Lake comprehensive ecological risk assessment method and system based on multi-source data fusion

Abstract

The invention proposes a lake comprehensive ecological risk assessment method and system based on multi-source data fusion, and relates to the technical field of ecological risk assessment, and the method comprises the steps: carrying out the sampling of a preset assessment space range of a target lake, and obtaining the multi-source ecological data of the target lake; obtaining a water environment risk value according to historical water quality monitoring data in the multi-source information database; acquiring ecological water level demand data of the target lake according to the historical water level monitoring data, and acquiring a hydrological situation risk value of the target lake; based on remote sensing image data and historical survey monitoring data of the target lake in the multi-source information database, evaluating lakeside vegetation condition, wetland area, blue-green algae coverage area and benthonic animal monitoring data respectively to obtain a water ecology risk value; and performing weight distribution operation on the water environment risk value, the hydrological situation risk value and the water ecology risk value to obtain a comprehensive ecology risk assessment index corresponding to the target lake. The method is beneficial to the accuracy and systematicness of ecological risk assessment.

Description

Technical Field

[0001] This invention relates to the field of ecological risk assessment technology, and in particular to a method and system for comprehensive ecological risk assessment of lakes based on multi-source data fusion. Background Technology

[0002] Ecological risk refers to the likelihood and severity of negative impacts on the structure, function, and services of an ecosystem under the influence of natural or human activities. Accurate ecological risk assessment is a prerequisite for identifying potential risk sources, constructing a risk prevention system, and taking targeted countermeasures. As an important carrier of surface water resources, lake ecosystems are a key component of the "mountains, rivers, forests, fields, lakes, grasslands, and deserts" community of life, undertaking multiple important functions such as water supply, flood control and drought relief, water purification, and habitat maintenance. However, current assessments of lake ecological risk mainly focus on water pollutants, analyzing pollutant concentrations in lake water or sediments and assessing their potential impacts.

[0003] Chinese patent CN117689199A discloses a lake risk prevention and control method based on water exchange and ecological restoration, including: assessing water quality risk based on historical water quality data of the target lake; increasing water exchange volume in the target lake to prevent water quality risk when risk exists; assessing ecological risk of the target lake; and implementing wetland ecological restoration projects when the target lake has a certain degree of ecological risk. The assessment of ecological risk involves using the loss of shallow wetland habitat area after superimposed water exchange conditions for ecological risk assessment. However, the above scheme requires high-frequency scheduling of inflow and water level in lake risk prevention and control based on water exchange and ecological restoration, coupled with wetland engineering construction. The scheduling strategy prioritizes the scale of water exchange and construction progress over ecological water demand rhythms and habitat integrity, leading to insufficient accuracy in ecological risk assessment. Therefore, it is essential to provide a comprehensive lake ecological risk assessment method and system based on multi-source data fusion to improve the accuracy and systematic nature of ecological risk assessment. Summary of the Invention

[0004] In view of this, the present invention proposes a method and system for comprehensive ecological risk assessment of lakes based on multi-source data fusion.

[0005] This invention provides a comprehensive ecological risk assessment method for lakes based on multi-source data fusion, the method comprising: Sampling is performed on the target lake within a predetermined assessment spatial range to obtain multi-source ecological data corresponding to the target lake; A multi-source information database corresponding to the target lake is constructed based on the multi-source ecological data, and the water environment risk value corresponding to the pollutant concentration is obtained based on the historical water quality monitoring data in the multi-source information database. The ecological water level demand data of the target lake is obtained based on the historical water level monitoring data in the multi-source information database, and the hydrological situation risk value corresponding to the target lake is obtained based on the ecological water level demand data. Based on the remote sensing image data and historical survey and monitoring data of the target lake in the multi-source information database, the vegetation status of the lakeside zone, wetland area status, benthic animal status and cyanobacteria coverage area are assessed respectively to obtain the water ecological risk value corresponding to the target lake. The water environment risk value, the hydrological situation risk value, and the water ecology risk value are weighted and assigned to obtain the comprehensive ecological risk assessment index corresponding to the target lake.

[0006] Based on the above technical solutions, preferably, the sampling of the preset evaluation spatial range of the target lake specifically includes: The preset evaluation spatial range of the target lake is loaded under a unified coordinate reference system, and a spatial mask for data extraction and statistics is constructed. The spatial mask includes at least a lake body mask, a lakeside zone mask generated based on the shoreline buffer, and a wetland mask based on wetland interpretation. According to the functional zoning of the target lake, the target lake is layered and remote sensing grid sampling is defined to form a spatial sampling framework; Data is collected from the target lake based on the spatial sampling framework to obtain multi-source ecological data corresponding to the target lake.

[0007] Based on the above technical solutions, preferably, the construction of the spatial sampling framework includes: A lake mask is generated using the boundary of the target lake as a baseline, and a lakeside mask is formed by extending the shoreline outward according to a preset buffer distance. Based on the wetland interpretation results, the lake area wetland polygons are extracted as wetland masks.

[0008] More preferably, the step of obtaining the water environment risk value corresponding to the pollutant concentration based on historical water quality monitoring data in the multi-source information database specifically includes: Historical water quality monitoring data of the target lake during the assessment period are extracted from the multi-source information database, and the concentration control thresholds of the corresponding categories of pollutants are determined according to the national surface water environmental quality standards. The measured pollutant concentrations for each year are compared with the corresponding pollutant concentration control thresholds to calculate the exceedance concentration index. The risk indices of each pollutant are then weighted to obtain the water environment risk value corresponding to the pollutant concentration.

