Water environment dynamic monitoring system and method based on data analysis

Abstract

The present application relates to the technical field of water environment data processing, and specifically discloses a water environment dynamic monitoring system and method based on data analysis, which constructs a multi-source water environment monitoring dataset by acquiring multi-source water environment monitoring data in real time, extracts multi-source water environment features based on the multi-source water environment monitoring dataset, constructs a river disturbance stage recognition mechanism according to the multi-source water environment features to capture the disturbance stage of the river, builds a credibility evaluation model based on a monitoring data sliding analysis window to extract credibility evaluation indexes and analyze the credibility state of the water environment monitoring data, acquires multi-source water environment monitoring data that has passed credibility evaluation, inputs a sediment pollution release contribution analysis mechanism to calculate the sediment pollution release contribution rate, dynamically optimizes the dredging sequence of each monitoring section of the river based on the pollutant change trend, and determines a dredging optimization scheme. The present application can master the change law of the river water environment in real time and improve the intelligent level of river pollution monitoring and treatment.

Description

Technical Field

[0001] This invention relates to the field of water environment data processing technology, and more specifically, to a water environment dynamic monitoring system and method based on data analysis. Background Technology

[0002] In recent years, with the widespread application of intelligent water environment monitoring systems, water bodies such as rivers, reservoirs, and lakes are typically monitored in real time using online monitoring equipment. The monitoring results are then used to develop plans for river dredging, ecological restoration, and pollution control. However, in actual operation, heavy rainfall often causes drastic fluctuations in water environment parameters. On the one hand, surface runoff from heavy rainfall carries sediment, fallen leaves, and non-point source pollutants into rivers, leading to a rapid increase in turbidity, suspended solids concentration, and some pollution indicators within a short period. On the other hand, heavy rainfall also causes rapid changes in river velocity, water level, and flow pattern, triggering resuspension of bottom sediments and releasing pollutants deposited in the riverbed back into the water, resulting in abrupt changes in online monitoring data. In such cases, it is difficult to accurately distinguish anomalies in the monitoring data, easily leading to distorted monitoring results and affecting the accurate assessment of the water environment status.

[0003] Meanwhile, most existing river dredging operations rely on fixed cycles, manual inspections, or single monitoring results to determine the timing of implementation, lacking comprehensive analysis of the impact of rainstorm events and the dynamic changes in sediment. When rainstorms cause sediment disturbance, monitoring indicators may show a short-term increase, but in some cases, this is a natural disturbance process and does not necessarily mean that the sediment pollution level has reached the point where dredging is necessary. Furthermore, for river sections with long-term sediment pollution accumulation and continuous release of pollutants after rainstorms, existing methods are insufficient to identify the true risks in a timely manner, easily leading to delayed dredging or over-dredging. This not only increases treatment costs but may also affect the ecological stability of the river channel due to repeated disturbance of the sediment.

[0004] Therefore, it is necessary to provide a water environment dynamic monitoring system and method based on data analysis to solve the above-mentioned technical problems. In order to solve the above problems, a technical solution is provided. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art, this invention provides a dynamic water environment monitoring system and method based on data analysis, which addresses the problem of how to accurately identify abnormal monitoring data under heavy rain conditions, dynamically assess river dredging needs, and determine the optimal dredging timing.

[0006] To achieve the above objectives, the present invention provides the following technical solution: The data analysis-based dynamic water environment monitoring system includes a multi-source data monitoring module, a river disturbance stage identification module, a data credibility assessment module, a sediment pollution release contribution analysis module, and a dredging optimization determination module. The multi-source data monitoring module is used to acquire multi-source water environment monitoring data from various monitoring sections of the target river in real time, perform synchronous preprocessing according to a unified time axis, and construct a multi-source water environment monitoring dataset; the water environment monitoring data includes water quality monitoring data, hydrodynamic parameters, meteorological parameters, and sediment parameters; The river disturbance stage identification module is used to extract multi-source water environment features based on multi-source water environment monitoring datasets, construct a river disturbance stage identification mechanism based on multi-source water environment features, and capture the disturbance stage of the river. The data credibility assessment module is used to build a credibility assessment model based on the sliding analysis window of monitoring data, extract credibility assessment indicators, and analyze the credibility status of water environment monitoring data. The sediment pollution release contribution analysis module is used to acquire multi-source water environment monitoring data that has passed the credibility assessment, input the sediment pollution release contribution analysis mechanism, and calculate the sediment pollution release contribution rate. The dredging optimization determination module is used to dynamically optimize the dredging sequence of each monitoring section of the river based on the pollutant change trend, and to determine the dredging optimization scheme.

[0007] As a further aspect of the present invention, the river disturbance stage identification module is used to extract multi-source water environment features based on a multi-source water environment monitoring dataset, and to construct a river disturbance stage identification mechanism based on the multi-source water environment features to capture the disturbance stage of the river, as detailed below: Multi-source water environment features are extracted from multi-source water environment monitoring data, and a water environment feature vector is constructed. The multi-source water environment features include rainfall intensity growth rate, water level change rate, flow velocity change rate, turbidity change rate, and flow rate change rate. Based on the characteristics of multi-source water environment, a mechanism for identifying river disturbance stages is constructed, and a comprehensive river disturbance index is built to determine the river disturbance stage.

