layer, a pest damage characteristic information map layer, a sensing node distribution map layer, a pest damage trend prediction map layer and a data storage module; wherein:
the forest geographic information layer is used for acquiring and displaying geographic information data;
the environmental characteristic information layer is used for acquiring and displaying environmental characteristic data, and the environmental characteristic data comprises natural climate information and soil information;
based on the insect pest characteristic information map layer, insect pest characteristic data are obtained and displayed, and the insect pest characteristic data comprise insect pest period and insect pest species;
the sensing node distribution layer is used for carrying out initialization global monitoring and displaying on a forest pest monitoring area, carrying out key monitoring and displaying on a pest high-incidence area, and acquiring and displaying the mobile information of the mobile sensing node and the acquired data;
the insect pest trend prediction map layer is used for predicting insect pest development trend and geographical position through geographic information data, environmental characteristic data, insect pest characteristic data and data acquired by the mobile sensing node based on the improved deep confidence model, and forming a visual insect pest prediction map;
the data storage module is used for storing geographic information data, environmental characteristic data, insect pest characteristic data and data collected by the mobile sensing node.
In another aspect, an electronic device is provided and includes a processor and a memory, where at least one instruction is stored in the memory, and the at least one instruction is loaded by the processor and executed to implement the forest pest prediction method.
In another aspect, a computer-readable storage medium is provided, and at least one instruction is stored in the storage medium and loaded and executed by a processor to implement the forest pest prediction method.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
the embodiment of the invention takes the existing sensor sensing technology as the basis, and combines the demand of accurate prediction of forest insect pests with the digital twinning technology to form an insect pest prediction enhanced forest twinning map. The enhanced insect pest prediction twin map mainly comprises five map layers, namely a forest geographic information map layer, an environment characteristic information map layer, an insect pest characteristic information map layer, a sensing node distribution map layer and an insect pest trend prediction map layer, and a data storage module. The enhanced insect pest prediction twin map provided by the invention has the advantages of high accuracy, full information quantity, intelligent management, real-time feedback and the like, and can realize forest health diagnosis and monitoring and early warning of ecological diversity change to a great extent, further reduce forest insect pest diffusion and improve forest ecological environment.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, 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 flow chart of a forest pest prediction method according to an embodiment of the present invention;
FIG. 2 is a schematic view of a polyhedron provided by an embodiment of the present invention;
FIG. 3 is a schematic diagram of an initial improved depth confidence model provided by an embodiment of the invention;
FIG. 4 is a block diagram of a system for predicting a forest map of pests according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
To make the technical problems, technical solutions and advantages of the present invention more apparent, the following detailed description is given with reference to the accompanying drawings and specific embodiments.
The embodiment of the invention provides a forest pest damage prediction method which can be realized by a pest damage prediction forest map system, wherein the pest damage prediction forest map system can comprise a forest geographic information map layer, an environment characteristic information map layer, a pest damage characteristic information map layer, a sensing node distribution map layer, a pest damage trend prediction map layer and a data storage module. As shown in fig. 1, a flow chart of a forest pest prediction method, a processing flow of the method may include the following steps:
s1, acquiring and displaying geographic information data based on a forest geographic information layer.
In a feasible implementation mode, the forest resource geographic position is acquired based on the existing geographic information system technology, and is sorted into geographic information data to be displayed. The geographic information data can be acquired and displayed by a method commonly used in the prior art, which is not described in detail in the embodiments of the present invention.
And S2, acquiring and displaying the environmental characteristic data based on the environmental characteristic information layer.
Wherein, the environmental characteristic data comprises natural climate information and soil information.
The natural climate information is used for reflecting the influence of natural climate factors on insect pest occurrence in a forest system, and the natural climate information can comprise the relevant information of environment temperature, humidity, atmospheric pollution, acid rain, climate warming, illumination, rainwater and the like because the natural phenomena of environment temperature, humidity, acid rain, climate warming, illumination, rainwater and the like have different influences on pest breeding.
The soil information is used for analyzing the influence of different soil environments on the forest development process and the influence of insect pest survival, and can comprise desertification land data, wetland data and the like.
