Water quality detection system and detection method for groundwater resource assessment

Abstract

The invention discloses a water quality detection system and detection method for groundwater resource assessment, and relates to the technical field of environmental monitoring, the method comprises the following steps: obtaining multi-source data of groundwater in a target area through a sensor network, and combining environmental parameters to carry out data fusion to generate a comprehensive result; performing water quality scoring based on the fused data, constructing a water quality spatial distribution diagram, and predicting a water quality change trend; and determining a pollution source according to trend data tracing, formulating a pollution control scheme in combination with multi-source data, and generating a treatment suggestion. The technical problem of insufficient water quality detection precision in existing groundwater resource evaluation is solved, and the technical effect of performing high-precision detection and comprehensive evaluation on groundwater quality data is achieved.

Description

Technical Field

[0001] The present application relates to the field of environmental monitoring technology, and in particular to a water quality detection system and detection method for groundwater resource assessment. Background Art

[0002] As groundwater resources become increasingly important in human production and life, their quality issues have attracted widespread attention. In existing technologies, groundwater quality testing often relies on traditional offline detection methods, which have problems such as complex processes, long cycles, and delayed data updates. In addition, the application of a single type of sensor is difficult to fully cover multi-dimensional water quality parameters, resulting in limited integrity and accuracy of the test results. Against the backdrop of increasingly complex environmental pollution, the identification and tracing of groundwater pollution sources face great difficulties, and traditional methods are difficult to quickly and accurately locate pollution sources. These problems have posed new challenges to the effective monitoring of groundwater quality and pollution prevention and control, and have also increased the difficulty of water resource management and protection.

[0003] At the current stage, there is a technical problem in the relevant technologies that the accuracy of water quality detection in groundwater resource assessment is insufficient. Summary of the invention

[0004] The present application solves the technical problem of insufficient water quality detection accuracy in existing groundwater resource assessment by providing a water quality detection system and detection method for groundwater resource assessment.

[0005] This application provides a water quality detection system for groundwater resource assessment, including: A multi-source data set acquisition module, the multi-source data set acquisition module is used to perform multi-source data sensing on the groundwater in the target area through a sensor network to obtain a multi-source data set of groundwater quality; a data fusion module, the data fusion module is used to introduce the environmental parameter set of the target area, fuse the groundwater quality multi-source data set with the environmental parameter set, and obtain a multi-source data fusion result; a water quality comprehensive score generation module, the water quality comprehensive score generation module is used to evaluate the groundwater quality multi-source data set based on the multi-source data fusion result to generate a water quality comprehensive score; a change trend data acquisition module, the change trend data acquisition module is used to construct a water quality spatial distribution map according to the water quality comprehensive score, predict water quality according to the water quality spatial distribution map, and obtain water quality change trend data; a governance suggestion generation module, the governance suggestion generation module is used to trace the pollution source based on the water quality change trend data, determine multiple pollution sources, and control the pollution of the groundwater in the target area according to the multiple pollution sources in combination with the groundwater quality multi-source data set to generate governance suggestions.

[0006] This application provides a water quality detection method for groundwater resource assessment, including: Through the sensor network, multi-source data sensing is performed on the groundwater in the target area to obtain a multi-source data set of groundwater quality; the environmental parameter set of the target area is introduced, and the groundwater quality multi-source data set is fused with the environmental parameter set to obtain a multi-source data fusion result; the groundwater quality multi-source data set is evaluated based on the multi-source data fusion result to generate a comprehensive water quality score; a water quality spatial distribution map is constructed according to the comprehensive water quality score, and water quality is predicted based on the water quality spatial distribution map to obtain water quality change trend data; pollution source tracing is performed based on the water quality change trend data to determine multiple pollution sources, and pollution control of groundwater in the target area is performed based on the multiple pollution sources in combination with the groundwater quality multi-source data set to generate governance recommendations.

[0007] The water quality detection system and detection method for groundwater resource assessment proposed in this application first obtains multi-source data of groundwater in the target area through a sensor network, and fuses the data in combination with environmental parameters to generate a comprehensive result; water quality is scored based on the fused data, a water quality spatial distribution map is constructed, and the trend of water quality changes is predicted; the pollution source is determined by tracing the trend data, and a pollution control plan is formulated and governance recommendations are generated in combination with multi-source data, thereby achieving the technical effect of high-precision detection and comprehensive evaluation of groundwater quality data. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0009] Figure 1 A schematic diagram of the structure of a water quality detection system for groundwater resource assessment provided in an embodiment of the present application.

[0010] Figure 2 A schematic flow chart of a water quality detection method for groundwater resource assessment provided in an embodiment of the present application.

[0011] Explanation of the reference numerals: multi-source data set acquisition module 10, data fusion module 20, water quality comprehensive score generation module 30, change trend data acquisition module 40, governance suggestion generation module 50. DETAILED DESCRIPTION

[0012] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0013] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0014] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0015] The present application embodiment provides a water quality detection system for groundwater resource assessment, such as Figure 1 As shown, the system comprises: The multi-source data set acquisition module 10 is used to perform multi-source data sensing on the groundwater in the target area through a sensor network to obtain a multi-source data set of groundwater quality. Specifically, the multi-source data set acquisition module 10 constructs a network covering the target area and carefully deploys sensors based on the geological structure, hydrological characteristics and distribution of potential pollution sources. The sensor types are diverse. Chemical sensors can detect chemical components such as heavy metal ions, pH, dissolved oxygen, nitrogen and phosphorus compounds and organic pollutants, and physical sensors can monitor physical parameters such as water temperature, water pressure, and conductivity. Each sensor operates according to a preset sampling frequency and time interval. For example, chemical sensors measure chemical components every hour, and physical sensors set different cycles according to parameter characteristics. The collected data is aggregated through wireless or wired transmission. Data from different sensors, time and location are aggregated into a multi-source data set of groundwater quality, which serves as a key basic data source for subsequent groundwater quality analysis, evaluation and management, helping to accurately grasp its quality status and dynamic change trends.

[0016] Data fusion module 20, the data fusion module 20 is used to introduce the environmental parameter set of the target area, fuse the groundwater quality multi-source data set with the environmental parameter set, and obtain the multi-source data fusion result. Specifically, the data fusion module 20 comprehensively collects the environmental parameter set of the target area, obtains the topography and soil type data with the help of the geographic information system, clarifies the land use status (distribution and proportion of industry, agriculture, commerce, residential areas and nature reserves), and collects meteorological data (rainfall, evaporation, etc.). After that, it is fused with the groundwater quality multi-source data set, first cleaning the two types of data to remove outliers and erroneous data, and then standardizing them to unify the dimensions of the two, and then establishing a data association model based on the association method of spatial position and time series, matching analysis and fusion calculation of the same or similar position data and data with time association, and finally obtaining the multi-source data fusion result, which integrates water quality and environmental information, can more accurately reflect the status of groundwater resources, and lay a solid foundation for subsequent evaluation, management and protection strategy formulation.