[0009] More preferably, obtaining the aquatic ecological risk value corresponding to the target lake specifically includes: The aquatic ecological risk is dynamically assessed based on the lakeside vegetation status, benthic animal status, wetland area, and cyanobacterial coverage area in the multi-source information database. Specifically, the aquatic ecological risk value is calculated with the multi-year NDVI average as the baseline for the lakeside vegetation status, the aquatic ecological risk value is calculated with the historical baseline abundance as the baseline for the benthic animal status, the aquatic ecological risk value is calculated with the historical baseline area as the baseline for the wetland area, and the aquatic ecological risk value is calculated with the historical baseline area as the baseline for the cyanobacterial coverage area.

[0010] More preferably, the step of performing principal component analysis on the water environment risk value, the hydrological situation risk value, and the water ecology risk value to obtain the comprehensive ecological risk assessment index corresponding to the target lake specifically includes: The water environment risk value, the hydrological situation risk value, and the water ecology risk value are standardized based on the maximum and minimum value method. The standardized water environment risk value, the hydrological situation risk value, and the water ecological risk value are assigned weights based on the variance contribution method to obtain the comprehensive ecological risk index corresponding to the target lake.

[0011] More preferably, the multi-source information database includes historical water level monitoring data, historical water quality monitoring data, remote sensing image data, land use data, ecological water demand data, and data on aquatic environmental functions and protection targets.

[0012] A second aspect of this application provides a comprehensive ecological risk assessment system for lakes based on multi-source data fusion. The system includes a data acquisition module, a data processing module, and a risk assessment module. The data acquisition module is used to sample the target lake within a preset assessment spatial range to obtain multi-source ecological data corresponding to the target lake; The data processing module is used to construct a multi-source information database corresponding to the target lake based on the multi-source ecological data, and to obtain the water environment risk value corresponding to the pollutant concentration based on the historical water quality monitoring data in the multi-source information database. It also obtains the ecological water level demand data of the target lake based on the historical water level monitoring data in the multi-source information database, and obtains the hydrological situation risk value corresponding to the target lake based on the ecological water level demand data. Furthermore, it assesses the lakeside vegetation status, wetland area status, benthic animal status, and cyanobacteria coverage area based on the remote sensing image data and historical survey and monitoring data of the target lake in the multi-source information database, so as to obtain the water ecological risk value corresponding to the target lake. The risk assessment module is used to perform weight allocation operations on the water environment risk value, the hydrological situation risk value, and the water ecology risk value to obtain the comprehensive ecological risk assessment index corresponding to the target lake.

[0013] A third aspect of this application provides an electronic device including a processor, a memory, a user interface, and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory.

[0014] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the steps of a method for comprehensive ecological risk assessment of lakes based on multi-source data fusion.

[0015] The lake integrated ecological risk assessment method and system based on multi-source data fusion provided by this invention has the following advantages over existing technologies: (1) By simultaneously covering the three dimensions of water environment, hydrological situation and water ecology, the one-sidedness caused by single indicators or single data sources is avoided. Remote sensing images provide continuous spatial coverage and high-frequency time series information to make up for the spatial sparsity of point monitoring, realize the fine identification and mapping of lake surface and lakeside zone, and adopt cross-validation of historical monitoring data and remote sensing data to reduce the impact of single-source data noise and outliers, improve the stability and credibility of risk identification. Algae coverage and water level time series can be used to identify sudden and seasonal risks, support over-threshold warning and trend warning, and assess hydrological situation risks based on ecological water level demand, provide quantitative basis for optimizing scheduling rules, take into account flood control, water supply and ecological goals, transform the three types of risks into standardized risk values ​​and generate a weighted comprehensive index, which facilitates horizontal comparison and vertical tracking across years, across lake areas and across management areas, thereby improving the accuracy and systematicness of ecological risk assessment.

[0016] (2) Using the national surface water environmental quality standard as the threshold, the measured values ​​of different pollutants are converted into the exceedance concentration index to achieve objective comparability across pollutants and years. The risk indices of each pollutant are weighted and summarized to form a continuous water environment risk value, which can reflect the coupling and superposition effects of multiple pollutants. Compared with the single index judgment, it is more in line with the actual water quality risk. Furthermore, based on remote sensing, the area of ​​cyanobacteria coverage is identified and compared with the multi-year average baseline, which can quickly detect the abnormal increase of algal blooms and improve the sensitivity to sudden risks. Using the multi-year average as a control, the misjudgment caused by seasonality and short-term fluctuations is effectively filtered out, and the robustness and temporal consistency of the assessment results are enhanced. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating the lake integrated ecological risk assessment method based on multi-source data fusion provided by this invention; Figure 2 A schematic diagram illustrating the execution steps of the lake integrated ecological risk assessment method based on multi-source data fusion provided by this invention; Figure 3 The annual variation charts of various ecological indicators provided for this invention; Figure 4 The following is a weighted chart of key ecological risk indicators provided for this project; Figure 5 This provides a comprehensive dynamic map of ecological risks. Figure 6 This is a schematic diagram of the structure of the integrated ecological risk assessment system for lakes provided by the present invention; Figure 7 This is a schematic diagram of the structure of the electronic device provided by the present invention.

[0019] Explanation of reference numerals in the attached diagram: 1. Integrated ecological risk assessment system for lakes; 11. Data acquisition module; 12. Data processing module; 13. Risk assessment module; 2. Electronic equipment; 21. Processor; 22. Communication bus; 23. User interface; 24. Network interface; 25. Memory. Detailed Implementation

[0020] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0021] This invention discloses a comprehensive ecological risk assessment method for lakes based on multi-source data fusion, referencing... Figure 1 The steps of this method include S1 to S5.

[0022] Step S1: Sample the preset assessment spatial range of the target lake to obtain multi-source ecological data corresponding to the target lake.

[0023] This step also includes steps S11 to S13.

[0024] Step S11: Load the preset evaluation spatial range of the target lake under a unified coordinate reference system, and construct a spatial mask for data extraction and statistics. The spatial mask includes at least a lake body mask, a lakeside zone mask generated based on the shoreline buffer, and a wetland mask based on wetland interpretation.

