Ecological environment dynamic monitoring method and system based on remote sensing and geographic information system

Abstract

The invention relates to an ecological environment dynamic monitoring method and system based on a remote sensing and geographic information system, and the method comprises the steps: carrying out the preprocessing of optical remote sensing image data and SAR radar data of a to-be-detected region, recognizing the change regions of the to-be-detected region at a current moment and a previous moment, and obtaining a target change region; extracting all environment monitoring information of the target change area at the current moment and the previous moment, and environment policy information related to the target change area; performing text analysis on the environmental policy information by using a natural language processing technology, and extracting a management and control area corresponding to the environmental policy information; according to all the environment monitoring information of the management and control area at the current moment and the previous moment, identifying an environment change area in the management and control area; performing position matching on the control area and the target change area to obtain a matching area, and extracting all environment monitoring station information of the matching area between the current moment and the previous moment; and splicing all environment monitoring station information of the target change area, the management and control area, the environment change area and the matching area between the current moment and the previous moment, generating a to-be-detected sequence, inputting the to-be-detected sequence into the AI large model for prediction, obtaining whether the environment of the to-be-detected area is abnormal or not, and if yes, performing early warning.

Description

Technical Field

[0001] The present invention belongs to the field of geological monitoring, and in particular relates to a method and system for dynamic monitoring of an ecological environment based on remote sensing and a geographic information system. Background Art

[0002] With the increasing impact of human activities on the natural environment, ecological and environmental monitoring has become a key link in maintaining ecological balance and sustainable development. In existing ecological and environmental monitoring systems, traditional monitoring equipment generally relies on multiple sets of sensors for data collection. This model not only leads to a geometric increase in the amount of monitoring data, increasing the burden of data storage and transmission, but also significantly increases the computational complexity of data preprocessing and feature extraction, directly extending the overall data processing cycle. At the same time, due to the lack of efficient dynamic data integration and spatial analysis mechanisms, existing monitoring systems struggle to track and provide early warnings of ecological and environmental changes in real time. When faced with sudden environmental events or dynamic adjustments to policy control areas, they often experience regulatory lags and slow responses. This significantly reduces the accuracy and timeliness of regional ecological and environmental control measures, and fails to fully meet the actual needs for refined and intelligent environmental monitoring in the current context of ecological civilization construction. Summary of the Invention

[0003] In order to solve the problems existing in the background technology, one aspect of the present invention provides a method for dynamic monitoring of ecological environment based on remote sensing and geographic information system, comprising:

[0004] S1: Preprocess the optical remote sensing image data and SAR radar data of the area to be detected, identify the changed area of ​​the area to be detected between the current moment and the previous moment, and obtain the target changed area;

[0005] S2: Extract all environmental monitoring information of the target change area at the current moment and the previous moment, as well as environmental policy information related to the target change area;

[0006] S3: Use natural language processing technology to parse environmental policy information and extract the corresponding control areas;

[0007] S4: Identify the environmental change area within the control area based on all environmental monitoring information of the control area at the current moment and the previous moment;

[0008] S5: Positionally match the control area with the target change area to obtain a matching area, and extract all environmental monitoring station information in the matching area between the current moment and the previous moment;

[0009] S6: All environmental monitoring station information of the target change area, control area, environmental change area and matching area between the current moment and the previous moment is spliced ​​to generate a sequence to be tested and input it into the AI ​​big model for prediction to determine whether the environment of the area to be tested is abnormal. If so, an early warning is issued.

[0010] Another aspect of the present invention provides an ecological environment dynamic monitoring system based on remote sensing and geographic information system, including: a memory and a processor; the memory is used to store application programs; the processor is used to run the application programs and execute the ecological environment dynamic monitoring method based on remote sensing and geographic information system.

[0011] Another aspect of the present invention provides a computer storage medium having a program stored thereon, which, when executed by a processor, implements the method for dynamic monitoring of an ecological environment based on remote sensing and a geographic information system.