In a possible implementation manner, the obtaining and displaying of the environmental characteristic data may be performed by a common method in the prior art, and the details of the embodiment of the present invention are not described herein.
And S3, acquiring and displaying pest characteristic data based on the pest characteristic information map layer, wherein the pest characteristic data comprises pest period and pest species.
Wherein, the pest period distance refers to the time interval of each pest period of pests, namely the days from the development of the larva period of the pests to the later period, and the pests in different periods have different threats to the damage of forest trees.
The insect pest species include pathogenic organisms that harm forest trees, such as bacteria, fungi, and mycoplasma-like organisms.
In a possible implementation manner, the acquisition and display of the pest characteristic data can be performed by a common method in the prior art, and the details of the embodiment of the present invention are not repeated herein.
And S4, based on the sensing node distribution layer, carrying out initialization global monitoring and displaying on the forest pest monitoring area, carrying out key monitoring and displaying on the pest high-incidence area, and acquiring and displaying the mobile information of the mobile sensing nodes and the acquired data.
In one possible embodiment, S4 may include the following steps S41-S42:
s41, carrying out initialization global monitoring and displaying on a forest pest monitoring area, including:
and deploying mobile sensing nodes according to a space division coverage algorithm to obtain current pest distribution information in the forest pest monitoring area.
The method specifically comprises the following steps:
s411, initializing the coverage radius, the communication radius and the insect pest monitoring area size of the mobile sensing node.
In a possible implementation, the coverage radius R of the mobile sensing node is initialized a Communication radius R c ＝2R a And insect pest monitoring area size AxBxC.
S412, randomly deploying a plurality of mobile sensing nodes in the forest pest monitoring area.
In a feasible implementation mode, n mobile sensing nodes S = { S } are randomly deployed in a pest monitoring area 1 ,…,S k ,…S n }。
S413, constructing a polyhedron based on a space division algorithm, and calculating the gravity center point (x) of the polyhedron i ,y i ,z i )。
In one possible embodiment, based on a spatial segmentation algorithm, a plurality of polyhedrons are constructed, as shown in FIG. 2 as an exemplary set of { D } 1 ,D 2 ,D 3 ,D 4 ,D 5 ,D 6 A polyhedron, which can be an octahedron, and then the gravity center point (x) of the polyhedron is calculated i ,y i ,z i ) Wherein D is 1 -D 6 Denotes the vertex of the polyhedron, and Q denotes the gravity center point of the polyhedron.
And S414, controlling the mobile sensing node to move towards the gravity center point of the polyhedron.
And S415, calculating the coverage rate of the mobile sensing nodes, and if the coverage of the whole forest pest monitoring area is preliminarily completed, executing the step S416. Otherwise, step S413 is executed.
It should be noted that, the method for calculating the coverage of the mobile sensing node may adopt a commonly used calculation method in the prior art, which is not described in detail in the embodiment of the present invention.
And S416, outputting a result to complete the insect pest initialization universe monitoring.
In one possible implementation, the information monitored by each mobile sensing node is output.
S42, carrying out key monitoring and displaying on the high-incidence areas of the insect pests, and comprising the following steps:
and S421, simulating the superposition effect of a plurality of insect damage sources by a Gaussian basis function based on a Gaussian estimation method, and acquiring an insect damage degree distribution map.
In one possible embodiment, a bounded and continuous density function is used
Insect pest estimation monitorThe value of each polyhedral centroid point of the region A x B x C is measured, wherein,
for bounded continuous basis functions, T represents the matrix transpose and β is the first weight coefficient.
Adopting a group of three-dimensional Gaussian functions which are evenly distributed in the task area as basis functions, wherein each basis function is expressed as:
in the formula (1)
Showing the influence range of insect pest sources, (x) 0 ,y 0 ,z 0 ) Is the spatial center point coordinate of the basis function,
indicating the lateral distance of the source of the infestation,
the longitudinal distance of the source of the infestation is indicated,
indicating the vertical distance of the source of the pest, x 0 Abscissa, y, representing the spatial center point of the basis function 0 Ordinate, z, representing the spatial centre point of the basis function 0 The vertical coordinate of the spatial central point of the basis function is represented, x represents the abscissa of the insect pest source, y represents the ordinate of the insect pest source, and z represents the vertical coordinate of the insect pest source.
