Vegetation environment coupling prediction method and system based on multi-source remote sensing data fusion

Abstract

The invention discloses a vegetation environment coupling prediction method and system based on multi-source remote sensing data fusion, and relates to the field of vegetation environment monitoring. Specifically, vegetation canopy structure data, vegetation environment temperature detection data and vegetation component characteristic data are disclosed, and vegetation canopy structure parameters are calculated through a data fusion algorithm; introducing vegetation canopy structure parameters to construct a vegetation transpiration intensity outlier detection model; identifying a local drought or ponding area based on a vegetation transpiration intensity outlier detection model; detecting trunk insect damage vibration signals and trunk insect passage scanning data based on a local drought or ponding area; and simulating an insect pest spreading path according to the trunk insect pest eating vibration signal and the trunk insect channel scanning data. According to the method, the specific ecological structure of vegetation is analyzed, and the in-depth research and application of an instant response mechanism aiming at disasters are realized.

Description

Technical Field

[0001] The present invention relates to the field of vegetation environment monitoring, and particularly to a method and system for coupling prediction of vegetation environment based on multi-source remote sensing data fusion. Background Art

[0002] In the field of vegetation management, intelligence has gradually become the main trend in crop cultivation and landscape gardening. The multi-modal perception system is precisely a key technology to improve management efficiency and accuracy. For example, by integrating diverse sensor devices and remote sensing technology to monitor the vegetation environment, and constructing an environment-plant response model based on big data analysis, aiming to provide scientific and accurate planting decision-making support. However, the above technologies are usually used for the detection of agricultural crops, and there is still a lack of in-depth research and application on analyzing the specific ecological structure of vegetation in landscape gardening and the instant response mechanism for disasters. Summary of the Invention

[0003] The technical problem to be solved by the present invention is that in the vegetation management of landscape gardening, there is still a lack of in-depth research and application on analyzing the specific ecological structure of vegetation and the instant response mechanism for disasters. The purpose is to provide a method and system for coupling prediction of vegetation environment based on multi-source remote sensing data fusion. By analyzing the canopy structure and dynamically modeling the transpiration intensity field, the spread path of insect pests is monitored and predicted in real time, thus solving the above technical problems.

[0004] The present invention is realized by the following technical solutions:

[0005] A method for coupling prediction of vegetation environment based on multi-source remote sensing data fusion includes: collecting vegetation canopy structure data, vegetation environment temperature detection data, and vegetation component characteristic data by using multiple sensors; calculating vegetation canopy structure parameters from the above vegetation canopy structure data, the above vegetation environment temperature detection data, and the above vegetation component characteristic data through a data fusion algorithm; introducing the above vegetation canopy structure parameters to construct a vegetation transpiration intensity outlier detection model; identifying local drought or waterlogging areas based on the above vegetation transpiration intensity outlier detection model; detecting the vibration signals of trunk pest infestation and trunk insect tunnel scanning data based on the local drought or waterlogging areas; simulating the spread path of insect pests according to the above trunk pest infestation vibration signals and the above trunk insect tunnel scanning data.

[0006] The above-mentioned collecting vegetation canopy structure data, vegetation environment temperature detection data, and vegetation component characteristic data by using multiple sensors specifically includes:

[0007] Detecting vegetation canopy structure data by using lidar; detecting vegetation environment temperature detection data by using thermal infrared imaging; detecting vegetation cost characteristic data by using a hyperspectral camera.

[0008] Before calculating the vegetation canopy structure parameters from the above vegetation canopy structure data, the above vegetation environmental temperature detection data, and the above vegetation component characteristic data through a data fusion algorithm, the following steps are also included:

[0009] Performing spatial domain registration on the above vegetation canopy structure data and satellite elevation data; performing time domain registration on the above vegetation environmental temperature detection data using the dynamic time warping algorithm; performing spectral domain registration on the above vegetation cost characteristic data through TV regularization.

[0010] The above step of introducing the above vegetation canopy structure parameters to construct a vegetation transpiration intensity outlier detection model specifically includes:

[0011] Introducing canopy structure parameters to establish the Penman-Monteith equation to calculate the transpiration intensity;

[0012] Using the Isolation Forest algorithm on the Penman-Monteith equation to construct a transpiration intensity outlier detection model.