[0017] In a possible implementation, the data fusion module 20 further includes: a sub-region generation unit, which is used to divide the target area based on the geographic information of the target area to generate multiple sub-regions. Specifically, the sub-region generation unit performs the division operation based on the geographic information of the target area. The geographic information includes the topographic and geomorphic features of the target area, such as the extension direction of the mountains, the distribution veins of the rivers, the distribution range of the plains and hills, etc., as well as accurate longitude and latitude information and administrative division details. By comprehensively using these geographic information elements, with the help of specific geographic information analysis algorithms or following predetermined scientific division criteria, the target area is accurately divided into multiple sub-regions. For example, according to the watershed or basin boundaries of the terrain, or according to the refined units of the administrative area, such as the boundary range of towns and streets, each sub-region has relatively independent and complete characteristics within the scope of geographic spatial structure and administrative management, thereby building a solid infrastructure for the precise collection and in-depth analysis of subsequent environmental data.

[0018] An environmental data acquisition unit, the environmental data acquisition unit is used to traverse the multiple sub-areas to perform multi-dimensional environmental sensing and obtain multiple environmental data. Specifically, after the sub-area division is completed, the environmental data acquisition unit starts the multi-dimensional environmental sensing operation for each sub-area. In the dimension of meteorological data collection, a professional meteorological sensor network covering each sub-area is constructed to accurately measure rainfall data, which is of key significance for analyzing the dynamics of groundwater recharge sources and water volume change trends; temperature data can reflect the thermal environment state of the region, and has a close intrinsic relationship with the evaporation process of groundwater, biochemical reaction rates, etc.; humidity information can assist in evaluating the water vapor interaction mechanism between the atmosphere and groundwater. For land use data, satellite remote sensing image analysis technology is used in combination with detailed on-site surveys to accurately determine the proportion of agricultural land, industrial land and residential areas in each sub-area. In terms of geological data acquisition, systematic geological exploration techniques are used, such as drilling and sampling to analyze rock properties, to gain an in-depth understanding of the types, composition, structural characteristics and permeability characteristics of underground rocks, and to determine soil types, clarify key properties such as soil texture, porosity, and pH. These geological elements have a profound impact on groundwater runoff paths, storage characteristics, and the formation and evolution mechanism of water quality. In addition, for pollution source data, professional monitoring equipment is deployed in industrial areas to monitor industrial wastewater discharge in real time, and systematic agricultural fertilizer application statistics are carried out in agricultural areas. With the help of the above-mentioned multi-dimensional and multi-technical collaborative sensing and monitoring operations, massive amounts of environmental data are obtained, which will gradually build a complete environmental data system for the target area.

[0019] An environmental parameter set acquisition unit, the environmental parameter set acquisition unit is used to perform data spatiotemporal matching between the multiple environmental data and the multiple sub-areas, and normalize the multiple environmental data according to the matching results to obtain the environmental parameter set. Specifically, the environmental parameter set acquisition unit first performs a data spatiotemporal matching operation. Strictly ensure that the sampling time of the environmental data collected in each sub-area accurately corresponds to the spatial identification of the sub-area, and eliminate the spatiotemporal dislocation of the data. For example, the rainfall data collected at a specific time point in a sub-area must be accurately associated with the sub-area to prevent analysis deviations caused by data mismatch. After completing the data spatiotemporal matching, the multi-source environmental data is normalized according to the matching results. In view of the fact that the collected environmental data comes from a wide range of sources, has a variety of types, and has significant differences in magnitude, the normalization process aims to unify these data to a standardized scale. For example, the rainfall data is normalized and converted according to a unified time period (such as monthly or annual rainfall) and magnitude range; the percentage values ​​in the land use data are standardized and mapped so that they fall into the standard range of 0 to 1 or other predetermined standard ranges; the lithology and soil types in the geological data are classified and coded, and the emissions and fertilizers in the pollution source data are converted and adjusted according to the standards of unit area or unit time. Through the above normalization process, a large number of complex and disordered environmental data are organized into a consistent and comparable set of environmental parameters, providing a standardized and reliable data resource foundation for the subsequent fusion analysis with multi-source groundwater quality data sets and a more in-depth comprehensive assessment of water resources.

[0020] In a possible implementation, the data fusion module further includes: a data spatiotemporal correlation coefficient generation unit, which is used to perform spatiotemporal correlation between the groundwater quality multi-source data set and the environmental parameter set to generate a data spatiotemporal correlation coefficient. Specifically, the data spatiotemporal correlation coefficient generation unit starts the data processing flow and implements integrated analysis operations on the groundwater quality multi-source data set and the environmental parameter set. For the groundwater quality multi-source data set, the sampling time details of each data point are accurately analyzed to the specific time scales such as year, month, day, hour, minute, and second, and the sampling points are accurately located by relying on the geographic coordinate system or specific area identification code; the environmental parameter set also determines the spatiotemporal elements corresponding to each data according to the same standard. Subsequently, professional data matching algorithms and technical specifications are enabled to verify the consistency of the two sets of data in the spatiotemporal dimensions one by one. For example, the groundwater quality data (ammonia nitrogen concentration in water 0.5 mg / L) and environmental data (rainfall 10 mm on the day) collected at specific spatiotemporal coordinates (such as 10:00 a.m. on May 10, 2023, longitude 110°, latitude 30°) are accurately correlated and matched. After all data spatiotemporal matching procedures are completed, mathematical models and statistical analysis methods are used to quantify the degree of correlation, and then generate the data spatiotemporal correlation coefficient. This coefficient accurately quantifies the degree of close correlation between groundwater quality data and environmental parameters under specific spatiotemporal conditions. For example, a coefficient of 0.8 indicates that the two have a strong correlation in this spatiotemporal context, indicating that there may be a significant causal relationship or mutual influence relationship, laying a key quantitative foundation for subsequent fusion calculations.

[0021] The log analysis unit is used to retrieve the historical environment-water quality data record log, analyze it in combination with the historical environment-water quality data record log using the Delphi method, and construct a causal model. Specifically, the log analysis unit extracts the historical environment-water quality data record log from the database, which records in detail the multivariate environmental data (covering meteorological data, land use data, pollution source data, etc.) and corresponding groundwater quality data of the target area in different periods of the past. Then the Delphi method is used to deeply analyze the historical data. The Delphi method uses multiple rounds of expert opinion consultation and feedback mechanisms to widely gather professional knowledge and practical experience in multiple fields such as environmental science, hydrogeology, and water quality analysis. In the first round of consultation, questionnaires on the intrinsic relationship of historical environment-water quality data are distributed to experts in various fields. Experts make preliminary judgments and analyses on the causal relationship of the data based on their professional knowledge, such as exploring the impact mechanism of rainfall changes on groundwater levels and dissolved oxygen concentrations in water, and analyzing the relationship between historical fluctuations in industrial wastewater discharge and the long-term evolution of heavy metal concentrations in groundwater. After completing the collection, collation and induction of expert opinions, a preliminary causal hypothesis framework is constructed. In subsequent rounds, the hypotheses will be fed back to the experts, who will interact with other experts based on the new information, conduct in-depth analysis and make fine corrections, and finally build a scientific and reasonable causal model that is widely recognized by the profession. The causal model is presented in the form of mathematical expressions, logical relationship diagrams or structured equations, such as clarifying the functional relationship between rainfall and dissolved oxygen concentration (dissolved oxygen concentration = f(rainfall)) and the quantitative or qualitative correlation pattern between industrial wastewater discharge and heavy metal concentration in groundwater, etc., providing a solid theoretical framework support for subsequent precise calculations.