[0012] The present invention has at least the following beneficial effects

[0013] The present invention addresses the problems of existing ecological and environmental monitoring that result in large data volumes, time-consuming processing, inconvenient dynamic supervision, and insufficient policy linkage, etc. The present invention uses optical remote sensing and SAR radar data to dynamically capture large-area environmental elements, greatly reducing dependence on dense sensors. Sensor data is extracted only in target change and control areas, and natural language processing is used to parse environmental policy texts and match them with remote sensing data positions. Multi-source data is spliced ​​and input into a large AI model to predict environmental anomalies and issue warnings, forming an efficient monitoring model of "macro-identification-micro-verification-policy linkage", which not only reduces data collection and processing pressure and hardware costs, but also improves the accuracy and timeliness of dynamic supervision, achieving a technological leap from passive data collection to active anomaly warning, and solving the pain points of traditional solutions such as single data dimension, discontinuous spatial coverage, and difficulty in tracing policy implementation effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 Schematic diagram of the method of the present invention. DETAILED DESCRIPTION

[0015] The following describes the embodiments of the present invention by means of specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and the following embodiments and features in the embodiments can be combined with each other without conflict.

[0016] See also Figure 1 The present invention provides a method for dynamic monitoring of ecological environment based on remote sensing and geographic information system, comprising:

[0017] S1: Preprocess the optical remote sensing image data and SAR radar data of the area to be detected, identify the changed area of ​​the area to be detected between the current moment and the previous moment, and obtain the target changed area;

[0018] Preferably, the step S1 includes:

[0019] S11: Radiometric calibration of optical remote sensing image data is performed using ENVI software to convert the original values ​​of remote sensing images into radiometric brightness values;

[0020] S12: After applying the precise orbit file to the SAR radar data through SNAP software to correct the position, the raw values ​​of the SAR radar data are converted into backscatter coefficients through radiometric calibration;

[0021] S13: converting the optical remote sensing image data and SAR radar data into a universal map coordinate system, using the optical remote sensing image as a reference, and selecting ground control points to perform geometric correction on the SAR radar data;

[0022] S14: Open the optical remote sensing image data after radiation calibration in ENVI software, calculate the NDVI index of the area to be detected by NDVI, and calculate the change in the NDVI index of the area to be detected between the current moment and the previous moment;

[0023] S15: Open the SAR radar data after radiometric calibration in the SNAP software and calculate the change in the backscatter coefficient of the area to be detected between the current moment and the previous moment;

[0024] S16: Setting a threshold index, comparing the change in NDVI index and backscatter coefficient of the area to be detected at the current moment and the previous moment with the set threshold index respectively, identifying the characteristic abnormal pixels of the area to be detected, and aggregating the identified characteristic abnormal pixels into polygons to obtain the target change area of ​​the area to be detected.

[0025] In this embodiment, step S1 achieves high-precision spatial positioning and quantitative analysis of ecological and environmental changes by preprocessing optical remote sensing images and SAR radar data and identifying change areas. Specifically, by using ENVI and SNAP software to perform radiometric calibration and geometric correction on remote sensing data and SAR radar data, the effects of sensor errors and terrain deformation are eliminated, and data accuracy is improved to the centimeter level that meets the needs of ecological monitoring. By calculating the change in NDVI index and backscatter coefficient and combining it with threshold analysis, the spatiotemporal variation of environmental factors such as vegetation coverage and surface roughness can be accurately captured. The process of aggregating characteristic abnormal pixels into polygonal target change areas realizes the semantic conversion from pixel-level anomalies to regional-level changes, providing a clear spatial range for subsequent environmental monitoring information extraction.