[0025] In this step, firstly, lake boundary data obtained from natural resources, watershed, or ecological environment departments are imported into the same projection coordinate system to ensure accurate spatial alignment of different data sources. Secondly, a lake mask is generated using the lake boundary vector as a baseline. Then, a lakeside mask is formed by extending outward along the shoreline according to a preset buffer distance, such as 100–500 meters, and non-ecological land types such as construction land are removed in conjunction with land use data. Finally, wetland polygons in the lake area are extracted as wetland masks based on wetland interpretation results, and geometric registration and topological consistency checks are performed on each mask, thereby constructing a unified spatial mask system for subsequent data extraction and spatial statistical analysis.

[0026] Step S12: According to the functional zoning of the target lake, the target lake is layered and the remote sensing grid sampling is defined to form a spatial sampling framework.

[0027] In this step, the construction of the spatial sampling framework includes generating a lake mask with the boundary of the target lake as the baseline, expanding the shoreline outward to form a lakeside mask according to a preset buffer distance, and extracting lake area wetland polygons as wetland masks based on wetland interpretation results.

[0028] Furthermore, firstly, based on the ecological functional zoning of the target lake, such as the lake body area, the lakeside zone area, and the wetland area, the principle of stratified layout is determined; within each functional zone, a spatial layout strategy combining stratification, zoning, and representativeness is adopted, and different sampling units and remote sensing grid sampling scales are set.

[0029] Lake area: Based on the lake boundary, sampling profiles are set up along the main water flow path or open water area, covering representative locations such as the lake inlet, the lake center, and the lake outlet; in the remote sensing data, a regular grid is used for continuous raster sampling to extract water quality, water color and algae distribution information.

[0030] Lakeside Zone: Divide the lake shoreline into equidistant transects, for example, one transect every 500m, and within each transect, set up sampling zones according to the gradient from the shore, for analysis of vegetation cover, NDVI index, or degree of human disturbance.

[0031] Wetland areas: Wetland areas are classified and stratified based on wetland type, and sampling points or grid units are set up according to area proportion or ecological representativeness to monitor changes in wetland area and ecological status.

[0032] At the spatial level, the geographic coordinates of all sampling units are unified to the same projected coordinate system. Data extraction templates are established by overlaying the spatial positions of sample point grids and remote sensing rasters, thereby enabling automatic positioning and consistent sampling of multi-source spatial data.

[0033] Step S13: Data collection is performed on the target lake based on the spatial sampling framework to obtain multi-source ecological data corresponding to the target lake.

[0034] In this step, a comprehensive ecological risk assessment index system is constructed. Corresponding indicators are selected from three aspects: water environment, hydrological situation, and aquatic ecology, to build the comprehensive assessment system. Optional indicators for the water environment include water pollutant concentration and cyanobacteria coverage area, which are respectively the core factors and direct manifestations of water environment deterioration. Optional indicators for the hydrological situation include water level, which is a direct reflection of the hydrological conditions. Optional indicators for the aquatic ecology include riparian vegetation status, benthic animal status, and wetland area; these three represent the primary sources of productivity in the aquatic ecosystem, key links in the material cycle, and fundamental manifestations of habitat conditions, respectively.

[0035] Furthermore, based on the functional zones, transects, and sampling point locations determined by the spatial sampling framework, multi-source data acquisition activities such as ground monitoring, sensor recording, and remote sensing data extraction are carried out.

[0036] Hydrological data collection can be carried out by setting up long-term monitoring sections in the lake area and major inlets and outlets to collect daily or hourly hydrological data such as water level and water temperature; for areas with missing data, water level estimation and correction can be carried out by combining remote sensing shoreline inversion and digital elevation model.

[0037] Water quality data collection can be carried out by collecting surface water and necessary vertical water samples at representative sampling points within the spatial sampling framework, and testing indicators such as total nitrogen (TN), total phosphorus (TP), chemical oxygen demand (COD), and chlorophyll a (Chl-a); and time series data can be generated based on the monitoring frequency.

[0038] Remote sensing image data acquisition can obtain high-resolution optical images of multiple time phases within a unified time range, such as Landsat, Sentinel-2, or GF-series, and extract indicators such as water color parameters, NDVI index, algal bloom distribution, and wetland area changes within the masked areas of lakes and shorelines.

[0039] Ecological data on lakeshore zones and wetlands can be collected through drone aerial photography, ground surveys, or satellite classification results to quantitatively acquire and interpret vegetation coverage, wetland type distribution, and area changes in lakeshore zones.

[0040] Biological monitoring data collection can be carried out by conducting ecological sample surveys of benthic animals, plankton, and vegetation communities in typical transects or functional areas to supplement biological indicators of ecosystem status.

[0041] Subsequently, the aforementioned monitoring data, remote sensing indicators, and ecological survey results were uniformly projected and coded, and imported into a multi-source information database to ensure that their spatial coordinates, timestamps, and sampling numbers were consistent, thereby achieving spatiotemporal registration and comparability analysis of the data.

[0042] Step S2: Construct a multi-source information database corresponding to the target lake based on multi-source ecological data, and obtain the water environment risk value corresponding to the pollutant concentration based on the historical water quality monitoring data in the multi-source information database.

[0043] In this step, a multi-source information database for the target lake is established by collecting historical water level monitoring data, historical water quality monitoring data, and land use data of the target lake, as well as basic information such as the ecological water level requirements of aquatic organisms, aquatic environmental functions, and protection targets of the lake. The processed data is then used to conduct an ecosystem risk assessment.

[0044] This step also includes steps S21 to S23.

[0045] Step S21: Extract historical water quality monitoring data of the target lake during the assessment period from the multi-source information database, and determine the concentration control thresholds of the corresponding categories of pollutants according to the national surface water environmental quality standards.

