Target area resource analysis method and system based on area remote sensing technology

Through the target area resource analysis method based on regional remote sensing technology, and combining environmental and ecosystem data for resource evaluation, the problem of inaccurate analysis results in the existing technology is solved, more accurate resource evaluation and prediction is achieved, and effective resources are helped to formulate effective resources. Management plan.

CN119068402AActive Publication Date: 2024-12-03江西两山生态技术有限公司

Patent Information

Application Number
CN202411567418.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-05
Publication Date
2024-12-03
Estimated Expiration
2044-11-05

AI Technical Summary

Technical Problem

The existing natural resource analysis methods mainly focus on the processing of low-dimensional data, and cannot effectively model and simulate the real natural resource environment, resulting in inaccurate analysis results.

Method used

The target area resource analysis method based on regional remote sensing technology is adopted to identify remote sensing images by collecting and feature-based identification, obtaining environmental variable data and ecosystem data, calculating regional value, and conducting risk assessment and expected change trend analysis to generate optimization suggestions decisions.

Benefits of technology

By combining environmental variables and ecosystem data for comprehensive assessment, we provide more accurate resource assessment results, help decision makers understand resource vulnerability and sustainability, predict changes in advance, and develop more reasonable resource management plans.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119068402A_ABST
    Figure CN119068402A_ABST
Patent Text Reader

Abstract

The invention provides a target area resource analysis method and system based on an area remote sensing technology, and the method comprises the steps: collecting an area remote sensing image, and carrying out the feature recognition of the area remote sensing image, and obtaining one or more target area resource feature blocks; environment variable data and ecological system data of the target area resource feature block are collected, and the area value of the target area resource feature block is evaluated based on the environment variable data and the ecological system data; and performing risk assessment on the resource feature block of the target region according to the environment variable data and the ecological system data to obtain a risk assessment result, performing analysis to obtain an expected change trend, and generating an optimization suggestion decision according to the region value, the risk assessment result and the expected change trend. According to the method, various included analysis factors are comprehensively considered, so that the real natural resource environment can be well modeled and simulated, and finally a more accurate analysis result is obtained.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of natural resource analysis, and in particular to a target area resource analysis method and system based on regional remote sensing technology. Background Art

[0002] Natural resource ecological big data analysis refers to the collection, storage, processing and analysis of various data on natural resources in order to achieve monitoring, management and decision support for natural resources; its data sources include: satellite remote sensing, drone remote sensing, forest resource surveys, ecological monitoring stations, sensor networks, smart devices and forest product market data.

[0003] However, existing methods for analyzing natural resources mainly focus on processing low-dimensional data, and the model factors considered are relatively simple. They are unable to model and simulate the real natural resource environment well, and the final analysis results are not particularly accurate.

[0004] Based on this, it is necessary to propose a target area resource analysis method based on regional remote sensing technology to solve the above technical problems. Summary of the Invention

[0005] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide a target area resource analysis method and system based on regional remote sensing technology to solve the problems existing in the above background technology.

[0006] The present invention is achieved by providing a target area resource analysis method based on regional remote sensing technology, the method comprising the following steps: Acquire regional remote sensing images, perform feature recognition on the regional remote sensing images to obtain one or more target area resource feature blocks, wherein the target area resource feature blocks include forest feature blocks, grassland feature blocks, farmland feature blocks, and water feature blocks; Obtain environmental variable data and ecosystem data for the target region's resource characteristic blocks. Environmental variable data include climate regulation, flood regulation, and water conservation. Ecosystem data include ecosystem diversity and oxygen release and carbon fixation. Calculate the regional value of the target region's resource characteristic blocks based on climate regulation, flood regulation, water conservation, and oxygen release and carbon fixation. Based on environmental variable data and ecosystem data, a risk assessment is conducted on the resource characteristic blocks in the target area to obtain risk assessment results, and the expected change trends are analyzed to generate optimization recommendation decisions based on the regional value, risk assessment results and expected change trends.

