Vegetation water source conservation amount change monitoring system and method

Abstract

The invention relates to the technical field of information, in particular to a vegetation water conservation amount change monitoring system and method, and the system comprises a data obtaining module which is used for obtaining vegetation coverage data and hydrological element data of a monitoring region; the data processing module is used for inputting the vegetation coverage data and the hydrological element data into a preset water conservation amount estimation model and outputting a water conservation amount estimation result, and the water conservation amount estimation model is constructed by adopting a water balance equation according to historical vegetation types, areas and meteorological and hydrological data of the monitoring area; and the abnormity early warning module is used for carrying out abnormity early warning and change trend prediction based on the water source conservation amount estimation result, and completing vegetation water source conservation amount change monitoring of the monitoring area. According to the invention, accuracy and time-space continuity of vegetation water source conservation amount monitoring can be improved, and a scientific basis is provided for basin water resource management decision.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a system and method for monitoring changes in vegetation water conservation capacity. Background Art

[0002] Monitoring the change of vegetation water conservation capacity faces technical difficulties in data collection and processing in practical applications. Due to the need for long-term continuous monitoring of vegetation coverage in a large area, a large number of sensors are usually deployed to obtain monitoring data with high temporal and spatial resolution. However, the field environment is complex and changeable, and sensors are easily damaged and difficult to maintain, resulting in missing data or reduced quality. In addition, the vegetation water conservation process involves multiple hydrological elements such as precipitation, evapotranspiration, and infiltration. The elements affect each other, the amount of data is large, and the relationship is complex. How to obtain accurate and continuous monitoring data in the case of equipment failure and data loss, and extract the law of water conservation capacity changes from massive heterogeneous data, is a key technical problem that needs to be solved urgently. At the same time, data quality control, data assimilation, uncertainty analysis, etc. need to be considered to improve the reliability and availability of monitoring data and provide a scientific decision-making basis for watershed ecological protection and water resources management. Therefore, a system and method for monitoring the change of vegetation water conservation capacity is proposed. Summary of the invention

[0003] The purpose of the present invention is to provide a system and method for monitoring changes in vegetation water conservation capacity, so as to improve the accuracy and spatiotemporal continuity of vegetation water conservation capacity monitoring and provide a scientific basis for basin water resources management decisions.

[0004] To achieve the above object, the present invention provides the following solutions:

[0005] A vegetation water conservation capacity change monitoring system, comprising: a data acquisition module, a data processing module, and an abnormal warning module;

[0006] The data acquisition module is used to acquire vegetation coverage data and hydrological element data of the monitoring area;

[0007] The data processing module is used to input the vegetation coverage data and hydrological element data into a water conservation capacity estimation model and output a water conservation capacity estimation result, wherein the water conservation capacity estimation model is constructed using a water balance equation based on the historical vegetation type, area, and meteorological and hydrological data of the monitoring area;

[0008] The abnormal warning module is used to perform abnormal warning and change trend prediction based on the water conservation capacity estimation result, and complete the monitoring of vegetation water conservation capacity changes in the monitoring area.

[0009] Optionally, the data acquisition module acquires the vegetation coverage data and hydrological element data of the monitoring area, including:

[0010] By adopting ensemble Kalman filtering or variational assimilation technology, remote sensing data, meteorological data and sensor monitoring data of different temporal and spatial scales are integrated to dynamically update the spatiotemporal distribution information of hydrological elements and vegetation coverage.

[0011] Optionally, the data processing module includes a model building unit and a data analysis unit;

[0012] The model building unit is used to collect and process the historical vegetation type, area, meteorological and hydrological data of the monitoring area, and then use the water balance equation to build the water conservation capacity estimation model;

[0013] The data analysis unit is used to input the vegetation coverage data and hydrological element data into the water conservation capacity estimation model and output the water conservation capacity estimation result.

[0014] Optionally, the historical vegetation type, area, meteorological and hydrological data of the monitoring area are processed including data cleaning, standardization, quality assessment, data completion and data fusion.