[0022] A causal model calculation unit, the causal model calculation unit is used to synchronize the groundwater quality multi-source data set and the environmental parameter set to the causal model for calculation according to the data spatiotemporal correlation coefficient, and obtain a causal fusion association list. Specifically, after obtaining the data spatiotemporal correlation coefficient, the causal model calculation unit synchronously inputs the groundwater quality multi-source data set and the environmental parameter set into the constructed causal model according to the data spatiotemporal correspondence. For the groundwater quality data (such as the concentration of specific pollutants in the water) and the corresponding environmental data (such as the surrounding land use type, recent meteorological data, etc.) at a specific sampling time and point, the weight distribution and association mode in the causal model are determined according to the data spatiotemporal correlation coefficient. Subsequently, the calculation process is carried out in accordance with the logical relationship and mathematical operation rules preset by the causal model. For example, if the causal model sets a specific functional relationship between rainfall and dissolved oxygen concentration, after inputting the rainfall data and related water quality data at the corresponding time and point, the correlation degree and potential change trend of dissolved oxygen concentration and other factors under this condition are derived according to the model calculation rules. By calculating and analyzing all data points in turn, a causal fusion association list is generated. This list records in detail the fusion calculation results of groundwater quality data and environmental parameters under the causal model framework, covering the degree of mutual influence between various factors, contribution ratio and changing relationship under different time and space conditions, etc., providing accurate data support for the final parameter set fusion.

[0023] The parameter set fusion unit is used to fuse the groundwater quality multi-source data set with the environmental parameter set according to the causal fusion association list to obtain the multi-source data fusion result. Specifically, the parameter set fusion unit promotes the fusion of the groundwater quality multi-source data set and the environmental parameter set according to the causal fusion association list. The causal fusion association list clearly defines the fusion strategy and weight ratio of the two sets of data under the causal relationship framework. For example, if the list shows that the weight of the industrial wastewater discharge in a specific area on the heavy metal concentration in the groundwater is 0.6, and the weight of the soil type on the heavy metal adsorption is 0.4, then when the heavy metal concentration data in the area is fused, the heavy metal concentration monitoring value in the groundwater quality multi-source data, the industrial wastewater discharge data in the environmental parameter set and the soil type data are comprehensively considered according to this weight ratio for precise calculation. By following similar fusion processing logic for all data, the role of each factor in the causal relationship is fully considered, the groundwater quality multi-source data set and the environmental parameter set are organically integrated, data redundancy and contradiction are eliminated, and data complementarity and synergy are strengthened, and finally the multi-source data fusion result is obtained. The fusion result integrates multi-dimensional information of groundwater quality data and environmental data, and can reflect the true status of groundwater resources in the target area more comprehensively, deeply and accurately, laying a solid foundation for high-quality data for subsequent comprehensive water quality evaluation, change trend prediction and pollution control.

[0024] A water quality comprehensive score generation module 30 is used to evaluate the groundwater quality multi-source data set based on the multi-source data fusion result to generate a water quality comprehensive score. Specifically, the water quality comprehensive score generation module 30 parses and mines the multi-source data fusion result, which covers various water quality index data and related environmental factor data of the groundwater quality multi-source data set, including chemical content such as heavy metals, organic pollutants, nutrient concentrations, physical properties such as water temperature, water pressure, conductivity, etc., as well as environmental parameters such as geology, meteorology, and land use. According to the evaluation index system constructed based on experimental data, environmental science theory, and water quality standards and regulations, different weight coefficients are determined by comprehensively considering the impact of indicators on human health, ecological environment, and their importance in the groundwater resource system. For example, heavy metals are given high weights due to their high toxicity and difficulty in degradation, while water temperature is given a lower weight. Mathematical model algorithms such as weighted summation are used to compare the actual values ​​of water quality indicators with the standard values ​​and combine them for comprehensive calculation based on weights. That is, the comprehensive water quality score = ∑ (actual value of each water quality indicator / standard value) × weight coefficient. After precise calculation and processing, a comprehensive score is generated that intuitively reflects the groundwater quality status in the target area, providing key basis and data support for water quality management decisions, pollution control planning, and resource protection strategy formulation.

[0025] The change trend data acquisition module 40 is used to construct a water quality spatial distribution map according to the water quality comprehensive score, perform water quality prediction according to the water quality spatial distribution map, and obtain water quality change trend data. Specifically, the change trend data acquisition module 40 is based on the water quality comprehensive score, uses geographic information system technology in combination with the geographic coordinates of the monitoring points, and sets visual identifiers such as color gradients or symbol changes according to different water quality comprehensive score ranges to construct a water quality spatial distribution map that can intuitively present the spatial distribution differences of the water quality comprehensive score of the target area. On this basis, water quality prediction work is carried out, comprehensively exploring the medium- and short-term change patterns of historical water quality data and environmental parameter sets and their correlation with water quality data, using advanced prediction models and algorithms such as time series analysis models, multivariate linear regression models and neural network models, and training with a large amount of historical data to enable the model to learn the complex relationship between water quality changes and influencing factors. The prediction results are integrated and analyzed with the water quality spatial distribution map to determine the direction, amplitude and spatial diffusion trend of the comprehensive water quality scores in different regions in the future, and form comprehensive, detailed and forward-looking water quality change trend data, which provides important decision-making basis for groundwater resource planning, pollution early warning and prevention, and ecological environmental protection.

[0026] In a possible implementation, the change trend data acquisition module 40 further includes: the scoring and identification unit carries out scoring and identification operations for each sampling point in multiple sub-areas based on the comprehensive water quality scoring data. It first accurately extracts the comprehensive water quality scoring information associated with each sampling point, which has been obtained through complex and rigorous data processing and analysis processes in the early stage. Subsequently, for each sampling point, its corresponding comprehensive water quality score is clearly recorded and marked in strict accordance with the established identification rules and data formats, thereby successfully obtaining multiple regional water quality scores. For example, in a specific sub-area, there are several sampling points, such as sampling point A with a comprehensive water quality score of 75 points, sampling point B with 60 points, etc. These accurately identified scoring data provide indispensable basic data support for the subsequent further construction of a water quality spatial distribution model, and lay the foundation for accurately presenting the water quality status of the target area.

[0027] A coverage calculation unit, the coverage calculation unit is used to perform coverage calculation according to the multiple sampling points based on the multiple regional water quality scores, and determine the scores of multiple unsampled points. Specifically, after receiving the multiple regional water quality scores and the corresponding sampling point information, the coverage calculation unit estimates the scores of the unsampled points. After receiving the multiple regional water quality scores and the corresponding sampling point information generated by the scoring identification unit, the coverage calculation unit immediately starts the estimation program for the scores of the unsampled points. In view of the fact that in the actual water quality monitoring scenario, due to various factors such as manpower, material resources and time, it is impossible to implement sampling and detection on all points in the target area, so it is necessary to use the existing sampling point data to reasonably infer the comprehensive water quality score of the unsampled points. The unit adopts a specific spatial interpolation algorithm, such as a mathematical model based on distance weighted average. Specifically, for each unsampled point, the weight coefficient of different sampling points is determined according to its spatial distance relationship with the surrounding known sampling points, and the sampling points with closer distance have a greater weight in the calculation. For example, for a certain unsampled point P, there are sampling points Q, R, and S around it. If the distance between sampling point Q and unsampled point P is the shortest, it is given a higher weight value in the calculation, such as 0.4; the distance between sampling point R is moderate, and the weight is set to 0.35; the distance between sampling point S and the sampling point S is relatively far, and the weight is 0.25. The estimated score of the unsampled point P is determined by weighted summing the regional water quality score of each sampling point and its corresponding weight coefficient. By analogy, the above calculation process is performed one by one for all unsampled points in the target area, and finally the scores of multiple unsampled points are determined, which effectively makes up for the data loss in the blank sampling area and greatly enriches the data resources used to construct the water quality spatial distribution map.