[0007] Another object of the present invention is to provide a target area resource analysis system based on regional remote sensing technology, the system comprising: A regional feature recognition module is used to collect regional remote sensing images and perform feature recognition on the regional remote sensing images to obtain one or more target regional resource feature blocks, wherein the target regional resource feature blocks include forest feature blocks, grassland feature blocks, farmland feature blocks, and water feature blocks; The regional resource assessment module is used to obtain environmental variable data and ecosystem data for the target regional resource characteristic blocks. The environmental variable data include climate regulation, flood regulation, and water conservation. The ecosystem data include ecosystem diversity and oxygen release and carbon fixation. The regional value of the target regional resource characteristic blocks is calculated based on climate regulation, flood regulation, water conservation, and oxygen release and carbon fixation. The regional optimization module conducts risk assessment on the resource characteristic blocks of the target area based on environmental variable data and ecosystem data to obtain risk assessment results, analyzes the expected change trends, and generates optimization recommendation decisions based on the regional value, risk assessment results and expected change trends.

[0008] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention combines environmental variable data and ecosystem data for resource analysis. By considering factors such as climate regulation, flood regulation, water conservation, and oxygen release and carbon fixation, the value of resources in the target area can be more comprehensively assessed. Comprehensive analysis can provide more accurate resource assessment results and provide a more comprehensive basis for decision-making.

[0009] 2. This invention analyzes the risk profile of resource-specific blocks in the target area and generates risk assessment results. This helps understand the vulnerability and sustainability of resources in the target area, ensuring that subsequent resource management plans achieve better results. This invention also analyzes the expected trends of resource-specific blocks in the target area, predicting potential changes in advance and providing decision makers with corresponding optimization recommendations. This helps decision makers develop more reasonable resource management plans and effectively address future changes and risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 The figure is a flow chart of a target area resource analysis method based on regional remote sensing technology.

[0011] Figure 2 The present invention is a flowchart for obtaining target area resource characteristic blocks in a target area resource analysis method based on regional remote sensing technology.

[0012] Figure 3 The present invention is a flowchart for evaluating the regional value of resource characteristic blocks in a target area resource analysis method based on regional remote sensing technology.

[0013] Figure 4 This is a structural diagram of a target area resource analysis system based on regional remote sensing technology. DETAILED DESCRIPTION

[0014] In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0015] The specific implementation of the present invention is described in detail below with reference to specific embodiments.

[0016] like Figure 1 As shown, an embodiment of the present invention provides a target area resource analysis method based on regional remote sensing technology, the method comprising the following steps: S100, collecting a regional remote sensing image, performing feature recognition on the regional remote sensing image to obtain one or more target area resource feature blocks, wherein the target area resource feature blocks include a forest feature block, a grassland feature block, a farmland feature block, and a water feature block; S200, obtaining environmental variable data and ecosystem data for a resource characteristic block in a target region, wherein the environmental variable data includes climate regulation, flood regulation, and water conservation, and the ecosystem data includes ecosystem diversity and oxygen release and carbon fixation, and calculating the regional value of the resource characteristic block in the target region based on climate regulation, flood regulation, water conservation, and oxygen release and carbon fixation; S300, performing risk assessment on the target area resource characteristic blocks based on environmental variable data and ecosystem data to obtain risk assessment results, and analyzing to obtain expected change trends, and generating optimization recommendation decisions based on the regional value, risk assessment results and expected change trends.

[0017] In an embodiment of the present invention, regional remote sensing images are first acquired through satellites or drones, and feature recognition is performed on the regional remote sensing images to obtain one or more target area resource feature blocks, wherein the target area resource feature blocks include forest feature blocks, grassland feature blocks, farmland feature blocks, and water feature blocks. The accurate division of different target area resource feature blocks is automatically achieved, which facilitates subsequent regional value assessment. The regional value of the target area resource feature blocks is then assessed based on factors such as climate regulation, flood regulation, water conservation, and oxygen release and carbon fixation.

[0018] like Figure 2 As shown, as a preferred embodiment of the present invention, the step of performing feature recognition on the regional remote sensing image to obtain one or more target area resource feature blocks specifically includes: S101, preprocessing the regional remote sensing image, segmenting the preprocessed remote sensing image into multiple regional objects, using a threshold-based segmentation method or an edge-based segmentation method; S102, extracting spectral features, texture features, and shape features from the segmented region objects, wherein the spectral features include reflectance and brightness values, and the texture features include gray-level co-occurrence matrix and local binary pattern; S103 , based on the extracted features and the random forest classification algorithm, the pixel objects in the remote sensing image are divided into different categories to obtain resource feature blocks of each target area.