[0046] In this step, a water quality data table is established in a multi-source information database, including the location of monitoring sections, sampling time, monitoring indicators, and test values. Historical water quality monitoring data for the assessment period is screened by retrieving the spatial and temporal ranges corresponding to the target lake. This data must include key indicators such as total nitrogen (TN), total phosphorus (TP), chemical oxygen demand (COD), permanganate index (CODMn), dissolved oxygen (DO), and chlorophyll a (Chl-a). Indicators that have consistently remained within acceptable limits over the years are not included in the risk assessment. Outlier detection, unit standardization, and time normalization are performed on the raw monitoring data to ensure data integrity and comparability. Based on the target lake's water function zoning or environmental management objectives, its water quality control category is determined (e.g., Class III, Class IV, or Class V standard water areas). The pollutant concentration limits for the corresponding category in the "Surface Water Environmental Quality Standard" (GB3838-2002) are consulted and referenced, and the standard limits for each indicator are used as pollutant concentration control thresholds. A correspondence is established between the pollutant concentration thresholds and historical monitoring data to form a data record table.

[0047] Step S22: Compare the measured pollutant concentrations for each year with the corresponding pollutant concentration control thresholds, calculate the exceedance concentration index, and weight the risk indices of each pollutant to obtain the water environment risk value corresponding to the pollutant concentration.

[0048] In this step, based on the pollutant concentration control thresholds obtained in step S21, measured pollutant concentration data for each year are extracted, including key indicators such as total nitrogen, total phosphorus, chemical oxygen demand, permanganate index, dissolved oxygen, and chlorophyll a. For each pollutant, the measured average concentration for that year is compared with the corresponding standard limit to calculate the exceedance concentration index, which is the exceedance ratio obtained by dividing the measured concentration by the standard limit. This index reflects the degree of pollution; indicators that have consistently not exceeded the standard over the years are not included in the risk assessment. When the index is greater than 1, it indicates that the pollutant concentration exceeds the control threshold, and the higher the value, the greater the pollution risk. To ensure the comparability of results for different pollutant indicators, the exceedance concentration indices for each indicator are standardized, converting values ​​of different orders of magnitude into dimensionless risk indices. Then, based on the importance of each pollutant in the lake ecosystem and its impact on water quality, corresponding weighting coefficients are determined. By weighting and summing the standardized risk indices of each pollutant according to their weights, a comprehensive pollutant concentration risk value is obtained, characterizing the overall water quality risk level of the lake during the assessment period. Different risk levels, such as low risk, medium risk, and high risk, are classified according to the magnitude of the comprehensive risk value to reflect the pollution status and potential water environment risk of the target lake.

[0049] In this embodiment, the measured values ​​of different pollutants are converted into exceedance concentration indices using the national surface water environmental quality standards as thresholds. This eliminates dimensional differences and enables objective comparability across pollutants and years. The risk indices of each pollutant are weighted and summarized to form a continuous water environment risk value, which can reflect the coupling and superposition effects of multiple pollutants. Compared with single-indicator judgment, this is more in line with the actual water quality risk.

[0050] Step S3: Obtain the ecological water level demand data of the target lake based on the historical water level monitoring data in the multi-source information database, and obtain the corresponding hydrological situation risk value of the target lake based on the ecological water level demand data.

[0051] In this step, hydrological risk is assessed based on historical water level monitoring data of the target lake. First, the ecological water level requirements for aquatic organisms in the target lake to complete their life cycle are obtained based on historical research data. Then, the ecologically suitable water level of the target lake is determined. When the lake water level exceeds the ecologically suitable water level in a specific year, it indicates that the lake ecosystem faces hydrological risk.

[0052] Step S4: Based on the remote sensing image data and historical survey and monitoring data of the target lake in the multi-source information database, assess the vegetation status of the lakeside zone, wetland area status, benthic animal status, and cyanobacteria coverage area to obtain the corresponding aquatic ecological risk value of the target lake.

[0053] In this step, the aquatic ecological risk is dynamically assessed based on the riparian vegetation status, benthic animal status, wetland area, and cyanobacterial coverage area from a multi-source information database. Specifically, the aquatic ecological risk value is calculated with the multi-year NDVI mean as the baseline for riparian vegetation status, the baseline for benthic animal status, the baseline for wetland area, and the baseline for cyanobacterial coverage area.

[0054] Furthermore, the vegetation status of the lakeshore is assessed using remote sensing image data of the target lake, specifically using the Normalized Difference Vegetation Index (NDVI). NDVI can be extracted from remote sensing images of the target lake's shoreline, and its expression is:

[0055] In the formula, NIR represents the near-infrared band, and R represents the red light band. First, the NDVI variation of the target lake's shoreline is identified, and its multi-year average is calculated. When the NDVI in a specific year is lower than the multi-year average, it indicates that the lake ecosystem faces aquatic ecological risks due to a lack of primary productivity and a decline in water quality self-purification capacity.

[0056] Regarding benthic animal status, benthic animal abundance was calculated based on historical benthic animal survey data of the lake over many years. The study period and historical period were defined, and the benthic animal abundance in the lake area during the historical period was used as the baseline. When the abundance of a specific benthic animal is lower than the historical abundance, it indicates that the lake ecosystem is facing ecological risks due to damage to the ecosystem's material cycle.

[0057] Regarding changes in wetland area, the multi-year wetland area of ​​the target lake area was calculated using lake land use data. The study period and historical period were defined, and the average wetland area of ​​the lake area during the historical period was used as the baseline. When the wetland area in a specific year is lower than the baseline area, it indicates that the lake ecosystem is facing ecological risks related to habitat loss.

