Wetland ecological risk regulation and control method, system and equipment based on multi-modal early warning

Abstract

The invention discloses a wetland ecological risk regulation and control method, system and equipment based on multi-modal early warning, and relates to the related field of water quality parameter abnormity alarm, the method comprises the following steps: collecting physical and chemical parameters of a wetland water body in real time, and generating a dynamic water quality data set; performing detection optimization on the dynamic water quality data set according to the historical abnormal data frequency, and determining a water quality detection sequence; and performing multi-level risk assessment on the target wetland area according to the water quality detection sequence to obtain a plurality of risk scores, triggering a multi-modal early warning mechanism based on the plurality of risk scores, generating a self-adaptive purification scheme, and pushing the self-adaptive purification scheme to a management terminal. The technical problems of insufficient early warning timeliness, monitoring comprehensiveness and data accuracy of the existing wetland water quality monitoring are solved, and the technical effects of improving the early warning timeliness, the monitoring comprehensiveness and the data accuracy of the wetland water quality monitoring are achieved.

Description

Technical Field

[0001] This application relates to the field of abnormal water quality parameter alarms, and particularly to a wetland ecological risk regulation method, system, and device based on multimodal early warning. Background Art

[0002] The effective monitoring and management of wetland water quality are of crucial significance for maintaining wetland ecological balance, ensuring water resource security, and promoting regional sustainable development. Currently, for wetland water quality monitoring, traditional manual sampling and laboratory analysis methods are mainly used. This method not only has poor timeliness and is difficult to issue early warning signals in a timely manner when water quality is abnormal, but also has limited monitoring scope and insufficient data continuity, resulting in the monitoring results being unable to comprehensively and accurately reflect the dynamic changes in the overall water quality status of the wetland. This lagging and one-sided monitoring status makes it difficult for management departments to obtain effective early warning information in a timely manner, thus seriously affecting the scientific formulation and rapid response of wetland protection and management decisions.

[0003] In the current related technologies, there are technical problems of insufficient early warning timeliness, monitoring comprehensiveness, and data accuracy in wetland water quality monitoring. Summary of the Invention

[0004] This application provides a wetland ecological risk regulation method, system, and device based on multimodal early warning. By using technical means such as real-time collecting the physical and chemical parameters of wetland water bodies to generate a dynamic data set, optimizing the data set according to the historical abnormal data frequency to determine the water quality detection sequence, then performing multi-level risk assessment on the target wetland area according to this sequence to obtain multiple risk scores, and finally triggering a multimodal early warning mechanism based on the scores and generating an adaptive purification plan to be pushed to the management terminal, it solves the technical problems of insufficient early warning timeliness, monitoring comprehensiveness, and data accuracy existing in the current wetland water quality monitoring, and achieves the technical effects of improving the early warning timeliness, monitoring comprehensiveness, and data accuracy of wetland water quality monitoring.

[0005] This application provides a wetland ecological risk regulation method based on multimodal early warning, including: real-time collecting the physical and chemical parameters of wetland water bodies to generate a dynamic water quality data set; detecting and optimizing the dynamic water quality data set according to the historical abnormal data frequency to determine the water quality detection sequence; performing multi-level risk assessment on the target wetland area according to the water quality detection sequence to obtain multiple risk scores, triggering a multimodal early warning mechanism based on the multiple risk scores, generating an adaptive purification plan and pushing it to the management terminal.

[0006] In a possible implementation, the dynamic water quality dataset is detected and optimized according to the historical anomaly data frequency to determine a water quality detection sequence, and the following processing is performed: Anomaly analysis is carried out on multi-source water quality parameters in the target wetland area according to the historical monitoring period to determine parameter anomaly event data, and a spatio-temporal distribution feature matrix is constructed based on the parameter anomaly event data; Anomaly correlation calculation is performed on the multi-source water quality parameters based on the spatio-temporal distribution feature matrix to generate a parameter detection priority weight matrix; The multi-source sensor network is detected and sorted according to the parameter detection priority weight matrix to construct the water quality detection sequence.

[0007] In a possible implementation, anomaly correlation calculation is performed on the multi-source water quality parameters based on the spatio-temporal distribution feature matrix to generate a parameter detection priority weight matrix, and the following processing is performed: Anomaly analysis is carried out on the multi-source water quality parameters based on the spatio-temporal distribution feature matrix to determine multiple anomaly events, and the multiple anomaly events include multiple anomaly occurrence probabilities; Spatial correlation analysis is performed on the multiple anomaly events according to the multiple anomaly occurrence probabilities to obtain the spatial aggregation characteristics of the multiple anomaly events; The target wetland area is traversed according to the spatial aggregation characteristics to allocate weights to adjacent monitoring nodes to construct the parameter detection priority weight matrix.

[0008] In a possible implementation, the multi-source sensor network is detected and sorted according to the parameter detection priority weight matrix to construct the water quality detection sequence, and the following processing is performed: Water quality exceeding the standard analysis is carried out by traversing the target wetland area to determine water quality exceeding the standard events, and the water quality exceeding the standard events include spatio-temporal distribution characteristics, and the spatio-temporal distribution characteristics have a corresponding relationship with the water quality exceeding the standard events; The parameter detection priority weight matrix is mapped to the multi-source sensor network for detection identification to determine multiple sensing priority identifications; Detection tasks are assigned in descending order according to the multiple sensing priority identifications to construct the water quality detection sequence.

[0009] In a possible implementation, a multi-level risk assessment is performed on the target wetland area according to the water quality detection sequence to obtain multiple risk scores, and the following processing is performed: Traverse the target wetland area according to the water quality detection sequence to determine the first pollution point; construct a spatial coordinate system of the target wetland area, and extract the first spatial coordinate data of the first pollution point; perform pollution analysis according to the spatio-temporal distribution characteristic matrix in combination with the first spatial coordinate data to determine a pollution impact data set, where the pollution impact data set includes pollutant concentration extreme value data and pollutant impact depth data; perform a local pollution risk assessment on the target wetland area according to the first spatial coordinate data in combination with the pollutant concentration extreme value data to generate a first risk score; perform an overall ecological risk assessment on the target wetland area according to the first spatial coordinate data in combination with the pollutant impact depth data to generate a second risk score; associate and integrate the first risk score and the second risk score to the first pollution point to obtain the multiple risk scores.

[0010] In a possible implementation, a multi-modal early warning mechanism is triggered based on the multiple risk scores, and the following processing is performed: Perform a local diffusion analysis on the first pollution point based on the first risk score, draw a local pollution diffusion trend map, perform an ecological risk analysis on the first pollution point based on the second risk score, and set the overall ecological risk level of the wetland; perform pollution diffusion calculation based on the local pollution diffusion trend map to generate a pollution diffusion rate; perform wetland self-purification calculation based on the overall ecological risk level of the wetland to generate a wetland self-purification rate; perform a balance analysis according to the pollution diffusion rate and the wetland self-purification rate to generate a dynamic balance coefficient; trigger the multi-modal early warning mechanism according to the dynamic balance coefficient.

[0011] In a possible implementation, the multi-modal early warning mechanism is triggered according to the dynamic balance coefficient, and the following processing is performed: Define an abnormal critical value according to the parameter abnormal event data, and set an expected balance value range according to the abnormal critical value; judge whether the dynamic balance coefficient is within the expected balance value range. When the dynamic balance coefficient is not within the expected balance value range, determine the type of the exceeded standard parameter according to the parameter abnormal event data, and determine the spatial distribution characteristics according to the spatio-temporal distribution characteristics; trigger the multi-modal early warning mechanism based on the type of the exceeded standard parameter and the spatial distribution characteristics.