Obtaining an estimated value of a density function by using a self-adaptive parameter adjusting method:
wherein, T tableThe matrix is shown as a transpose,
is a second weight coefficient;
in the pest monitoring area, if the density function estimation result satisfies every point in the area
And calling the estimation result as a global optimal estimation, and determining a pest damage degree distribution map according to the global optimal estimation.
S422, determining a high-pest-damage-degree distribution map, controlling the mobile sensing nodes to perform key coverage on the high-pest-damage-degree distribution map, and acquiring detailed data of a severe pest region.
In one possible embodiment, areas with pest damage degrees larger than a preset threshold value are determined as regions with high pest incidence according to the pest damage degree distribution map.
It should be noted that, the method for controlling the mobile sensing node to perform the key coverage on the area with high occurrence of the insect pest and the method for obtaining the detailed data of the area with the serious insect pest according to the mobile sensing node may adopt a common method in the prior art, and the embodiment of the present invention is not described herein again.
And S5, predicting a pest development trend and a geographic position based on the pest trend prediction layer and the improved deep confidence model through geographic information data, environmental characteristic data, pest characteristic data and data acquired by the mobile sensing nodes, and forming a visual pest prediction map.
In a possible embodiment, the step S5 may specifically include the following steps S51 to S55:
and S51, forming an original data set by the environment characteristic data.
In one possible embodiment, the environmental characteristic data (soil temperature, humidity, soil moisture, rain season, air humidity, illumination intensity, etc.) are formed into the originalStarting data set E o 。
And S52, establishing a forest environment information database of the pest occurrence rule according to the original data set, and carrying out normalization processing on data in the forest environment information database to form a training data set and a testing data set.
S53, constructing an initial improved depth confidence model, wherein the initial improved depth confidence model consists of three layers of unsupervised limited Boltzmann machines and 1 back propagation neural network.
In one possible embodiment, as shown in FIG. 3, first, the preprocessed raw data D is processed o Inputting into a first layer of unsupervised limited Boltzmann machine for unsupervised training, and adding pest prior knowledge P during the training i = { i =1,2,3}, obtaining weight parameters, using the output as the input of the next layer of unsupervised limited Boltzmann machine, repeatedly training in such a way, extracting pest depth characteristics layer by layer, and obtaining an initialized parameter model;
then, adding a label layer on the top layer through forward propagation, obtaining model parameters through unsupervised learning, and using backward propagation to propagate errors from top to bottom to each layer of unsupervised limited Boltzmann machine to obtain more abstract insect pest characteristics from original data;
finally, a back propagation neural network is arranged behind the third layer of unsupervised limited Boltzmann machine to obtain the final output characteristics; the top back propagation neural network comprises an input layer, a hidden layer and an output layer and is used for predicting insect pest development trend.
And S54, training the initial improved depth confidence model based on the training data set to obtain the trained improved depth confidence model.
And S55, inputting the test data set into the trained improved deep confidence model, and calculating a prediction result of the insect pest development trend.
And S56, forming a visual pest prediction map according to the pest prediction result.
The embodiment of the invention takes the existing sensor sensing technology as the basis, and combines the digital twinning technology with the requirement of accurate prediction of forest insect damage to form an insect damage prediction enhanced forest twinning map. The enhanced insect pest prediction twin map mainly comprises five map layers, namely a forest geographic information map layer, an environment characteristic information map layer, an insect pest characteristic information map layer, a sensing node distribution map layer and an insect pest trend prediction map layer, and a data storage module. The enhanced insect pest prediction twin map provided by the invention has the advantages of high accuracy, full information quantity, intelligent management, real-time feedback and the like, and can realize forest health diagnosis and monitoring and early warning of ecological diversity change to a great extent, further reduce forest insect pest diffusion and improve forest ecological environment.