[0028] A water quality labeling unit, which is used to map the multiple regional water quality scores and the multiple unsampled point scores to the two-dimensional planes of the multiple sub-regions for water quality labeling, and obtain multiple water quality label distribution data. Specifically, after obtaining the multiple regional water quality scores and the multiple unsampled point scores determined by the coverage calculation unit, the water quality labeling unit proceeds to map these score data to the two-dimensional planes of the multiple sub-regions to implement the water quality labeling operation. For each sub-region, its precise geographical boundary range is used as a limiting framework, and the water quality score information of the sampling points and unsampled points contained therein is intuitively presented in a specific labeling form with a clear expressive function. For example, for sampling points or unsampled areas with high regional water quality scores (such as 80-100 points), specific blue circular marks are selected on the two-dimensional plane to represent them, and the subtle differences in the scores are further reflected by changes in the size or color depth of the marks, that is, the higher the score, the larger the size of the blue circular mark or the darker the color; for areas with medium scores (such as 40-79 points), yellow triangle marks are used; and for areas with low scores (such as 0-39 points), red square marks are used. Through this intuitive and standardized marking method, the water quality score data is successfully converted into visual water quality label information, and then multiple water quality label distribution data are obtained. These data not only fully contain the detailed information of the water quality score of each point, but also clearly show the spatial distribution characteristics and differences of water quality on the two-dimensional plane in the form of markings, providing a data material basis with highly intuitive visual effects for the subsequent visualization processing link, so that the spatial distribution pattern of water quality conditions can be presented to relevant researchers and decision makers at a glance.

[0029] A visualization processing unit, the visualization processing unit is used to visualize the multiple water quality label distribution data and construct the water quality spatial distribution map. Specifically, after receiving the multiple water quality label distribution data generated by the water quality labeling unit, the visualization processing unit immediately uses professional geographic information system (GIS) software or advanced data visualization tools to carry out visualization processing. First, the two-dimensional plane maps of multiple sub-areas are accurately imported as the basic base map framework, and then various types of marks are accurately drawn on the base map based on the marking information in the water quality label distribution data and its corresponding precise geographical location information. For example, the blue circle, yellow triangle and red square marks representing different water quality scores are placed strictly according to the geographical location coordinates of the sampling point or unsampled point to which they belong. Then, a series of refined visualization adjustment operations are carried out for the entire map, including key steps such as color adjustment, scale setting and legend addition. In terms of color adjustment, we carefully set appropriate color gradient effects to ensure that the transition from the blue area to the red area is natural and smooth with clear semantic logic, which can intuitively reflect the continuous change process of water quality from good to bad; in the scale setting stage, according to the actual size of the target area and the difference in display needs, we scientifically determine the appropriate scale value to ensure that the water quality distribution can be accurately and clearly presented in different display scenarios (whether it is an overall overview of the macro area or an in-depth view of local details); finally, we add detailed and standardized legends to clearly explain the specific water quality score range and level corresponding to different marking colors and shapes, so that users can quickly and accurately interpret the water quality information contained in the map. Through the above set of rigorous and professional visualization processing steps, we finally successfully constructed a water quality spatial distribution map that can comprehensively, intuitively and vividly present the spatial distribution of groundwater quality in the target area. As a key result display form in the entire water quality monitoring and analysis system, this map provides an extremely important and intuitive visual basis for relevant decision-making in many fields such as water resources management, environmental protection, and pollution control. It can effectively help decision makers quickly and accurately grasp the changes in water quality trends in the entire region, and then formulate more scientific, reasonable and targeted management and governance strategies and plans.

[0030] In a possible implementation, the change trend data acquisition module 40 further includes: a water quality evaluation point determination unit, which is used to traverse the multiple sub-areas based on the multiple water quality label distribution data to select points and determine multiple water quality evaluation points. Specifically, the water quality evaluation point determination unit starts the point selection process in multiple sub-areas based on multiple water quality label distribution data. The water quality label distribution data contains rich water quality spatial distribution information, including water quality scoring conditions in different areas and corresponding geographical coordinates. The unit first conducts an in-depth analysis of these data, fully considering various factors such as the geographical characteristics, land use types, water supply conditions, and existing water quality monitoring data distribution of each sub-area. Then, based on a specific algorithm or established selection criteria, multiple key points are carefully selected in each sub-area as water quality evaluation points. For example, in sub-areas close to industrial pollution sources, key points such as water flow intersections downstream of sewage outlets will be selected; in areas with frequent agricultural activities, priority will be given to points located at the intersection of farmland irrigation canals and groundwater runoff and around concentrated fertilization areas. Through this comprehensive and targeted selection method, multiple representative and key water quality evaluation points will be identified. These points will serve as core sites for collecting historical water quality score time series data, laying the foundation for subsequent in-depth analysis of water quality change patterns.

[0031] A serialization processing unit, the serialization processing unit is used to perform serialization processing of data according to the scoring time sequence through the multiple water quality evaluation points to generate a water quality score time series. Specifically, after obtaining multiple water quality evaluation points, the serialization processing unit carries out serialization processing of data according to the scoring time sequence information recorded by these points. For each water quality evaluation point, the water quality comprehensive score data measured at different time points constitutes a time series. The unit first organizes and cleans these time series data to remove possible abnormal values ​​or erroneous data, which may be caused by sensor failure, data recording errors or special short-term interference events. Then, the valid scoring data of each point is strictly sorted in chronological order, and the scattered, time-recorded scoring data is converted into an ordered, continuous sequence form. For example, for a certain water quality evaluation point, its monthly comprehensive water quality scores in the past year are arranged in sequence to form a sequence such as [80,75,78,82,…]. By executing the same processing flow for all selected water quality evaluation points, a water quality score time series is finally generated. This series of data can intuitively reflect the dynamic changes in the water quality score of each point over time, providing a structured data basis for further exploring the inherent laws and trends of water quality changes.

[0032] A score change correlation coefficient generation unit is used to perform correlation learning based on the water quality score time series to generate a score change correlation coefficient. Specifically, the score change correlation coefficient generation unit uses the generated water quality score time series as the core data input to start the correlation learning process. This unit adopts advanced time series analysis technology and machine learning algorithms to deeply explore the long-term dependencies of score changes. First, the water quality score time series is preprocessed, including data standardization, stationarity test and other operations. Data standardization enables score data of different magnitudes and ranges to be compared and analyzed on the same scale; stationarity test ensures that the statistical characteristics of the data do not change significantly over time, so that subsequent models can accurately capture the laws in the data. Then, the time series data is modeled and trained using algorithms such as the autoregressive moving average (ARMA) model and the long short-term memory network (LSTM). These models can learn the relationship between water quality scores at different time lags, that is, how past scores affect current and future score changes. For example, through training, it is found that the water quality scores of a certain water quality evaluation point in the previous three months have a significant linear or nonlinear impact on the scores of the current month. After training and optimization with a large amount of data, the model finally generates score change correlation coefficients. These coefficients quantify the strength and direction of the correlation of water quality scores in time series, providing key model parameter basis for accurately predicting water quality change trends.