[0019] In an embodiment of the present invention, in order to accurately perform feature recognition on a regional remote sensing image to obtain one or more target area resource feature blocks, the regional remote sensing image must first be preprocessed, specifically including: performing radiation correction on the regional remote sensing image to adjust the image data to eliminate the influence of atmospheric and solar altitude factors on the image; performing geometric correction to correct geometric distortion in the image; performing image enhancement to improve image quality through histogram equalization and filtering methods, and to improve the distinguishability of different types of land objects. Then, the preprocessed remote sensing image is segmented into multiple regional objects. These regions or objects have similar features in terms of spectrum, texture, shape, etc. The segmentation method is threshold-based segmentation or edge-based segmentation; spectral features, texture features, and shape features are extracted from the segmented regional objects. The spectral features include reflectance and brightness values, and the texture features include grayscale co-occurrence matrix and local binary pattern; and a suitable classification algorithm is selected to classify the extracted features. Commonly used classification algorithms include supervised classification (such as maximum likelihood classification, support vector machine, random forest, etc.) and unsupervised classification (such as K-means clustering, ISODATA clustering, etc.). Finally, based on the extracted features and the selected classification algorithm, the pixels or objects in the remote sensing image are divided into different categories, namely, resource characteristic blocks in the target area such as forests, grasslands, farmlands and waters.

[0020] As a preferred embodiment of the present invention, the preprocessing of the regional remote sensing image and segmentation of the preprocessed remote sensing image into multiple regional objects, wherein the segmentation method is a threshold-based segmentation or an edge-based segmentation step, specifically includes: Convert the regional remote sensing image into a grayscale image, apply a Gaussian blur operation to the grayscale image, and obtain a blurred grayscale image; Use LBP to encode the relationship between each pixel and its neighboring pixels in the blurred grayscale image to obtain LBP features; Use the Sobel operator to calculate the gradient of the blurred grayscale image in the horizontal and vertical directions respectively, and combine the gradients in the two directions to obtain the gradient amplitude of the image; The blurred grayscale image, LBP features and gradient amplitude are combined to form a multidimensional feature vector, where each pixel corresponds to a multidimensional feature vector; The KMeans clustering algorithm is used to classify the multidimensional feature vector into several categories to obtain the category label of each pixel; Remap the category label of each pixel to each position of the regional remote sensing image to form a segmented image; The Otsu threshold segmentation operation is used to find the optimal threshold for segmenting the image, and the segmented image is binarized using the optimal threshold to obtain the threshold segmented image; The threshold segmentation image is closed to fill the small holes in the image, and then opened to remove the residual noise in the image to obtain a refined segmentation image.

[0021] As a preferred embodiment of the present invention, the pixel objects in the remote sensing image are divided into different categories based on the extracted features and the random forest classification algorithm to obtain the resource feature blocks of each target area. The corresponding process has the following relationship: ; in, Indicates that the pixel object is classified as t The probability of the class, Indicates the t category, The feature vector of the pixel object formed by spectral characteristics, texture characteristics and shape characteristics, represents the number of trees in the random forest, Indicates the j The adaptive weight of each tree, represents the exponential function, represents the number of features, Indicates the k The weight coefficient of the feature, Indicates the j The first i Pixel objects are transformed to perform feature transformation operations. Indicates the k The weight coefficient of the global feature, Indicates the global feature transformation operation on the feature vector of the pixel object. Indicates the j The first i The classification decision output of pixel objects, Indicates bias; In the above process of dividing the pixel objects in the remote sensing image into different categories, each tree has an adaptive weight , reflecting the importance of the tree in the overall classification. Adjusting these weights during training allows more effective trees to have a greater impact on the final decision, thereby improving overall classification accuracy. Furthermore, through feature transformation and global feature transformation operations, features can be processed nonlinearly, capturing complex patterns that were not recognized in the original feature space. This transformation makes the model more flexible in responding to different features, helping to improve classification performance.