Fig. 4 illustrates a pest prediction forest map system for implementing a forest pest prediction method according to an exemplary embodiment. As shown in fig. 4, the system includes a forest geographic information layer, an environment characteristic information layer, a pest characteristic information layer, a sensing node distribution layer, a pest tendency prediction layer, and a data storage module; wherein:
the forest geographic information layer is used for acquiring and displaying geographic information data;
the environmental characteristic information layer is used for acquiring and displaying environmental characteristic data, and the environmental characteristic data comprises natural climate information and soil information;
the pest characteristic information map layer is used for acquiring and displaying pest characteristic data, and the pest characteristic data comprises pest period and pest species;
the sensing node distribution layer is used for carrying out initialization global monitoring and displaying on a forest pest monitoring area, carrying out key monitoring and displaying on a pest high-incidence area, and acquiring and displaying the mobile information of the mobile sensing node and the acquired data;
the pest trend prediction layer is used for predicting the pest development trend and the geographic position through geographic information data, environmental characteristic data, pest characteristic data and data acquired by the mobile sensing nodes based on the improved deep confidence model, and forming a visual pest prediction map;
and the data storage module is used for storing geographic information data, environmental characteristic data, insect pest characteristic data and data acquired by the mobile sensing node.
The embodiment of the invention takes the existing sensor sensing technology as the basis, and combines the demand of accurate prediction of forest insect pests with the digital twinning technology to form an insect pest prediction enhanced forest twinning map. The enhanced insect pest prediction twin map mainly comprises five layers of a forest geographic information layer, an environment characteristic information layer, an insect pest characteristic information layer, a sensing node distribution layer and an insect pest trend prediction layer and a data storage module. The enhanced insect pest prediction twin map provided by the invention has the advantages of high accuracy, full information quantity, intelligent management, real-time feedback and the like, and can realize forest health diagnosis and monitoring and early warning of ecological diversity change to a great extent, further reduce forest insect pest diffusion and improve forest ecological environment.
Fig. 5 is a schematic structural diagram of an electronic device 500 according to an embodiment of the present invention, where the electronic device 500 may generate a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 501 and one or more memories 502, where the memory 502 stores at least one instruction, and the at least one instruction is loaded and executed by the processor 501 to implement the steps of the forest pest prediction method.
In an exemplary embodiment, a computer-readable storage medium, such as a memory including instructions executable by a processor in a terminal, to perform the forest pest prediction method is also provided. For example, the computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A forest pest prediction method is characterized in that the method is realized based on a pest prediction forest map system, and the pest prediction forest map system comprises a forest geographic information map layer, an environment characteristic information map layer, a pest characteristic information map layer, a sensing node distribution map layer, a pest trend prediction map layer and a data storage module;
the method comprises the following steps:
acquiring and displaying geographic information data based on the forest geographic information layer;
acquiring and displaying environmental characteristic data based on the environmental characteristic information map layer, wherein the environmental characteristic data comprises natural climate information and soil information;
acquiring and displaying pest characteristic data based on the pest characteristic information map layer, wherein the pest characteristic data comprises pest period and pest species;
based on the sensing node distribution layer, carrying out initialized global monitoring and displaying on a forest pest monitoring area, carrying out key monitoring and displaying on a pest high-incidence area, and acquiring and displaying the mobile information of the mobile sensing node and the acquired data;
based on the pest trend prediction layer and an improved deep confidence model, predicting pest development trend and geographic position through geographic information data, environmental characteristic data, pest characteristic data and data acquired by a mobile sensing node, and forming a visual pest prediction map;
and storing geographic information data, environmental characteristic data, insect pest characteristic data and data acquired by the mobile sensing node based on the data storage module.
2. The method of claim 1, wherein the natural climate information comprises information about temperature, humidity, atmospheric pollution, acid rain, climate warming, light, rain water of the environment;
the soil information comprises desertification land data and wetland data.
3. The method of claim 1, wherein the pest phase interval refers to a time interval between pest phases, i.e., a number of days until a pest larva phase develops to a later stage;
the insect pest species include pathogenic organisms that harm forest trees, such as bacteria, fungi, and mycoplasma-like organisms.
4. The method of claim 1, wherein the initialized global monitoring and displaying of the forest pest monitoring area comprises:
and deploying mobile sensing nodes according to a space division coverage algorithm, and acquiring current pest distribution information in a forest pest monitoring area.