[0058] Regarding cyanobacteria coverage area, remote sensing is used to identify the area of ​​cyanobacteria coverage and compare it with multi-year average baselines. This allows for the rapid detection of abnormal increases in algal blooms, enhancing sensitivity to sudden risks. Using multi-year averages as a control effectively filters out misjudgments caused by seasonality and short-term fluctuations, enhancing the robustness and temporal consistency of the assessment results. Mapping the increase in cyanobacteria area and the exceedance concentration index to a unified risk value facilitates the setting of tiered thresholds and triggering conditions, enabling timely early warning and refined execution of measures such as source control, drainage scheduling, and dredging.

[0059] This study assesses the aquatic ecological risk posed by excessive pollutant concentrations in a target lake using historical water quality monitoring data. Regarding pollutant concentration, the first step is to determine the ecological function and protection objectives of the target lake. Then, based on the "Surface Water Environmental Quality Standard," the concentration standards for various types of pollutants in the target lake are specified. For example, secondary protection zones for centralized drinking water sources should adopt Class III water concentration standards, while general industrial water areas can adopt Class IV standards. Taking total nitrogen as an example, its concentration should not exceed 1.0 mg / L in Class III water management areas and should not exceed 1.5 mg / L in Class IV water management areas. When the pollutant concentration exceeds its corresponding standard in a specific year, it indicates that the lake ecosystem faces aquatic ecological risk due to pollutant concentration. Regarding cyanobacterial blooms, high concentrations of chlorophyll-containing algae accumulate on the water surface during blooms, exhibiting spectral characteristics similar to terrestrial vegetation: absorption valleys in the red light band and reflection peaks in the near-infrared band. Based on this principle, this patent first utilizes the NDVI index of the target lake and combines it with on-site investigation to determine a suitable NDVI threshold. This threshold allows for the identification and analysis of changes in the area of ​​cyanobacteria on the lake surface, and the calculation of its multi-year average. When the area of ​​cyanobacteria in a specific year is higher than the multi-year average, it indicates that the lake ecosystem faces a water ecological risk value brought by cyanobacteria.

[0060] Furthermore, remote sensing image data from the assessment period were loaded under a unified coordinate reference system, prioritizing multi-temporal images from the same season or peak algal bloom periods. After preprocessing the images including radiometric calibration, atmospheric correction, and geometric correction, algal bloom identification was performed using remote sensing characteristic indices such as the Facial Algae Identification Index (FAI), the Modified Normalized Difference Water Index (MNDWI), or the Normalized Difference Vegetation Index (NDVI). Validation was conducted using measured cyanobacteria samples on the water surface, and an algal bloom inversion threshold was set to distinguish algal bloom areas from non-algal bloom areas, thereby extracting the current cyanobacteria coverage area and calculating its corresponding area. Historical remote sensing data was retrieved from a multi-source information database to calculate the baseline value of the multi-year average cyanobacteria coverage area. The current cyanobacteria coverage area was compared with the multi-year average cyanobacteria area to obtain the increase in cyanobacteria area, calculated by subtracting the multi-year average area from the current area and then dividing by the multi-year average area. The water environment risk value corresponding to the cyanobacteria coverage area was then calculated based on the area increase rate. When the growth rate is less than or equal to zero, it indicates that the algal bloom has not expanded or has lessened, and a lower risk level can be assigned. When the growth rate is greater than zero, the risk index is calculated according to the magnitude of the growth rate; the larger the growth rate, the higher the risk value. Linear or hierarchical functions can be used for risk mapping. For example, a growth rate between 0 and 50% corresponds to low to medium risk, between 50% and 100% corresponds to medium to high risk, and greater than 100% corresponds to high risk.

[0061] Step S5: Assess the vegetation status of the lakeshore zone based on remote sensing image data of the target lake in the multi-source information database, so as to obtain the corresponding water ecological risk value of the target lake.

[0062] This step also includes steps S51 to S52.

[0063] Step S51: Standardize the water environment risk value, hydrological situation risk value, and water ecological risk value based on the maximum and minimum value method.

[0064] Step S52: Based on the variance contribution method, assign weights to the standardized water environment risk value, hydrological situation risk value, and water ecological risk value to obtain the comprehensive ecological risk index corresponding to the target lake.

[0065] The comprehensive ecological risk of the target lake is dynamically assessed based on its comprehensive ecological risk index. The original values ​​of each ecological risk indicator across the three aspects—water environment, hydrological situation, and aquatic ecology—are standardized to a range of 0-1 using the minimax method to eliminate the impact of dimensional differences between indicators. Secondly, the variance contribution method is used to assign weights to the standardized values ​​of each indicator. This method, based on the objective weight determination method of principal component analysis (PCA), determines the weights by analyzing the contribution of each indicator to data variation, making it more scientific and objective than scoring methods relying on expert experience. Finally, the comprehensive ecological risk index is obtained, and its multi-year average is calculated. When the index is higher than the multi-year average, it indicates that the lake ecosystem exhibits a stronger comprehensive ecological risk in that year.

[0066] In this embodiment, by simultaneously covering three dimensions—water environment, hydrological situation, and aquatic ecology—the limitations of single indicators or single data sources are avoided. Remote sensing imagery provides continuous spatial coverage and high-frequency temporal information, compensating for the spatial sparsity of point monitoring and enabling refined identification and mapping of the lake surface and lakeside zone. Furthermore, cross-validation of historical monitoring data and remote sensing data reduces the impact of noise and outliers from single-source data, improving the stability and reliability of risk identification. Algal cover and water level time series can be used to identify sudden and seasonal risks, supporting threshold-exceeding and trend-based early warnings. Simultaneously, hydrological situation risks are assessed based on ecological water level requirements, providing a quantitative basis for optimizing scheduling rules. Taking into account flood control, water supply, and ecological objectives, the three types of risks are transformed into standardized risk values ​​and weighted to generate a comprehensive index, facilitating horizontal comparisons and vertical tracking across years, lake areas, and management regions, thereby improving the accuracy and systematic nature of ecological risk assessment.