[0013] The above step of detecting trunk pest boring vibration signals and trunk insect tunnel scan data based on local drought or waterlogging areas specifically includes:

[0014] Using multiple trunk vibration sensors to capture trunk pest boring signals at a preset frequency; using an X-ray tomography device to detect the insect tunnels inside the trunk.

[0015] The above step of simulating the pest spread path based on the above trunk pest boring vibration signals and the above trunk insect tunnel scan data specifically includes:

[0016] Based on the boring vibration signal characteristics and the bored trunks, constructing a boring feature library for multiple pest types;

[0017] Identifying the pest type of the insect tunnel to be detected according to the above boring feature library;

[0018] Collecting the changes in the acquisition positions of multiple groups of the above trunk pest boring vibration signals, and the spread speed in at least one insect tunnel direction, and predicting the spread speed in at least one insect tunnel direction of the above insect tunnel to be detected based on a deep learning classification model;

[0019] Generating a three-dimensional model of the pest spread of the above insect tunnel to be detected.

[0020] The above step of identifying local drought or waterlogging areas based on the above vegetation transpiration intensity outlier detection model specifically includes:

[0021] When there are more transpiration intensity outliers, the corresponding area is a local waterlogging area; when there are fewer transpiration intensity outliers, the corresponding area is a local waterlogging area.

[0022] Vegetation-environment coupling prediction system based on multi-source remote sensing data fusion, comprising: Data acquisition module: Multiple sensors are used to acquire vegetation canopy structure data, vegetation environment temperature detection data, and vegetation component characteristic data; Data fusion module: The above-mentioned vegetation canopy structure data, the above-mentioned vegetation environment temperature detection data, and the above-mentioned vegetation component characteristic data are used to calculate vegetation canopy structure parameters through a data fusion algorithm; Model construction module: The above-mentioned vegetation canopy structure parameters are introduced to construct an outlier detection model for vegetation transpiration intensity; Region identification module: Based on the above-mentioned outlier detection model for vegetation transpiration intensity, local drought or waterlogging areas are identified; Insect tunnel detection module: Based on local drought or waterlogging areas, trunk pest feeding vibration signals and trunk insect tunnel scanning data are detected; Insect tunnel simulation module: According to the above-mentioned trunk pest feeding vibration signals and the above-mentioned trunk insect tunnel scanning data, the pest spread path is simulated.

[0023] An electronic device, comprising a memory, a processor, and a computer program running on the above-mentioned processor, and when the above-mentioned processor executes the above-mentioned computer program, the steps of the above-mentioned vegetation-environment coupling prediction method based on multi-source remote sensing data fusion are implemented.

[0024] A computer-readable storage medium, the above-mentioned computer-readable storage medium stores a computer program, and when the above-mentioned computer program is executed by a processor, the steps of the above-mentioned vegetation-environment coupling prediction method based on multi-source remote sensing data fusion are implemented.

[0025] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0026] The present application proposes a vegetation-environment coupling prediction method and system based on multi-source remote sensing data fusion. The vegetation canopy structure parameters are calculated through a data fusion algorithm using vegetation canopy structure data, vegetation environment temperature detection data, and vegetation component characteristic data; the outlier detection model for vegetation transpiration intensity is constructed by introducing the vegetation canopy structure parameters, so as to identify local drought or waterlogging areas by combining the characteristics of the vegetation canopy structure, environmental temperature, and vegetation components with the vegetation transpiration intensity; and based on local drought or waterlogging areas, trunk pest feeding vibration signals and trunk insect tunnel scanning data are detected; according to the trunk pest feeding vibration signals and the trunk insect tunnel scanning data, the pest spread path in local drought or waterlogging areas is simulated. The present invention realizes the monitoring of grassland ecological degradation through the identification of drought or waterlogging areas, and can also conduct real-time monitoring and prediction of multi-dimensional ecological behaviors such as pest spread paths, canopy structures, and transpiration intensity fields, realizing the lack of analysis of specific ecological structures of vegetation and in-depth research and application of an instant response mechanism for disasters in the vegetation management of landscape gardening, providing more comprehensive, accurate, and real-time intelligent decision-making support for vegetation management, thereby filling the gap in the monitoring and prediction of multi-modal ecological events in the prior art. Description of the Drawings

[0027] To more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following will briefly introduce the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and thus should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative effort, other related drawings can also be obtained based on these drawings. In the drawings:

[0028] Figure 1 This is a flowchart of the vegetation-environment coupling prediction method based on multi-source remote sensing data fusion in the embodiments of this application. Specific embodiments

[0029] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the following will further elaborate on the present invention in combination with the embodiments and the drawings. The illustrative embodiments of the present invention and their descriptions are only used to explain the present invention and are not intended to limit the present invention.