[0033] A distribution prediction unit, the distribution prediction unit is used to perform distribution prediction on the water quality spatial distribution map according to the water quality score time series based on the score change correlation coefficient, and generate multiple water quality distribution prediction data. Specifically, the distribution prediction unit carries out distribution prediction work on the water quality spatial distribution map based on the score change correlation coefficient and in combination with the water quality score time series. First, the future water quality score of each water quality evaluation point is predicted using the time series correlation law reflected by the score change correlation coefficient. For example, if the score change correlation coefficient indicates that the water quality score of a certain point has a certain seasonal periodic change and has a strong linear relationship with the score of the previous few months, then according to the current and historical score data, the predicted score of the point in the next few months or years is calculated by the established prediction model. Then, these predicted score data are mapped back to the corresponding sub-region position, and the water quality spatial distribution changes of the entire target area are inferred and simulated based on the existing water quality spatial distribution pattern and geographic information. For example, if the water quality evaluation point in a sub-region near a river predicts that the water quality score will decrease, combined with the water flow direction and diffusion model of the region, it is inferred that the water quality of the surrounding area may also be affected and show a similar downward trend. By comprehensively analyzing and spatially interpolating the predicted scores of all water quality evaluation points, multiple water quality distribution prediction data are finally generated. These data not only include the predicted values ​​of the future water quality scores of each point, but also show the dynamic change prediction results of the spatial distribution of water quality in the entire target area, providing forward-looking information support for the early formulation of water resources management and pollution prevention and control strategies.

[0034] A trend analysis unit, the trend analysis unit is used to combine the multiple water quality distribution prediction data with the score change correlation coefficient to perform trend analysis and construct the water quality change trend data. Specifically, the trend analysis unit combines multiple water quality distribution prediction data with the score change correlation coefficient to carry out in-depth trend analysis. First, the water quality distribution prediction data of each water quality evaluation point is analyzed in detail to observe the change trajectory of its score value over time. According to the pre-set trend judgment standard, that is, the upward trend indicates that the water quality score value is gradually improving, and the downward trend indicates that the water quality score value is gradually deteriorating, the water quality change trend type of each point is determined. For example, if the predicted water quality score of a certain point shows a continuous upward trend in the next few years, it is determined that the point is in an upward trend of water quality improvement; conversely, if the score continues to decline, it is in a downward trend of water quality deterioration. Then, combined with the inherent laws and influencing factors of the score change revealed by the score change correlation coefficient, the causes of trend formation and possible driving mechanisms are further analyzed. For example, if the score change correlation coefficient indicates that the water quality score of a certain point is closely related to rainfall and agricultural activities, and the forecast data shows that the water quality score will show an upward trend if the rainfall decreases in the future and agricultural non-point source pollution is effectively controlled, then it can be inferred that the reduction in rainfall has reduced the pollution caused by rainwater erosion, and the control of agricultural non-point source pollution has reduced the input of pollutants, which is the main reason for the improvement in water quality. By summarizing and integrating the trend analysis results of all water quality evaluation points, water quality change trend data that comprehensively reflects the trend of water quality changes in the target area are constructed. These data provide a scientific basis for sustainable utilization planning of water resources, optimization and adjustment of pollution control plans, and ecological and environmental protection decision-making, which helps relevant departments to take effective measures in a timely manner to respond to the challenges of water quality changes and ensure the quality of groundwater resources and the health and stability of the ecosystem.

[0035] A control suggestion generation module 50 is used to trace the pollution source based on the water quality change trend data, determine multiple pollution sources, control the pollution of groundwater in the target area according to the multiple pollution sources in combination with the groundwater quality multi-source data set, and generate control suggestions. Specifically, the governance suggestion generation module 50 carries out its work with water quality trend data as the core. It first deeply analyzes the data to locate the abnormal water quality areas and time periods, and uses water quality fingerprint recognition technology to determine the type of pollution source based on the results of chemical substance content measurement in the groundwater quality multi-source data set and the pollution source water quality fingerprint library. At the same time, with the help of hydrogeological models, the possible pollution source locations are traced back according to the pollution diffusion direction and speed. After determining multiple pollution sources, it formulates pollution control strategies and generates governance suggestions in combination with the groundwater quality multi-source data set. For industrial pollution sources, it proposes measures such as strengthening wastewater treatment supervision, upgrading processes, and anti-seepage treatment. For agricultural pollution sources, it advocates the application of ecological agricultural technology, rational use of fertilizers and pesticides, and setting up buffer zones. For domestic pollution sources, it emphasizes strengthening the maintenance and updating of sewage pipe networks, the transformation of landfills, and leachate monitoring. In this way, comprehensive and targeted governance suggestions are generated to help the target area to control groundwater pollution, maintain ecological balance, and maintain human health.

[0036] In a possible implementation, the governance suggestion generation module 50 further includes: a water quality deterioration area determination unit, which is used to perform a decline analysis based on the water quality change trend data, trace the source and locate the area according to the decline trend, and determine the water quality deterioration area. Specifically, the water quality deterioration area determination unit first receives the water quality change trend data, which records in detail the dynamic changes in the water quality score of the target area at different time points and spatial locations. The unit starts the decline analysis program to comprehensively sort out and deeply mine the data. By setting specific thresholds or using trend analysis algorithms, the parts showing a downward trend can be accurately identified. For example, if the water quality score of a certain area continues to decrease over multiple consecutive monitoring periods, and the decrease exceeds the preset standard, it will be marked as a suspected area with a declining water quality trend. Subsequently, the traceability and positioning work is carried out based on these downward trend information. This process takes into account a variety of factors, including geographical features in the region, such as topography, river direction, etc., because these factors will affect the migration path of pollutants; land use type, industrial land may have specific types of pollutant emissions, agricultural land may become a source of pollution due to the use of pesticides and fertilizers; and existing environmental monitoring data, such as whether there are known pollution emission points or abnormal environmental indicators nearby. By cross-checking and analyzing this information with the water quality decline trend data, we can finally determine the area of ​​water quality deterioration and clarify the specific geographical scope where pollution problems are more prominent and water quality continues to deteriorate, laying the foundation for subsequent accurate tracking of pollution diffusion paths.

[0037] A pollution diffusion path determination unit is used to track pollution based on the score change correlation coefficient in combination with the water quality deterioration area, and determine multiple pollution diffusion paths. Specifically, the pollution diffusion path determination unit uses the score change correlation coefficient as an important reference basis and carries out pollution tracking operations in combination with the determined water quality deterioration area. The score change correlation coefficient reflects the inherent correlation and change law of water quality scores in the time series, which contains potential information about the spread and evolution of pollution. For water quality deterioration areas, the law revealed by the coefficient is used to analyze the possible diffusion direction and speed of pollutants. For example, if the score change correlation coefficient shows that the water quality deterioration in a certain area has a time lag and numerical correlation relationship with the surrounding areas, then the possibility of pollutants spreading from the area to the surrounding areas can be inferred. By constructing a mathematical model or using the spatial analysis function of a geographic information system (GIS), the migration process of pollutants in groundwater under the influence of water flow, geological structure and other environmental factors is simulated. Taking into account the flow rate and direction of groundwater, the permeability of aquifers, and the adsorption and desorption characteristics of different regions, multiple pollution diffusion paths are gradually determined. These paths depict the propagation trajectories of pollutants from areas with deteriorating water quality in different time and space dimensions, clearly showing the possible scope of pollution and the main direction of diffusion, and providing key line information for constructing a water pollution diffusion path map.