[0008] As a further aspect of the present invention, a river disturbance stage identification mechanism is constructed based on the characteristics of multi-source water environment, the comprehensive river disturbance index is analyzed, and the river disturbance stage is determined. The specific steps are as follows: The characteristics of multi-source water environment are obtained and normalized, and weighting coefficients are assigned according to the degree of influence of each multi-source water environment characteristic on rainstorm disturbance. The characteristics of multi-source water environment and their corresponding weighting coefficients are input into the river disturbance stage identification mechanism. Based on the comprehensive river disturbance index, the stage of river disturbance is determined.

[0009] As a further aspect of the present invention, determining the river disturbance stage of the river channel specifically involves: comparing the comprehensive river disturbance index with a preset disturbance threshold range; if the comprehensive river disturbance index is greater than the upper limit of the preset disturbance threshold range, the river channel is in a first-level disturbance stage, where the river disturbance is severe; if the comprehensive river disturbance index is within the preset disturbance threshold range, the river channel is in a second-level disturbance stage, where there is no disturbance in the river channel, but disturbance exists; if the comprehensive river disturbance index is less than the lower limit of the preset disturbance threshold range, the river channel is in a third-level disturbance stage, where there is no disturbance in the river channel.

[0010] As a further aspect of the present invention, the data reliability assessment module is used to perform reliability assessment by extracting multi-source water environment monitoring data corresponding to the disturbance stage of the river channel, and to obtain the monitoring reliability coefficient to analyze the source of anomalies in the monitoring data, as follows: Extract multi-source water environment monitoring data corresponding to the disturbance stage of the river channel and construct a sliding analysis window for the monitoring data; Based on the sliding analysis window of the monitoring data, credibility assessment indicators are extracted, a credibility assessment model is built based on the credibility assessment indicators, and the monitoring credibility coefficient is calculated. An anomaly source analysis model is constructed based on the credibility coefficient to analyze the sources of anomalies in the monitoring data and generate a credibility evaluation result for the monitoring data.

[0011] As a further aspect of the present invention, the data credibility assessment module is used to build a credibility assessment model based on a sliding analysis window of monitoring data, extract credibility assessment indicators, and analyze the credibility status of water environment monitoring data, as follows: Reliability assessment indicators are extracted based on a sliding analysis window of monitoring data; Based on the credibility assessment index, the credibility status of water environment monitoring data is judged and analyzed. The credibility assessment index is compared with the preset credibility threshold. If the credibility assessment index is greater than or equal to the preset credibility threshold, the credibility of the water environment monitoring data is unqualified. If the credibility assessment index is less than the preset credibility threshold, the credibility of the water environment monitoring data is qualified.

[0012] As a further aspect of the present invention, the credibility assessment index is specifically as follows: the multi-source water environment characteristics are calculated per unit time using water environment monitoring data, the average rate of change of monitoring data within the sliding analysis window of the monitoring data is analyzed, and a credibility assessment index is constructed based on the multi-source water environment characteristics and the average rate of change of monitoring data.

[0013] As a further aspect of the present invention, the sediment pollution release contribution analysis module is used to acquire multi-source water environment monitoring data that has passed the reliability assessment, input the sediment pollution release contribution analysis mechanism, and calculate the sediment pollution release contribution rate, as follows: Obtain multi-source water environment monitoring data with acceptable reliability, input the multi-source water environment monitoring data into the sediment pollution release contribution analysis mechanism, calculate the sediment pollution release contribution amount, calculate the sediment pollution release contribution concentration based on the sediment pollution release contribution amount, and calculate the sediment pollution release contribution rate based on the ratio of sediment pollution release contribution concentration to pollutant concentration.

[0014] The data analysis-based dynamic monitoring method for the water environment includes the following steps: By acquiring multi-source water environment monitoring data from various monitoring sections of the target river in real time, and performing synchronous preprocessing according to a unified timeline, a multi-source water environment monitoring dataset is constructed. The water environment monitoring data includes water quality monitoring data, hydrodynamic parameters, meteorological parameters, and sediment parameters. Based on the multi-source water environment monitoring dataset, multi-source water environment characteristics are extracted, and a river disturbance stage identification mechanism is constructed according to the multi-source water environment characteristics to capture the disturbance stage of the river. A credibility assessment model was built based on a sliding analysis window of monitoring data to extract credibility assessment indicators and analyze the credibility status of water environment monitoring data. Acquire multi-source water environment monitoring data that have passed the credibility assessment, input them into the sediment pollution release contribution analysis mechanism, and calculate the sediment pollution release contribution rate. Based on the changing trends of pollutants, the dredging sequence of each monitoring section of the river is dynamically optimized, and the dredging optimization plan is determined.