[0012] In a possible implementation, during the process of generating an adaptive purification plan and pushing it to the management terminal, the following processing is performed: matching a multi-level early warning mode based on the type of over-standard parameters and the spatial distribution characteristics, generating a multi-modal early warning linkage instruction according to the matching result; adaptively adjusting the target wetland area through the multi-modal early warning linkage instruction to generate an adaptive purification plan; pushing the adaptive purification plan to the management terminal through a blockchain encryption channel, and synchronously updating the regulation log of the target wetland area.

[0013] This application also provides a wetland ecological risk regulation system based on multi-modal early warning, including: a dynamic water quality data set generation module, configured to collect the physical and chemical parameters of wetland water bodies in real time and generate a dynamic water quality data set; a water quality detection sequence determination module, configured to detect and optimize the dynamic water quality data set according to the historical abnormal data frequency to determine a water quality detection sequence; an adaptive purification plan generation module, configured to perform multi-level risk assessment on the target wetland area according to the water quality detection sequence, obtain multiple risk scores, trigger a multi-modal early warning mechanism based on the multiple risk scores, generate an adaptive purification plan and push it to the management terminal.

[0014] This application also provides an electronic device, including: a memory, configured to store executable instructions; a processor, configured to implement the wetland ecological risk regulation method based on multi-modal early warning when executing the executable instructions stored in the memory.

[0015] It is intended to first collect the physical and chemical parameters of wetland water bodies in real time through the wetland ecological risk regulation method, system and device based on multi-modal early warning proposed in this application to generate a dynamic water quality data set, then detect and optimize the dynamic water quality data set according to the historical abnormal data frequency to determine a water quality detection sequence, and finally perform multi-level risk assessment on the target wetland area according to the water quality detection sequence, obtain multiple risk scores, trigger a multi-modal early warning mechanism based on the multiple risk scores, generate an adaptive purification plan and push it to the management terminal. The technical effects of improving the early warning timeliness, monitoring comprehensiveness and data accuracy of wetland water quality monitoring are achieved. Description of the Drawings

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings of the embodiments of the present invention will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the systems according to the embodiments of the application. It should be understood that the operations in the front or below do not necessarily need to be executed precisely in sequence. On the contrary, according to needs, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0017] Figure 1It is a schematic flow chart of a wetland ecological risk regulation method based on multimodal early warning provided by an embodiment of the present application.

[0018] Figure 2 It is a schematic structural diagram of a wetland ecological risk regulation system based on multimodal early warning provided by an embodiment of the present application.

[0019] Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0020] Explanation of reference numerals: Dynamic water quality data set generation module 10, water quality detection sequence determination module 20, adaptive purification scheme generation module 30, input device 301, processor 302, memory 303, output device 304. Detailed implementation manners

[0021] The above description is only an overview of the technical solution of the present application. In order to understand the technical means of the present application more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically gives the detailed implementation manners of the present application.

[0022] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings. The described embodiments should not be regarded as limitations of the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present application.

[0023] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first / second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0024] An embodiment of the present application provides a wetland ecological risk regulation method based on multimodal early warning, as Figure 1 shown, the method includes: Step S100, collect the physicochemical parameters of the wetland water body in real time to generate a dynamic water quality dataset.

[0025] Specifically, a variety of sensors are reasonably arranged in the wetland water body, including a dissolved oxygen sensor, an ORP (oxidation-reduction potential) sensor, a pH sensor, and a turbidity sensor. These sensors transmit the collected data to the data acquisition terminal in real time through a wireless communication module (such as LoRa, NB-IoT, etc.). The dissolved oxygen sensor uses the fluorescence method principle to determine the dissolved oxygen concentration by measuring the change in fluorescence intensity generated by the interaction between the fluorescent substance on the fluorescence probe and the dissolved oxygen molecules in the water; the ORP sensor uses the electrochemical principle to reflect the oxidation-reduction state of the water body by measuring the potential difference between the electrode and the water body; the pH sensor is based on the glass electrode method to determine the pH value by measuring the hydrogen ion activity of the water body; the turbidity sensor uses the scattered light method to determine the turbidity of the water body by measuring the change in the light intensity after the incident light is scattered in the water body.

[0026] After the data acquisition terminal receives the data transmitted by the sensors, it performs preliminary preprocessing, including data format conversion, filtering processing (such as using the Kalman filtering algorithm to remove noise interference), etc., to ensure the accuracy and integrity of the data. Then the processed data is stored in the local database and a dynamic water quality dataset is generated according to the time series. The dynamic water quality dataset is a set of water quality data that is continuously updated over time and can reflect the changes in the water quality status of the wetland water body at different time points.

[0027] For example, in a river in a wetland, a sensor node is arranged every 50 meters, and each node contains the above four sensors. The sensors collect data every 10 minutes and send the data to the nearby acquisition terminal through the LoRa module. After the acquisition terminal receives the data, it first performs filtering processing on the data to remove noise interference caused by water flow fluctuations, etc., and then stores the data in the local database to form a dynamic water quality dataset. Each record in the dataset includes information such as the collection time, sensor number, dissolved oxygen concentration, ORP value, pH value, and turbidity.

[0028] Step S200, detect and optimize the dynamic water quality dataset according to the historical abnormal data frequency to determine the water quality detection sequence.

[0029] Specifically, historical water quality data is extracted from the database, and the frequency of anomalies (outside the normal range) in each water quality parameter is counted. For example, by writing SQL query statements, count the number of times the dissolved oxygen concentration was below the normal range (e.g., less than 3 mg / L) and the number of times the ORP value was above the normal range (e.g., greater than 700 mV) in the past year. According to the historical anomaly frequencies, a priority queue algorithm (such as a heap-based priority queue) is used to determine the water quality detection sequence. Set the priority of the sensor detection tasks corresponding to the water quality parameters with high anomaly frequencies higher, and give priority to executing their detection tasks. At the same time, combine a dynamic adjustment algorithm for the sensor sampling frequency, and dynamically adjust the sensor sampling frequency based on real-time detection results and historical data. For example, if the detection results of a certain water quality parameter are normal for several consecutive times, appropriately reduce its sampling frequency; if an anomaly is detected, increase the sampling frequency for detailed monitoring. The algorithm can adopt an adaptive sampling frequency adjustment algorithm based on feedback control to calculate the new sampling frequency according to the deviation degree between the current detection result and historical data.

[0030] For example, it is statistically found that within the past six months, the pH value of the wetland water body had the highest anomaly frequency, accounting for 40% of the total anomaly times; followed by turbidity, accounting for 30%; the anomaly frequencies of dissolved oxygen and ORP values were relatively low. Therefore, when determining the detection sequence, set the highest priorities for the sensor detection tasks corresponding to the pH value and turbidity. During the actual detection process, the initial sampling frequencies of the pH sensor and turbidity sensor are set to once every 5 minutes, and the sampling frequencies of the dissolved oxygen and ORP sensors are once every 10 minutes. When the pH sensor has five consecutive normal detection results, adjust its sampling frequency to once every 10 minutes; if an abnormal pH value is detected, immediately restore the sampling frequency to once every 5 minutes and notify other relevant sensors to cooperate in monitoring.