[0038] A water pollution diffusion path map construction unit, the water pollution diffusion path map construction unit is used to assign weights to the multiple pollution diffusion paths, determine multiple weight coefficients, and construct a water pollution diffusion path map based on the multiple pollution diffusion paths and the multiple weight coefficients. Specifically, after obtaining multiple pollution diffusion paths, the water pollution diffusion path map construction unit proceeds to perform weight assignment to determine multiple weight coefficients, and these weight coefficients are used to represent the pollution diffusion intensity. For each pollution diffusion path, the relative intensity of pollution diffusion is evaluated according to factors such as its corresponding regional characteristics, geological conditions, and water flow velocity. For example, in an area with a fast water flow velocity, loose geological structure, and no obvious adsorbent substances in the surrounding area, the weight coefficient of the pollution diffusion path is relatively high, indicating that the pollutant has a strong diffusion ability on this path and may spread more widely; on the contrary, in an area with slow water flow, stable geological conditions, and a large amount of adsorbent substances, the weight coefficient is low. After determining the weight coefficients, multiple pollution diffusion paths are associated with these weight coefficients. A water pollution diffusion path map is constructed by representing pollution diffusion paths with different weight coefficients with different line widths, colors, or symbols on a geographic information system (GIS) platform. This map not only intuitively shows the path of pollution diffusion, but also reflects the intensity differences of pollution diffusion through visual elements such as line width and color reflected by the weight coefficient, allowing decision makers and researchers to understand the overall picture of pollution diffusion in the target area at a glance, providing a powerful visualization tool for formulating targeted pollution prevention and control and governance strategies.

[0039] A traversal matching unit, the traversal matching unit is used to traverse and match the geographic information of the target area based on the water pollution diffusion path map to determine the multiple pollution sources. Specifically, the traversal matching unit performs a comprehensive traversal and matching work on the geographic information of the target area based on the constructed water pollution diffusion path map to determine multiple pollution sources. The geographic information covers the topography, water system distribution, land use type, population concentration, and existing infrastructure layout of the target area. The unit first matches the path information in the water pollution diffusion path map with the topography data in the geographic information. For example, it analyzes whether the pollution diffusion path extends along valleys, rivers and other low-lying areas where water flows converge, because these areas are often channels where pollutants are easily gathered and spread. If it is found that the path is highly consistent with specific terrain features, possible pollution sources near the area, such as industrial plants or agricultural planting areas located upstream of the valley, will be focused on. Next, matching is performed in combination with land use type information. If the pollution diffusion path passes through a large area of ​​agricultural land, then agricultural non-point source pollution, such as excessive use of pesticides and fertilizers or discharge of livestock and poultry waste, may be one of the pollution sources; if the path is close to industrial concentration areas, then the sources of industrial wastewater, waste gas and waste residue emissions need to be thoroughly investigated. At the same time, considering the population concentration and infrastructure layout, such as the direction of the sewage network and the location of the treatment facilities, if it is found that the pollution diffusion path matches the sewage network leakage area or the surrounding area of ​​the landfill, then the relevant facilities in these areas may also be pollution sources. Through multi-dimensional and all-round traversal matching of geographic information, comprehensive analysis of various possible factors, and ultimately accurate determination of the location and type of multiple pollution sources, a clear target orientation is provided for subsequent pollution control work.

[0040] In a possible implementation, the governance suggestion generation module 50 further includes: a data extraction unit, which is used to use the multiple pollution sources as indexes, traverse the groundwater quality multi-source data set to extract data, and obtain water quality data around multiple pollution sources. Specifically, the data extraction unit uses multiple determined pollution sources as index information to systematically and comprehensively traverse the groundwater quality multi-source data set. The data set contains rich content, such as detailed water quality index data of each sampling point, accurate sampling time records, and corresponding geographical location information. Through precise geographic coordinate matching and data screening technology, water quality data located within a specific geographical range around each pollution source are extracted. These data cover a lot of key information, including concentration values ​​of various chemical substances, such as heavy metal ion concentration, organic pollutant content, etc., as well as physical property parameters of water, such as pH, conductivity, temperature, etc., and then successfully obtain water quality data around multiple pollution sources. These data will serve as a key basis for in-depth exploration of pollution conditions and their impacts, and lay a solid data foundation for subsequent analysis.

[0041] The pollution impact analysis unit is used to perform pollution impact analysis based on the water quality data around the multiple pollution sources and generate multiple impact factors. Specifically, the pollution impact analysis unit carries out a comprehensive and in-depth pollution impact analysis based on the water quality data around the multiple pollution sources obtained. In the analysis process, the unique physical and chemical properties of different types of pollutants are fully taken into account. For example, some heavy metal pollutants have strong bioaccumulation, while organic pollutants may have characteristics such as volatility and difficulty in degradation. At the same time, in-depth research is conducted on the content levels of various pollutants in water bodies and the complex interactions that may occur between them, such as chemical reactions to generate new harmful substances or synergistic effects to enhance pollution effects. Using professional water quality analysis models and advanced mathematical algorithms, the comprehensive impact of these pollution factors on water quality conditions is systematically explored from multiple dimensions. For example, by analyzing the degree of damage to the acid-base balance of the water body, the consumption of dissolved oxygen content in the water, and the changes in the structure and function of the microbial community, etc., multiple influencing factors that can accurately reflect the degree and mode of action of pollution on water quality are generated. These influencing factors will present the effects of pollution in the actual water environment in a quantitative form, providing important intermediate data support for the subsequent accurate assessment of the contribution of pollution sources.

[0042] A contribution calculation unit, the contribution calculation unit is used to calculate the contribution of the water quality data around the multiple pollution sources according to the multiple influencing factors, and identify multiple key pollution sources. Specifically, the contribution calculation unit uses the multiple influencing factors generated previously to perform a detailed and rigorous contribution calculation on the water quality data around the multiple pollution sources. A specific, scientifically verified mathematical model is used for data processing, such as multivariate regression analysis or principal component analysis. During the calculation process, an in-depth analysis is made of the relative importance of the pollutants discharged by each pollution source in the entire process of causing water quality changes. By performing correlation analysis and mathematical operations on the pollutant emission data of each pollution source and the corresponding influencing factors, the proportional relationship of each pollution source's contribution to the water quality deterioration phenomenon or the change of a specific water quality indicator is determined. For example, for the problem of excessive total nitrogen content in water quality in a certain area, the contribution ratio of different pollution sources such as industrial wastewater discharge, agricultural non-point source pollution and domestic sewage discharge to the increase in total nitrogen content can be clarified through contribution calculation, and multiple key pollution sources that play a key role in the entire pollution system can be accurately identified, thereby clarifying the main target objects for subsequent pollution control work, so as to concentrate more resources and energy on effective control and management of these key pollution sources.