[0015] A readable storage medium storing a computer program, which, when executed by a processor, is used to implement the data analysis-based dynamic monitoring system for the water environment as described in any of the above claims.

[0016] The technical effects and advantages of this invention's data-driven dynamic water environment monitoring system and method are as follows: This invention simultaneously acquires multi-dimensional information such as water quality, hydrodynamics, meteorology, sediment, and river operation through a multi-source data monitoring module. This overcomes the limitations of traditional water environment monitoring that relies on a single pollution indicator, providing a more comprehensive reflection of the actual river's operational status and improving the ability to perceive river conditions under complex environments. By setting up a river disturbance stage identification module, potential risks such as rainstorm erosion, pollution diffusion, and sediment resuspension can be detected in advance, providing early warning for subsequent pollution control. This invention not only determines the reliability of monitoring data but also analyzes the sources of anomalies by combining data change patterns, enabling the system to distinguish between real environmental changes and equipment malfunctions, thus improving the credibility of pollution analysis results. The sediment pollution release contribution analysis module effectively identifies the impact of endogenous pollution, providing a more accurate basis for determining whether dredging and remediation are necessary, avoiding resource waste caused by indiscriminate dredging. The dredging optimization module dynamically adjusts the dredging sequence based on pollution change trends and pollution risk levels, enabling treatment measures to be implemented preferentially in severely polluted areas. This improves river management efficiency, reduces treatment costs, and minimizes the impact of unnecessary engineering disturbances on the river's ecological environment. Attached Figure Description

[0017] Figure 1 A system diagram of a water environment dynamic monitoring system based on data analysis provided in an embodiment of the present invention; Figure 2 This is a flowchart illustrating the dynamic monitoring method for water environment based on data analysis provided in an embodiment of the present invention. Detailed Implementation

[0018] The technical solutions of this invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described technical solutions are only a part of this invention, and not all of it. All other technical solutions obtained by those skilled in the art based on the technical solutions of this invention without inventive effort are within the scope of protection of this invention.

[0019] like Figure 1 The diagram shown is a system diagram of a water environment dynamic monitoring system based on data analysis provided in an embodiment of the present invention. The water environment dynamic monitoring system based on data analysis includes a multi-source data monitoring module, a river disturbance stage identification module, a data credibility assessment module, a sediment pollution release contribution analysis module, and a dredging optimization determination module. The multi-source data monitoring module is connected to the river disturbance stage identification module, the river disturbance stage identification module is connected to the data credibility assessment module, the data credibility assessment module is connected to the sediment pollution release contribution analysis module, and the sediment pollution release contribution analysis module is connected to the dredging optimization determination module.

[0020] The multi-source data monitoring module is used to acquire multi-source water environment monitoring data from various monitoring sections of the target river in real time, perform synchronous preprocessing according to a unified time axis, and construct a multi-source water environment monitoring dataset. The water environment monitoring data includes water quality monitoring data, hydrodynamic parameters, meteorological parameters, and sediment parameters; specifically, water quality monitoring data includes turbidity and pollutant concentration; hydrodynamic parameters include water depth, flow velocity, flow direction, water temperature, and flow rate; meteorological parameters include rainfall, rainfall intensity, wind speed, and air temperature; and sediment parameters include sediment thickness and suspended solids concentration.

[0021] This invention, through the establishment of multiple monitoring sections at different locations along a target river channel, continuously collects various types of water environment monitoring data and synchronously processes the collected data according to a unified timeline to construct a complete multi-source water environment monitoring dataset. It acquires water quality monitoring data, hydrodynamic parameters, meteorological parameters, sediment parameters, and river operation parameters from each monitoring section. The water quality monitoring data includes indicators reflecting the river's pollution status, such as turbidity and pollutant concentration. Hydrodynamic parameters include indicators describing the pollutant migration and diffusion environment, such as water depth, flow velocity, flow direction, water temperature, and flow rate. Meteorological parameters include indicators characterizing external environmental influencing factors, such as rainfall, rainfall intensity, wind speed, and air temperature. Sediment parameters include indicators reflecting the storage of endogenous pollution sources and the state of sediment disturbance, such as sediment thickness and suspended solids concentration. River operation parameters record operational status information such as gate control, water replenishment and drainage, and manual scheduling.

[0022] Due to inconsistencies in sampling cycles, data formats, and time bases among different monitoring devices, this module performs unified timeline mapping on the acquired multi-source monitoring data. It achieves synchronous correlation of data from different sources through timestamp matching and further employs methods such as outlier removal, missing data compensation, noise filtering, and data standardization to improve the quality of monitoring data. Ultimately, it forms a multi-source water environment monitoring dataset containing different time nodes and monitoring sections, providing a continuous and reliable data foundation for subsequent river disturbance stage identification, data credibility assessment, sediment pollution release contribution analysis, and pollution trend prediction, thereby enabling dynamic monitoring of the river water environment status.