[0031] In a possible implementation, the dynamic water quality dataset is detected and optimized according to the historical anomaly data frequencies to determine the water quality detection sequence. Step S200 further includes step S210 of performing anomaly analysis on multi-source water quality parameters in the target wetland area according to the historical monitoring period to determine parameter anomaly event data, and constructing a spatio-temporal distribution feature matrix based on the parameter anomaly event data. Specifically, a monitoring buffer zone with a radius of 5 km can be delimited with the target wetland as the center, that is, the target wetland area is the specific implementation scope of the monitoring activity. Through geographic information system (GIS) technology, determine the boundary of the buffer zone and arrange monitoring points within this area. For example, use GIS software such as ArcGIS to draw a circular area with a radius of 5 km centered on the wetland on the map and mark the positions of all monitoring points within this area. Extract hourly water quality monitoring data for the past three years from the database, including multi-source water quality parameters such as dissolved oxygen, ORP value, pH value, and turbidity. For example, the database stores hourly monitoring data in the format shown in Table 1.

[0032] Table 1: Example of Historical Monitoring Data of Multi-Source Water Quality Parameters The K-means clustering algorithm is used to analyze the historical monitoring data to identify the spatio-temporal clustering centers of abnormal events. Each data point (including time, location, and water quality parameter value) in the monitoring data is used as input, and the abnormal data points are clustered together through the clustering algorithm to determine the spatio-temporal distribution center of the abnormal events.

[0033] Calculate the exceeding standard frequency and duration of each parameter. For example, for the dissolved oxygen parameter, the normal range is set to 6-10 mg / L, and values below 6 mg / L are considered to exceed the standard. The situation of dissolved oxygen exceeding the standard in the hourly data of each monitoring point is counted, and the exceeding standard frequency and the duration of each exceeding standard are recorded.

[0034] A three-dimensional spatio-temporal cube model is established, where the three dimensions are longitude, latitude, and the time axis. In this model, the density values of abnormal events are marked along the longitude, latitude, and time axes. The three-dimensional spatio-temporal cube model is the spatio-temporal distribution feature matrix, which is used to intuitively represent the distribution of abnormal events in time and space. For example, the three-dimensional spatio-temporal cube model can be represented as a three-dimensional array, and each element corresponds to the density value of an abnormal event at a specific time and location. The density value can be quantified by the number of abnormal events or the degree of abnormality.

[0035] For example, assume that there are 5 monitoring points labeled A, B, C, D, and E within a 5-km radius around the target wetland. After extracting the hourly water quality monitoring data for the past three years, the spatio-temporal clustering centers of abnormal events are identified through the K-means clustering algorithm. For example, it is found that the dissolved oxygen at monitoring point C continuously dropped below 6 mg / L during the period from 14:00 to 16:00 on July 15, 2024, forming a clustering center of abnormal events. In the three-dimensional spatio-temporal cube model, the density value of this abnormal event is marked as a relatively high value at the corresponding time and location.

[0036] Step S220, based on the spatio-temporal distribution feature matrix, perform abnormal association calculation on the multi-source water quality parameters to generate a parameter detection priority weight matrix. Specifically, calculate the abnormal occurrence probability of each water quality parameter. For example, for the dissolved oxygen parameter, count the proportion of the number of abnormal occurrences in the historical data to the total number of monitoring times. Calculate the spatial correlation degree between each water quality parameter. Use spatial autocorrelation analysis methods (such as Moran's I index) or machine learning-based association rule mining algorithms to analyze the spatial correlation of abnormal events of different water quality parameters. For example, calculate the spatial correlation degree between dissolved oxygen abnormality and pH value abnormality. If it is found that the areas with dissolved oxygen abnormality are often accompanied by pH value abnormality, it is considered that there is a strong correlation between these two parameters in space.

[0037] According to the abnormal occurrence probability and spatial correlation degree, a priority weight is assigned to each water quality parameter. The priority weight can be calculated by weighted summation. For example, weight = abnormal occurrence probability × α + spatial correlation degree × β, where α and β are weight coefficients and are adjusted according to actual requirements. The priority weights of each water quality parameter are organized into a matrix. The rows and columns of the matrix represent different water quality parameters respectively, and the matrix elements represent the priority weights between the corresponding parameters.

[0038] In step S230, the multi-source sensor network is detected and sorted according to the parameter detection priority weight matrix to construct the water quality detection sequence. Specifically, according to the parameter detection priority weight matrix, each sensor in the multi-source sensor network is detected and sorted. The water quality parameter corresponding to the sensor with a higher priority weight is detected first. For example, for the four parameters of dissolved oxygen, ORP value, pH value, and turbidity, according to the priority weight matrix, the pH value has the highest priority, followed by dissolved oxygen, then the ORP value, and finally the turbidity. Therefore, the order of sensor detection is pH sensor, dissolved oxygen sensor, ORP sensor, and turbidity sensor in sequence. The sorted sensor detection tasks are arranged in chronological order to form a water quality detection sequence. During the actual monitoring process, the detection tasks of each sensor are executed in sequence according to this sequence. For example, the detection sequence can be expressed as: pH sensor → dissolved oxygen sensor → ORP sensor → turbidity sensor. The detection task of each sensor can be carried out at a set time interval (such as once every 10 minutes). For example, at the 1st minute: detect the pH value; at the 11th minute: detect the dissolved oxygen; at the 21st minute: detect the ORP value; at the 31st minute: detect the turbidity; at the 41st minute: detect the pH value again, and cycle the above process. This arrangement of the detection sequence can ensure that high-priority parameters (such as the pH value) can be monitored more frequently, so as to timely discover potential water quality problems.

[0039] In a possible implementation, based on the spatio-temporal distribution feature matrix, abnormal correlation calculation is performed on the multi-source water quality parameters to generate a parameter detection priority weight matrix. Step S220 further includes step S221, where abnormal analysis is performed on the multi-source water quality parameters based on the spatio-temporal distribution feature matrix to determine multiple abnormal events, and the multiple abnormal events include multiple abnormal occurrence probabilities. Specifically, the spatio-temporal distribution feature matrix (i.e., the three-dimensional spatio-temporal cube model) is used to perform abnormal analysis on the multi-source water quality parameters. This matrix contains the spatio-temporal distribution information of abnormal events in historical monitoring data, and the density values of abnormal events are marked along the longitude, latitude, and time axes. The threshold judgment method is used to determine abnormal events. For each water quality parameter, a normal range is set (for example, the normal range of dissolved oxygen is 6-10 mg / L). When the monitoring data exceeds this range, it is marked as an abnormal event. The abnormal occurrence probability of each abnormal event is calculated. The abnormal occurrence probability refers to the frequency of occurrence of this abnormal event in historical monitoring data. For example, the abnormal occurrence probability of dissolved oxygen is calculated by counting its proportion in the total number of monitoring times. The abnormal occurrence probability reflects the frequency of abnormality of this parameter.

[0040] Step S222, according to the multiple abnormal events, spatial correlation analysis is performed according to the multiple abnormal occurrence probabilities to obtain the spatial aggregation characteristics of the multiple abnormal events. Specifically, for each abnormal event, the spatial correlation degree between it and other abnormal events is calculated. Spatial autocorrelation analysis methods (such as Moran's I index) or association rule mining algorithms based on machine learning can be used. The spatial correlation degree reflects the degree of aggregation of abnormal events in space. The spatial aggregation characteristics are used to describe the distribution pattern of abnormal events in space, reflecting whether abnormal events tend to concentrate in certain specific areas. For example, if two abnormal events often occur simultaneously at adjacent monitoring points, their spatial correlation degree is high. The abnormal events are sorted according to the abnormal occurrence probability, and the spatial correlation of high-probability abnormal events is analyzed first. For example, the spatial correlation degree of the pH value abnormal event is analyzed first because its abnormal occurrence probability is the highest.