[0067] In one example, such as Figure 2 As shown, a feasible approach for comprehensive ecological risk assessment of lakes based on multi-source data fusion is presented. The target scope for ecological risk assessment is determined; in this embodiment, a specific lake is selected as the target scope. Ecological risk assessment indicators were determined. In this embodiment, assessment indicators were selected from three aspects: water environment, hydrological situation, and water ecology. Specific indicators included: total nitrogen concentration, total phosphorus concentration, water level in winter and spring, cyanobacteria coverage area, NDVI of the lakeside zone, benthic organism abundance, and wetland area. The time span was determined. In this embodiment, the time range selected was 2000-2019.

[0068] A multi-source information database for the target lake was established. The data collected in this example includes: historical water level monitoring data, historical water quality monitoring data, remote sensing imagery data, and land use data for the target lake, as well as basic information such as the ecological water requirements of aquatic organisms, aquatic environmental functions, and protection targets. The processed data was then used to conduct an ecosystem risk assessment.

[0069] The risk to the water environment quality of the target lake was assessed based on historical water quality monitoring data and dynamic data on the area of ​​cyanobacteria. Regarding pollutant concentrations, total phosphorus and total nitrogen (TPN) were selected as representative pollutants based on the actual conditions of the lake, and the national Class III water quality standard was used as the basis for ecological risk assessment. Both TPN and TNI concentrations consistently exceeded the Class III standard, reaching their highest values ​​in 2015 at 0.23 mg / L and 4.17 mg / L, respectively, indicating a significant risk to the lake's ecological environment. MK analysis showed that the trend in TPN concentration was not significant (Z=0.10, P>0.05), while TPN concentration showed a significant upward trend (Z=2.69, P<0.01), indicating that TPN concentration may further increase the risk to the lake's water environment. The hydrological situation risk was also assessed based on historical water level monitoring data of the target lake. Winter and spring are critical times for spawning and propagation of aquatic organisms in the lake, with an ecological water level requirement of 7.5 m. Exceeding this water level will negatively impact the completion of the aquatic organism's life cycle; therefore, this level was used as the hydrological situation risk threshold. Between 2000 and 2019, the lake's water level consistently exceeded the ecologically suitable level during winter and spring, with levels even exceeding 9 meters in 2007-2016 and 2018-2019. This indicates that the rising water level posed a significant ecological risk to the growth and development of aquatic plants. MK analysis results show a significant upward trend in the water level during winter and spring, with a Z-value of 2.63 (P<0.01), suggesting that the ecological risks from changes in hydrological conditions are likely to intensify.

[0070] like Figure 3As shown, the aquatic ecological risk of the target lake was assessed based on the vegetation dynamics and wetland area of ​​the lakeshore. The multi-year average NDVI of the lakeshore was used as the basis for risk assessment, with years exceeding the average being identified as high-risk years. The NDVI of the lakeshore remained consistently low, with the lowest value occurring in 2016 (0.035). Compared to its multi-year average (0.039), the NDVI of the lakeshore showed higher values ​​in 2002, 2005, 2007-2008, 2011-2015, and 2017-2019, reaching a maximum of 0.042 in 2012. MK analysis revealed no significant trend in the NDVI of the lakeshore (Z=1.79, P>0.05), indicating that despite some ecological restoration measures implemented for the lake, the aquatic ecological quality of the lakeshore has not shown significant improvement. Regarding benthic animals, the historical benthic animal abundance of the lake in 1980 was used as the baseline data, and the degree of ecological risk faced by benthic animals was determined based on the extent of their decline. From 2000 to 2008, the abundance of benthic animals in this case study was relatively high, but from 2008 to 2019, their abundance continued to decline. MK analysis results showed that the wetland area of ​​this lake had a significant downward trend, with a Z-value of -5.72 (P<0.01), indicating that the abundance of benthic animals faces the risk of further decline. Regarding wetland area, the historical average area of ​​the lake from 1990 to 1999 was 860 km². 2 As baseline data, the degree of ecological risk faced by wetland habitats was assessed based on the amount of shrinkage. From 2001 to 2010, the wetland area of ​​the subject of this case study was relatively large, but after 2011, it showed a shrinking trend, reaching its minimum in 2019, indicating that the shrinkage posed a significant risk to the lake's wetland habitat. Furthermore, MK trend analysis results showed a significant downward trend in the lake's wetland area, with a Z-value of -4.19 (P<0.01), indicating that the risk to its wetland habitat was likely to worsen. Regarding cyanobacteria, the multi-year average cyanobacterial area of ​​the lake, 506 km², was used. 2 As a risk assessment criterion, years exceeding the average were identified as high-risk years. The cyanobacteria area in this lake posed significant ecological risks in 2002, 2006-2010, 2012-2016, and 2018-2019, reaching its maximum in 2019. MK analysis results indicate a significant increase in cyanobacteria area during the study period, with a Z-value of 2.30 (P<0.05), suggesting a further expansion trend in cyanobacteria area, which may lead to a further increase in the lake's aquatic ecological risks.

[0071] like Figure 4 and Figure 5As shown, the comprehensive ecological risk of the target lake was dynamically assessed based on its comprehensive ecological risk index. In this example, the variance contribution method yielded the weights of total phosphorus concentration, total nitrogen concentration, cyanobacterial coverage area, winter and spring water level, NDVI of the lakeshore zone, benthic animal abundance, and wetland area for the comprehensive risk index: 21.39%, 23.58%, 7.58%, 9.26%, 11.33%, and 16.45%, respectively. This result indicates that the ecological risk of the lake's water environment changed most significantly between 2000 and 2019, exerting the most critical influence on its comprehensive ecological risk dynamics and should be considered the core entry point for its integrated ecosystem management. The calculated multi-year average comprehensive ecological risk index of the lake is approximately 0.40. Since 2010, the lake has consistently exhibited a high comprehensive ecological risk index, reaching a peak of 0.81 in 2015. Although it has decreased in subsequent years, it still faces relatively high ecological risks. The MK analysis results show that the comprehensive risk index exhibits a significant upward trend, with a Z value of 4.44 (P<0.01). This indicates that under the influence of multiple factors such as water environment, hydrological conditions, and water ecology, the comprehensive ecological risk of the target lake is continuously increasing, and it is urgent to carry out systematic restoration and management through targeted engineering measures and scientific strategies.