[0030] Embodiment

[0031] As Figure 1 shown, the embodiments of this application provide a vegetation-environment coupling prediction method based on multi-source remote sensing data fusion, including: collecting vegetation canopy structure data, vegetation environment temperature detection data, and vegetation component characteristic data using multiple sensors; calculating vegetation canopy structure parameters from the above-mentioned vegetation canopy structure data, vegetation environment temperature detection data, and vegetation component characteristic data through a data fusion algorithm; introducing the above-mentioned vegetation canopy structure parameters to construct a vegetation transpiration intensity outlier detection model; identifying local drought or waterlogging areas based on the above-mentioned vegetation transpiration intensity outlier detection model; detecting trunk pest boring vibration signals and trunk insect tunnel scanning data based on the local drought or waterlogging areas; and simulating the pest spread path according to the above-mentioned trunk pest boring vibration signals and the above-mentioned trunk insect tunnel scanning data.

[0032] The above-mentioned step of collecting vegetation canopy structure data, vegetation environment temperature detection data, and vegetation component characteristic data using multiple sensors specifically includes:

[0033] Detecting vegetation canopy structure data using lidar; detecting vegetation environment temperature detection data using thermal infrared imaging; and detecting vegetation cost characteristic data using a hyperspectral camera.

[0034] Among them, the lidar (LiDAR) uses a 1550nm wavelength solid-state radar, and the point cloud density is increased to 500 points / m², supporting penetrative vegetation scanning. The thermal infrared imaging is upgraded to a cooled indium antimonide detector (resolution 1280×1024), and the temperature sensitivity reaches 0.03°C. The hyperspectral camera covers the 400 - 2500nm band, and subdivides multiple vegetation component characteristic channels, such as the 650nm chlorophyll a and the 1450nm water absorption band.

[0035] Before calculating the vegetation canopy structure parameters from the above vegetation canopy structure data, the above vegetation environment temperature detection data, and the above vegetation component characteristic data through a data fusion algorithm, it further includes:

[0036] Performing spatial domain registration on the above vegetation canopy structure data and satellite elevation data; performing temporal domain registration on the above vegetation environment temperature detection data using the dynamic time warping algorithm; performing spectral domain registration on the above vegetation cost characteristic data through TV regularization.

[0037] The spatial domain registration specifically includes: point cloud rasterization (matching the satellite resolution), which can be expressed as:

[0038] grid = voxelize(lidar, resolution=dem.resolution);

[0039] lidar represents the point cloud data of the vegetation canopy structure data; dem represents the satellite elevation data; voxelize represents the voxelization function that divides the lidar data into a three-dimensional grid (voxel); lidar,resolution=dem.resolution means setting the voxel grid resolution of the lidar data to be the same as that of the dem data.

[0040] Fine registration based on the Iterative Closest Point (ICP) algorithm, which can be expressed as:

[0041] transform = ICP_optimize(grid, dem, max_iter=100);

[0042] ICP_optimize represents the Iterative Closest Point (ICP) algorithm; grid represents the lidar data after point cloud rasterization; dem represents the satellite elevation data; grid, dem, max_iter=100 means that the grid data uses the dem data as the reference benchmark for spatial resolution registration, and the maximum number of iterations of the ICP algorithm is 100.

[0043] Generating a canopy height model, which can be expressed as:

[0044] CHM = grid - dem.