5. The method according to claim 4, wherein the deploying of the mobile sensing nodes according to the space division coverage algorithm to obtain the current pest distribution information in the forest pest monitoring area comprises:
s51, initializing the coverage radius, the communication radius and the insect pest monitoring area size of the mobile sensing node;
s52, randomly deploying a plurality of mobile sensing nodes in a forest pest monitoring area;
s53, constructing a plurality of polyhedrons based on a space division algorithm, and calculating the gravity center point (x) of each polyhedron i ,y i ,z i )；
S54, controlling the mobile sensing nodes to move towards the gravity center point of each polyhedron;
s55, calculating the coverage rate of the mobile sensing nodes, and executing the step S56 if the coverage of the whole forest pest monitoring area is preliminarily finished; otherwise, executing the step S53;
and S56, outputting a result to complete insect pest initialization global monitoring.
6. The method of claim 1, wherein said highlighting and displaying areas of high pest occurrence comprises:
simulating the superposition effect of a plurality of insect damage sources by a Gaussian basis function based on a Gaussian estimation method to obtain an insect damage degree distribution map;
and determining a high pest occurrence area according to the pest damage degree distribution map, controlling the mobile sensing node to perform key coverage on the high pest occurrence area, and acquiring detailed data of a severe pest area.
7. The method of claim 6, wherein the Gaussian estimation-based method for simulating the superposition effect of multiple pest damage sources by a Gaussian base function to obtain the pest damage degree distribution map comprises:
s71, using bounded and continuous density function
Estimating a value of each point in the forest pest monitoring area, wherein,
beta represents a first weight coefficient for a bounded continuous basis function;
s72, adopting a group of three-dimensional Gaussian functions evenly distributed in the task area as basis functions, wherein each basis function is represented by the following formula (1):
wherein the content of the first and second substances,
the influence range of insect pest sources is shown,
indicating the lateral distance of the source of the infestation,
indicating the longitudinal distance of the source of the infestation,
indicating the vertical distance of the source of the pest, x 0 Abscissa, y, representing the spatial center of the basis function 0 Ordinate, z, representing the spatial centre point of the basis function 0 The vertical coordinate of the spatial central point of the basis function is represented, x represents the abscissa of the insect pest source, y represents the ordinate of the insect pest source, and z represents the vertical coordinate of the insect pest source;
s73, obtaining an estimation result of the density function by adopting the following formula (2) through a self-adaptive parameter adjusting method:
wherein the content of the first and second substances,
represents the result of the estimation of the density function, T represents the matrix transposition,
represents a second weight coefficient;
s74, if the estimation result of the density function of each point in the forest pest monitoring area meets the requirement
Determining the estimation result as a global optimal estimation;
and S75, determining a pest damage degree distribution map according to the global optimal estimation.
8. The method of claim 1, wherein the predicting pest development trend and geographic location based on the improved deep confidence model by geographic information data, environmental characteristic data, pest characteristic data and data collected by the mobile sensing node, and forming a visual pest prediction map comprises:
forming an original data set from the environment characteristic data;
establishing a forest environment information database of pest occurrence rules according to the original data set, and carrying out normalization processing on data in the forest environment information database to form a training data set and a test data set;
constructing an initial improved depth confidence model, wherein the initial improved depth confidence model consists of three layers of unsupervised limited Boltzmann machines and 1 back propagation neural network;
training the initial improved depth confidence model based on the training data set to obtain a trained improved depth confidence model;
inputting the test data set into a trained improved deep confidence model, and calculating a prediction result of the insect pest development trend;
and forming a visual pest prediction map according to the pest prediction result.