[0022] In order to capture the complex interaction between multiple features, the present invention introduces global feature weights and bias , and set weights for each feature , the contribution of each feature to the classification result can be adjusted more finely. This configuration helps capture richer feature information and improves classification accuracy. Finally, the weighted decision sum of all trees is used to form the final classification result. Such an ensemble method can reduce the bias and variance of a single tree, thereby improving the stability and accuracy of the model. The contribution of each tree is adjusted by its adaptive weight. to make adjustments to ensure that valid trees have a greater impact on the final results.

[0023] like Figure 3 As shown, as a preferred embodiment of the present invention, the step of obtaining environmental variable data and ecosystem data of the target area resource characteristic block, the environmental variable data including climate regulation, flood regulation and water conservation, the ecosystem data including ecosystem diversity and oxygen release and carbon fixation, and calculating the regional value of the target area resource characteristic block based on climate regulation, flood regulation, water conservation and oxygen release and carbon fixation, specifically includes: S201, collect climate regulation index, flood regulation index, water conservation index and oxygen release and carbon fixation index of forests, grasslands, farmlands and water bodies; S202, automatically identifying the area of ​​each target region's resource characteristic block, and evaluating the regional value based on the area of ​​each target region's resource characteristic block and the corresponding climate regulation index, flood regulation index, water conservation index, and oxygen release and carbon fixation index.

[0024] In an embodiment of the present invention, relevant data need to be collected in advance to calculate the climate regulation index, flood regulation index, water conservation index and oxygen release and carbon fixation index of forests, grasslands, farmlands and waters, and then automatically identify the area of ​​the resource characteristic blocks of each target area. Based on the area of ​​the resource characteristic blocks of each target area and the corresponding climate regulation index, flood regulation index, water conservation index and oxygen release and carbon fixation index, the regional value is evaluated to obtain a specific comprehensive regional value.

[0025] As a preferred embodiment of the present invention, the regional value is assessed based on the area of ​​the resource characteristic blocks of each target area and the corresponding climate regulation index, flood regulation index, water conservation index and oxygen release and carbon fixation index. The corresponding process has the following relationship: ; in, represents the total area value, Indicates the number of resource feature blocks in the target area, Indicates the n The area of ​​the resource characteristic blocks in the target area, Indicates the n The climate regulation index of the resource characteristic blocks in the target area, Indicates the n The flood regulation index of the resource characteristic block in the target area, Indicates the n Water conservation index of resource characteristic blocks in target areas, Indicates the n Oxygen release and carbon fixation index of resource characteristic blocks in target areas, They represent the weights corresponding to the climate regulation index, flood regulation index, water conservation index, and oxygen release and carbon fixation index, respectively. They represent the fuzzy membership values ​​corresponding to the climate regulation index, flood regulation index, water conservation index, and oxygen release and carbon fixation index respectively.

[0026] In the above-mentioned process of evaluating regional value, the present invention uses the area of ​​each target regional resource characteristic block as This method weights the contribution of each index to regional value, reflecting the proportion of different areas in the total value. By taking a weighted average of the different indices, it comprehensively considers their impact on regional value. Furthermore, due to the inherent complexity and uncertainty of ecosystems, this method introduces a fuzzy membership function to convert each index into a fuzzy membership value. Fuzzy logic effectively captures this characteristic, thereby improving the accuracy and robustness of the assessment results.

[0027] As a preferred embodiment of the present invention, a risk assessment is performed on a target area resource characteristic block based on environmental variable data and ecosystem data to obtain a risk assessment result, and an expected change trend is analyzed to obtain an optimization recommendation decision based on the regional value, risk assessment result, and expected change trend, specifically including: Normalizing and standardizing the environmental variable data and the ecosystem data in sequence to obtain preprocessed environmental variable data and ecosystem data; Assign weights to the pre-processed environmental variable data and ecosystem data according to preset scoring rules; Calculate the weighted values ​​of the pre-processed environmental variable data and ecosystem data and sum them up to obtain a comprehensive risk assessment value; Obtain historical data of the target area, including historical risk assessment values, historical environmental variable data, and historical ecosystem data; A spatiotemporal prediction model is constructed using a long short-term memory network, and the spatiotemporal prediction model is trained using historical data of the target area to obtain a trained spatiotemporal prediction model; Input the current risk assessment value, environmental variable data, and ecosystem data into the trained spatiotemporal prediction model to obtain the predicted value of future change trends; Construct a multi-objective optimization model with ecosystem health, economic benefits, and social impact factors as optimization objectives, and land management measures and water resource management measures as input variables; Based on the regional value, comprehensive risk assessment value and future change trend prediction value, combined with land management measures and water resources management measures, the optimization target value of each target area resource characteristic block is calculated through a multi-objective optimization method to obtain the optimal land management measures and water resources management measures.