[0045] The time - domain registration (thermal infrared data synchronization) uses the Dynamic Time Warping (DTW) algorithm, which can be expressed as:

[0046] C(i,j) = D(i,j) + min{C(i - 1,j), C(i,j - 1), C(i - 1,j - 1)};

[0047] C(i,j) represents the cumulative distance matrix; where D(i,j) represents the distance between the current time series and the standard time series; C(i - 1,j) represents that a point in the reference sequence one step before D(i,j) only matches one point in the target sequence; C(i,j - 1) represents that a point in the reference sequence one step before D(i,j) matches multiple consecutive points in the target sequence; C(i - 1,j - 1) represents that a point in the target sequence one step before D(i,j) matches multiple consecutive points in the reference sequence.

[0048] Spectral - domain registration (hyperspectral feature extraction): The spectral features of chlorophyll / water / lignin are collected using an end - member spectral library, and optimization is carried out by maintaining spatial continuity through TV regularization.

[0049] The comprehensive data fusion algorithm calculates the canopy structure parameters , which can be expressed as:

[0050] ;

[0051] Among them, n represents the number of spatial sampling points in the same canopy area when multiple sensors synchronously collect vegetation canopy structure data, vegetation environmental temperature detection data, and vegetation component feature data; is the canopy structure data; is the environmental temperature detection data; T is the affine transformation matrix; λ is the hyperspectral gradient regularization term; is the vegetation cost feature data.

[0052] The above - mentioned vegetation canopy structure parameters are introduced to construct a vegetation transpiration intensity outlier detection model, which specifically includes:

[0053] Introduce canopy structure parameters to establish the Penman - Monteith equation to calculate the transpiration intensity;

[0054] The Penman - Monteith equation uses the Isolation Forest algorithm to construct a transpiration intensity outlier detection model.

[0055] Specifically, introduce canopy structure parameters into the Penman - Monteith equation , can be expressed as:

[0056] ;

[0057] represents the slope of the saturated water vapor pressure - temperature curve; represents the net surface radiation; represents the soil heat flux, usually negligible; represents the psychrometric constant; represents the average air temperature; represents the average wind speed; represents the saturated water vapor pressure; represents the actual water vapor pressure.

[0058] The saturated water vapor pressure can be calculated in the following way:

[0059] ;

[0060] where, is the Celsius temperature.

[0061] The actual water vapor pressure can be calculated through the relative humidity:

[0062] ;

[0063] where, is the saturated water vapor pressure; is the relative humidity.

[0064] Net surface radiation:

[0065] ;

[0066] where, represents the incident short - wave radiation (direct solar radiation + scattered radiation); represents the short - wave radiation reflected by the surface (depending on the surface albedo ); represents the downward long - wave radiation from the atmosphere (greenhouse effect); represents the upward long - wave radiation from the surface (surface thermal radiation).

[0067] The above - mentioned detection of trunk pest feeding vibration signals and trunk insect tunnel scanning data based on local drought or waterlogging areas specifically includes:

[0068] Use multiple trunk vibration sensors to capture trunk pest feeding signals at a preset frequency; use X - ray computed tomography equipment to detect the insect tunnels inside the trunk.

[0069] Simulating the pest infestation spread path based on the above trunk pest infestation vibration signals and the above trunk insect tunnel scan data specifically includes:

[0070] Constructing a pest infestation feature library for various pest types based on the pest infestation vibration signal characteristics and the infested trunk;

[0071] Identifying the pest type of the insect tunnel to be detected according to the above pest infestation feature library;

[0072] Collecting the changes in the acquisition positions of multiple groups of the above trunk pest infestation vibration signals and the spread speed in at least one insect tunnel direction, and predicting the spread speed in at least one insect tunnel direction of the insect tunnel to be detected based on a deep learning classification model;

[0073] Generating a three-dimensional model of the pest infestation spread of the insect tunnel to be detected.