[0023] The river disturbance stage identification module is used to extract multi-source water environment features based on multi-source water environment monitoring datasets, construct a river disturbance stage identification mechanism based on multi-source water environment features, and capture the disturbance stage of the river.

[0024] This invention analyzes the impact of multi-source water environment monitoring data on the current external environmental changes and internal operational changes of a river channel, constructing a river disturbance stage identification mechanism to dynamically judge different disturbance states of the river channel. Based on the characteristics of the multi-source water environment, it comprehensively considers factors such as water quality changes, hydrodynamic changes, meteorological changes, and sediment state changes to extract key characteristic parameters that can reflect the degree of river channel disturbance. Specifically, it analyzes water quality disturbance characteristics based on pollutant concentration changes, and determines whether the river pollution state has undergone abnormal changes by calculating the pollutant concentration change rate, concentration fluctuation degree, and pollutant growth trend; simultaneously, it analyzes changes in river flow state based on hydrodynamic parameters such as flow velocity, flow rate, and water depth to determine whether hydrodynamics have strengthened or weakened; combined with meteorological parameters such as rainfall and rainfall intensity, it identifies external disturbance factors such as rainfall erosion and non-point source pollution input; further, it combines suspended solids concentration and sediment parameter changes to determine whether the sediment has been disturbed by water flow and has released pollutants.

[0025] After extracting the aforementioned disturbance characteristics, various disturbance indicators are fused and calculated to construct a comprehensive river disturbance index. By setting different disturbance level thresholds, the river state is divided into different states, such as a stable stage, a slightly disturbed stage, a strongly disturbed stage, and a disturbance recovery stage, enabling continuous identification of the river disturbance process. This module can clearly define the disturbance background of current river pollution changes, providing a state-based basis for subsequent data reliability analysis, sediment pollution release contribution calculation, and pollution control plan formulation, thereby improving the accuracy and targeting of river pollution monitoring.

[0026] The data credibility assessment module is used to build a credibility assessment model based on the sliding analysis window of monitoring data, extract credibility assessment indicators, and analyze the credibility status of water environment monitoring data.

[0027] This invention establishes a comprehensive reliability assessment model through weighted fusion, calculates the monitoring reliability coefficient for each monitoring section, and judges the data reliability status based on a preset threshold. When the monitoring data reliability meets the qualified standard, it is used as input data for subsequent pollution analysis and prediction models; when the data reliability is insufficient, it is judged as abnormal data and is removed or corrected. This module can effectively improve the reliability of multi-source monitoring data and avoid interference from sensor malfunctions, data transmission errors, and local anomalies on river pollution analysis results. The sediment pollution release contribution analysis module is used to acquire multi-source water environment monitoring data that has passed the credibility assessment, input the sediment pollution release contribution analysis mechanism, and calculate the sediment pollution release contribution rate.

[0028] This invention converts the amount of sediment pollution released into a corresponding pollutant concentration contribution value based on the water volume relationship at the monitoring section. Combined with the actual pollutant concentrations obtained from water environment monitoring data, the sediment pollution release contribution rate is calculated. The calculated sediment pollution release contribution rate can determine whether the current river pollution mainly originates from internal sediment release or external pollution input. A high sediment pollution release contribution rate indicates that sediment pollution release has a significant impact on water quality deterioration, requiring priority consideration of dredging and remediation measures. A low contribution rate indicates that pollution mainly originates from external input, necessitating focused pollution source control. This achieves quantitative analysis of river pollution sources, providing a basis for subsequent dredging optimization decisions. The dredging optimization module is used to dynamically optimize the dredging sequence of each monitoring section of the river based on pollutant change trends, and to determine the optimal dredging scheme. Specifically, by arranging the contribution rate of sediment pollution release in descending order of value, the dredging sequence of the river sections is determined accordingly, and the optimization scheme is determined based on the dredging sequence.

[0029] This invention comprehensively considers the severity of pollution, pollution growth trends, contribution of sediment pollution release, and river operating conditions at different monitoring sections to rank the risks of each monitoring section and determine priority treatment areas. For example, sections with predicted continuously rising pollution concentrations, high sediment pollution contribution rates, and obvious pollution accumulation trends are given higher dredging priorities; sections with stable pollution changes and low pollution risk have lower dredging priorities. After determining the dredging priorities, the dredging sequence, scope, and implementation time are further optimized by considering factors such as dredging resource allocation, construction impact range, river ecological protection requirements, and treatment costs, forming a dynamic dredging optimization plan. Compared to the traditional method of carrying out dredging according to a fixed cycle, this approach can adjust the treatment strategy in real time according to changes in river pollution status, realizing a shift from passive treatment to proactive predictive treatment, improving the targeting and effectiveness of river dredging work, reducing resource waste caused by ineffective dredging, and enhancing the long-term stability maintenance capacity of the river water environment.

[0030] It should be noted that all parameter data involved in the model calculation must undergo preprocessing operations including dimensionless transformation.