[0041] For example, assume that through spatial correlation analysis, it is found that: the spatial correlation degree between the dissolved oxygen abnormal event and the pH value abnormal event is 0.7, indicating that these two abnormal events are highly correlated in space. The spatial correlation degree between the ORP value abnormal event and the turbidity abnormal event is 0.5, indicating that these two abnormal events are also somewhat correlated in space. The spatial correlation degree of the pH value abnormal event with other abnormal events is generally high, indicating that the pH value abnormal event has strong aggregation characteristics in space.

[0042] Step S223: Traverse the target wetland area according to the spatial aggregation characteristics to assign weights to adjacent monitoring nodes, and construct the parameter detection priority weight matrix. Specifically, according to the spatial aggregation characteristics of abnormal events, weights are assigned to adjacent monitoring nodes within the target wetland area to reflect the priority of each monitoring node in detecting abnormal events. For abnormal events with high spatial correlation, higher weights are assigned. For example, if the dissolved oxygen abnormal event is highly correlated with the pH value abnormal event in space, then higher weights will be given to these two parameters during weight assignment. Traverse all monitoring nodes within the target wetland area, and calculate their weight values according to the abnormal event characteristics and spatial correlation of each node. Organize the weight values of each monitoring node into a matrix, where the rows and columns of the matrix represent different water quality parameters, and the matrix elements represent the priority weights between the corresponding parameters.

[0043] In a possible implementation, perform detection sorting on the multi-source sensor network according to the parameter detection priority weight matrix to construct the water quality detection sequence. Step S230 further includes step S231: Traverse the target wetland area for water quality exceedance analysis to determine water quality exceedance events, where the water quality exceedance events include spatio-temporal distribution characteristics, and there is a corresponding relationship between the spatio-temporal distribution characteristics and the water quality exceedance events. Specifically, traverse all monitoring nodes within the target wetland area and perform exceedance analysis on the real-time water quality data of each node. The exceedance analysis is based on preset water quality parameter thresholds (for example, the normal range of dissolved oxygen is 6 - 10 mg / L, and the normal range of pH value is 6.5 - 8.5). For each monitoring node, check whether its water quality parameters exceed the normal range. If so, record this event as a water quality exceedance event. Record the spatio-temporal distribution characteristics of each water quality exceedance event, including the occurrence time, location (longitude and latitude), and duration.

[0044] Step S232: Map to the multi-source sensor network according to the parameter detection priority weight matrix for detection identification to determine multiple sensing priority identifications. Specifically, map the parameter detection priority weight matrix into the multi-source sensor network. Each sensor corresponds to a water quality parameter, and a priority identification is assigned to each sensor according to the weight matrix. The priority identification reflects the priority of the sensor in detecting water quality exceedance events. The higher the value of the priority identification, the higher the priority of the sensor during detection.

[0045] Step S233: Perform descending order assignment of detection tasks according to the multiple sensing priority identifications to construct the water quality detection sequence. Specifically, perform descending order assignment of detection tasks according to the priority identification of each sensor. The sensor with the highest priority identification value performs the detection task first. Construct the water quality detection sequence to ensure that high-priority sensors perform detection first.

[0046] Step S300: Conduct multi-level risk assessment on the target wetland area according to the water quality detection sequence, obtain multiple risk scores, trigger a multi-modal warning mechanism based on the multiple risk scores, generate an adaptive purification plan, and push it to the management terminal.

[0047] Specifically, based on the diffusion equation (such as the Gaussian diffusion model) and the real-time data in the water quality detection sequence, evaluate the diffusion trend of local pollution. For example, taking the pollution source as the center, according to parameters such as the concentration gradient of pollutants and the water flow velocity, use the Gaussian diffusion model to calculate the concentration distribution of pollutants in the surrounding area within a certain time, so as to determine the diffusion range and speed of local pollution, and obtain a risk score. This score can use a percentage system, and the higher the value, the greater the risk of local pollution diffusion.

[0048] Conduct an overall ecological risk level assessment of the wetland, comprehensively considering various factors of the wetland ecosystem, including water quality parameters, biodiversity, vegetation coverage, etc. For example, establish an assessment model based on the Analytic Hierarchy Process (AHP), take water quality parameters (such as dissolved oxygen, pH value, etc.), biodiversity (such as the number of fish species, aquatic plant coverage, etc.) and vegetation coverage as assessment indicators, determine the weights of each indicator through expert scoring, and then calculate the scores of each indicator according to the real-time monitoring data. Finally, obtain the risk score of the overall ecological risk level of the wetland, also using a percentage system, and the higher the value, the greater the overall ecological risk of the wetland.

[0049] According to the multiple risk scores, set different warning thresholds. When the risk score exceeds the corresponding threshold, trigger multi-modal warnings. For example, when the local pollution risk score exceeds 70 points, trigger a local pollution diffusion warning, and send warning information to the management personnel through methods such as text messages, emails, and pushing through the management terminal App, and at the same time display the warning information on the display screen at the wetland site; when the overall ecological risk score of the wetland exceeds 80 points, trigger an overall ecological risk warning of the wetland. In addition to the above warning methods, the sound and light alarm device in the wetland protection area can also be activated to remind the surrounding personnel to pay attention.

[0050] According to the risk scores and specific pollution situations, use an expert system and machine learning algorithms to generate an adaptive purification plan. For example, based on historical purification cases and real-time monitoring data, establish a purification plan recommendation model through machine learning algorithms (such as decision tree algorithms), and recommend corresponding purification measures (such as biological purification, chemical purification, etc.) according to the risk scores and pollution types (such as organic pollution, heavy metal pollution, etc.). Then push the generated purification plan to the management terminal through the network. The management personnel can view the specific content of the purification plan on the terminal, including purification measures, implementation steps, required equipment and materials, etc.

[0051] For example, in a certain monitoring, the risk score calculated by the local pollution diffusion trend assessment model is 75 points, and the risk score calculated by the wetland overall ecological risk level assessment model is 82 points. According to the warning threshold setting, the local pollution diffusion warning and the wetland overall ecological risk warning are triggered. After receiving the warning information, the management personnel view the adaptive purification plan. The plan recommends using biological purification measures, specifically including putting a certain amount of purification algae and microbial agents, and at the same time suggesting local isolation of the polluted area to prevent further pollution diffusion. The management personnel arrange relevant personnel to conduct on-site treatment according to the content of the plan. The embodiment of the present application uses technical means such as real-time collection of wetland water body physicochemical parameters to generate a dynamic data set, optimizing the data set based on the historical abnormal data frequency to determine the water quality detection sequence, then performing multi-level risk assessment on the target wetland area according to this sequence to obtain multiple risk scores, and finally triggering a multi-modal warning mechanism based on the scores and generating an adaptive purification plan to be pushed to the management terminal, etc., to solve the technical problems of insufficient warning timeliness, monitoring comprehensiveness, and data accuracy in the existing wetland water quality monitoring, and achieve the technical effects of improving the warning timeliness, monitoring comprehensiveness, and data accuracy of wetland water quality monitoring.

[0052] In a possible implementation manner, when performing multi-level risk assessment on the target wetland area according to the water quality detection sequence to obtain multiple risk scores, step S300 further includes step S310 of traversing the target wetland area according to the water quality detection sequence to determine the first pollution point. Specifically, according to the water quality detection sequence, the real-time water quality data of each monitoring node is checked in turn. The water quality parameters of each monitoring node are analyzed for exceeding the standard to determine whether they exceed the preset threshold (for example, the normal range of dissolved oxygen is 6-10 mg / L, and the normal range of pH value is 6.5-8.5). The monitoring node where the first detected water quality exceeding the standard event occurs is recorded and marked as the first pollution point.