9. The method of claim 8, wherein training the initial improved deep confidence model based on the training data set to obtain a trained improved deep confidence model comprises:
inputting the training data set into a first layer of unsupervised limited Boltzmann machine for unsupervised training, and adding pest prior knowledge P in the training process i The method comprises the steps of (1), (2) and (3), obtaining weight parameters, using the obtained weight parameters as the input of the next layer of unsupervised limited Boltzmann machine, and repeating the steps to extract the depth characteristics of the insect pests layer by layer to obtain an initialized parameter model;
adding a label layer on the top layer through forward propagation, obtaining model parameters through unsupervised learning, using backward propagation to propagate errors from top to bottom to each layer of unsupervised limited Boltzmann machine, and obtaining second pest characteristics from the training data set;
acquiring output characteristics corresponding to the training data set through a back propagation neural network arranged behind a third layer of unsupervised limited Boltzmann machine;
adjusting parameters in the initial improved depth confidence model according to the output characteristics corresponding to the training data set, and performing iteration;
and when the iteration times reach the preset times, stopping the iteration and determining the trained improved depth confidence model.
10. A pest damage prediction forest map system is characterized by comprising a forest geographic information map layer, an environment characteristic information map layer, a pest damage characteristic information map layer, a sensing node distribution map layer, a pest damage trend prediction map layer and a data storage module; wherein:
the forest geographic information layer is used for acquiring and displaying geographic information data;
the environment characteristic information layer is used for acquiring and displaying environment characteristic data, and the environment characteristic data comprises natural climate information and soil information;
based on the insect pest characteristic information map layer, acquiring and displaying insect pest characteristic data, wherein the insect pest characteristic data comprises insect pest period and insect pest type;
the sensing node distribution layer is used for carrying out initialization global monitoring and displaying on a forest pest monitoring area, carrying out key monitoring and displaying on a pest high-incidence area, and acquiring and displaying the mobile information of the mobile sensing node and the acquired data;
the insect pest trend prediction map layer is used for predicting insect pest development trend and geographical position through geographic information data, environmental characteristic data, insect pest characteristic data and data acquired by the mobile sensing node based on the improved deep confidence model, and forming a visual insect pest prediction map;
the data storage module is used for storing geographic information data, environmental characteristic data, insect pest characteristic data and data collected by the mobile sensing node.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211537475.5A CN115796366B (en) | 2022-12-02 | 2022-12-02 | Forest pest prediction method and pest prediction forest map system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211537475.5A CN115796366B (en) | 2022-12-02 | 2022-12-02 | Forest pest prediction method and pest prediction forest map system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115796366A true CN115796366A (en) | 2023-03-14 |
| CN115796366B CN115796366B (en) | 2023-08-01 |
Family
ID=85444922
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211537475.5A Active CN115796366B (en) | 2022-12-02 | 2022-12-02 | Forest pest prediction method and pest prediction forest map system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115796366B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117390110B (en) * | 2023-12-13 | 2024-02-06 | 四川省林业科学研究院 | Method and system for generating electronic map of plant diseases and insect pests |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020016676A1 (en) * | 2000-07-26 | 2002-02-07 | Christopher Sann | Climatic conditions based pest control management |
| CN103604880A (en) * | 2013-11-07 | 2014-02-26 | 同济大学 | Method for detecting triazophos pesticide in environmental samples of different types |
| CN105631526A (en) * | 2014-10-31 | 2016-06-01 | 航天恒星科技有限公司 | Forest pest disease outbreak risk prediction method and device |
| CN113963262A (en) * | 2021-12-20 | 2022-01-21 | 中国地质大学（武汉） | Mining area land coverage classification method based on depth feature fusion model |
| CN114067311A (en) * | 2021-08-11 | 2022-02-18 | 中国农业科学院茶叶研究所 | Tea tree pest and disease prediction method based on intelligent recognition crowd-sourced data |