[0072] Based on the above method, this application discloses a comprehensive ecological risk assessment system for lakes based on multi-source data fusion, with reference to... Figure 6 The lake integrated ecological risk assessment system 1 includes a data acquisition module 11, a data processing module 12, and a risk assessment module 13, among which... The data acquisition module 11 is used to sample the target lake within a preset assessment spatial range to obtain multi-source ecological data corresponding to the target lake; The data processing module 12 is used to construct a multi-source information database corresponding to the target lake based on multi-source ecological data, and to obtain the water environment risk value corresponding to the pollutant concentration based on the historical water quality monitoring data in the multi-source information database. It also obtains the ecological water level demand data of the target lake based on the historical water level monitoring data in the multi-source information database, and obtains the hydrological situation risk value corresponding to the target lake based on the ecological water level demand data. Based on the remote sensing image data and historical survey and monitoring data of the target lake in the multi-source information database, it assesses the vegetation status of the lakeside zone, wetland area status, benthic animal status and cyanobacterial coverage status, respectively, in order to obtain the water ecological risk value corresponding to the target lake. The risk assessment module 13 is used to perform weight allocation operations on water environment risk value, hydrological situation risk value and water ecology risk value to obtain the comprehensive ecological risk assessment index corresponding to the target lake.

[0073] In one example, the data acquisition module 11 is used to load the preset evaluation spatial range of the target lake under a unified coordinate reference system, and construct a spatial mask for data extraction and statistics. The spatial mask includes at least a lake body mask, a lakeside zone mask generated based on the shoreline buffer, and a wetland mask based on wetland interpretation. According to the functional zoning of the target lake, the target lake is layered and remote sensing grid sampling is defined to form a spatial sampling framework. Data is collected from the target lake based on the spatial sampling framework to obtain multi-source ecological data corresponding to the target lake.

[0074] In one example, the construction of the spatial sampling framework includes: generating a lake mask with the boundary of the target lake as the baseline, expanding the shoreline outward to form a lakeside mask according to a preset buffer distance, and extracting lake area wetland polygons as wetland masks based on wetland interpretation results.

[0075] In one example, the data processing module 12 is used to extract historical water quality monitoring data of the target lake during the assessment period from a multi-source information database, determine the corresponding pollutant concentration control thresholds according to the national surface water environmental quality standards, compare the measured pollutant concentrations of each year with the corresponding pollutant concentration control thresholds, calculate the exceedance concentration index, and weight the risk indices of each pollutant to obtain the water environment risk value corresponding to the pollutant concentration.

[0076] In one example, the data processing module 12 is used to dynamically assess the water ecological risk based on the riparian vegetation status, benthic animal status, wetland area, and cyanobacterial coverage area in a multi-source information database. Specifically, the water ecological risk value is calculated with the multi-year NDVI average as the baseline for the riparian vegetation status, the water ecological risk value is calculated with the historical baseline abundance as the baseline for the benthic animal status, the water ecological risk value is calculated with the historical baseline area as the baseline for the wetland area, and the water ecological risk value is calculated with the historical baseline area as the baseline for the cyanobacterial coverage area.

[0077] In one example, the risk assessment module 13 is used to standardize the water environment risk value, hydrological situation risk value, and water ecological risk value based on the maximum-minimum method; and to assign weights to the standardized water environment risk value, hydrological situation risk value, and water ecological risk value based on the variance contribution method to obtain the comprehensive ecological risk index corresponding to the target lake.

[0078] In one example, the multi-source information database includes historical water level monitoring data, historical water quality monitoring data, remote sensing image data, land use data, ecological water demand data, and data on aquatic environmental functions and protection targets.

[0079] Please see Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 7As shown, the electronic device 2 may include: at least one processor 21, at least one network interface 24, user interface 23, memory 25, and at least one communication bus 22.

[0080] The communication bus 22 is used to enable communication between these components.

[0081] The user interface 23 may include a display screen and a camera. Optionally, the user interface 23 may also include a standard wired interface and a wireless interface.

[0082] The network interface 24 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0083] The processor 21 may include one or more processing cores. The processor 21 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 25, and by calling data stored in the memory 25. Optionally, the processor 21 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 21 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 21 and may be implemented as a separate chip.

[0084] The memory 25 may include random access memory (RAM) or read-only memory. Optionally, the memory 25 may include non-transitory computer-readable storage medium. The memory 25 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 25 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 25 may also be at least one storage device located remotely from the aforementioned processor 21. Figure 7 As shown, the memory 25, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a comprehensive ecological risk assessment method for lakes based on multi-source data fusion.

[0085] exist Figure 7 In the electronic device 2 shown, the user interface 23 is mainly used to provide an input interface for the user and to obtain the user input data; while the processor 21 can be used to call an application stored in the memory 25 for a lake integrated ecological risk assessment method based on multi-source data fusion. When executed by one or more processors, the electronic device executes one or more methods as described in the above embodiments.

[0086] A computer-readable storage medium storing instructions that, when executed by one or more processors, cause a computer to perform one or more methods as described in the embodiments above.

[0087] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0088] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0089] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the shown or discussed mutual couplings or direct couplings or communication connections may be through some service interfaces; indirect couplings or communication connections between apparatuses or units may be electrical or other forms.