[0053] Step S320, constructing a spatial coordinate system for the target wetland area and extracting the first spatial coordinate data of the first pollution point. Specifically, using Geographic Information System (GIS) technology, a spatial coordinate system for the target wetland area is constructed. The position of each monitoring node is represented by its longitude and latitude coordinates. The longitude and latitude coordinates of the first pollution point are extracted as the first spatial coordinate data.

[0054] Step S330: Perform pollution analysis based on the spatio-temporal distribution feature matrix and the first spatial coordinate data to determine a pollution impact dataset, where the pollution impact dataset includes pollutant concentration extreme value data and pollutant impact depth data. Specifically, in combination with the spatio-temporal distribution feature matrix (3D spatio-temporal cube model), analyze the historical and real-time water quality data of the first pollution point and its surrounding area. For each water quality parameter (such as dissolved oxygen, pH value, etc.), calculate its minimum and maximum values within a specified time range. These extreme values reflect the severity of the pollution event. For example, assume that the pH value of the first pollution point C is detected to be 6.2 (lower than the normal range of 6.5 - 8.5) and the dissolved oxygen is 5.8 mg / L (lower than the normal range of 6 - 10 mg / L) at 00:00 on April 1, 2024. Through the spatio-temporal distribution feature matrix, extract the data of this point and its surrounding area in the past 24 hours, and calculate that the minimum value of dissolved oxygen is 4.5 mg / L and the minimum value of pH is 6.0.

[0055] Use a pollutant diffusion model (such as the Gaussian diffusion model or numerical simulation method) to calculate the diffusion range and depth of pollutants. These models are based on the principles of fluid mechanics and chemical transport, considering factors such as water flow velocity, direction, and pollutant release amount. Extract the historical and real-time water quality data of the first pollution point and its surrounding area from the spatio-temporal distribution feature matrix to determine the diffusion range of pollution. Combine topographic data and water depth data to calculate the depth of pollutant impact. GIS technology can be used to analyze topographic and water depth information. For example, assume that the pollution diffusion range of the first pollution point C is a radius of 1 km. Through GIS analysis of the water depth data in this area, the impact depth is determined to be 0.5 m.

[0056] Step S340: Conduct a local pollution risk assessment on the target wetland area based on the first spatial coordinate data and the pollutant concentration extreme value data to generate a first risk score. Specifically, use a preset risk assessment model to calculate the local pollution risk in combination with the spatial coordinate data of the first pollution point and the pollutant concentration extreme value data. The risk assessment model can be based on an expert system or a machine learning algorithm and output a risk score. An example of the risk assessment model is as follows: First risk score = ∑(pollutant concentration extreme value score × weight), where dissolved oxygen score = max(0, 6 - dissolved oxygen extreme value), pH score = max(0, 6.5 - pH extreme value, pH extreme value - 8.5), ORP score = max(0, 200 - ORP extreme value, ORP extreme value - 300), turbidity score = max(0, turbidity - 10). Combining the example in Step S330, assume that the weight of dissolved oxygen is 0.6, the weight of pH value is 0.4, the minimum value of dissolved oxygen at the first pollution point C is 4.5 mg / L, and the minimum value of pH is 6.0. Then: First risk score = dissolved oxygen score × 0.6 + pH score × 0.4 = 1.5 × 0.6 + 0.5 × 0.4 = 0.9 + 0.2 = 1.1.

[0057] Step S350, based on the first spatial coordinate data and in combination with the pollutant impact depth data, conduct an overall ecological risk assessment on the target wetland area to generate a second risk score. Specifically, use a preset risk assessment model, in combination with the spatial coordinate data of the first pollution point and the pollutant impact depth data, to calculate the overall ecological risk. The risk assessment model can be based on an expert system or a machine learning algorithm and output a risk score. An example of the risk assessment model is as follows: Second risk score = ∑(pollutant impact depth score × weight). Combining the example in step S330, the pollutant impact depth data of the first pollution point C is as follows: Dissolved oxygen impact depth: 0.5 m, pH value impact depth: 0.5 m. Assuming the impact depth weights of each parameter are as follows: Dissolved oxygen weight: 0.6, pH value weight: 0.4, then: Second risk score = 0.5 × 0.6 + 0.5 × 0.4 = 0.5.

[0058] Step S360, associate and integrate the first risk score and the second risk score to the first pollution point to obtain the multiple risk scores. Specifically, associate and integrate the first risk score and the second risk score to the first pollution point to form a comprehensive risk assessment result. The comprehensive risk assessment result is used to trigger a multimodal warning mechanism and generate an adaptive purification plan.

[0059] In a possible implementation manner, based on the multiple risk scores to trigger a multimodal warning mechanism, step S300 further includes step S370. Conduct a local diffusion analysis on the first pollution point based on the first risk score, draw a local pollution diffusion trend map, conduct an ecological risk analysis on the first pollution point based on the second risk score, and set the overall ecological risk level of the wetland. Specifically, use a pollutant diffusion model (such as the Gaussian diffusion model or numerical simulation method) to simulate the local pollution diffusion of the first pollution point. According to the first risk score, determine the initial conditions of pollution diffusion (such as pollutant concentration, diffusion range, etc.). Draw a local pollution diffusion trend map to show the change of pollution over time and space. According to the second risk score, evaluate the impact of the first pollution point on the overall ecology of the wetland and set the overall ecological risk level of the wetland, which is divided into three levels: low, medium, and high. The specific thresholds are set according to historical data and expert experience. For example, the first risk score of the first pollution point C is 1.1, and the second risk score is 0.5. Use the Gaussian diffusion model, assuming the pollution diffusion range is a radius of 1 km and the impact depth is 0.5 m. Draw a local pollution diffusion trend map to show the change of pollution over time and space. For example, the pollution spreads to within a radius of 1 km within 1 hour and the concentration gradually decreases. According to the second risk score of 0.5, set the overall ecological risk level of the wetland to medium (risk level division standard: low risk: 0 - 0.3; medium risk: 0.3 - 0.7; high risk: 0.7 - 1.0).

[0060] Step S380: Perform pollution diffusion calculation based on the local pollution diffusion trend graph to generate a pollution diffusion rate. Specifically, extract key data from the local pollution diffusion trend graph, such as the distance and time of pollution diffusion. Use a mathematical model (such as linear regression or non - linear fitting) to calculate the pollution diffusion rate. Assume the following data is extracted from the local pollution diffusion trend graph: The pollution spreads within a radius of 1 km within 1 hour. Calculate the pollution diffusion rate: Pollution diffusion rate = Diffusion area ÷ Time = π km 2 ÷1 hour = π km 2 / hour.

[0061] Step S390: Perform wetland self - purification calculation based on the overall wetland ecological risk level to generate a wetland self - purification rate. Specifically, use a wetland ecological model (such as an ecosystem model or a biogeochemical model) to evaluate the self - purification ability of the wetland. For example, the ecosystem model takes into account parameters such as biodiversity, vegetation coverage, water flow velocity, and water depth. The biogeochemical model takes into account parameters such as biodegradation rate, plant absorption rate, etc. According to the overall wetland ecological risk level, adjust the calculation parameters of the self - purification rate. The specific adjustment method can adjust the key parameters in the model, such as biodegradation rate, plant absorption rate, etc., according to different risk levels. For example, if the overall wetland ecological risk level is medium, the biodegradation rate and plant absorption rate can be appropriately reduced to reflect the decline in the wetland self - purification ability.