[0028] like Figure 4 As shown, an embodiment of the present invention further provides a target area resource analysis system based on regional remote sensing technology, the system comprising: The regional feature recognition module 100 is used to collect regional remote sensing images and perform feature recognition on the regional remote sensing images to obtain one or more target regional resource feature blocks, wherein the target regional resource feature blocks include forest feature blocks, grassland feature blocks, farmland feature blocks, and water feature blocks; The regional resource assessment module 200 is used to obtain environmental variable data and ecosystem data of the target regional resource characteristic block, the environmental variable data including climate regulation, flood regulation, and water conservation, and the ecosystem data including ecosystem diversity and oxygen release and carbon fixation, and calculate the regional value of the target regional resource characteristic block based on climate regulation, flood regulation, water conservation, and oxygen release and carbon fixation; The regional optimization module 300 is used to perform risk assessment on the resource characteristic blocks of the target area based on environmental variable data and ecosystem data to obtain risk assessment results, analyze and obtain expected change trends, and generate optimization recommendation decisions based on the regional value, risk assessment results and expected change trends.

[0029] As a preferred embodiment of the present invention, the region feature recognition module 100 includes: A remote sensing image segmentation unit is used to preprocess the regional remote sensing image and segment the preprocessed remote sensing image into multiple regional objects. The segmentation method is threshold-based segmentation or edge-based segmentation; A feature extraction unit is used to extract spectral features, texture features and shape features from the segmented region objects, wherein the spectral features include reflectance and brightness value, and the texture features include gray-level co-occurrence matrix and local binary pattern; The target area resource feature block unit is used to classify the pixel objects in the remote sensing image into different categories based on the extracted features and the random forest classification algorithm to obtain the resource feature blocks of each target area.

[0030] As a preferred embodiment of the present invention, the regional value assessment module 200 includes: Parameter index collection unit, used to collect climate regulation index, flood regulation index, water conservation index and oxygen release and carbon fixation index of forests, grasslands, farmlands and water bodies; The above is only a detailed description of the preferred embodiments of the present invention, which is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0031] It should be understood that, although the various steps in the flow chart of each embodiment of the present invention are shown in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in order, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0032] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When executed, the program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the various embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0033] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the disclosure in the specification and examples. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered merely as exemplary, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. A target area resource analysis method based on regional remote sensing technology, characterized in that: The method comprises the following steps: Collecting regional remote sensing images, and performing feature recognition on the regional remote sensing images to obtain one or more target regional resource feature blocks, wherein the target regional resource feature blocks include forest feature blocks, grassland feature blocks, farmland feature blocks, and water feature blocks; Obtain environmental variable data and ecosystem data of the target area resource characteristic blocks. Environmental variable data include climate regulation, flood regulation and water conservation. Ecosystem data include ecosystem diversity and oxygen release and carbon fixation. Calculate the regional value of the target area resource characteristic blocks based on climate regulation, flood regulation, water conservation and oxygen release and carbon fixation. Conduct risk assessment on the resource characteristic blocks in the target area based on environmental variable data and ecosystem data to obtain risk assessment results, analyze and obtain expected change trends, and generate optimization recommendations and decisions based on the regional value, risk assessment results and expected change trends; The step of performing feature recognition on the regional remote sensing image to obtain one or more target regional resource feature blocks specifically includes: Preprocessing the regional remote sensing image, segmenting the preprocessed remote sensing image into multiple regional objects, the segmentation method is threshold-based segmentation or edge-based segmentation; Extracting spectral features, texture features and shape features from the segmented regional objects, wherein the spectral features include reflectance and brightness value, and the texture features include gray-level co-occurrence matrix and local binary pattern; According to the extracted features and random forest classification algorithm, the pixel objects in the remote sensing image are divided into different categories to obtain the resource feature blocks of each target area.