[0015] Optionally, after constructing the water conservation capacity estimation model, the process further includes performing uncertainty analysis on the estimation result of the water conservation capacity estimation model, and performing the uncertainty analysis includes:

[0016] Through the Monte Carlo simulation technology, multiple random samplings are performed on the parameters and input data of the water conservation capacity estimation model, and the water conservation capacity estimation model is run to quantitatively evaluate the impact of uncertainty on the water conservation capacity estimation results and determine the confidence interval of the water conservation capacity change.

[0017] Optionally, performing abnormal warning and change trend prediction based on the water conservation capacity estimation result includes:

[0018] Collect continuous vegetation coverage data and hydrological element data to obtain continuous water conservation estimation results, use the autoregressive integrated moving average model for time series analysis, and use the long short-term memory network for machine learning to obtain the spatiotemporal variation patterns and influencing factors of vegetation water conservation;

[0019] When the water conservation capacity estimation result shows abnormal changes, the abnormal causes and future change trends are analyzed based on the spatiotemporal variation patterns and influencing factors of the vegetation water conservation capacity, and an early warning is issued.

[0020] Optionally, the system further includes a visualization display module, which is used to display the vegetation coverage data, hydrological element data, and corresponding water conservation capacity estimation results, as well as abnormal warnings and change trend predictions in interactive charts.

[0021] To further achieve the above object, the present invention also provides a method for monitoring changes in vegetation water conservation, comprising:

[0022] Obtain vegetation coverage data and hydrological element data in the monitoring area;

[0023] The vegetation coverage data and hydrological element data are input into a water conservation capacity estimation model, and a water conservation capacity estimation result is output. Based on the water conservation capacity estimation result, abnormal warnings and change trend predictions are performed to complete the monitoring of changes in vegetation water conservation capacity in the monitoring area. The water conservation capacity estimation model is constructed using a water balance equation based on historical vegetation type, area, meteorological and hydrological data of the monitoring area.

[0024] The beneficial effects of the present invention are:

[0025] The present invention processes massive heterogeneous monitoring data through data cleaning and standardization, uses random forest or support vector regression algorithm to establish a quantitative relationship model between hydrological elements and vegetation water conservation, and uses ensemble Kalman filtering or variational assimilation technology to fuse multi-source data, and dynamically updates the spatiotemporal distribution information of hydrological elements and vegetation conditions. The present invention also introduces Monte Carlo simulation technology for uncertainty analysis, uses autoregressive integral moving average model and long short-term memory network to mine the changing law of vegetation water conservation, and generates interactive charts and spatial distribution maps through visualization technology, which can effectively improve the accuracy and spatiotemporal continuity of vegetation water conservation monitoring, and provide a scientific basis for basin water resources management decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 This is a schematic diagram of the structure of a system for monitoring changes in vegetation water conservation capacity according to an embodiment of the present invention;

[0028] Figure 2 This is a flow chart of a method for monitoring changes in vegetation water conservation capacity according to an embodiment of the present invention; DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0031] This embodiment provides a system for monitoring changes in vegetation water conservation capacity. Figure 1 As shown, it includes: a data acquisition module, a data processing module, and an abnormal warning module;

[0032] Data acquisition module, used to obtain vegetation coverage data and hydrological element data of the monitoring area;

[0033] The data processing module is used to input the vegetation coverage data and the hydrological element data into the water conservation capacity estimation model and output the water conservation capacity estimation result. The water conservation capacity estimation model is constructed by using the water balance equation according to the historical vegetation type, area, meteorological and hydrological data of the monitoring area;

[0034] The abnormal warning module is used to provide abnormal warning and change trend prediction based on the water conservation capacity estimation results, and complete the monitoring of changes in vegetation water conservation capacity in the monitoring area.

[0035] Furthermore, the data acquisition module obtains the vegetation coverage data and hydrological element data of the monitoring area by adopting the ensemble Kalman filter or variational assimilation technology, and integrates the remote sensing data, meteorological data and sensor monitoring data of different temporal and spatial scales to dynamically update the temporal and spatial distribution information of hydrological elements and vegetation coverage.