[0062] Step S3100: Perform a balance analysis based on the pollution diffusion rate and the wetland self - purification rate to generate a dynamic balance coefficient. Specifically, compare the pollution diffusion rate and the wetland self - purification rate to evaluate the balance state of the wetland ecosystem. Use a mathematical model (such as a difference equation or a dynamic system model) to calculate the dynamic balance coefficient. For example, assume the pollution diffusion rate is π km² / hour and the wetland self - purification rate is 10 km² / year. Convert the pollution diffusion rate and the wetland self - purification rate to the same unit (such as km² / year): Pollution diffusion rate = π km 2 / hour × 24 hours / day × 365 days / year = 8760π km 2 / year, calculate the dynamic balance coefficient: Dynamic balance coefficient = Wetland self - purification rate ÷ Pollution diffusion rate = 10 km² / year ÷ 8760π km 2 / year ≈ 0.00036.

[0063] Step S3110, trigger the multi-modal warning mechanism according to the dynamic balance coefficient. Specifically, trigger the multi-modal warning mechanism according to the dynamic balance coefficient. The multi-modal warning mechanism may include multiple methods such as text messages, emails, APP push, etc. Set a warning threshold, and when the dynamic balance coefficient is lower than the set threshold, trigger the warning.

[0064] In a possible implementation manner, when triggering the multi-modal warning mechanism according to the dynamic balance coefficient, step S3110 further includes step S3111, delimit an abnormal critical value according to the parameter abnormal event data, and set an expected balance value range according to the abnormal critical value. Specifically, determine the abnormal critical value of each water quality parameter according to the historical monitoring data and the parameter abnormal event data. The abnormal critical value refers to the value when the parameter value exceeds which, the water quality is considered abnormal. For example, the normal range of dissolved oxygen is 6-10mg / L, and the abnormal critical value can be set to less than 6mg / L; the normal range of pH value is 6.5-8.5, and the abnormal critical value can be set to less than 6.5 or greater than 8.5. Set the expected dynamic balance coefficient value range according to the abnormal critical value and the characteristics of the wetland ecosystem. The expected balance value range reflects the dynamic balance range of the wetland ecosystem in the normal state. For example, set the expected range of the dynamic balance coefficient to 0.0005-0.0010.

[0065] Step S3112, determine whether the dynamic balance coefficient is within the expected balance value range. When the dynamic balance coefficient is not within the expected balance value range, determine the type of the exceeded standard parameter according to the parameter abnormal event data, and determine the spatial distribution characteristics according to the spatio-temporal distribution characteristics. Specifically, compare the calculated dynamic balance coefficient with the expected balance value range to determine whether it is within this range. If the dynamic balance coefficient is lower than the lower limit of the expected range, it indicates that the pollution diffusion rate is much higher than the wetland self-purification rate, and the wetland ecosystem may face a relatively high risk. According to the parameter abnormal event data, determine which parameters exceed the abnormal critical value. For example, if the dissolved oxygen is lower than 6mg / L and the pH value is lower than 6.5, then these parameters are the types of exceeded standard parameters. Determine the spatial distribution characteristics of the exceeded standard parameters according to the spatio-temporal distribution characteristic matrix. For example, analyze the distribution of the exceeded standard parameters in the wetland through GIS technology to determine the concentrated pollution area. Suppose the calculated dynamic balance coefficient is 0.00036, which is lower than the expected balance value range of 0.0005-0.0010. It is detected that the dissolved oxygen is 5.8mg / L (lower than 6mg / L) and the pH value is 6.2 (lower than 6.5), so the types of exceeded standard parameters are dissolved oxygen and pH value. Through GIS technology analysis, it is found that the exceeded standard parameters are mainly concentrated in the southeast area of the wetland, and the specific monitoring points are C and D.

[0066] Step S3113, trigger the multimodal warning mechanism based on the type of excessive parameters and the spatial distribution characteristics. Specifically, according to the type of excessive parameters and the spatial distribution characteristics, trigger the multimodal warning mechanism. The multimodal warning mechanism can include multiple methods such as text messages, emails, and App push notifications. Set a warning threshold, and when the dynamic balance coefficient is lower than the set threshold, trigger a warning. Assume that the set warning threshold is 0.0005 and the dynamic balance coefficient is 0.00036, which is lower than the warning threshold. Send warning messages to the management personnel through methods such as text messages, emails, and App push notifications. The content includes the type of excessive parameters (dissolved oxygen and pH value) and the spatial distribution characteristics (southeast region, monitoring points C and D). Display the warning information on the display screen at the wetland site to remind the surrounding personnel to pay attention.

[0067] In a possible implementation manner, an adaptive purification plan is generated and pushed to the management terminal. Step S300 further includes step S3120, match a multi-level warning mode based on the type of excessive parameters and the spatial distribution characteristics, and generate a multimodal warning linkage instruction according to the matching result. Specifically, according to the type of excessive parameters and the spatial distribution characteristics, select a matching warning mode from a preset multi-level warning mode library. The multi-level warning mode library contains warning strategies corresponding to different types of excessive parameters and spatial distribution characteristics. For example, for the excessive dissolved oxygen and pH value, and mainly concentrated in the southeast region of the wetland, select the corresponding warning mode. Generate a multimodal warning linkage instruction according to the matching warning mode. These instructions can activate the audible and visual alarm, pop-up window on the management terminal, and emergency equipment. For example, generate an instruction to activate the audible and visual alarm device in the southeast region of the wetland, send a pop-up notification to the management terminal at the same time, and start the emergency equipment (such as the aeration system).

[0068] Step S3130, perform adaptive adjustment on the target wetland area through the multimodal warning linkage instruction, and generate an adaptive purification plan. Specifically, perform adaptive adjustment on the target wetland area according to the multimodal warning linkage instruction. The adjustment measures include dynamically adjusting the aeration intensity of the wetland purification system and ecological restoration measures. For example, increase the aeration intensity of the aeration system to improve the dissolved oxygen level; put in biological purifying agents to improve the pH value. Generate an adaptive purification plan according to the adjustment measures. The plan includes specific purification measures, implementation steps, required equipment and materials, etc. For example, the plan recommends increasing the aeration intensity of the aeration system in the southeast region from 100 m³ per hour to 150 m³, and putting in a certain amount of purified algae and microbial agents, including 100 kg of purified algae and 50 kg of microbial agents.

[0069] Step S3140: Push the adaptive purification plan to the management terminal through the blockchain encryption channel, and synchronously update the regulation log of the target wetland area. Specifically, use blockchain technology to securely push the adaptive purification plan to the management terminal through the encryption channel. Blockchain technology ensures the immutability and transparency of data. For example, use the Hyperledger Fabric blockchain framework to encrypt and send the purification plan to the management terminal. Synchronously update the implementation status of the purification plan in the regulation log of the target wetland area. The regulation log records information such as the implementation time, location, and effect of all purification measures. For example, record that at 12:00 on October 1, 2024, the aeration intensity in the southeast region was increased to 150 m³ / h, and 100 kg of algae-purifying agents and 50 kg of microbial inoculants were put in.

[0070] In the above text, reference is made to Figure 1 the method for regulating wetland ecological risks based on multimodal early warning according to an embodiment of the present invention is described in detail. Next, reference will be made to Figure 2 describe a wetland ecological risk regulation system based on multimodal early warning according to an embodiment of the present invention.

[0071] The wetland ecological risk regulation system based on multimodal early warning according to an embodiment of the present invention is used to solve the technical problems of insufficient timeliness, comprehensiveness, and data accuracy of early warning in existing wetland water quality monitoring, and achieve the technical effects of improving the timeliness, comprehensiveness, and data accuracy of early warning in wetland water quality monitoring. The wetland ecological risk regulation system based on multimodal early warning includes: a dynamic water quality data set generation module 10, a water quality detection sequence determination module 20, and an adaptive purification plan generation module 30.