2. The target area resource analysis method based on regional remote sensing technology according to claim 1 is characterized in that: The preprocessing of the regional remote sensing image, segmenting the preprocessed remote sensing image into a plurality of regional objects, wherein the segmentation method is a threshold-based segmentation or an edge-based segmentation step, specifically includes: Convert the regional remote sensing image into a grayscale image, apply a Gaussian blur operation to the grayscale image, and obtain a blurred grayscale image; Use LBP to encode the relationship between each pixel and its neighboring pixels in the blurred grayscale image to obtain LBP features; Use the Sobel operator to calculate the gradients of the blurred grayscale image in the horizontal and vertical directions respectively, and combine the gradients in the two directions to get the gradient amplitude of the image; The blurred grayscale image, LBP features and gradient amplitude are combined to form a multi-dimensional feature vector, where each pixel corresponds to a multi-dimensional feature vector; The KMeans clustering algorithm is used to divide the multidimensional feature vector into several categories to obtain the category label of each pixel; Remap the category label of each pixel to each position of the regional remote sensing image to form a segmented image; The Otsu threshold segmentation operation is used to find the optimal threshold for segmenting the image, and the segmented image is binarized using the optimal threshold to obtain the threshold segmented image; The threshold segmentation image is closed to fill the small holes in the image, and then opened to remove the residual noise in the image to obtain a refined segmentation image.

3. The target area resource analysis method based on regional remote sensing technology according to claim 2 is characterized in that: According to the extracted features and the random forest classification algorithm, the pixel objects in the remote sensing image are divided into different categories to obtain the resource feature blocks of each target area. The corresponding process has the following relationship: ; in, Indicates that the pixel object is classified as t The probability of the class, Indicates t category, The feature vector of the pixel object formed by spectral features, texture features and shape features, represents the number of trees in the random forest, Indicates j The adaptive weight of each tree, represents the exponential function, represents the number of features, Indicates k The weight coefficient of the feature, Indicates j The tree i Pixel objects are transformed to perform feature transformation operations. Indicates k The weight coefficient of the global feature, Indicates the global feature transformation operation on the feature vector of the pixel object. Indicates j The tree i The classification decision output of pixel objects, Indicates bias.

4. The target area resource analysis method based on regional remote sensing technology according to claim 3 is characterized in that: The steps of evaluating the regional value of the resource characteristic blocks in the target area based on climate regulation, flood regulation, water conservation, and oxygen release and carbon fixation specifically include: Collect climate regulation index, flood regulation index, water conservation index and oxygen release and carbon fixation index of forests, grasslands, farmlands and waters; Automatically identify the area of ​​resource characteristic blocks in each target area, and evaluate the regional value based on the area of ​​resource characteristic blocks in each target area and the corresponding climate regulation index, flood regulation index, water conservation index and oxygen release and carbon fixation index.

5. The target area resource analysis method based on regional remote sensing technology according to claim 4 is characterized in that: The regional value is evaluated based on the area of ​​the resource characteristic blocks of each target area and the corresponding climate regulation index, flood regulation index, water conservation index and oxygen release and carbon fixation index. The corresponding process has the following relationship: ; in, represents the total area value, Indicates the number of resource feature blocks in the target area. Indicates n The area of ​​the resource characteristic blocks in the target area, Indicates n The climate regulation index of the resource characteristic blocks in the target area, Indicates n The flood regulation index of the resource characteristic blocks in the target area, Indicates n Water conservation index of resource characteristic blocks in target areas, Indicates n Oxygen release and carbon fixation index of resource characteristic blocks in target areas, They represent the weights of climate regulation index, flood regulation index, water conservation index, and oxygen release and carbon fixation index, respectively. They respectively represent the fuzzy membership values ​​corresponding to the climate regulation index, flood regulation index, water conservation index, and oxygen release and carbon fixation index.