[0074] Optionally, a high-sensitivity acceleration sensor is used to collect the vibration signals when different pests (such as longhorn beetles, bark beetles, etc.) infest the trunk. Thus, various pest infestation vibration signal characteristics are collected, such as frequency spectrum analysis (FFT), time-domain energy, pulse interval, etc., and combined with the types of trunks that various pests often infest, and the corresponding pest types are identified through deep learning, so as to obtain a constructed pest infestation feature library for various pest types. Optionally, according to the change in the acquisition position of the pest infestation vibration signal, that is, the change in the pest position, and by means of CT scanning or ultrasonic detection, the change in the infested area of the insect tunnel map is obtained, and the three-dimensional structure data of the insect tunnel such as diameter, branch angle, depth, tortuosity and other insect tunnel morphological characteristics are collected, so as to obtain the spread speed in at least one insect tunnel branch direction, that is, the change in the shape and area of the insect tunnel cross-section. The problem of low accuracy of insect tunnel prediction caused by different tree hardness and pest types is solved. And a three-dimensional model of the pest infestation spread is simulated through the change in the position of the trunk pest infestation vibration signal of the insect tunnel to be detected and the spread speed in the corresponding insect tunnel direction. Among them, the Marching Cubes algorithm can be used for three-dimensional reconstruction, and a three-dimensional software is used to simulate and generate the predicted three-dimensional model of the pest infestation spread.

[0075] Identifying local drought or waterlogging areas based on the above vegetation transpiration intensity outlier detection model specifically includes:

[0076] When there are more transpiration intensity outliers, the corresponding area is a local waterlogging area; when there are fewer transpiration intensity outliers, the corresponding area is a local waterlogging area.

[0077] When the outlier points of transpiration intensity are clustered, and the number is judged to be large according to the preset anomaly threshold, it indicates that transpiration is inhibited (such as caused by root hypoxia), and the area is determined to be a waterlogging area. When the outlier points of transpiration intensity are sparsely distributed, and the significant number is judged to be small according to the preset anomaly threshold, it indicates that transpiration is intensified, which may be caused by stress-induced water loss, and the area is determined to be a drought area.

[0078] In summary, the embodiments of the present application provide a method and system for predicting the coupling of vegetation environment based on multi-source remote sensing data fusion: using vegetation canopy structure data, vegetation environment temperature detection data, and vegetation component characteristic data to calculate vegetation canopy structure parameters through a data fusion algorithm; introducing vegetation canopy structure parameters to construct a detection model for outlier points of vegetation transpiration intensity, so as to identify local drought or waterlogging areas by combining the characteristics of vegetation canopy structure, environmental temperature, and vegetation components with vegetation transpiration intensity; and detecting trunk pest boring vibration signals and trunk insect tunnel scanning data based on local drought or waterlogging areas; simulating the pest spread path in local drought or waterlogging areas according to the trunk pest boring vibration signals and trunk insect tunnel scanning data. The present invention realizes the monitoring of grassland ecological degradation through the identification of drought or waterlogging areas, and can also monitor and predict multi-dimensional ecological behaviors such as pest spread paths, canopy structures, and transpiration intensity fields in real time. It realizes that the vegetation management in landscape gardening still lacks the analysis of specific ecological structures of vegetation, as well as in-depth research and application of an instant response mechanism for disasters, provides more comprehensive, accurate, and real-time intelligent decision-making support for vegetation management, and thus fills the gap in the monitoring and prediction of multi-modal ecological events in the prior art. The embodiments of the present application combine multi-modal sensing technologies such as lidar, thermal infrared imaging, and hyperspectral cameras, as well as data fusion algorithms and cellular automata models, and can not only realize canopy structure analysis and dynamic modeling of transpiration intensity fields, but also monitor and predict pest spread paths in real time, providing comprehensive, accurate, and real-time intelligent decision-making support for vegetation management. By integrating various ecological data and intelligent algorithms, the present application aims to achieve more refined and dynamic monitoring and prediction of the vegetation environment, and further improve the scientificity and effectiveness of ecological decision-making.

[0079] The specific embodiments described above further elaborate on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above description is only for the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A vegetation-environment coupling prediction method based on multi-source remote sensing data fusion, characterized in that Including: Collecting vegetation canopy structure data, vegetation environmental temperature detection data, and vegetation component characteristic data using multiple sensors; Calculating vegetation canopy structure parameters from the vegetation canopy structure data, the vegetation environmental temperature detection data, and the vegetation component characteristic data through a data fusion algorithm; Introducing the vegetation canopy structure parameters to construct a vegetation transpiration intensity outlier detection model; Identifying local drought or waterlogging areas based on the vegetation transpiration intensity outlier detection model; Detecting trunk pest boring vibration signals and trunk insect tunnel scan data based on local drought or waterlogging areas; Simulating the pest spread path according to the trunk pest boring vibration signals and the trunk insect tunnel scan data.