[0036] Further, the data processing module includes a model building unit and a data analysis unit;

[0037] The model building unit is used to collect and process the historical vegetation type, area, meteorological and hydrological data of the monitoring area and then build a water conservation capacity estimation model;

[0038] The data analysis unit is used to input vegetation coverage data and hydrological element data into the water conservation capacity estimation model and output the water conservation capacity estimation result.

[0039] Specifically, the historical vegetation type, area, meteorological and hydrological data of the monitoring area are processed, including data cleaning, standardization, quality assessment, data completion and data fusion.

[0040] Data cleaning, standardization, and quality assessment: For the massive heterogeneous monitoring data collected by sensors, data cleaning and standardization processing technologies are used to remove noise data and outliers, and convert data from different sources and formats into a unified data structure and format. Through data quality assessment, data with unqualified quality is eliminated to improve data reliability and availability. Data quality assessment indicators include completeness, accuracy, consistency, and timeliness, and corresponding thresholds are set for screening.

[0041] Data completion: Obtain precipitation, evapotranspiration, and infiltration monitoring data, and use random forest or support vector regression algorithms to establish a quantitative relationship model between hydrological elements and vegetation water conservation capacity. When the data of a hydrological element is missing, the data of the missing element is estimated through a quantitative relationship model based on the monitoring data of other elements to complete the data and ensure the accuracy of the water conservation capacity estimation.

[0042] Data fusion: Use ensemble Kalman filtering or variational assimilation technology to fuse remote sensing data, meteorological data and sensor monitoring data of different temporal and spatial scales, dynamically update the temporal and spatial distribution information of hydrological elements and vegetation conditions, and if a data source is abnormal, it can be corrected based on the information of other data sources to improve the accuracy and temporal and spatial continuity of the monitoring data.

[0043] Specifically, after constructing the water conservation capacity estimation model, it also includes performing uncertainty analysis on the estimation results of the water conservation capacity estimation model, and the uncertainty analysis includes:

[0044] Through Monte Carlo simulation technology, multiple random samplings were carried out on the parameters and input data of the water conservation estimation model, the water conservation estimation model was run, the impact of uncertainty on the water conservation estimation results was quantitatively evaluated, and the confidence interval of the water conservation change was determined.

[0045] Furthermore, abnormal warning and change trend prediction based on the water conservation capacity estimation results include:

[0046] Collect continuous vegetation coverage data and hydrological element data to obtain continuous water conservation estimation results, use the autoregressive integrated moving average model for time series analysis, and use the long short-term memory network for machine learning to obtain the spatiotemporal variation patterns and influencing factors of vegetation water conservation;

[0047] When abnormal changes occur in the estimated results of water conservation capacity, the abnormal causes and future change trends are analyzed based on the spatiotemporal variation patterns and influencing factors of vegetation water conservation capacity, and early warnings are issued.

[0048] Furthermore, the vegetation water conservation capacity change monitoring system provided in this embodiment also includes a visualization display module for interactively displaying vegetation coverage data, hydrological element data, and corresponding water conservation capacity estimation results, as well as abnormal warnings and change trend predictions.

[0049] Specifically, based on monitoring data and analysis results, visualization technology is used to generate water conservation change charts and spatial distribution maps, and an interactive query function is set up. Users can retrieve monitoring data and analysis results within any time and space range as needed, providing a scientific basis for basin water resources management decisions. Visualization technologies include heat maps, contour maps, and three-dimensional topographic maps, which are combined with the timeline to achieve dynamic display.

[0050] To further optimize the above technical solution, this embodiment also provides a method for monitoring changes in vegetation water conservation, including:

[0051] Obtain vegetation coverage data and hydrological element data in the monitoring area;

[0052] The vegetation coverage data and hydrological element data are input into the preset water conservation capacity estimation model, and the water conservation capacity estimation results are output. Abnormal warnings and change trend predictions are carried out based on the water conservation capacity estimation results to complete the monitoring of vegetation water conservation capacity changes in the monitoring area. The water conservation capacity estimation model is constructed using the water balance equation based on the vegetation type, area, meteorological and hydrological data of the monitoring area.