[0026] For example, in a forest ecological monitoring scenario in a certain watershed, the S1 step is used to process the Landsat optical imagery and Sentinel-1 SAR data of the area. The image values ​​are converted into radiation brightness values ​​through ENVI radiometric calibration, and the backscatter coefficient is obtained after SNAP correction. The NDVI index difference between the current moment and the previous moment (such as from 0.6 to 0.4) and the change in SAR backscatter coefficient (such as -3dB) are calculated. After setting a threshold to filter normal fluctuations, the abnormal pixel aggregation area within 200 hectares along the river is identified. Finally, this area is determined to be the target change area caused by recent deforestation, providing a precise spatial benchmark for the subsequent targeted extraction of water quality and vegetation cover data.

[0027] S2: Extract all environmental monitoring information of the target change area at the current moment and the previous moment, as well as environmental policy information related to the target change area;

[0028] Preferably, the environmental monitoring information includes: air quality data, water quality data, soil quality data and vegetation coverage data; the environmental policy information includes: environmental planning, pollution prevention and control measures and ecological protection policies.

[0029] In this embodiment, step S2 systematically extracts the environmental monitoring information of the target change area at the current and previous moments (covering air quality (PM2.5, PM10, sulfur dioxide, etc. concentrations), water pH value, chemical oxygen demand, ammonia nitrogen content, etc.), soil quality (soil acidity, heavy metal content, etc.), vegetation cover data (normalized difference vegetation index NDVI), etc.) and related environmental policy information (including environmental planning, pollution prevention and control measures, ecological protection policies, etc.), thereby constructing a multi-dimensional data association system of "spatial change-environmental parameters-policy constraints". This step can not only accurately capture the dynamic changes of environmental factors in key areas, but also parse policy texts through natural language processing technology, clarify the control requirements of the target area, and avoid the problem of disconnection between data and policy in traditional monitoring. At the same time, data is only extracted for the target change area identified by remote sensing, which reduces the amount of data processing compared to the full-area sensor acquisition mode and significantly improves data utilization efficiency.

[0030] For example, in a watershed ecological monitoring scenario, after determining a 200-hectare vegetation-degraded area along the riverbank through step S1, step S2 extracts environmental data such as the COD concentration of the water quality in the area at the current moment increasing by 10 mg / L compared to the previous moment, and the heavy metal cadmium content in the soil exceeding the standard by 1.2 times. This data is then matched with the policy requirement of the local "Regulations on Pollution Prevention and Control in Water Source Protection Areas" that "direct discharge of industrial wastewater within 2 kilometers of the coast is prohibited." This directly links environmental data anomalies with policy-controlled areas, quickly locates industrial pollution sources, shortens problem tracing time compared to traditional single-sensor monitoring modes, and provides dual support of data and policy for environmental supervision.

[0031] S3: Use natural language processing technology to parse environmental policy information and extract the corresponding control areas;

[0032] Preferably, step S3 includes:

[0033] S31: Download environmental policy-related PDF documents, Word documents, or HTML documents from official websites using Internet crawler technology, and convert the downloaded documents into plain text TXT format;

[0034] S32: Use NLTK or Jieba word segmentation tools to segment TXT text and perform part-of-speech tagging;

[0035] S33: Using named entity recognition technology, identify the region name and policy implementation time from the text after word segmentation and part-of-speech tagging;

[0036] S34: Determine whether the policy implementation time is between the current moment and the previous moment. If so, compare the extracted regional names with the standard place name database one by one, and standardize the names that are inconsistent but refer to the same region;

[0037] S35: Substitute the standardized area name into the environmental protection policy rule template library for matching. If the match is successful, the area is determined to be a controlled area; and the geographical boundaries and scope of the controlled area are delineated through spatial analysis based on administrative division data, watershed division data or topographic data.

[0038] In this embodiment, step S3 retrieves policy documents through an internet crawler and performs word segmentation and named entity recognition. This accurately extracts the names of the areas covered by the policy and the implementation dates. After standardization and rule template matching, the boundaries of the control areas are delineated in conjunction with spatial data such as administrative divisions. This resolves the disconnect between policy text and geographic spatial information in traditional monitoring. Its core value lies in: through semantic parsing, it transforms abstract policy requirements into quantifiable and locatable geographic spatial scopes, providing a policy compliance reference for subsequent environmental change analysis, while also enabling spatial tracing of policy implementation effects and improving the accuracy of ecological control.