2. The vegetation environment coupling prediction method based on multi-source remote sensing data fusion according to claim 1, wherein The collecting of the vegetation canopy structure data, the vegetation environmental temperature detection data, and the vegetation component characteristic data using multiple sensors specifically includes: Detecting vegetation canopy structure data using lidar; detecting vegetation environmental temperature detection data using thermal infrared imaging; detecting vegetation cost characteristic data using a hyperspectral camera.

3. The vegetation environment coupling prediction method based on multi-source remote sensing data fusion according to claim 2, wherein, Before calculating the vegetation canopy structure parameters from the vegetation canopy structure data, the vegetation environmental temperature detection data, and the vegetation component characteristic data through a data fusion algorithm, it further includes: Performing spatial domain registration of the vegetation canopy structure data with satellite elevation data; performing time domain registration of the vegetation environmental temperature detection data using the dynamic time warping algorithm; performing spectral domain registration of the vegetation cost characteristic data through TV regularization.

4. The vegetation environment coupling prediction method based on multi-source remote sensing data fusion according to claim 1, characterized in that The introducing of the vegetation canopy structure parameters to construct a vegetation transpiration intensity outlier detection model specifically includes: Introducing canopy structure parameters to establish the Penman-Monteith equation to calculate transpiration intensity; Using the Isolation Forest algorithm in the Penman-Monteith equation to construct a transpiration intensity outlier detection model.

5. The vegetation environment coupling prediction method based on multi-source remote sensing data fusion according to claim 1, characterized in that The detecting of the trunk pest boring vibration signals and the trunk insect tunnel scan data based on local drought or waterlogging areas specifically includes: Using multiple trunk vibration sensors to capture trunk pest boring signals at a preset frequency; using an X-ray tomography device to detect the insect tunnels inside the trunk.

6. The vegetation environment coupling prediction method based on multi-source remote sensing data fusion according to claim 1, characterized in that The simulating of the pest spread path according to the trunk pest boring vibration signals and the trunk insect tunnel scan data specifically includes: Constructing a boring feature library of multiple pest types based on the boring vibration signal characteristics and the bored trunks; Identifying the pest type of the insect tunnel to be detected according to the boring feature library; Collecting the changes in the collection positions of multiple groups of the trunk pest boring vibration signals and the spread speed in at least one insect tunnel direction, and predicting the spread speed in at least one insect tunnel direction of the insect tunnel to be detected based on a deep learning classification model; Generating a three-dimensional pest spread model of the insect tunnel to be detected.

7. The vegetation environment coupling prediction method based on multi-source remote sensing data fusion according to claim 1, characterized in that The identifying of local drought or waterlogging areas based on the vegetation transpiration intensity outlier detection model specifically includes: When there are more transpiration intensity outliers, the corresponding area is a local waterlogging area; when there are fewer transpiration intensity outliers, the corresponding area is a local waterlogging area.

8. A vegetation-environment coupling prediction system based on multi-source remote sensing data fusion, characterized in that, Including: Data acquisition module: Collecting vegetation canopy structure data, vegetation environmental temperature detection data, and vegetation component characteristic data using multiple sensors; Data fusion module: The vegetation canopy structure data, the vegetation environmental temperature detection data, and the vegetation component characteristic data are used to calculate the vegetation canopy structure parameters through a data fusion algorithm; Model construction module: The vegetation canopy structure parameters are introduced to construct a detection model for outliers in vegetation transpiration intensity; Region identification module: Based on the detection model for outliers in vegetation transpiration intensity, local drought or waterlogging regions are identified; Insect tunnel detection module: Based on local drought or waterlogging regions, the vibration signals of trunk pest infestation and the trunk insect tunnel scanning data are detected; Insect tunnel simulation module: According to the vibration signals of trunk pest infestation and the trunk insect tunnel scanning data, the spread path of pests is simulated.

9. An electronic device, comprising a memory, a processor, and a computer program running on the processor, characterized in that: When the processor executes the computer program, the steps of the vegetation environment coupling prediction method based on multi-source remote sensing data fusion as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, the steps of the vegetation environment coupling prediction method based on multi-source remote sensing data fusion as described in any one of claims 1 to 7 are implemented.

Images