[0053] Combine the following Figure 2 A method for monitoring changes in vegetation water conservation capacity provided in this embodiment is described in detail, specifically including:

[0054] Step S101, collecting and processing historical vegetation type, area, meteorological and hydrological data of the monitoring area;

[0055] (1) Data cleaning, standardization, and quality assessment: For the massive heterogeneous monitoring data collected by sensors, data cleaning and standardization processing technologies are used to remove noise data and outliers, and convert data from different sources and formats into a unified data structure and format. Through data quality assessment, data with substandard quality is eliminated to improve data reliability and availability. Data quality assessment indicators include completeness, accuracy, consistency, and timeliness, and corresponding thresholds are set for screening;

[0056] The original monitoring data collected by the sensor is obtained, and the original monitoring data includes heterogeneous data from different sources and formats; for the heterogeneous data, a preset data cleaning algorithm is used to remove noise data and outliers in the heterogeneous data to obtain a first data set after preliminary processing; for the first data set, a preset data standardization algorithm is used to convert the data of different structures and formats in the first data set into a unified standardized data structure and format to obtain a standardized second data set.

[0057] Specifically, in the environmental monitoring system of a smart city, a variety of sensors are deployed to collect environmental parameters, including temperature, humidity, PM5 concentration, etc. The temperature sensor collects data once a minute, and the data format is "timestamp, temperature"; the humidity sensor collects data once every 30 seconds, and the data format is "timestamphumidity"; the PM5 sensor collects data once every 10 minutes, and the data format is "timestamp, pm25_value". The Kalman filter algorithm is used to remove noise and outliers from heterogeneous data to obtain the first data set after preliminary processing. Then, the minimum-maximum normalization algorithm is used to convert the first data set into a unified standardized data structure, that is, the timestamps of all data are unified into the "yyyy-MM-dd HH:mm:ss" format, and the values ​​of temperature, humidity, and PM5 concentration are uniformly scaled to between 0-1, and finally the standardized second data set is obtained. For example, the original temperature data "1622246412,25" is converted to "2021-06-01 12:00:12,713", the original humidity data "1622246442 65" is converted to "2021-06-01 12:00:42,65", and the original PM5 data "1622246600,76" is converted to "2021-06-01 12:10:00,304". Through the above data cleaning and standardization processing, the effective fusion of multi-source heterogeneous environmental monitoring data is achieved, providing high-quality data support for subsequent data analysis and intelligent decision-making.

[0058] (2) Data completion: Obtain monitoring data on precipitation, evapotranspiration, and infiltration, and use random forest or support vector regression algorithms to establish a quantitative relationship model between hydrological elements and vegetation water conservation capacity. When the data of a hydrological element is missing, the data of the missing element is estimated through a quantitative relationship model based on the monitoring data of other elements to complete the data and ensure the accuracy of the water conservation capacity estimation.

[0059] Specifically, the hydrological monitoring data after data cleaning and standardization, including rainfall, runoff, evaporation, etc., were obtained, 80% of the data were randomly selected as the training set, and 20% of the data were randomly selected as the test set. The quantitative relationship model between hydrological elements and vegetation water conservation was established using the random forest algorithm. In view of the missing rainfall data in the training set, the rainfall at the missing time point was estimated based on the monitoring data of other elements such as evaporation and runoff in the same period through the constructed quantitative relationship model. The estimation results showed that the average daily rainfall was 15mm during the time period of missing data. The estimated vegetation water conservation was compared with the actual monitoring values ​​in the test set, and the mean absolute percentage error (MAPE) of the model estimation was calculated to be 2%, meeting the preset model accuracy requirements. Further analysis found that the estimation error gradually expanded with the increase of the missing time period. Therefore, according to the estimation accuracy index, the quantitative relationship model was optimized, and the time decay factor was introduced to give smaller weights to the time points farther away from the missing data, which improved the estimation accuracy of the model. The optimized model MAPE was reduced to 4%.

[0060] (3) Data fusion: Use ensemble Kalman filtering or variational assimilation technology to fuse remote sensing data, meteorological data, and sensor monitoring data of different temporal and spatial scales, dynamically update the temporal and spatial distribution information of hydrological elements and vegetation conditions, and if a data source is abnormal, it can be corrected based on the information of other data sources, thereby improving the accuracy and temporal and spatial continuity of the monitoring data.