[0031] Preferably, the river disturbance stage identification module is used to extract multi-source water environment features based on the multi-source water environment monitoring dataset, construct a river disturbance stage identification mechanism based on the multi-source water environment features, and capture the disturbance stage of the river, as follows: Multi-source water environment characteristics are extracted based on multi-source water environment monitoring data, and a water environment feature vector is constructed. These multi-source water environment characteristics include rainfall intensity growth rate, water level change rate, flow velocity change rate, turbidity change rate, and flow rate change rate. The calculation formulas for these multi-source water environment characteristics are as follows: In the formula: The characteristics of the multi-source water environment of type a at time t are as follows: The data for the multi-source water environment at time t is for category a. for Time-based Class A multi-source water environment monitoring data, For time intervals; Based on the characteristics of multi-source water environment, a mechanism for identifying river disturbance stages is constructed, and a comprehensive river disturbance index is built to determine the river disturbance stage.

[0032] Preferably, a river disturbance stage identification mechanism is constructed based on the characteristics of multi-source water environment, the comprehensive river disturbance index is analyzed, and the river disturbance stage is determined. The specific steps are as follows: The characteristics of multi-source water environment are obtained and normalized, and weighting coefficients are assigned according to the degree of influence of each multi-source water environment characteristic on rainstorm disturbance. The multi-source water environment characteristics and corresponding weighting coefficients are input into the river disturbance stage identification mechanism. The specific formula for analyzing the comprehensive river disturbance index is as follows: In the formula: The comprehensive index of river disturbance is represented by A, which is the total number of multi-source water environment characteristics. The weighting coefficients for the multi-source water environment characteristics of the monitoring data of category a are given. For the characteristics of the multi-source water environment of type a at time t, the river disturbance stage is determined based on the comprehensive river disturbance index. Specifically, the comprehensive river disturbance index is compared with a preset disturbance threshold range. If the comprehensive river disturbance index is greater than the upper limit of the preset disturbance threshold range, the river disturbance stage is a first-level disturbance stage, where the river disturbance is severe. If the comprehensive river disturbance index is within the preset disturbance threshold range, the river disturbance stage is a second-level disturbance stage, where the river is undisturbed. If the comprehensive river disturbance index is less than the lower limit of the preset disturbance threshold range, the river disturbance stage is a third-level disturbance stage, where the river is undisturbed.

[0033] In a practical application scenario of river water environment monitoring, taking the dynamic monitoring of pollution status in a city river during a rainstorm as an example, this invention sets up multiple monitoring sections along the target river at key locations such as upstream, midstream, and downstream. Online water environment monitoring equipment is deployed at each monitoring section to collect multi-source monitoring data in real time, including rainfall, water level, flow velocity, flow rate, turbidity, and pollutant concentration. When heavy rainfall occurs in the region, the runoff enters the river, changing the river's hydrodynamic conditions and potentially causing bank erosion, sediment disturbance, and increased pollutant concentration. Therefore, it is necessary to quickly identify the current disturbance state of the river.

[0034] The system acquires multi-source water environment monitoring data from various monitoring sections over continuous time periods. For example, the sampling period is set to 5 minutes to acquire real-time data on rainfall intensity, water level, flow velocity, turbidity, and flow rate at both the current and historical times. For each type of monitoring data, corresponding change characteristics are calculated at uniform time intervals. These include rainfall intensity growth rate, water level change rate, flow velocity change rate, turbidity change rate, and flow rate change rate, reflecting the degree of change of different environmental factors over time. For instance, during a heavy rainfall event, the monitoring system detects a continuous increase in rainfall intensity, leading to a rapid rise in river water level, a significant increase in flow velocity and flow rate, and a rapid increase in turbidity due to sediment erosion. In this case, the calculated high rainfall intensity growth rate, water level change rate, flow velocity change rate, flow rate change rate, and turbidity change rate indicate that the river is significantly affected by external disturbances.

[0035] The extracted multi-source water environment features are normalized to eliminate dimensional differences between parameters, and weighting coefficients are assigned based on the degree of influence of each feature on the river channel disturbance. For example, in a rainstorm scenario, the flow rate change rate and turbidity rate change rate directly reflect river scouring and sediment disturbance, and are therefore given higher weights; the rainfall intensity growth rate, as an external driving factor, is also assigned a corresponding weight. The normalized multi-source water environment features are then input into the river channel disturbance stage identification mechanism to calculate the comprehensive river channel disturbance index.

[0036] The calculated comprehensive river disturbance index is compared with a pre-set disturbance threshold range to identify the stage of river disturbance. For example, when continuous heavy rainfall causes a rapid increase in river flow, and significant changes in flow velocity, water level, and turbidity occur, causing the calculated comprehensive river disturbance index to exceed the upper limit of the preset threshold, the river is judged to be in the first-level disturbance stage, indicating that the river is currently under strong disturbance and there may be significant risks of pollutant diffusion, sediment resuspension, and water quality deterioration. When the comprehensive river disturbance index is within the normal fluctuation range, the river is judged to be in the second-level disturbance stage, indicating that the river has a certain degree of disturbance and requires continuous monitoring. When the comprehensive river disturbance index is below the lower limit of the threshold, the river is judged to be in the third-level disturbance stage, indicating that the overall state of the river is stable and there is no significant disturbance.