[0043] A control area determination unit, the control area determination unit is used to take the multiple key pollution sources as control objects, divide the target area according to the control objects, and determine the control area. Specifically, the control area determination unit takes the multiple key pollution sources that have been accurately identified as core control objects, and carries out regional division work based on the actual distribution of these key pollution sources in the target area. In the division process, a variety of factors are comprehensively considered, including the diffusion range of pollutants from key pollution sources, which requires scientific prediction and estimation based on factors such as the type of pollutants, emission intensity, local meteorological conditions, and hydrogeological characteristics; at the same time, the surrounding geographical environment factors are fully considered, such as topographic and geomorphic characteristics, different terrains such as mountains, plains, rivers and lakes have different effects on the diffusion and control of pollutants, as well as ecological sensitivity, and special attention and protection are needed for ecologically fragile areas. Through the comprehensive weighing and scientific analysis of these multiple factors, a reasonable and effective control area boundary is determined to ensure that the demarcated control area can comprehensively and effectively cover the key pollution sources and the surrounding areas that may have an impact, and provide a clear spatial scope definition for the subsequent formulation of targeted and operational control measures, so that the control work can be carried out in an orderly and efficient manner within a specific area.

[0044] The pollution control plan formulation unit is used to conduct a comprehensive analysis based on the governance object and the governance area, formulate a pollution control plan, and add the pollution control plan to the governance proposal. Specifically, the pollution control plan formulation unit conducts in-depth and detailed comprehensive analysis based on the already determined governance object and governance area. For different types of key pollution sources, such as industrial pollution sources, in-depth research is conducted on their production process, analysis of the links that may produce pollutants, and formulation of source reduction and end-of-pipe treatment measures including the use of advanced clean production processes to reduce the amount of pollutants generated and the installation of efficient sewage treatment equipment to deeply treat the generated sewage; for agricultural pollution sources, combined with the local agricultural planting structure and breeding model, formulate and promote green planting technologies, such as precision fertilization, ecological irrigation, and green breeding technologies, such as the resource utilization of livestock and poultry manure; for domestic pollution sources, considering factors such as population density and infrastructure construction in the area, formulate a complete sewage collection and treatment system upgrade plan, garbage classification and treatment optimization plan, etc. These comprehensive, systematic and targeted pollution control plans developed for different pollution sources and treatment area characteristics are then added to the treatment recommendations, thereby providing a detailed and feasible action guide for effectively improving the water quality in the target areas, and providing a scientific basis and clear direction for relevant departments and decision makers when implementing pollution control actions.

[0045] The embodiment of the present application uses a sensor network to obtain multi-source data of groundwater in the target area, and combines environmental parameters to perform data fusion to generate a comprehensive result; water quality is scored based on the fused data, a water quality spatial distribution map is constructed, and water quality change trends are predicted; pollution sources are determined based on trend data, and pollution control plans are formulated and governance recommendations are generated in combination with multi-source data, thereby achieving the technical effect of high-precision detection and comprehensive evaluation of groundwater quality data.

[0046] In the above, refer to Figure 1 The water quality detection system for groundwater resource assessment according to an embodiment of the present invention is described in detail. Figure 2 A water quality detection method for groundwater resource assessment according to an embodiment of the present invention is described.

[0047] Water quality testing methods used for groundwater resource assessment, such as Figure 2 As shown, the method includes: Through the sensor network, multi-source data sensing is performed on the groundwater in the target area to obtain a multi-source data set of groundwater quality; the environmental parameter set of the target area is introduced, and the groundwater quality multi-source data set is fused with the environmental parameter set to obtain a multi-source data fusion result; the groundwater quality multi-source data set is evaluated based on the multi-source data fusion result to generate a comprehensive water quality score; a water quality spatial distribution map is constructed according to the comprehensive water quality score, and water quality is predicted based on the water quality spatial distribution map to obtain water quality change trend data; pollution source tracing is performed based on the water quality change trend data to determine multiple pollution sources, and pollution control of groundwater in the target area is performed based on the multiple pollution sources in combination with the groundwater quality multi-source data set to generate governance recommendations.

[0048] In a possible implementation, the water quality detection method for groundwater resource assessment also includes: dividing the target area based on the geographic information of the target area to generate multiple sub-areas; traversing the multiple sub-areas to perform multi-dimensional environmental sensing to obtain multiple environmental data; performing data spatiotemporal matching of the multiple environmental data with the multiple sub-areas, and normalizing the multiple environmental data according to the matching results to obtain the environmental parameter set.

[0049] In a possible implementation, the water quality detection method for groundwater resource assessment also includes: temporally and spatially correlating the groundwater quality multi-source data set with the environmental parameter set to generate a data temporal and spatial correlation coefficient; retrieving historical environment-water quality data record logs, analyzing the historical environment-water quality data record logs using the Delphi method, and constructing a causal model; synchronizing the groundwater quality multi-source data set with the environmental parameter set to the causal model for calculation according to the data temporal and spatial correlation coefficient to obtain a causal fusion association list; and fusing the groundwater quality multi-source data set with the environmental parameter set according to the causal fusion association list to obtain a multi-source data fusion result.

[0050] In a possible implementation, the water quality detection method for groundwater resource assessment also includes: scoring and identifying multiple sampling points in the multiple sub-areas based on the comprehensive water quality score to obtain multiple regional water quality scores; performing coverage calculations according to the multiple sampling points based on the multiple regional water quality scores to determine multiple unsampled point scores; mapping the multiple regional water quality scores and the multiple unsampled point scores to the two-dimensional planes of the multiple sub-areas for water quality marking to obtain multiple water quality label distribution data; and visualizing the multiple water quality label distribution data to construct the water quality spatial distribution map.

[0051] In a possible implementation, the water quality detection method for groundwater resource assessment also includes: traversing the multiple sub-areas to select points based on the multiple water quality label distribution data, and determining multiple water quality evaluation points; serializing the data according to the scoring time series through the multiple water quality evaluation points to generate a water quality score time series; performing correlation learning based on the water quality score time series to generate a score change correlation coefficient; performing distribution prediction on the water quality spatial distribution map according to the water quality score time series based on the score change correlation coefficient to generate multiple water quality distribution prediction data; performing trend analysis on the multiple water quality distribution prediction data in combination with the score change correlation coefficient to construct the water quality change trend data.

[0052] In one possible implementation, the water quality detection method for groundwater resource assessment also includes: performing a decline analysis based on the water quality change trend data, tracing the source based on the decline trend, and determining the area of ​​water quality deterioration; tracking pollution based on the score change correlation coefficient in combination with the water quality deterioration area, and determining multiple pollution diffusion paths; assigning weights to the multiple pollution diffusion paths, determining multiple weight coefficients, and constructing a water pollution diffusion path map based on the association of the multiple pollution diffusion paths with the multiple weight coefficients; and traversing and matching the geographic information of the target area based on the water pollution diffusion path map to determine the multiple pollution sources.

[0053] In one possible implementation, the water quality detection method for groundwater resource assessment also includes: taking the multiple pollution sources as indexes, traversing the groundwater quality multi-source data set to extract data, and obtaining water quality data around the multiple pollution sources; performing pollution impact analysis based on the water quality data around the multiple pollution sources to generate multiple influencing factors; calculating the contribution of the water quality data around the multiple pollution sources based on the multiple influencing factors to identify multiple key pollution sources; taking the multiple key pollution sources as governance objects, dividing the target area according to the governance objects, and determining the governance area; performing a comprehensive analysis based on the governance objects and the governance area, formulating a pollution control plan, and adding the pollution control plan to the governance recommendations.