[0061] Specifically, during the data fusion process, the weight coefficient of each data source is dynamically adjusted. When a data source is abnormal, its weight is reduced, while the weights of other reliable data sources are increased to ensure the robustness of the fusion result.

[0062] Step S102: Based on the processed historical vegetation type, area, meteorological and hydrological data, a water balance equation is used to construct a water conservation capacity estimation model and the model is trained and evaluated;

[0063] In view of the complexity and uncertainty of the vegetation water conservation process, an uncertainty analysis method was introduced. Through the Monte Carlo simulation technology, multiple random sampling of model parameters and input data was carried out, and the water conservation estimation model was run to quantitatively evaluate the impact of uncertainty on the water conservation estimation results, determine the confidence interval of the water conservation change, and provide a reference for decision-making.

[0064] Specifically, a target data set is constructed based on the data processed in step 101, 80% of the data in the target data set is used as training samples, and 20% of the data is used as test samples. After the established water conservation capacity estimation model is trained and tested using the training samples and the test samples, the model that meets the preset requirements is saved.

[0065] The complexity and uncertainty of the vegetation water conservation process must be considered when establishing a water conservation estimation model. This embodiment uses Monte Carlo simulation technology to perform multiple random samplings on the model's parameters and input data to generate multiple sets of random sample data sets. For each set of random sample data sets, the water conservation estimation model is run to obtain corresponding estimation results. Statistical analysis is performed on multiple estimation results to quantitatively evaluate the impact of uncertainty on the water conservation estimation results. Based on the uncertainty analysis results, the confidence interval of the water conservation change is determined to judge the credibility of the estimation results. The water conservation estimation results and the uncertainty analysis results are used as decision-making references to provide a quantitative basis for vegetation water conservation management.

[0066] Step S103, obtaining vegetation coverage data and hydrological element data of the monitoring area, inputting them into a water conservation capacity estimation model, and outputting a water conservation capacity estimation result;

[0067] When receiving input data containing known hydrological elements such as precipitation and evapotranspiration, the input data is input into the saved water conservation capacity estimation model to obtain the predicted value of vegetation water conservation capacity corresponding to the input data. For example, if the input precipitation is 2mm / d and the evapotranspiration is 1mm / d, the corresponding vegetation water conservation capacity is predicted to be 120t / hm 2 .

[0068] Step S104: performing abnormal warning and change trend prediction based on the water conservation capacity estimation result;

[0069] Obtain continuous vegetation coverage monitoring data and water conservation estimation results, use the autoregressive integrated moving average model for time series analysis, use the long short-term memory network for machine learning, and explore the spatiotemporal variation patterns and influencing factors of vegetation water conservation. When abnormal changes occur, analyze the causes and predict future change trends to provide early warning for watershed ecological protection.

[0070] Specifically, continuous vegetation coverage monitoring data and water conservation estimation results are obtained to construct a spatiotemporal data set. The spatiotemporal data set is preprocessed, including data cleaning, missing value processing, and outlier detection, to ensure data quality. The autoregressive integral moving average model is used to analyze the time series data and extract the change characteristics in the time dimension. The long short-term memory network is used to model the spatiotemporal data to explore the spatiotemporal change laws and influencing factors of vegetation water conservation. According to the modeling results, it is determined whether there are abnormal changes. If there are abnormal changes, the reasons are analyzed, and the future change trends are predicted by combining historical data and expert knowledge. The abnormal change information and future change trend prediction results are visualized to generate early warning reports to provide decision-making support for watershed ecological protection.

[0071] At the same time, an early warning mechanism is established. When abnormal changes in the water conservation capacity of vegetation are monitored, an early warning is automatically triggered, and corresponding ecological protection measures are taken according to the early warning level. The early warning threshold is set to 10%. When the monitoring data reaches the threshold, an early warning is automatically triggered, and ecological protection measures of different intensities are taken according to the early warning levels of yellow, orange and red, including strengthening vegetation management, artificial rainfall and emergency water source scheduling. Through the above early warning mechanism, abnormal changes in the water conservation function of vegetation can be discovered in time, early warnings can be issued and measures can be taken to ensure the ecological security of the basin.