[0072] The dynamic water quality data set generation module 10 is used to collect the physicochemical parameters of the wetland water body in real time and generate a dynamic water quality data set; the water quality detection sequence determination module 20 is used to detect and optimize the dynamic water quality data set according to the historical abnormal data frequency to determine the water quality detection sequence; the adaptive purification plan generation module 30 is used to perform multi-level risk assessment on the target wetland area according to the water quality detection sequence, obtain multiple risk scores, trigger a multimodal early warning mechanism based on the multiple risk scores, generate an adaptive purification plan and push it to the management terminal.

[0073] Next, the specific configuration of the water quality detection sequence determination module 20 will be described in detail. As described above, the dynamic water quality data set is detected and optimized according to the historical anomaly data frequency to determine the water quality detection sequence. The water quality detection sequence determination module 20 may further include: a spatio-temporal distribution feature matrix construction unit for performing anomaly analysis on multi-source water quality parameters in the target wetland area according to the historical monitoring period to determine parameter anomaly event data, and constructing a spatio-temporal distribution feature matrix according to the parameter anomaly event data; an anomaly correlation calculation unit for performing anomaly correlation calculation on the multi-source water quality parameters based on the spatio-temporal distribution feature matrix to generate a parameter detection priority weight matrix; a detection sorting unit for sorting the detection of the multi-source sensor network according to the parameter detection priority weight matrix to construct the water quality detection sequence.

[0074] Among them, when performing anomaly correlation calculation on the multi-source water quality parameters based on the spatio-temporal distribution feature matrix to generate a parameter detection priority weight matrix, the anomaly correlation calculation unit may further include: an anomaly event determination subunit for performing anomaly analysis on the multi-source water quality parameters based on the spatio-temporal distribution feature matrix to determine a plurality of anomaly events, and the plurality of anomaly events include a plurality of anomaly occurrence probabilities; a spatial correlation analysis subunit for performing spatial correlation analysis on the plurality of anomaly events according to the plurality of anomaly occurrence probabilities to obtain the spatial aggregation characteristics of the plurality of anomaly events; a weight assignment subunit for traversing the target wetland area according to the spatial aggregation characteristics to assign weights to adjacent monitoring nodes to construct the parameter detection priority weight matrix.

[0075] Among them, when sorting the detection of the multi-source sensor network according to the parameter detection priority weight matrix to construct the water quality detection sequence, the detection sorting unit may further include: a water quality exceeding standard event determination subunit for traversing the target wetland area to perform water quality exceeding standard analysis to determine a water quality exceeding standard event, and the water quality exceeding standard event includes spatio-temporal distribution characteristics, and the spatio-temporal distribution characteristics have a corresponding relationship with the water quality exceeding standard event; a detection identification subunit for mapping to the multi-source sensor network according to the parameter detection priority weight matrix for detection identification to determine a plurality of sensing priority identifications; a detection task descending order assignment subunit for performing detection task descending order assignment according to the plurality of sensing priority identifications to construct the water quality detection sequence.

[0076] Next, the specific configuration of the adaptive purification scheme generation module 30 will be described in detail. As described above, a multi-level risk assessment is performed on the target wetland area according to the water quality detection sequence to obtain multiple risk scores. The adaptive purification scheme generation module 30 may further include: a first pollution point determination unit for traversing the target wetland area according to the water quality detection sequence to determine the first pollution point; a first spatial coordinate data extraction unit for constructing a spatial coordinate system of the target wetland area and extracting the first spatial coordinate data of the first pollution point; a pollution impact data set determination unit for performing pollution analysis according to the spatio-temporal distribution feature matrix in combination with the first spatial coordinate data to determine a pollution impact data set, where the pollution impact data set includes pollutant concentration extreme value data and pollutant impact depth data; a local pollution risk assessment unit for performing a local pollution risk assessment on the target wetland area according to the first spatial coordinate data in combination with the pollutant concentration extreme value data to generate a first risk score; an overall ecological risk assessment unit for performing an overall ecological risk assessment on the target wetland area according to the first spatial coordinate data in combination with the pollutant impact depth data to generate a second risk score; an association integration unit for associating and integrating the first risk score and the second risk score to the first pollution point to obtain the multiple risk scores.

[0077] Among them, based on the multiple risk scores to trigger a multi-modal warning mechanism, the adaptive purification scheme generation module 30 may further include: a first pollution point analysis unit for performing a local diffusion analysis on the first pollution point based on the first risk score, drawing a local pollution diffusion trend diagram, performing an ecological risk analysis on the first pollution point based on the second risk score, and setting the overall ecological risk level of the wetland; a pollution diffusion calculation unit for performing pollution diffusion calculation based on the local pollution diffusion trend diagram to generate a pollution diffusion rate; a wetland self-purification calculation unit for performing wetland self-purification calculation based on the overall ecological risk level of the wetland to generate a wetland self-purification rate; a balance analysis unit for performing a balance analysis according to the pollution diffusion rate and the wetland self-purification rate to generate a dynamic balance coefficient; a multi-modal warning mechanism trigger unit for triggering the multi-modal warning mechanism according to the dynamic balance coefficient.

[0078] Among them, the multi-modal warning mechanism is triggered according to the dynamic balance coefficient. The multi-modal warning mechanism triggering unit may further include: an expected balance numerical range setting subunit for demarcating an abnormal critical value according to the parameter abnormal event data and setting an expected balance numerical range according to the abnormal critical value; a judgment subunit for judging whether the dynamic balance coefficient is within the expected balance numerical range. When the dynamic balance coefficient is not within the expected balance numerical range, determining the type of over-standard parameter according to the parameter abnormal event data and determining the spatial distribution characteristics according to the spatio-temporal distribution characteristics; a multi-modal warning mechanism triggering subunit for triggering the multi-modal warning mechanism based on the over-standard parameter type and the spatial distribution characteristics.

[0079] Among them, an adaptive purification plan is generated and pushed to the management terminal. The adaptive purification plan generation module 30 may further include: a multi-modal warning linkage instruction generation unit for matching a multi-level warning mode based on the over-standard parameter type and the spatial distribution characteristics and generating a multi-modal warning linkage instruction according to the matching result; an adaptive adjustment unit for adaptively adjusting the target wetland area through the multi-modal warning linkage instruction to generate an adaptive purification plan; a plan pushing unit for pushing the adaptive purification plan to the management terminal through a blockchain encryption channel and synchronously updating the regulation log of the target wetland area.

[0080] The wetland ecological risk regulation system based on multi-modal warning provided by the embodiments of the present invention can execute the wetland ecological risk regulation method provided by any embodiment of the present invention, and has corresponding function modules and beneficial effects for executing the method.

[0081] Although various references are made to certain modules in the system of the embodiments according to the present application, any number of different modules may be used and run on the user terminal and / or the server. The included individual units and modules are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0082] Based on the foregoing embodiments, the embodiments of the present application further provide an electronic device. Figure 3 It is a schematic structural diagram of the electronic device provided by the embodiment of the present invention, showing a block diagram of an exemplary electronic device suitable for implementing the embodiment of the present invention. Figure 3The electronic device shown is merely an example and should not impose any limitations on the functions and scope of use of the embodiments of the present invention. The electronic device is presented in the form of a general-purpose computing device, and its components may include, but are not limited to, an input device 301, a processor 302, a memory 303, and an output device 304. Among them, the processor 302 may be one or more; the memory 303 may include a computer-readable medium and at least one program product, and this program product has a set (at least one) of program modules, and these program modules are configured to execute the functions of the embodiments of the present application.