[0039] For example, in an ecological monitoring scenario at a provincial nature reserve:

[0040] Policy document acquisition and processing: We downloaded the PDF document "XX River Basin Water Ecological Environment Protection Plan (2023-2030)" from the official website of the Department of Ecology and Environment through a crawler. After converting it into TXT text, we used the Jieba word segmentation tool to identify key information such as "within 5 kilometers along the XX section of the Yangtze River tributary" and "implemented from January 1, 2024";

[0041] Regional name standardization: Compare the "XX River Section" in the text with the standard place name database to confirm that its corresponding administrative division is "XX Town, Yubei District, Chongqing City to XX Township, Banan District", and unify it as the official standard name;

[0042] Delineation of control areas: The standardized area names were substituted into the environmental protection policy rule template library, matching the clause "Development and construction are prohibited in water conservation areas". Combining watershed demarcation data with GIS spatial analysis, a 5-kilometer range (120 square kilometers) along the river section was delineated as a control area, generating a vector data layer containing geographic boundaries.

[0043] S4: Identify the environmental change area within the control area based on all environmental monitoring information of the control area at the current moment and the previous moment;

[0044] Preferably, step S4 includes:

[0045] S41: Compare the environmental indicator data monitored by the environmental monitoring station at the current moment and the previous moment within the control area, and calculate the change value of each environmental indicator;

[0046] S42: Determine whether the environment in the monitoring area corresponding to each environmental monitoring station has changed based on the set environmental indicator change threshold; if the change value of the environmental indicator monitored by a certain environmental monitoring station exceeds the set threshold, it is considered that the environment in the monitoring area corresponding to the environmental monitoring station has changed;

[0047] S43: Fitting the monitoring areas of all environmental monitoring stations where the environment has changed to obtain the environmental change areas within the control area.

[0048] In this embodiment, step S4 realizes the precise positioning and quantitative analysis of environmental changes in the policy control area by comparing the time series and spatial fitting of the environmental monitoring station data in the control area. This step calculates the change value of the environmental indicators (such as air quality, water quality, soil quality, etc.) between the current moment and the previous moment, and compares it with the set threshold value. It can automatically identify the monitoring points where the environment has changed significantly, and then convert the discrete points into continuous change areas through spatial interpolation or polygon fitting technology, solving the problem that traditional manual inspections or single-point monitoring are difficult to capture regional environmental changes. Its core value lies in dynamically associating the control area defined by the policy text with real-time environmental monitoring data to form a closed-loop analysis of "policy constraints-environmental response", which not only provides precise spatial targeting for environmental supervision, but also can trace the ecological effects after the implementation of the policy, thereby improving the timeliness and accuracy of dynamic supervision.

[0049] For example, in a drinking water source protection area management scenario, the area is designated as a management area by the "Water Source Protection Regulations", and 5 water quality monitoring stations and 3 air quality monitoring stations are deployed. Through step S4, the water quality data monitored at the current moment (such as the ammonia nitrogen concentration rising from 0.5mg / L to 1.2mg / L) is compared with the data at the previous moment, and the change value is calculated to be 0.7mg / L, which exceeds the set threshold of 0.5mg / L. At the same time, the COD concentration change value of another monitoring station also exceeds the threshold; no significant abnormalities are found in the simultaneous analysis of the air quality data. Based on the above results, a water quality deterioration area of ​​about 2 square kilometers is generated through spatial fitting, and it is located near the sewage outlet of an enterprise upstream of the protection area. This process does not require manual traversal of the data in the entire area. The polluted area is directly locked through threshold judgment and spatial fitting, which shortens the response time compared to the traditional manual inspection method and provides an accurate basis for the scope of pollution for environmental law enforcement.