[0072] Step S105, the vegetation coverage data, hydrological element data, and corresponding water conservation capacity estimation results, as well as abnormal warnings and change trend predictions are displayed in interactive charts;

[0073] Based on the monitoring data and analysis results, visualization technology is used to generate water conservation change charts and spatial distribution maps, and an interactive query function is set up. Users can retrieve monitoring data and analysis results within any time and space range as needed, providing a scientific basis for basin water resources management decisions. Visualization technologies include heat maps, contour maps and three-dimensional topographic maps, which are combined with the timeline to achieve dynamic display.

[0074] Based on the monitoring data and analysis results, the clustering algorithm is used to classify the water conservation capacity and obtain water conservation capacity areas of different levels; for each water conservation capacity area, an interpolation algorithm is used to generate a contour map to show the spatial distribution characteristics of the water conservation capacity; the basin terrain data is obtained, and a three-dimensional topographic map of the basin is generated using three-dimensional modeling technology. The water conservation capacity contour map is superimposed on the three-dimensional topographic map to achieve a three-dimensional visualization of the water conservation capacity; a spatiotemporal index is constructed to associate the water conservation capacity analysis results at different times with the time axis to achieve a dynamic display of the water conservation capacity changes; an interactive query interface is designed to quickly retrieve the corresponding monitoring data and analysis results according to the time range and spatial range entered by the user, and highlight them in the chart; the spatiotemporal variation characteristics of the water conservation capacity are comprehensively analyzed to identify areas where the water conservation function is degraded, and to provide early warning information for the water resources management of the basin; the water conservation capacity analysis results are correlated with other hydrological, meteorological and land use data to explore the driving factors affecting the change of water conservation capacity and provide a scientific basis for basin management decisions.

[0075] Specifically, in order to classify water conservation, the K-means clustering algorithm can be used. First, the water conservation data is standardized, and then the number of clusters is set to 5 and the number of iterations is set to 100. By calculating the Euclidean distance from each data point to the cluster center, the data point is assigned to the cluster with the nearest distance, and the cluster center is continuously updated until the clustering result is stable. After clustering, the water conservation value of each cluster is divided into five levels: extremely high, high, medium, low, and extremely low according to the average value of the water conservation value of each cluster. For each level of water conservation area, the Kriging interpolation method is used to generate contour maps to reflect the spatial distribution characteristics of water conservation. The basin DEM data is loaded in ArcGIS, and a three-dimensional topographic map of the basin is generated through a three-dimensional analysis tool. The contour map of water conservation is then superimposed on the three-dimensional topographic map to intuitively display the three-dimensional distribution of water conservation. In order to achieve a dynamic display of changes in water conservation, the spatiotemporal cube indexing method can be used to associate the water conservation analysis results at different times with the time axis. The user enters the start time and end time, as well as the spatial range of interest through the interactive query interface, and the system quickly retrieves the monitoring data and analysis results within the corresponding time and space range, and highlights them in the chart. Through the Mann-Kendall trend test and Pettitt mutation test, the significant change trend and mutation points in the water conservation time series are identified to determine the area where the water conservation function is degraded. Grey correlation analysis and principal component analysis are used to study the relationship between water conservation and factors such as precipitation, temperature, and land use, calculate the correlation and contribution rate of each factor, find out the dominant factors affecting the change of water conservation, and provide a quantitative basis for basin management decisions.

[0076] Specifically, the present embodiment provides a vegetation water conservation capacity change monitoring system and method, which processes massive heterogeneous monitoring data through data cleaning and standardization, uses random forest or support vector regression algorithm to establish a quantitative relationship model between hydrological elements and vegetation water conservation capacity, and uses ensemble Kalman filtering or variational assimilation technology to fuse multi-source data, and dynamically updates the spatiotemporal distribution information of hydrological elements and vegetation conditions. Monte Carlo simulation technology is also introduced for uncertainty analysis, and the autoregressive integral moving average model and long short-term memory network are used to mine the change law of vegetation water conservation capacity, and interactive charts and spatial distribution maps are generated through visualization technology, which can effectively improve the accuracy and spatiotemporal continuity of vegetation water conservation capacity monitoring, and provide a scientific basis for basin water resources management decision-making.