[0090] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0091] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0092] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0093] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A comprehensive ecological risk assessment method for lakes based on multi-source data fusion, characterized in that, The method includes: Sampling is performed on the target lake within a predetermined assessment spatial range to obtain multi-source ecological data corresponding to the target lake; A multi-source information database corresponding to the target lake is constructed based on the multi-source ecological data, and the water environment risk value corresponding to the pollutant concentration is obtained based on the historical water quality monitoring data in the multi-source information database. The ecological water level demand data of the target lake is obtained based on the historical water level monitoring data in the multi-source information database, and the hydrological situation risk value corresponding to the target lake is obtained based on the ecological water level demand data. Based on the remote sensing image data and historical survey and monitoring data of the target lake in the multi-source information database, the vegetation status of the lakeside zone, wetland area status, benthic animal status and cyanobacteria coverage area are assessed respectively to obtain the water ecological risk value corresponding to the target lake. The water environment risk value, the hydrological situation risk value, and the water ecology risk value are weighted and assigned to obtain the comprehensive ecological risk assessment index corresponding to the target lake.

2. The lake integrated ecological risk assessment method based on multi-source data fusion as described in claim 1, characterized in that, The sampling of the preset evaluation spatial range of the target lake specifically includes: The preset evaluation spatial range of the target lake is loaded under a unified coordinate reference system, and a spatial mask for data extraction and statistics is constructed. The spatial mask includes at least a lake body mask, a lakeside zone mask generated based on the shoreline buffer, and a wetland mask based on wetland interpretation. According to the functional zoning of the target lake, the target lake is layered and remote sensing grid sampling is defined to form a spatial sampling framework; Data is collected from the target lake based on the spatial sampling framework to obtain multi-source ecological data corresponding to the target lake.

3. The lake integrated ecological risk assessment method based on multi-source data fusion as described in claim 2, characterized in that, The construction of the spatial sampling framework includes: A lake mask is generated using the boundary of the target lake as a baseline, and a lakeside mask is formed by extending the shoreline outward according to a preset buffer distance. Based on the wetland interpretation results, the lake area wetland polygons are extracted as wetland masks.

4. The lake integrated ecological risk assessment method based on multi-source data fusion as described in claim 1, characterized in that, The step of obtaining the water environment risk value corresponding to the pollutant concentration based on historical water quality monitoring data in the multi-source information database specifically includes: Historical water quality monitoring data of the target lake during the assessment period are extracted from the multi-source information database, and the concentration control thresholds of the corresponding categories of pollutants are determined according to the national surface water environmental quality standards. The measured pollutant concentrations for each year are compared with the corresponding pollutant concentration control thresholds to calculate the exceedance concentration index. The risk indices of each pollutant are then weighted to obtain the water environment risk value corresponding to the pollutant concentration.

5. The lake integrated ecological risk assessment method based on multi-source data fusion as described in claim 1, characterized in that, The acquisition of the aquatic ecological risk value corresponding to the target lake specifically includes: The aquatic ecological risk is dynamically assessed based on the lakeside vegetation status, benthic animal status, wetland area, and cyanobacterial coverage area in the multi-source information database. Specifically, the aquatic ecological risk value is calculated with the multi-year NDVI average as the baseline for the lakeside vegetation status, the aquatic ecological risk value is calculated with the historical baseline abundance as the baseline for the benthic animal status, the aquatic ecological risk value is calculated with the historical baseline area as the baseline for the wetland area, and the aquatic ecological risk value is calculated with the historical baseline area as the baseline for the cyanobacterial coverage area.

6. The lake integrated ecological risk assessment method based on multi-source data fusion as described in claim 1, characterized in that, The principal component analysis operation on the water environment risk value, the hydrological situation risk value, and the water ecology risk value to obtain the comprehensive ecological risk assessment index corresponding to the target lake specifically includes: The water environment risk value, the hydrological situation risk value, and the water ecology risk value are standardized based on the maximum and minimum value method. The standardized water environment risk value, the hydrological situation risk value, and the water ecological risk value are assigned weights based on the variance contribution method to obtain the comprehensive ecological risk index corresponding to the target lake.

7. The lake integrated ecological risk assessment method based on multi-source data fusion as described in claim 1, characterized in that, The multi-source information database includes historical water level monitoring data, historical water quality monitoring data, remote sensing image data, land use data, ecological water demand data, and data on aquatic environmental functions and protection targets.

8. A comprehensive ecological risk assessment system for lakes based on multi-source data fusion, characterized in that, The lake integrated ecological risk assessment system (1) includes a data acquisition module (11), a data processing module (12), and a risk assessment module (13), wherein, The data acquisition module (11) is used to sample the preset evaluation spatial range of the target lake and obtain multi-source ecological data corresponding to the target lake; The data processing module (12) is used to construct a multi-source information database corresponding to the target lake based on the multi-source ecological data, and to obtain the water environment risk value corresponding to the pollutant concentration based on the historical water quality monitoring data in the multi-source information database, to obtain the ecological water level demand data of the target lake based on the historical water level monitoring data in the multi-source information database, and to obtain the hydrological situation risk value corresponding to the target lake based on the ecological water level demand data, and to evaluate the lakeside vegetation status, wetland area status, benthic animal status and cyanobacteria coverage area based on the remote sensing image data and historical survey monitoring data of the target lake in the multi-source information database, so as to obtain the water ecological risk value corresponding to the target lake. The risk assessment module (13) is used to perform weight allocation operations on the water environment risk value, the hydrological situation risk value and the water ecology risk value to obtain the comprehensive ecological risk assessment index corresponding to the target lake.

9. An electronic device, characterized in that, The device includes a processor (21), a memory (25), a user interface (23), and a network interface (24). The memory (25) is used to store instructions. The user interface (23) and the network interface (24) are used to communicate with other devices. The processor (21) is used to execute the instructions stored in the memory (25) to cause the electronic device (2) to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-7.

Images