[0050] S5: Positionally match the control area with the target change area to obtain a matching area, and extract all environmental monitoring station information in the matching area between the current moment and the previous moment;

[0051] Preferably, step S5 includes: using the spatial analysis function of the geographic information system (GIS) to import the vector boundary data of the control area and the target change area into the GIS platform, and calculating the overlapping part of the two areas through the overlay analysis tool of the GIS to obtain the matching area.

[0052] In this embodiment, step S5 realizes the accurate superposition analysis of the control area and the target change area through GIS spatial analysis. Its core value lies in spatially matching the control range defined by the policy with the actual environmental change area identified by remote sensing, thereby locking the key overlapping area of ​​"policy constraints and environmental responses" and providing data targeting for subsequent refined monitoring. Specifically, this step uses the vector overlay analysis tool of the GIS platform to perform spatial operations on the boundary data of the control area (such as the water source protection area defined by the policy) and the target change area (such as the vegetation degradation area identified by remote sensing), automatically calculate the intersection of the two (i.e., the matching area), and simultaneously extract the time series data of the environmental monitoring stations in the area. This process solves the problem of "disconnection between policy areas and actual change areas" in traditional monitoring. Through precise matching of spatial dimensions, environmental monitoring data can be directly mapped to key areas of policy control, providing high-value input data for the AI ​​large model, and significantly improving the pertinence and accuracy of abnormal warnings.

[0053] S6: All environmental monitoring station information of the target change area, control area, environmental change area and matching area between the current moment and the previous moment is spliced ​​to generate a sequence to be tested and input it into the AI ​​big model for prediction to determine whether the environment of the area to be tested is abnormal. If so, an early warning is issued.

[0054] Preferably, step S6 includes:

[0055] S61: Clean and standardize the spliced ​​test sequences, remove duplicate and missing data, normalize different types of environmental indicator data, and unify the data format and dimension;

[0056] S62: Input the pre-processed test sequence into the trained AI model. The AI ​​model predicts the probability value of environmental abnormality by learning the data features of the test sequence.

[0057] S63: When the probability value of environmental abnormality is higher than the set threshold, start the warning.

[0058] In this embodiment, step S6 integrates multi-dimensional spatial data with environmental monitoring information to build a closed-loop mechanism of "data fusion-intelligent prediction-automatic warning", realizing intelligent identification and rapid response to ecological and environmental anomalies. This step structurally splices multi-source spatial data such as target change areas and control areas with time series data from environmental monitoring stations, and inputs them into the AI ​​big model after pre-processing such as cleaning and normalization. By mining the implicit correlation between data features, it realizes the prediction of abnormal probability, solving the problems of low efficiency of manual analysis and weak correlation of multi-source data in traditional monitoring. Its core value lies in the collaborative analysis of multi-dimensional data, which transforms scattered environmental information into a knowledge graph with early warning value, and enables monitoring to shift from "post-event tracing" to "pre-event prediction", greatly improving the intelligent level of ecological and environmental supervision.

[0059] For example, in a certain urban agglomeration ecological monitoring scenario, steps S1-S5 have identified the target change area where 30 hectares of cultivated land in the urban fringe are converted to construction land. This area also belongs to the control area defined in the Soil Pollution Prevention and Control Action Plan, and step S4 fits the environmental change area where 5 hectares of soil heavy metal concentrations increase. Step S6 combines the time series data of the three soil monitoring stations and two air quality monitoring stations in the above area (such as cadmium concentration increases from 0.3mg / kg to 0.5mg / kg, PM2.5 concentration increases from 25μg / m 3 Increased to 40 μg / m 3 ) were spliced ​​together, cleaned to remove outliers, and normalized before being fed into a trained AI model. The model analyzed and identified synergistic variations between soil heavy metal and air quality data, predicting an 82% probability of environmental anomaly (exceeding the 70% threshold). This triggered an early warning mechanism, indicating the risk of industrial pollution spreading in the area.