[0077] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A vegetation water conservation capacity change monitoring system, characterized in that: include: Data acquisition module, data processing module, abnormal warning module; The data acquisition module is used to acquire vegetation coverage data and hydrological element data of the monitoring area; The data processing module is used to input the vegetation coverage data and hydrological element data into a water conservation capacity estimation model and output a water conservation capacity estimation result, wherein the water conservation capacity estimation model is constructed using a water balance equation based on the historical vegetation type, area, and meteorological and hydrological data of the monitoring area; The abnormal warning module is used to perform abnormal warning and change trend prediction based on the water conservation capacity estimation result, and complete the monitoring of vegetation water conservation capacity changes in the monitoring area.

2. The vegetation water conservation capacity change monitoring system according to claim 1 is characterized in that: The data acquisition module acquires the vegetation coverage data and hydrological element data of the monitoring area, including: By adopting ensemble Kalman filtering or variational assimilation technology, remote sensing data, meteorological data and sensor monitoring data of different temporal and spatial scales are integrated to dynamically update the spatiotemporal distribution information of hydrological elements and vegetation coverage.

3. The vegetation water conservation capacity change monitoring system according to claim 1 is characterized in that: The data processing module includes a model building unit and a data analysis unit; The model building unit is used to collect and process the historical vegetation type, area, meteorological and hydrological data of the monitoring area, and then use the water balance equation to build the water conservation capacity estimation model; The data analysis unit is used to input the vegetation coverage data and hydrological element data into the water conservation capacity estimation model and output the water conservation capacity estimation result.

4. The vegetation water conservation capacity change monitoring system according to claim 3 is characterized in that: The historical vegetation type, area, meteorological and hydrological data of the monitoring area are processed including data cleaning, standardization, quality assessment, data completion and data fusion.

5. The vegetation water conservation capacity change monitoring system according to claim 3 is characterized in that: After constructing the water conservation capacity estimation model, the method further includes performing uncertainty analysis on the estimation result of the water conservation capacity estimation model, and performing the uncertainty analysis includes: Through the Monte Carlo simulation technology, multiple random samplings are performed on the parameters and input data of the water conservation capacity estimation model, and the water conservation capacity estimation model is run to quantitatively evaluate the impact of uncertainty on the water conservation capacity estimation results and determine the confidence interval of the water conservation capacity change.

6. The vegetation water conservation capacity change monitoring system according to claim 1 is characterized in that: Based on the water conservation capacity estimation results, abnormal warning and change trend prediction are performed, including: Collect continuous vegetation coverage data and hydrological element data to obtain continuous water conservation estimation results, use the autoregressive integrated moving average model for time series analysis, and use the long short-term memory network for machine learning to obtain the spatiotemporal variation patterns and influencing factors of vegetation water conservation; When the water conservation capacity estimation result shows abnormal changes, the abnormal causes and future change trends are analyzed based on the spatiotemporal variation patterns and influencing factors of the vegetation water conservation capacity, and an early warning is issued.

7. The vegetation water conservation capacity change monitoring system according to any one of claims 1 to 6, characterized in that: The system also includes a visualization display module, which is used to display the vegetation coverage data, hydrological element data, and corresponding water conservation capacity estimation results, as well as abnormal warnings and change trend predictions in interactive charts.

8. A method for monitoring changes in vegetation water conservation capacity, characterized in that: include: Obtain vegetation coverage data and hydrological element data in the monitoring area; The vegetation coverage data and hydrological element data are input into a water conservation capacity estimation model, and a water conservation capacity estimation result is output. Based on the water conservation capacity estimation result, abnormal warnings and change trend predictions are performed to complete the monitoring of changes in vegetation water conservation capacity in the monitoring area. The water conservation capacity estimation model is constructed using a water balance equation based on historical vegetation type, area, meteorological and hydrological data of the monitoring area.

Images