[0037] Through the above implementation methods, the river disturbance stage identification module transforms the traditional method of judging river status based on a single water quality indicator into a method based on the fusion analysis of multi-source environmental information, enabling dynamic perception of river disturbance processes. By comprehensively utilizing rainfall, hydrodynamic, and water quality change information, the accuracy of river disturbance identification is improved, allowing for the early detection of risk events such as rainstorm erosion, pollution diffusion, and sediment disturbance. By clearly identifying the current disturbance stage of the river, a status-based basis is provided for subsequent data reliability assessment, sediment pollution release contribution analysis, and pollution control measure formulation. This transforms river water environment management from reactive treatment to real-time monitoring and proactive early warning, improving the scientific basis of river pollution prevention and maintenance decisions.

[0038] Preferably, the data credibility assessment module is used to perform credibility assessment by extracting multi-source water environment monitoring data corresponding to the disturbance stage of the river channel, and to obtain the monitoring credibility coefficient to analyze the source of anomalies in the monitoring data, as follows: Extract multi-source water environment monitoring data corresponding to the disturbance stage of the river channel, and construct a sliding analysis window for the monitoring data. ,in, Let T be the sliding analysis window for the i-th river monitoring section at time t, where T is the window length. To monitor the cross-section in real time; Based on the sliding analysis window of the monitoring data, credibility assessment indicators are extracted, a credibility assessment model is built based on the credibility assessment indicators, and the monitoring credibility coefficient is calculated. An anomaly source analysis model is constructed based on the credibility coefficient to analyze the sources of anomalies in the monitoring data and generate a credibility evaluation result for the monitoring data.

[0039] Preferably, a credibility assessment model is built based on a sliding analysis window of monitoring data to extract credibility assessment indicators and analyze the credibility status of water environment monitoring data, as follows: Reliability assessment indicators are extracted based on a sliding analysis window of monitoring data. Specifically, this involves calculating the characteristics of multi-source water environment per unit time using water environment monitoring data, analyzing the average rate of change of monitoring data within the sliding analysis window, and constructing and obtaining reliability assessment indicators based on the multi-source water environment characteristics and the average rate of change of monitoring data. These reliability assessment indicators characterize the degree of deviation between the current rate of change of monitoring data and the historical average rate of change within the sliding time window. The specific formula for the reliability assessment indicators is as follows: In the formula: As a credibility assessment indicator, Let a be the average rate of change of the monitoring data of type a. For the monitoring data of category a in the first... The rate of change at time t, k is the historical sampling sequence number within the sliding analysis window, and its value ranges from 0 to 1. , The characteristics of the multi-source water environment of type a at time t, This is a very small positive number set to prevent the denominator from being zero; Based on the credibility assessment index, the credibility status of water environment monitoring data is judged and analyzed. The credibility assessment index is compared with the preset credibility threshold. If the credibility assessment index is greater than or equal to the preset credibility threshold, the credibility of the water environment monitoring data is unqualified. If the credibility assessment index is less than the preset credibility threshold, the credibility of the water environment monitoring data is qualified.

[0040] In a real-world river water environment dynamic monitoring scenario, this invention takes the online monitoring data quality assessment during a city river disturbance caused by heavy rainfall as an example. Due to factors such as heavy rainfall, changes in river flow patterns, and rapid migration of pollutants, monitoring equipment may experience sudden data changes, signal interference, or local anomalies, resulting in the collected water environment monitoring data failing to accurately reflect the actual state of the river. Therefore, it is necessary to conduct a reliability assessment of multi-source water environment monitoring data acquired at different disturbance stages, screen reliable data, and provide an accurate data foundation for subsequent sediment pollution release analysis, pollution evolution prediction, and dredging optimization.

[0041] Based on the current disturbance state output by the river disturbance stage identification module, multi-source water environment monitoring data from each monitoring section under the corresponding stage are extracted. For example, when the river is in a stage of severe disturbance caused by heavy rainfall, water quality data, hydrodynamic parameters, meteorological parameters, and sediment parameters collected during this stage are selected as the objects of credibility analysis. For the I-th monitoring section, a sliding analysis window for monitoring data is constructed with the current time T as the center. The sliding window method enables dynamic analysis of the temporal variation patterns of the monitoring data, avoiding misjudgments caused by relying solely on data from a single moment.

[0042] Reliability assessment indicators are extracted within the sliding analysis window. Specifically, the rate of change of various environmental characteristics per unit time is calculated based on water environment monitoring data, such as the rate of change of pollutant concentration, flow velocity, water level, and turbidity. The average rate of change of historical data within the sliding window is also calculated, and the deviation between the current monitoring data rate of change and the historical average rate of change is further calculated. When the river is under normal disturbance, changes in pollutant concentration and hydrodynamic parameters are usually continuous; therefore, the current rate of change should be close to the historical average rate of change. If the monitoring equipment is disturbed or malfunctions, there may be sudden and significant changes, causing the current rate of change to deviate significantly from the historical pattern, thus increasing the reliability assessment index.