[0083] The memory 303 shown in the embodiments of the present invention may adopt any combination of one or more computer-readable media; the computer-readable storage medium may be, but is not limited to, infrared rays, semiconductor systems, devices or components, or any combination of the above, for storing software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the wetland ecological risk regulation method based on multi-modal warning in the embodiments of the present invention. The processor 302 executes various functional applications and data processing of the computer device by running the software programs, instructions, and modules stored in the memory 303, that is, implements the above-mentioned wetland ecological risk regulation method based on multi-modal warning.

[0084] The above specific implementation manners do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand 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 principle of the present application shall be included within the protection scope of the present application. In some cases, the actions or steps recorded in the present application may be executed in a different order from that in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In certain embodiments, multi-tasking and parallel processing are also possible or may be advantageous.

Claims

1. A wetland ecological risk regulation method based on multimodal early warning, characterized in that The method includes: Collecting the physicochemical parameters of wetland water bodies in real time to generate a dynamic water quality data set; Detecting and optimizing the dynamic water quality data set according to the historical anomaly data frequency to determine a water quality detection sequence; Performing multi-level risk assessment on the target wetland area according to the water quality detection sequence to obtain multiple risk scores, triggering a multi-modal early warning mechanism based on the multiple risk scores, generating an adaptive purification plan and pushing it to the management terminal.

2. The wetland ecological risk regulation method based on multi-modal early warning according to claim 1, wherein Detecting and optimizing the dynamic water quality data set according to the historical anomaly data frequency to determine a water quality detection sequence, the method including: Performing anomaly analysis on the multi-source water quality parameters of the target wetland area according to the historical monitoring cycle to determine parameter anomaly event data, and constructing a spatio-temporal distribution feature matrix according to the parameter anomaly event data; Performing anomaly correlation calculation on the multi-source water quality parameters based on the spatio-temporal distribution feature matrix to generate a parameter detection priority weight matrix; Sorting the detection of the multi-source sensor network according to the parameter detection priority weight matrix to construct the water quality detection sequence.

3. The wetland ecological risk regulation method based on multimodal early warning according to claim 2, wherein, Performing anomaly correlation calculation on the multi-source water quality parameters based on the spatio-temporal distribution feature matrix to generate a parameter detection priority weight matrix, the method including: Performing anomaly analysis on the multi-source water quality parameters based on the spatio-temporal distribution feature matrix to determine multiple anomaly events, the multiple anomaly events including multiple anomaly occurrence probabilities; Performing spatial correlation analysis on the multiple anomaly events according to the multiple anomaly occurrence probabilities to obtain the spatial aggregation characteristics of the multiple anomaly events; Traversing the target wetland area according to the spatial aggregation characteristics to assign weights to adjacent monitoring nodes to construct the parameter detection priority weight matrix.

4. The wetland ecological risk regulation method based on multi-modal early warning according to claim 2, wherein, Sorting the detection of the multi-source sensor network according to the parameter detection priority weight matrix to construct the water quality detection sequence, the method including: Traversing the target wetland area to perform water quality exceedance analysis to determine water quality exceedance events, the water quality exceedance events including spatio-temporal distribution characteristics, and the spatio-temporal distribution characteristics having a corresponding relationship with the water quality exceedance events; Mapping to the multi-source sensor network according to the parameter detection priority weight matrix for detection identification to determine multiple sensing priority identifications; Performing descending order assignment of detection tasks according to the multiple sensing priority identifications to construct the water quality detection sequence.

5. The wetland ecological risk regulation method based on multi-modal early warning according to claim 4, characterized in that, Performing multi-level risk assessment on the target wetland area according to the water quality detection sequence to obtain multiple risk scores, the method including: Traversing the target wetland area according to the water quality detection sequence to determine the first pollution point; Constructing a spatial coordinate system of the target wetland area and extracting the first spatial coordinate data of the first pollution point; Performing pollution analysis according to the spatio-temporal distribution feature matrix in combination with the first spatial coordinate data to determine a pollution impact data set, the pollution impact data set including pollutant concentration extreme value data and pollutant impact depth data; Performing local pollution risk assessment on the target wetland area according to the first spatial coordinate data in combination with the pollutant concentration extreme value data to generate a first risk score; Based on the first spatial coordinate data and combined with the pollutant impact depth data, conduct an overall ecological risk assessment of the target wetland area to generate a second risk score; Associate and integrate the first risk score and the second risk score to the first pollution point to obtain the multiple risk scores.

6. The wetland ecological risk regulation method based on multi-modal early warning according to claim 5, wherein, Trigger a multimodal early warning mechanism based on the multiple risk scores. The method includes: Conduct a local diffusion analysis of the first pollution point based on the first risk score, draw a local pollution diffusion trend map, conduct an ecological risk analysis of the first pollution point based on the second risk score, and set the overall ecological risk level of the wetland; Conduct pollution diffusion calculation based on the local pollution diffusion trend map to generate a pollution diffusion rate; Conduct wetland self-purification calculation based on the overall ecological risk level of the wetland to generate a wetland self-purification rate; Conduct a balance analysis based on the pollution diffusion rate and the wetland self-purification rate to generate a dynamic balance coefficient; Trigger the multimodal early warning mechanism according to the dynamic balance coefficient.

7. The wetland ecological risk regulation method based on multi-modal early warning according to claim 6, wherein, Trigger the multimodal early warning mechanism according to the dynamic balance coefficient. The method includes: Define an abnormal critical value according to the parameter abnormal event data, and set an expected balance numerical range according to the abnormal critical value; Judge whether the dynamic balance coefficient is within the expected balance numerical range. When the dynamic balance coefficient is not within the expected balance numerical range, determine the type of exceeded standard parameter according to the parameter abnormal event data, and determine the spatial distribution characteristics according to the spatio-temporal distribution characteristics; Trigger the multimodal early warning mechanism based on the type of exceeded standard parameter and the spatial distribution characteristics.

8. The wetland ecological risk regulation method based on multimodal early warning according to claim 7, characterized in that The process of generating an adaptive purification plan and pushing it to the management terminal. The method includes: Match a multi-level early warning mode based on the type of exceeded standard parameter and the spatial distribution characteristics, and generate a multimodal early warning linkage instruction according to the matching result; Conduct an adaptive adjustment of the target wetland area through the multimodal early warning linkage instruction to generate an adaptive purification plan; Push the adaptive purification plan to the management terminal through the blockchain encryption channel, and synchronously update the regulation log of the target wetland area.

9. A wetland ecological risk regulation system based on multimodal early warning, characterized in that, The system is used to implement the wetland ecological risk regulation method based on multimodal early warning according to any one of claims 1-8. The system includes: A dynamic water quality data set generation module, which is used to collect the physical and chemical parameters of the wetland water body in real time and generate a dynamic water quality data set; A water quality detection sequence determination module, which is used to detect and optimize the dynamic water quality data set according to the historical abnormal data frequency to determine the water quality detection sequence; An adaptive purification plan generation module, which is used to conduct a multi-level risk assessment of the target wetland area according to the water quality detection sequence, obtain multiple risk scores, trigger a multimodal early warning mechanism based on the multiple risk scores, generate an adaptive purification plan and push it to the management terminal.

10. An electronic device, characterized in that, The electronic device includes: A memory, which is used to store executable instructions; A processor, which is used to implement the wetland ecological risk regulation method based on multimodal early warning according to any one of claims 1 to 8 when executing the executable instructions stored in the memory.

Images