[0060] Preferably, the AI ​​large model of the present invention can adopt a model architecture that can handle multi-source heterogeneous data fusion and spatiotemporal feature analysis, such as a hybrid model combining Transformer and graph neural network (GNN), or a spatiotemporal sequence prediction model integrating convolutional neural network (CNN) and long short-term memory network (LSTM). This type of model can effectively learn the feature associations between multi-dimensional spatial data such as target change areas and control areas and time series data of environmental monitoring stations, and realize the probability prediction of ecological environment anomalies through weighted fusion of remote sensing image features, policy text semantic information and environmental indicator values ​​through the attention mechanism. For example, in the urban agglomeration ecological monitoring scenario, the model can learn the spatiotemporal coupling laws of soil heavy metal concentrations, air quality indicators and land use changes through training. When the spliced ​​multi-source data sequence is input, it can quickly capture the implicit associations between data features, output the probability value of environmental anomalies and trigger an early warning, meeting the full process requirements from multi-source data to intelligent prediction.

[0061] Another aspect of the present invention provides an ecological environment dynamic monitoring system based on remote sensing and geographic information system, including: a memory and a processor; the memory is used to store application programs; the processor is used to run the application programs and execute the ecological environment dynamic monitoring method based on remote sensing and geographic information system.

[0062] Another aspect of the present invention provides a computer storage medium having a program stored thereon, which, when executed by a processor, implements the method for dynamic monitoring of an ecological environment based on remote sensing and a geographic information system.

[0063] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can 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 (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0064] In summary, the present invention addresses the problems of existing ecological environmental monitoring that over-rely on multiple sets of sensors, resulting in large data volumes, time-consuming processing, inconvenient dynamic supervision, and insufficient policy linkage. It uses optical remote sensing and SAR radar data to dynamically capture large-area environmental elements, greatly reducing dependence on dense sensors. Sensor data is extracted only in target changes and control areas, and natural language processing is used to parse environmental policy texts and match them with remote sensing data positions. Multi-source data is spliced ​​and input into a large AI model to predict environmental anomalies and issue warnings, forming an efficient monitoring model of "macro-identification-micro-verification-policy linkage", which not only reduces data collection and processing pressure and hardware costs, but also improves the accuracy and timeliness of dynamic supervision, achieving a technological leap from passive data collection to active anomaly warning, and solving the pain points of traditional solutions such as single data dimension, discontinuous spatial coverage, and difficulty in tracing policy implementation effects.

[0065] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solutions, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for dynamic monitoring of ecological environment based on remote sensing and geographic information system, characterized in that: include: S1: Preprocess the optical remote sensing image data and SAR radar data of the area to be detected, identify the changed area of ​​the area to be detected between the current moment and the previous moment, and obtain the target changed area; S2: Extract all environmental monitoring information of the target change area at the current moment and the previous moment, as well as environmental policy information related to the target change area; S3: Use natural language processing technology to parse environmental policy information and extract the corresponding control areas; S4: Identify the environmental change area within the control area based on all environmental monitoring information of the control area at the current moment and the previous moment; S5: Positionally match the control area with the target change area to obtain a matching area, and extract all environmental monitoring station information in the matching area between the current moment and the previous moment; S6: All environmental monitoring station information of the target change area, control area, environmental change area and matching area between the current moment and the previous moment is spliced ​​to generate a sequence to be tested and input it into the AI ​​big model for prediction to determine whether the environment of the area to be tested is abnormal. If so, an early warning is issued.

2. The method for dynamic monitoring of ecological environment based on remote sensing and geographic information system according to claim 1, characterized in that: The step S1 comprises: S11: Radiometric calibration of optical remote sensing image data is performed using ENVI software to convert the original values ​​of remote sensing images into radiometric brightness values; S12: After applying the precise orbit file to the SAR radar data through SNAP software to correct the position, the raw values ​​of the SAR radar data are converted into backscatter coefficients through radiometric calibration; S13: converting the optical remote sensing image data and SAR radar data into a universal map coordinate system, using the optical remote sensing image as a reference, and selecting ground control points to perform geometric correction on the SAR radar data; S14: Open the optical remote sensing image data after radiation calibration in ENVI software, calculate the NDVI index of the area to be detected by NDVI, and calculate the change in the NDVI index of the area to be detected between the current moment and the previous moment; S15: Open the SAR radar data after radiometric calibration in the SNAP software and calculate the change in the backscatter coefficient of the area to be detected between the current moment and the previous moment; S16: Setting a threshold index, comparing the change in NDVI index and backscatter coefficient of the area to be detected at the current moment and the previous moment with the set threshold index respectively, identifying the characteristic abnormal pixels of the area to be detected, and aggregating the identified characteristic abnormal pixels into polygons to obtain the target change area of ​​the area to be detected.

3. The method for dynamic monitoring of ecological environment based on remote sensing and geographic information system according to claim 1, characterized in that: The environmental monitoring information includes: air quality data, water quality data, soil quality data and vegetation cover data; the environmental policy information includes: environmental planning, pollution prevention and control measures and ecological protection policies.

4. The method for dynamic monitoring of ecological environment based on remote sensing and geographic information system according to claim 3, characterized in that: The step S3 comprises: S31: Download environmental policy-related PDF documents, Word documents, or HTML documents from official websites using Internet crawler technology, and convert the downloaded documents into plain text TXT format; S32: Use NLTK or Jieba word segmentation tools to segment TXT text and perform part-of-speech tagging; S33: Using named entity recognition technology, identify the region name and policy implementation time from the text after word segmentation and part-of-speech tagging; S34: Determine whether the policy implementation time is between the current moment and the previous moment. If so, compare the extracted regional names with the standard place name database one by one, and standardize the names that are inconsistent but refer to the same region; S35: Substitute the standardized area name into the environmental protection policy rule template library for matching. If the match is successful, the area is determined to be a controlled area; and the geographical boundaries and scope of the controlled area are delineated through spatial analysis based on administrative division data, watershed division data or topographic data.

5. The method for dynamic monitoring of ecological environment based on remote sensing and geographic information system according to claim 3, characterized in that: The step S4 comprises: S41: Compare the environmental indicator data monitored by the environmental monitoring station at the current moment and the previous moment within the control area, and calculate the change value of each environmental indicator; S42: Determine whether the environment in the monitoring area corresponding to each environmental monitoring station has changed based on the set environmental indicator change threshold; if the change value of the environmental indicator monitored by a certain environmental monitoring station exceeds the set threshold, it is considered that the environment in the monitoring area corresponding to the environmental monitoring station has changed; S43: Fitting the monitoring areas of all environmental monitoring stations where the environment has changed to obtain the environmental change areas within the control area.

6. The method for dynamic monitoring of ecological environment based on remote sensing and geographic information system according to claim 1, characterized in that: The step S5 includes: using the spatial analysis function of the geographic information system (GIS) to import the vector boundary data of the control area and the target change area into the GIS platform, and using the GIS overlay analysis tool to calculate the overlapping part of the two areas to obtain the matching area.

7. The method for dynamic monitoring of ecological environment based on remote sensing and geographic information system according to claim 1, characterized in that: The step S6 comprises: S61: Clean and standardize the spliced ​​test sequences, remove duplicate and missing data, normalize different types of environmental indicator data, and unify the data format and dimension; S62: Input the pre-processed test sequence into the trained AI model. The AI ​​model predicts the probability value of environmental abnormality by learning the data features of the test sequence. S63: When the probability value of environmental abnormality is higher than the set threshold, start the warning.

8. A dynamic ecological environment monitoring system based on remote sensing and geographic information system, characterized in that: The system includes a memory and a processor; the memory is used to store applications; the processor is used to run the applications and execute the method for dynamic monitoring of the ecological environment based on remote sensing and geographic information system as described in any one of claims 1 to 7.

9. A computer storage medium, characterized in that The computer storage medium stores a program, and when the program is executed by the processor, the method for dynamic monitoring of the ecological environment based on remote sensing and geographic information system according to any one of claims 1 to 7 is implemented.

Images