[0043] After obtaining the credibility assessment index, it is compared with a preset credibility threshold to determine the credibility status of the monitoring data. For example, during a rainstorm, if the flow velocity, water level, and turbidity data at a certain monitoring section all change synchronously with the increase in rainfall, and the calculated credibility assessment index is lower than the preset threshold, then the monitoring data is considered to be in a qualified state and can be directly used for subsequent analysis. If the pollutant concentration collected by a sensor shows an abnormal peak value in a short period of time that is much higher than the change pattern of other monitoring indicators, causing the credibility assessment index to exceed the threshold, then the data is considered to be in a qualified state and needs to be corrected or removed.

[0044] An anomaly source analysis model is constructed based on the calculated monitoring reliability coefficient to identify the sources of abnormal data. For example, when the data change rate is inconsistent, while data from adjacent monitoring sections and hydrodynamic conditions remain normal, it can be determined that the anomaly mainly originates from abnormal data collection by the monitoring equipment. When multiple adjacent sections simultaneously show abnormal increases in pollutant concentrations, and these increases conform to hydrodynamic propagation patterns, it is determined that a real pollution event may exist. When changes in pollution data do not match changes in flow velocity and water level, it may be due to sensor drift or abnormal data transmission. Through anomaly source analysis, a monitoring data reliability evaluation result can be further generated.

[0045] In this embodiment of the invention, the data reliability assessment module can dynamically evaluate the reliability of monitoring data at different stages of river disturbance, realizing the transformation from "data acquisition" to "data quality judgment." The module's main functions are: firstly, by analyzing time-varying patterns, it improves the ability to identify abnormal monitoring data and reduces the impact of single-point anomalies on river condition assessment; secondly, by combining disturbance stage information, the reliability assessment process can adapt to complex environments such as heavy rainfall, hydrodynamic changes, and pollution diffusion, improving the authenticity and stability of monitoring results. Simultaneously, anomaly source analysis can distinguish between equipment malfunctions, data anomalies, and actual pollution changes, providing more reliable data support for subsequent pollution source analysis, pollution trend prediction, and river dredging optimization.

[0046] Preferably, the sediment pollution release contribution analysis module is used to acquire multi-source water environment monitoring data that has passed the reliability assessment, input the sediment pollution release contribution analysis mechanism, and calculate the sediment pollution release contribution rate, as follows: Obtain multi-source water environment monitoring data with acceptable credibility, input the multi-source water environment monitoring data into the sediment pollution release contribution analysis mechanism, calculate the sediment pollution release contribution, and calculate the sediment pollution release contribution rate in combination with pollutant concentration.

[0047] It should be further noted that the specific formula for the contribution of sediment pollution release is as follows: In the formula: Contributing to the release of pollutants from sediment. The sediment pollution release coefficient. The content of pollutants in the sediment. Factors influencing sediment release; In the formula: The weighting coefficients represent the characteristics of hydrodynamic disturbance. The hydrodynamic disturbance characteristics at time t. The weighting coefficients for the characteristics of suspended matter changes. The characteristics of the suspended matter changes at time t; in, In the formula: The hydrodynamic disturbance characteristics at time t. The weighting factor for flow velocity. Let be the flow velocity at time t. The weighting coefficient for traffic. Let be the flow rate at time t. This is a weighting coefficient for water depth. Let t be the water depth. The characteristics of suspended matter changes at time t, Let be the concentration of suspended matter at time t. The concentration of suspended matter at time t-1.

[0048] The formula for calculating the concentration of sediment pollution release contribution based on the contribution amount of sediment pollution release is as follows: In the formula: Contributes to the concentration of pollutants released from sediment. To control the water volume at the i-th monitoring section, Let i be the water flow area of ​​the i-th monitoring section. The length of the river segment at the i-th monitoring section; The contribution rate of sediment pollution release is calculated based on the ratio of the concentration of sediment pollution released to the concentration of pollutants.

[0049] This invention acquires qualified multi-source water environment monitoring data after being screened by a data reliability assessment module, including information such as pollutant concentrations, hydrodynamic parameters, suspended solids concentrations, and sediment parameters at each monitoring section. For a specific target monitoring section, real-time data such as flow velocity, water depth, flow rate, and suspended solids concentration are acquired at the current moment. Combined with sediment pollutant content and sediment pollution release coefficient obtained from sediment monitoring, the above data are input into a sediment pollution release contribution analysis mechanism to calculate the sediment pollution release under the current disturbance conditions.