6. The target area resource analysis method based on regional remote sensing technology according to claim 5 is characterized in that: Conduct risk assessment on the resource characteristic blocks in the target area based on environmental variable data and ecosystem data to obtain risk assessment results, and analyze the expected change trend. Generate optimization recommendations based on the regional value, risk assessment results and expected change trend, including: Normalizing and standardizing the environmental variable data and the ecosystem data in turn to obtain preprocessed environmental variable data and ecosystem data; According to the preset scoring rules, weights are assigned to the preprocessed environmental variable data and ecosystem data; Calculate and sum the weighted values ​​of the preprocessed environmental variable data and ecosystem data to obtain a comprehensive risk assessment value; Obtain historical data of the target area, including historical risk assessment values, historical environmental variable data, and historical ecosystem data; A spatiotemporal prediction model is constructed using a long short-term memory network, and the spatiotemporal prediction model is trained using historical data of the target area to obtain a trained spatiotemporal prediction model; Input the current risk assessment value, environmental variable data and ecosystem data into the trained spatiotemporal prediction model to obtain the predicted value of future change trend; Construct a multi-objective optimization model with ecosystem health, economic benefits and social impact factors as optimization objectives and land management measures and water resource management measures as input variables; According to the regional value, comprehensive risk assessment value and future change trend forecast value, combined with land management measures and water resources management measures, the optimization target value of each resource characteristic block in the target area is calculated through a multi-objective optimization method to obtain the optimal land management measures and water resources management measures.

7. The target area resource analysis method based on regional remote sensing technology according to claim 6 is characterized in that: The step of preprocessing the regional remote sensing image specifically includes: Perform radiation correction on regional remote sensing images and adjust image data to eliminate the influence of atmosphere and solar altitude angle on images; Perform geometric correction to correct the geometric distortion in the image; Perform image enhancement to improve image quality through histogram equalization and filtering methods, and increase the distinguishability of different types of objects.

8. A target area resource analysis system based on regional remote sensing technology, the system being applied to the target area resource analysis method based on regional remote sensing technology as claimed in any one of claims 1 to 7, characterized in that: The system comprises: A regional feature recognition module is used to collect regional remote sensing images, perform feature recognition on the regional remote sensing images to obtain one or more target regional resource feature blocks, wherein the target regional resource feature blocks include forest feature blocks, grassland feature blocks, farmland feature blocks and water feature blocks; The regional resource assessment module is used to obtain the environmental variable data and ecosystem data of the target regional resource characteristic blocks. The environmental variable data include climate regulation, flood regulation and water conservation. The ecosystem data include ecosystem diversity and oxygen release and carbon fixation. The regional value of the target regional resource characteristic blocks is calculated based on climate regulation, flood regulation, water conservation and oxygen release and carbon fixation. The regional optimization module conducts risk assessment on the resource characteristic blocks in the target area based on environmental variable data and ecosystem data to obtain risk assessment results, and analyzes the expected change trends, and generates optimization recommendation decisions based on the regional value, risk assessment results and expected change trends.

9. The target area resource analysis system based on regional remote sensing technology according to claim 8, characterized in that: The regional feature recognition module comprises: A remote sensing image segmentation unit is used to preprocess the regional remote sensing image and segment the preprocessed remote sensing image into a plurality of regional objects, wherein the segmentation method is threshold-based segmentation or edge-based segmentation; A feature extraction unit, used to extract spectral features, texture features and shape features from the segmented regional objects, wherein the spectral features include reflectance and brightness value, and the texture features include gray-level co-occurrence matrix and local binary pattern; The target area resource feature block unit is used to classify the pixel objects in the remote sensing image into different categories according to the extracted features and the random forest classification algorithm to obtain the resource feature blocks of each target area.

Citation Information

Patent Citations

  • Historical cultivated land distribution reconstruction method based on random forest model

    CN113902580A

  • Method and system for quickly estimating total production value of terrestrial ecosystem

    CN115239175A

  • Method and device for acquiring hologram, electronic equipment and medium

    CN115661321A

  • Ecological risk assessment method and early warning system based on ecological protection red line demarcation

    CN117522117A

  • Remote sensing image retrieval method and system, computer equipment and storage medium

    CN117763186A

Cited By

  • Mowing robot operation area identification method based on multi-feature channel quality evaluation

    CN122574753A