| CN114170513A (en) * | 2021-12-08 | 2022-03-11 | 广东省农业科学院植物保护研究所 | Spodoptera frugiperda pest situation monitoring method and system and storage medium |
| CN115017704A (en) * | 2022-06-07 | 2022-09-06 | 同济大学 | Covering method and system for sensing insect pest key area coupled by dynamic and static nodes |
-
2022
- 2022-12-02 CN CN202211537475.5A patent/CN115796366B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020016676A1 (en) * | 2000-07-26 | 2002-02-07 | Christopher Sann | Climatic conditions based pest control management |
| CN103604880A (en) * | 2013-11-07 | 2014-02-26 | 同济大学 | Method for detecting triazophos pesticide in environmental samples of different types |
| CN105631526A (en) * | 2014-10-31 | 2016-06-01 | 航天恒星科技有限公司 | Forest pest disease outbreak risk prediction method and device |
| CN114067311A (en) * | 2021-08-11 | 2022-02-18 | 中国农业科学院茶叶研究所 | Tea tree pest and disease prediction method based on intelligent recognition crowd-sourced data |
| CN114170513A (en) * | 2021-12-08 | 2022-03-11 | 广东省农业科学院植物保护研究所 | Spodoptera frugiperda pest situation monitoring method and system and storage medium |
| CN113963262A (en) * | 2021-12-20 | 2022-01-21 | 中国地质大学（武汉） | Mining area land coverage classification method based on depth feature fusion model |
| CN115017704A (en) * | 2022-06-07 | 2022-09-06 | 同济大学 | Covering method and system for sensing insect pest key area coupled by dynamic and static nodes |
Non-Patent Citations (2)
| Title |
|---|
| 张雨辰;: "农业物联网智能信息管理系统需求", 农业工程, no. 01 * |
| 石根生,李典谟: "地理信息系统与森林病虫害管理", 森林病虫通讯, no. 03 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117390110B (en) * | 2023-12-13 | 2024-02-06 | 四川省林业科学研究院 | Method and system for generating electronic map of plant diseases and insect pests |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115796366B (en) | 2023-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kamdem et al. | Anthropogenic habitat disturbance and ecological divergence between incipient species of the malaria mosquito Anopheles gambiae | |
| Yost et al. | Predictive modeling and mapping sage grouse (Centrocercus urophasianus) nesting habitat using Maximum Entropy and a long-term dataset from Southern Oregon | |
| CN109902885A (en) | Typhoon prediction method based on deep learning mixed CNN-LSTM model | |
| Valle et al. | Comparing the performance of species distribution models of Zostera marina: implications for conservation | |
| Snell | Simulating long‐distance seed dispersal in a dynamic vegetation model | |
| Pérez et al. | ForestSimMPB: A swarming intelligence and agent-based modeling approach for mountain pine beetle outbreaks | |
| Mi et al. | Combining occurrence and abundance distribution models for the conservation of the Great Bustard | |
| Koldasbayeva et al. | Large-scale forecasting of Heracleum sosnowskyi habitat suitability under the climate change on publicly available data | |
| CN115796366A (en) | Forest pest prediction method and forest pest prediction map system | |
| JP2009136265A (en) | Predicting system for biodiversity progress effect of city greening | |
| CN115359366A (en) | Remote sensing image target detection method based on parameter optimization | |
| CN115810149A (en) | High-resolution remote sensing image building extraction method based on superpixel and image convolution | |
| CN115457408A (en) | Land monitoring method and device, electronic equipment and medium | |
| Gauffre et al. | Agricultural intensification alters marbled newt genetic diversity and gene flow through density and dispersal reduction | |
| Radiarta et al. | Biophysical models for Japanese scallop, Mizuhopecten yessoensis, aquaculture site selection in Funka Bay, Hokkaido, Japan, using remotely sensed data and geographic information system | |
| Chadœuf et al. | Modelling unbiased dispersal kernels over continuous space by accounting for spatial heterogeneity in marking and observation efforts | |
| Vanhove et al. | Estimating resistance surfaces using gradient forest and allelic frequencies | |
| CN116341841A (en) | Runoff forecast error correction method, apparatus, device, medium and program product | |
| Matsushima et al. | Effects of landscape heterogeneity at multiple spatial scales on paddy field-breeding frogs in a large alluvial plain in Japan | |
| CN114169646A (en) | Water bloom prediction method, device, electronic equipment and computer readable storage medium | |
| Dytham et al. | Modelling the effects of habitat fragmentation | |
| Hirschfeld et al. | What Darwin could not see: island formation and historical sea levels shape genetic divergence and island biogeography in a coastal marine species | |
| Hennen et al. | Global-Detector-GIS-and Knowledge-based Tool for a Global Detection of the Potential for Production, Supply and Demand. | |
| Li et al. | Visualization of tomato growth based on dry matter flow | |
| CN112528574A (en) | Method and device for calculating ecological water demand of wetland |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |