Ecological geology dynamic monitoring and evaluation method based on multi-source data fusion

Abstract

The invention discloses an ecological geology dynamic monitoring and evaluation method based on multi-source data fusion, and belongs to the field of geological environment monitoring, and the monitoring and evaluation method specifically comprises the following steps: S1, collecting different types of geological monitoring data from satellite remote sensing, ground sensor data sources and geological survey, and carrying out preprocessing research; s2, dynamically adjusting the weight of each type of geological monitoring data, carrying out fusion, and carrying out data modeling on an incomplete collection region; s3, according to the processed geological monitoring data, evaluating an ecological geological problem of the target area, simulating an evolutionary path of the ecological geological problem, and identifying potential risks; according to the method, multi-dimensional data collaboration can be realized, the monitoring accuracy of the change of the ecogeological problem is improved, the real-time response capability is enhanced, the early warning response time is shortened, the problem of scale fracture in a traditional method is effectively solved, and comprehensive evaluation of the ecogeological problem is realized.

Description

Technical Field

[0001] The present invention relates to the field of geological environment monitoring, and in particular to an ecological geological dynamic monitoring and assessment method based on multi-source data fusion. Background Art

[0002] The dynamics of the ecological and geological environment are directly related to natural disaster early warning, ecological security, and sustainable resource utilization. With the intensification of mineral development, urban expansion, and climate change, the geological environment is under greater pressure, and ecological and geological problems such as landslides, ground subsidence, and soil erosion are becoming increasingly prominent. Traditional geological monitoring methods often rely on a single data source, such as ground sensors or remote sensing imagery. However, due to limitations in data timeliness, spatial resolution, and environmental interference, they are unable to fully reflect the dynamic evolution of ecological and geological systems. Therefore, it is particularly important to develop dynamic ecological and geological monitoring and assessment methods based on multi-source data fusion.

[0003] After searching, Chinese patent number CN119322164A discloses a geological ecological monitoring system and method. Although this invention better serves geological disaster prevention and ecological environment protection through comprehensive, dynamic and systematic monitoring and evaluation of geological ecosystems, it cannot achieve multi-dimensional data collaboration, which reduces the accuracy of monitoring ecological geological changes. In addition, there is a scale fracture problem in the monitoring process, which makes it impossible to conduct a comprehensive assessment of the ecological geological system. Therefore, we propose an ecological geological dynamic monitoring and evaluation method based on multi-source data fusion. Summary of the Invention

[0004] The purpose of the present invention is to solve the defects in the prior art and to propose an ecological geological dynamic monitoring and assessment method based on multi-source data fusion.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] The ecological geological dynamic monitoring and assessment method based on multi-source data fusion has the following specific steps:

[0007] S1. Collect different types of geological monitoring data from satellite remote sensing, ground sensors and geological surveys, and conduct pre-processing research;

[0008] S2. Dynamically adjust the weights of various geological monitoring data, integrate them, and then perform data modeling for areas with incomplete data collection;

[0009] S3. Based on the processed geological monitoring data, evaluate the ecological and geological problems in the target area, simulate the evolution path of ecological and geological problems, and identify potential geological risks;

[0010] S4. Collect the monitoring and assessment results of the ecological geology of the target area, generate the corresponding ecological geology assessment report, and feed back the generated assessment report to each staff member.

[0011] As a further solution of the present invention, the specific steps of pre-processing various types of geological monitoring data in S1 are as follows:

[0012] P1.1: Collect remote sensing data, geological sensor data, and survey data from satellite remote sensing, ground sensors, and geological survey data sources. Unify the remote sensing data into a standard projected coordinate system. Standardize the timestamps of the geological sensor data and unify the data unit format. Finally, convert the survey data into a database table structure.

[0013] P1.2: Use linear interpolation to fill in unevenly spaced time intervals for remote sensing data and geological sensor data. Time-align the data according to a time window with a preset step size. Resample the remote sensing data based on the spatial resolution of the geological sensor data. Use Kriging interpolation to fill in the spatially missing points in the geological sensor data to synchronize them with the grid distribution of the remote sensing data.

[0014] P1.3: After the spatiotemporal alignment of various data types is completed, adaptive filtering and deformation time series analysis are used to remove occlusion and noise interference in each remote sensing data. Low-pass filtering is used to remove environmental noise in each geological sensor data. The box plot method is then used to identify and eliminate abnormal geological sensor data in each geological sensor data. Then, through cross-validation, duplicate or erroneous data in each survey data is eliminated. Based on historical survey data, abnormal survey data in each survey data is identified and eliminated.

[0015] As a further solution of the present invention, the specific steps of dynamically adjusting the weights of various types of geological monitoring data in S2 are as follows:

[0016] P2.1: Based on the contribution of various historical data from different data sources, the initial weights of various types of real-time remote sensing data, geological sensor data, and survey data are set. The intensity of the sudden change of each geological event is calculated based on the geological sensor data. When the intensity of the sudden change of a geological event exceeds the preset threshold, it is judged that a significant geological change has occurred, and the weights are adjusted accordingly.

[0017] P2.2: Collect weight sequences within a preset time range, various data from different data sources, the intensity of geological event mutations, and the historical changes of the corresponding geological events. Then, normalize each set of data to the range of [-1, 1], and use the processed data as input data.

[0018] P2.3: Establish a hybrid adjustment model consisting of an input layer, an LSTM layer, a GRU layer, and an output layer. Each input data is transmitted to the hybrid adjustment model. The input layer receives each input data and performs forward propagation. The LSTM layer receives each set of input data and calculates through the input gate, forget gate, and output gate to obtain the changing trend of the weights of various data sources.

[0019] P2.4: The LSTM layer transmits the changing trends of the weights of various data sources to the GRU layer. Based on the changing trends of different weights, the GRU layer updates the gate, resets the gate, and calculates the candidate state to output the final predicted weights of various data sources. The output layer uses exponential smoothing to optimize the predicted weights of various data sources.

[0020] P2.5: Based on the optimized prediction weights of various data types from different data sources, as well as the type of geological event and the scope of its impact, adjust the weight values ​​of various data types from each data source to improve the contribution of key data sources. After the adjustment is completed, the actual error is calculated based on the feedback of new data monitored within the subsequent preset time range. If the error is higher than the preset threshold, the parameters of each network layer of the hybrid adjustment model are updated, and the weights of various data types from each data source are readjusted.

[0021] As a further solution of the present invention, the specific calculation formula for the mutation intensity of the geological event described in P2.1 is as follows:

[0022]

[0023] Where S t represents the sudden change intensity of geological events at time t; P t represents the geological sensing data monitored at time t, including microseismic signals, surface inclination and soil moisture; P t-1 represents the same geological sensor data monitored at time t; σ P Represents the standard deviation of the geological sensor data P in the historical data.

[0024] As a further solution of the present invention, the specific steps of evaluating the ecological geology of the target area in S3 are as follows:

[0025] P3.1: Collect μm-level geological anomaly signals through ground sensors. Based on the calculated weights of each geological anomaly signal, perform weighted mean fusion on each set of ground sensor data. Then, decompose each raw geological anomaly signal into intrinsic mode functions to obtain geological deformation patterns at different scales. Calculate the power spectral density of the current geological sensor data through Fourier transform.

[0026] P3.2: Use the sliding window method to calculate the local deformation rate at different times. If the local deformation rate exceeds the preset threshold, it is determined that accelerated deformation is occurring. LOESS filtering is then used to extract the deformation trend and generate a corresponding deformation curve. If the generated deformation curve shows exponential growth, the current regional ecological and geological problems pose a disaster risk. The current geological deformation pattern type is also determined, and an early warning signal is issued.

[0027] P3.3: Select key ecological and geological factors such as surface water erosion intensity, soil organic matter content, vegetation cover, and soil moisture from remote sensing and geological sensor data. Calculate the ecological carrying capacity index of the current area using a normalization method based on the calculated weights of each type of data. Then, calculate the geological stability index based on the survey data.

[0028] P3.4: When an early warning signal is received, the ecological carrying capacity index value is lowered and regional monitoring efforts are increased. When the geological stability index falls below the set value, the frequency of monitoring data collection is increased. Simultaneously, a macro-scale comprehensive evaluation model is established based on geological stability, ecological carrying capacity, and external interference factors.

[0029] P3.5: The macro-scale comprehensive evaluation model divides regional risks into zones based on the weighted values ​​of remote sensing data, geological sensor data, and survey data, as well as the corresponding geological events, and identifies high-risk areas. When the change in the geological stability index decreases by more than the preset threshold, the monitoring density of high-risk areas is increased, and the high-risk areas are fed back to the staff.

[0030] As a further solution of the present invention, the specific calculation formula for the local deformation rate in P3.2 is as follows:

[0031]

[0032] Where, D(t V ) represents the time t V Deformation; Δt V Represents the time interval; V m represents the local deformation rate;

[0033] The specific calculation formula for the ecological carrying capacity index mentioned in P3.3 is as follows:

[0034]

[0035] Where Et represents the surface water erosion intensity; So represents the soil organic matter content; Vc represents the vegetation coverage; Ws represents the soil moisture; w1, w2, w3 and w4 represent the corresponding weight values ​​of each data respectively.

[0036] As a further solution of the present invention, the specific steps of simulating the ecological geological evolution path and identifying potential geological risks in S3 are as follows:

[0037] P4.1: Consider the eco-geological system and human activity as the game players. Based on the various eco-geological states and human development plans, establish eco-geological system strategies and human activity strategies. Construct benefit and cost functions, calculate the impact of different combinations of the two strategies, and establish the corresponding payoff matrix.

[0038] P4.2: Calculate the probability of the ecological geological system maintaining a stable state, and based on the calculated probability of the stable state, obtain the average benefit of the current ecological geological system. Calculate the probability of human ecological development, and based on the calculated probability of human ecological development, obtain the average benefit of current human activities.

[0039] P4.3: Based on the calculated probability values, construct the ecological geological problem evolution equation and the human activity evolution equation. Then, calculate the values ​​of the two evolution equations. If the ecological geological evolution equation value is greater than 0, the ecological geological system is stable. If the human activity evolution equation value is greater than 0, it indicates that human activities are increasing ecological development.

[0040] P4.4: Repeatedly use the ecological and geological evolution equations and the human activity evolution equations to conduct game evolution, and calculate the average benefits of the ecological and geological system and the average benefits of human activities in each round of evolution;

[0041] P4.5: Based on the evolution results, the eco-geological safety index is updated in real time. If the eco-geological safety index is lower than the set threshold, an early warning is triggered, and the potential disaster risk types in the eco-geological system are analyzed, and mineral development is reduced or ecological restoration is strengthened.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] This ecological geological dynamic monitoring and assessment method based on multi-source data fusion calculates the mutation intensity of geological events through geological sensor data. If it exceeds the threshold, the data weight is adjusted, and the weight change trend is extracted using a hybrid neural network. The prediction weight is optimized through exponential smoothing. The contribution of key data sources is adjusted in combination with the type of geological event and the scope of influence. Afterwards, ground sensor data is collected and weighted fused, and the deformation rate is calculated using Fourier transform and sliding window method. If the deformation curve shows exponential growth, a disaster warning is issued. Further combined with remote sensing and survey data, the ecological carrying capacity index and geological stability index are calculated, and regional risk levels are divided based on a macro-scale comprehensive evaluation model. When the geological stability index decreases beyond the threshold, the monitoring density of high-risk areas is increased. It can achieve multi-dimensional data collaboration, improve the monitoring accuracy of ecological geological changes, enhance real-time response capabilities, shorten the warning response time, effectively solve the problem of mid-scale fractures in traditional methods, and achieve a comprehensive assessment of ecological geological problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0045] Figure 1 This is a flowchart of the ecological geological dynamic monitoring and assessment method based on multi-source data fusion proposed in this invention. DETAILED DESCRIPTION

[0046] Example 1, with reference to Figure 1 , an ecological geological dynamic monitoring and assessment method based on multi-source data fusion, the specific steps of this monitoring and assessment method are as follows:

[0047] Different types of geological monitoring data are collected from satellite remote sensing, ground sensors and geological surveys, and pre-processing research is carried out.

[0048] Specifically, after collecting remote sensing data, geological sensor data, and survey data from satellite remote sensing, ground sensors, and geological survey data, the remote sensing data are unified into a standard projected coordinate system. The timestamps of each geological sensor data are then standardized and the data unit format is unified. The survey data are then converted into a database table structure. Linear interpolation is used to fill in remote sensing data and geological sensor data with uneven time intervals. The various data are time-aligned according to a time window with a preset step size. The remote sensing data are then resampled based on the spatial resolution of the geological sensor data. Kriging interpolation is used to fill in the spatial missing points of the geological sensor data to synchronize them with the raster distribution of the remote sensing data. After the spatiotemporal alignment of the various data is completed, adaptive filtering and deformation time series analysis are used to remove occlusion and noise interference in each remote sensing data. Low-pass filtering is used to remove environmental noise in each geological sensor data. Anomalous geological sensor data in each geological sensor data is then identified and eliminated using the boxplot method. Repeated or erroneous data in each survey data are eliminated through cross-validation. Anomalous survey data in each survey data is also identified and eliminated based on historical survey data.

[0049] Dynamically adjust the weights of various types of geological monitoring data, integrate them, and then perform data modeling for areas with incomplete collection.

[0050] Specifically, according to the contribution of various historical data from different data sources, the initial weights of various current real-time remote sensing data, geological sensor data and survey data are set, and the mutation intensity of each geological event is calculated based on the geological sensor data. When the mutation intensity of the geological event exceeds the preset threshold, it is judged that a significant geological change has occurred, and the weight is adjusted at the same time. The weight sequence within the preset time range, various data from different data sources, the mutation intensity of geological events and the historical changes of the corresponding geological events are collected, and then each group of data is unified to the range of [-1, 1] through normalization processing. After that, each group of processed data is used as input data, and a hybrid adjustment model including an input layer, an LSTM layer, a GRU layer and an output layer is established. Each input data is transmitted to the hybrid adjustment model. The input layer receives each input data and performs forward propagation. The LSTM layer receives each group of input data and passes through the input gate, the forget gate and the output layer. And output gate calculation, obtain the changing trend of the weights of various types of data from different data sources. The LSTM layer transmits the changing trend of the weights of various types of data from different data sources to the GRU layer. The GRU layer is based on the changing trend of different weights, through update gates, reset gates and candidate state calculations to output the final predicted weights of various types of data from different data sources. The output layer uses exponential smoothing to optimize the predicted weights of various types of data from different data sources. According to the optimized predicted weights of various types of data from different data sources, as well as the type of geological event and the impact range of the geological event, the weight values ​​of various types of data from each data source are adjusted to improve the contribution of key data sources. After the adjustment is completed, the actual error is calculated based on the new data feedback monitored within the subsequent preset time range. If the error is higher than the preset threshold, the parameters of each network layer of the hybrid adjustment model are updated, and the weights of various types of data from each data source are readjusted.

[0051] It should be further explained that the specific calculation formula for the mutation intensity of geological events is as follows:

[0052]

[0053] Where S t represents the sudden change intensity of geological events at time t; P t represents the geological sensing data monitored at time t, including microseismic signals, surface inclination and soil moisture; P t-1 represents the same geological sensor data monitored at time t; σ P Represents the standard deviation of the geological sensor data P in the historical data.

[0054] Example 2, reference Figure 1 , an ecological geological dynamic monitoring and assessment method based on multi-source data fusion, the specific steps of this monitoring and assessment method are as follows:

[0055] Based on the processed geological monitoring data, the ecological and geological problems in the target area are evaluated, the evolution path of the ecological and geological problems is simulated, and potential geological risks are identified.

[0056] Specifically, μm-level geological anomaly signals are collected through ground sensors, and weighted mean fusion is performed on each group of ground sensor data based on the calculated weights of each geological anomaly signal. Then, each original geological anomaly signal is decomposed into intrinsic mode functions to obtain geological deformation patterns of different scales. The power spectrum density of the current geological sensor data is calculated by Fourier transform, and the local deformation rate at different times is calculated using the sliding window method. If the local deformation rate exceeds the preset threshold, it is judged that there is accelerated deformation. The deformation trend is extracted using LOESS filtering, and the corresponding deformation curve is generated. If the generated deformation curve is exponential growth, there is a disaster risk for the current regional ecological geological problem. At the same time, the current geological deformation mode type is judged, and an early warning signal is sent. Surface water erosion intensity, soil organic matter content, vegetation coverage, and soil moisture are selected from remote sensing data and geological sensor data. The key factors of ecological geology are calculated based on the weights of various data and the normalization method to calculate the ecological carrying capacity index of the current area. Then, the geological stability index is calculated based on the survey data. Based on the ecological carrying capacity index and the geological stability index, when an early warning signal is received, the ecological carrying capacity index value is reduced and the regional monitoring intensity is increased. When the geological stability index is lower than the set value, the collection frequency of each monitoring data is increased. At the same time, based on geological stability, ecological carrying capacity and external interference factors, a macro-scale comprehensive evaluation model is established. The macro-scale comprehensive evaluation model divides regional risks according to the weight values ​​of remote sensing data, geological sensor data and survey data, as well as the corresponding geological events, and identifies high-risk areas. When the change value of the geological stability index decreases by more than the preset threshold, the monitoring density of high-risk areas is increased, and the high-risk areas are fed back to the staff.

[0057] Specifically, the ecological geological system and human activities are taken as the game subjects respectively. At the same time, according to the ecological geological status and human development plans, the ecological geological system strategy and human activity strategy are established, and the benefit function and cost function are constructed. The impact of different combinations of the two sets of strategies is calculated to establish the corresponding payment matrix, calculate the probability of the ecological geological system maintaining a stable state, and obtain the average benefit of the current ecological geological system based on the calculated stable state probability value. The probability of human ecological development is calculated, and the average benefit of the current human activities is obtained based on the calculated human ecological development probability value. According to the calculated probability values ​​of each group, the evolution equation of the ecological geological problem is constructed. and the human activity evolution equation, and then calculate the two sets of evolution equation values ​​respectively. If the value of the ecological geological evolution equation is greater than 0, the ecological geological system is stable. If the value of the human activity evolution equation is greater than 0, it means that human activities are increasing ecological development. The ecological geological evolution equation and the human activity evolution equation are repeatedly used to carry out game evolution, and the average benefits of the ecological geological system and the average benefits of human activities in each round of evolution are calculated. According to the evolution results, the ecological geological safety index is updated in real time. If the ecological geological safety index is lower than the set threshold, an early warning is triggered, and the potential disaster risk types in the ecological geological system are analyzed, and mineral development is reduced or ecological restoration is strengthened.

[0058] It should be further explained that the specific calculation formula for the local deformation rate is as follows:

[0059]

[0060] Where, D(t V ) represents the time t V Deformation; Δt V Represents the time interval; V m represents the local deformation rate;

[0061] The specific calculation formula of the ecological carrying capacity index is as follows:

[0062]

[0063] Where Et represents the surface water erosion intensity; So represents the soil organic matter content; Vc represents the vegetation coverage; Ws represents the soil moisture; w1, w2, w3 and w4 represent the corresponding weight values ​​of each data respectively.

[0064] Collect the monitoring and assessment results of the ecological geology of the target area, generate the corresponding ecological geology assessment report, and feed back the generated assessment report to each staff member.

Claims

1. The ecological geological dynamic monitoring and assessment method based on multi-source data fusion is characterized by: The specific steps of the monitoring and evaluation method are as follows: S1. Collect different types of geological monitoring data from satellite remote sensing, ground sensors and geological surveys, and conduct pre-processing research; S2. Dynamically adjust the weights of various geological monitoring data, integrate them, and then perform data modeling for areas with incomplete data collection; S3. Based on the processed geological monitoring data, evaluate the ecological and geological problems in the target area, simulate the evolution path of ecological and geological problems, and identify potential geological risks; S4. Collect the monitoring and assessment results of the ecological geology of the target area, generate the corresponding ecological geology assessment report, and feed back the generated assessment report to each staff member.

2. The method for dynamic monitoring and assessment of ecological geology based on multi-source data fusion according to claim 1, characterized in that: The specific steps for preprocessing various types of geological monitoring data described in S1 are as follows: P1.1: Collect remote sensing data, geological sensor data, and survey data from satellite remote sensing, ground sensors, and geological survey data sources. Unify the remote sensing data into a standard projected coordinate system. Standardize the timestamps of the geological sensor data and unify the data unit format. Finally, convert the survey data into a database table structure. P1.2: Use linear interpolation to fill in unevenly spaced time intervals for remote sensing data and geological sensor data. Time-align the data according to a time window with a preset step size. Resample the remote sensing data based on the spatial resolution of the geological sensor data. Use Kriging interpolation to fill in the spatially missing points in the geological sensor data to synchronize them with the grid distribution of the remote sensing data. P1.3: After the spatiotemporal alignment of various data types is completed, adaptive filtering and deformation time series analysis are used to remove occlusion and noise interference in each remote sensing data. Low-pass filtering is used to remove environmental noise in each geological sensor data. The box plot method is then used to identify and eliminate abnormal geological sensor data in each geological sensor data. Then, through cross-validation, duplicate or erroneous data in each survey data is eliminated. Based on historical survey data, abnormal survey data in each survey data is identified and eliminated.

3. The method for dynamic monitoring and assessment of ecological geology based on multi-source data fusion according to claim 2 is characterized in that: The specific steps for dynamically adjusting the weights of various types of geological monitoring data described in S2 are as follows: P2.1: Based on the contribution of various historical data from different data sources, the initial weights of various types of real-time remote sensing data, geological sensor data, and survey data are set. The intensity of the sudden change of each geological event is calculated based on the geological sensor data. When the intensity of the sudden change of a geological event exceeds the preset threshold, it is judged that a significant geological change has occurred, and the weights are adjusted accordingly. P2.2: Collect weight sequences within a preset time range, various data from different data sources, the intensity of geological event mutations, and the historical changes of the corresponding geological events. Then, normalize each set of data to the range of [-1, 1], and use the processed data as input data. P2.3: Establish a hybrid adjustment model consisting of an input layer, an LSTM layer, a GRU layer, and an output layer. Each input data is transmitted to the hybrid adjustment model. The input layer receives each input data and performs forward propagation. The LSTM layer receives each set of input data and calculates through the input gate, forget gate, and output gate to obtain the changing trend of the weights of various data sources. P2.4: The LSTM layer transmits the changing trends of the weights of various data sources to the GRU layer. Based on the changing trends of different weights, the GRU layer updates the gate, resets the gate, and calculates the candidate state to output the final predicted weights of various data sources. The output layer uses exponential smoothing to optimize the predicted weights of various data sources. P2.5: Based on the optimized prediction weights of various data types from different data sources, as well as the type of geological event and the scope of its impact, adjust the weight values ​​of various data types from each data source to improve the contribution of key data sources. After the adjustment is completed, the actual error is calculated based on the feedback of new data monitored within the subsequent preset time range. If the error is higher than the preset threshold, the parameters of each network layer of the hybrid adjustment model are updated, and the weights of various data types from each data source are readjusted.

4. The method for dynamic monitoring and assessment of ecological geology based on multi-source data fusion according to claim 3 is characterized in that: The specific calculation formula for the mutation intensity of geological events described in P2.1 is as follows: Where S t represents the sudden change intensity of geological events at time t; P t represents the geological sensing data monitored at time t, including microseismic signals, surface inclination and soil moisture; P t-1 represents the same geological sensor data monitored at time t; σ P Represents the standard deviation of the geological sensor data P in the historical data.

5. The method for dynamic monitoring and assessment of ecological geology based on multi-source data fusion according to claim 3 is characterized in that: The specific steps for evaluating the ecogeology of the target area described in S3 are as follows: P3.1: Collect μm-level geological anomaly signals through ground sensors. Based on the calculated weights of each geological anomaly signal, perform weighted mean fusion on each set of ground sensor data. Then, decompose each raw geological anomaly signal into intrinsic mode functions to obtain geological deformation patterns at different scales. Calculate the power spectral density of the current geological sensor data through Fourier transform. P3.2: Use the sliding window method to calculate the local deformation rate at different times. If the local deformation rate exceeds the preset threshold, it is determined that accelerated deformation is occurring. LOESS filtering is then used to extract the deformation trend and generate a corresponding deformation curve. If the generated deformation curve shows exponential growth, the current regional ecological and geological problems pose a disaster risk. The current geological deformation pattern type is also determined, and an early warning signal is issued. P3.3: Select key ecological and geological factors such as surface water erosion intensity, soil organic matter content, vegetation cover, and soil moisture from remote sensing and geological sensor data. Calculate the ecological carrying capacity index of the current area using a normalization method based on the calculated weights of each type of data. Then, calculate the geological stability index based on the survey data. P3.4: When an early warning signal is received, the ecological carrying capacity index value is lowered and regional monitoring efforts are increased. When the geological stability index falls below the set value, the frequency of monitoring data collection is increased. Simultaneously, a macro-scale comprehensive evaluation model is established based on geological stability, ecological carrying capacity, and external interference factors. P3.5: The macro-scale comprehensive evaluation model divides regional risks into zones based on the weighted values ​​of remote sensing data, geological sensor data, and survey data, as well as the corresponding geological events, and identifies high-risk areas. When the change in the geological stability index decreases by more than the preset threshold, the monitoring density of high-risk areas is increased, and the high-risk areas are fed back to the staff.

6. The method for dynamic monitoring and assessment of ecological geology based on multi-source data fusion according to claim 5 is characterized in that: The specific calculation formula for the local deformation rate described in P3.2 is as follows: Where, D(t V ) represents the time t V Deformation; Δt V Represents the time interval; V m represents the local deformation rate; The specific calculation formula for the ecological carrying capacity index mentioned in P3.3 is as follows: Where Et represents the surface water erosion intensity; So represents the soil organic matter content; Vc represents the vegetation coverage; Ws represents the soil moisture; w1, w2, w3 and w4 represent the corresponding weight values ​​of each data respectively.

7. The method for dynamic monitoring and assessment of ecological geology based on multi-source data fusion according to claim 5, characterized in that: The specific steps for simulating the eco-geological evolution path and identifying potential geological risks described in S3 are as follows: P4.1: Consider the eco-geological system and human activity as the game players. Based on the various eco-geological states and human development plans, establish eco-geological system strategies and human activity strategies. Construct benefit and cost functions, calculate the impact of different combinations of the two strategies, and establish the corresponding payoff matrix. P4.2: Calculate the probability of the ecological geological system maintaining a stable state, and based on the calculated probability of the stable state, obtain the average benefit of the current ecological geological system. Calculate the probability of human ecological development, and based on the calculated probability of human ecological development, obtain the average benefit of current human activities. P4.3: Based on the calculated probability values, construct the ecological geological problem evolution equation and the human activity evolution equation. Then, calculate the values ​​of the two evolution equations. If the ecological geological evolution equation value is greater than 0, the ecological geological system is stable. If the human activity evolution equation value is greater than 0, it indicates that human activities are increasing ecological development. P4.4: Repeatedly use the ecological and geological evolution equations and the human activity evolution equations to conduct game evolution, and calculate the average benefits of the ecological and geological system and the average benefits of human activities in each round of evolution; P4.5: Based on the evolution results, the eco-geological safety index is updated in real time. If the eco-geological safety index is lower than the set threshold, an early warning is triggered, and the potential disaster risk types in the eco-geological system are analyzed, and mineral development is reduced or ecological restoration is strengthened.

Images