[0054] The water quality detection system for groundwater resource assessment provided by the embodiment of the present invention can execute the water quality detection method for groundwater resource assessment provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0055] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0056] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A water quality detection system for groundwater resource assessment, characterized in that: The system comprises: A multi-source data set acquisition module, which is used to perform multi-source data sensing on groundwater in a target area through a sensor network to obtain a multi-source data set of groundwater quality; A data fusion module, wherein the data fusion module is used to introduce an environmental parameter set of a target area, fuse the groundwater quality multi-source data set with the environmental parameter set, and obtain a multi-source data fusion result; A water quality comprehensive score generation module, the water quality comprehensive score generation module is used to evaluate the groundwater quality multi-source data set based on the multi-source data fusion result to generate a water quality comprehensive score; A change trend data acquisition module, the change trend data acquisition module is used to construct a water quality spatial distribution map according to the water quality comprehensive score, perform water quality prediction based on the water quality spatial distribution map, and obtain water quality change trend data; A governance suggestion generation module is used to trace the pollution source based on the water quality change trend data, determine multiple pollution sources, control the pollution of groundwater in the target area based on the multiple pollution sources in combination with the groundwater quality multi-source data set, and generate governance suggestions.

2. The water quality detection system for groundwater resource assessment according to claim 1, characterized in that: The data fusion module comprises: A sub-region generating unit, wherein the sub-region generating unit is used to divide the target region based on the geographic information of the target region to generate a plurality of sub-regions; An environmental data acquisition unit, the environmental data acquisition unit is used to traverse the multiple sub-areas to perform multi-dimensional environmental sensing and obtain multiple environmental data; An environmental parameter set acquisition unit is used to perform data spatiotemporal matching between the multiple environmental data and the multiple sub-areas, and normalize the multiple environmental data according to the matching result to obtain the environmental parameter set.

3. The water quality detection system for groundwater resource assessment according to claim 1, characterized in that: The data fusion module comprises: A data spatiotemporal correlation coefficient generating unit, the data spatiotemporal correlation coefficient generating unit is used to perform spatiotemporal correlation between the groundwater quality multi-source data set and the environmental parameter set to generate a data spatiotemporal correlation coefficient; A log analysis unit, the log analysis unit is used to retrieve historical environment-water quality data record logs, analyze the historical environment-water quality data record logs using the Delphi method, and construct a causal model; A causal model calculation unit, the causal model calculation unit is used to synchronize the groundwater quality multi-source data set and the environmental parameter set to the causal model for calculation according to the data spatiotemporal correlation coefficient, and obtain a causal fusion association list; A parameter set fusion unit is used to fuse the groundwater quality multi-source data set with the environmental parameter set according to the causal fusion association list to obtain a multi-source data fusion result.

4. The water quality detection system for groundwater resource assessment according to claim 2, characterized in that: The change trend data acquisition module includes: A scoring identification unit, the scoring identification unit is used to score and identify multiple sampling points in the multiple sub-areas based on the comprehensive water quality score to obtain multiple regional water quality scores; A coverage calculation unit, the coverage calculation unit is used to perform coverage calculation according to the multiple sampling points based on the multiple regional water quality scores to determine the scores of multiple unsampled points; A water quality labeling unit, the water quality labeling unit is used to map the water quality scores of the multiple regions and the scores of the multiple unsampled points to the two-dimensional planes of the multiple sub-regions to perform water quality labeling, and obtain multiple water quality label distribution data; A visualization processing unit is used to visualize the plurality of water quality label distribution data to construct the water quality spatial distribution map.

5. The water quality detection system for groundwater resource assessment according to claim 4, characterized in that: The change trend data acquisition module includes: A water quality assessment point determination unit, the water quality assessment point determination unit is used to traverse the multiple sub-areas to select points based on the multiple water quality label distribution data, and determine multiple water quality assessment points; A serialization processing unit, the serialization processing unit is used to perform serialization processing on the data according to the scoring time sequence through the multiple water quality evaluation points to generate a water quality scoring time series; A score change correlation coefficient generating unit, the score change correlation coefficient generating unit is used to perform correlation learning based on the water quality score time series to generate a score change correlation coefficient; A distribution prediction unit, the distribution prediction unit is used to perform distribution prediction on the water quality spatial distribution map according to the water quality score time series based on the score change correlation coefficient, and generate a plurality of water quality distribution prediction data; A trend analysis unit is used to perform trend analysis on the multiple water quality distribution prediction data in combination with the score change correlation coefficient to construct the water quality change trend data.

6. The water quality detection system for groundwater resource assessment according to claim 5, characterized in that: The governance suggestion generation module includes: A water quality deterioration area determination unit, the water quality deterioration area determination unit is used to perform a decline analysis based on the water quality change trend data, trace the source and locate the water quality deterioration area based on the decline trend; A pollution diffusion path determination unit, the pollution diffusion path determination unit is used to track pollution based on the score change correlation coefficient in combination with the water quality deterioration area, and determine multiple pollution diffusion paths; A water pollution diffusion path map construction unit, the water pollution diffusion path map construction unit is used to assign weights to the multiple pollution diffusion paths, determine multiple weight coefficients, and construct a water pollution diffusion path map based on the association between the multiple pollution diffusion paths and the multiple weight coefficients; A traversal matching unit is used to perform traversal matching on the geographic information of the target area based on the water pollution diffusion path map to determine the multiple pollution sources.

7. The water quality detection system for groundwater resource assessment according to claim 1, characterized in that: According to the multiple pollution sources combined with the groundwater quality multi-source data set, groundwater pollution in the target area is controlled and governance suggestions are generated. The system includes: A data extraction unit, the data extraction unit is used to use the multiple pollution sources as indexes, traverse the groundwater quality multi-source data set to extract data, and obtain water quality data around the multiple pollution sources; A pollution impact analysis unit, the pollution impact analysis unit is used to perform pollution impact analysis based on the water quality data around the multiple pollution sources to generate multiple impact factors; A contribution calculation unit, the contribution calculation unit is used to calculate the contribution of the water quality data around the multiple pollution sources according to the multiple influencing factors, and identify multiple key pollution sources; A control area determination unit, the control area determination unit is used to take the multiple key pollution sources as control objects, divide the target area according to the control objects, and determine the control area; A pollution control plan formulation unit is used to make a comprehensive analysis based on the governance object and the governance area, formulate a pollution control plan, and add the pollution control plan to the governance proposal.

8. A water quality detection method for groundwater resource assessment, characterized in that: The method is applied to the water quality detection system for groundwater resource assessment according to any one of claims 1 to 7, and the method comprises: Multi-source data sensing of groundwater in the target area is performed through a sensor network to obtain a multi-source data set of groundwater quality; An environmental parameter set of a target area is introduced, and the groundwater quality multi-source data set is fused with the environmental parameter set to obtain a multi-source data fusion result; Evaluate the groundwater quality multi-source data set based on the multi-source data fusion result to generate a comprehensive water quality score; Constructing a water quality spatial distribution map according to the comprehensive water quality score, performing water quality prediction based on the water quality spatial distribution map, and obtaining water quality change trend data; Based on the water quality change trend data, pollution source tracing is performed to determine multiple pollution sources. Based on the multiple pollution sources and the groundwater quality multi-source data set, groundwater pollution in the target area is controlled to generate treatment recommendations.

Images