[0050] The sediment release influencing factor was calculated based on hydrodynamic parameters. Since sediment pollutant release is primarily influenced by water flow disturbance and sediment particle resuspension, constructing hydrodynamic disturbance characteristics using parameters such as flow velocity, flow rate, and water depth can reflect the impact of current river hydrodynamic conditions on sediment disturbance capacity. For example, during heavy rainfall, river flow and velocity increase rapidly, and the hydrodynamic disturbance characteristic value rises accordingly, indicating that sediment particles are more prone to resuspension. Simultaneously, suspended solids change characteristics were calculated based on suspended solids monitoring data; a sustained increase in suspended solids concentration indicates that riverbed sediment may be disturbed and particles may be released. Therefore, by integrating hydrodynamic disturbance characteristics and suspended solids change characteristics, a sediment release influencing factor is obtained, which comprehensively reflects the likelihood of sediment pollution release under current environmental conditions.

[0051] Furthermore, by calculating the contribution of sediment pollution release based on the pollutant content, release coefficient, and release influencing factors in the sediment, the amount of pollutants released from the sediment into the water body under the current river disturbance conditions can be obtained. For example, during periods of heavy rainfall, the sediment release influencing factors increase due to increased flow velocity, rising water levels, and elevated suspended solids concentrations. Even if the external pollution input remains constant, the sediment release contribution may still increase significantly.

[0052] Subsequently, the contribution of sediment pollution release is converted into the pollution concentration contribution value of the corresponding monitoring section. This is calculated based on the control water volume of the monitoring section. This calculation allows the mass of pollutants released from sediment to be converted into the degree of influence of water pollution concentration, enabling direct comparison with the pollutant concentration obtained from online monitoring.

[0053] The sediment pollution release contribution rate is calculated based on the ratio between the concentration contributed by sediment pollution release and the actual monitored pollutant concentration. This indicator can be used to determine the proportion of endogenous pollution in the sediment in the current pollution state. For example, a high sediment pollution release contribution rate indicates that the increase in pollutant concentration is mainly caused by sediment release, requiring priority for dredging and remediation; a low contribution rate indicates that the pollution mainly originates from external input, necessitating focus on pollution source control.

[0054] Through the embodiments of this invention, the sediment pollution release contribution analysis module can achieve quantitative analysis of the river's endogenous pollution release process based on reliable multi-source monitoring data. This is mainly reflected in two aspects: First, by integrating multi-source information such as hydrodynamics, suspended solids, and sediment pollution status, it improves the accuracy of sediment pollution release judgment and avoids misjudgments of pollution sources based solely on changes in water concentration. Second, by calculating the sediment pollution release contribution rate, it achieves quantitative differentiation of pollution sources, providing a scientific basis for whether river dredging and remediation are necessary. Simultaneously, it can dynamically analyze sediment release risks at different disturbance stages, providing reliable data support for subsequent pollution evolution prediction, dredging sequence optimization, and long-term river water environment management.

[0055] Example 2: In this embodiment of the invention, a data-driven dynamic water environment monitoring system is used for dynamic monitoring and dredging of a polluted river in a certain urban area. The river is approximately 15 km long and passes through residential areas, industrial parks, and agricultural irrigation areas. During the rainy season, it is susceptible to various factors such as rainfall runoff, sediment disturbance, and external pollution input, resulting in significant fluctuations in river water quality. To achieve real-time monitoring and scientific management of river pollution, multiple online monitoring sections are deployed at the upstream, midstream, downstream, and tributary confluence points of the river. Each monitoring section is equipped with a water quality monitor, water level gauge, flow meter, flow velocity meter, meteorological monitoring equipment, and sediment monitoring equipment. Multi-source water environment monitoring data, including turbidity, pollutant concentration, water depth, flow velocity, flow rate, rainfall, rainfall intensity, wind speed, air temperature, sediment thickness, and suspended solids concentration, are collected in real time at a 5-minute sampling cycle and transmitted to the dynamic water environment monitoring platform via a wireless communication network. The multi-source data monitoring module is used to perform unified timeline synchronization processing on data from different monitoring devices, timestamp alignment on data with different sampling frequencies, and outlier removal, missing value compensation and data standardization processing are completed to build a complete multi-source water environment monitoring dataset, providing a unified data foundation for subsequent analysis.

[0056] The river disturbance stage identification module analyzes multi-source monitoring data, constructs a water environment feature vector based on multi-source water environment characteristics such as rainfall intensity growth rate, water level change rate, flow velocity change rate, turbidity change rate, and flow rate change rate, and calculates the comprehensive river disturbance index. When a continuous rainstorm occurs, monitoring data shows a rapid increase in rainfall intensity, a continuous rise in river water level, a significant increase in flow velocity and flow, and a rapid increase in turbidity. The calculated comprehensive river disturbance index exceeds the first-level disturbance threshold, determining that the river is currently in the first-level disturbance stage, and outputting the current disturbance status information to subsequent modules. If the rainstorm ends and the various monitoring indicators gradually stabilize, and the comprehensive river disturbance index drops to a preset range, it automatically adjusts to the second-level or third-level disturbance stage, achieving dynamic identification of the river's operating status.

[0057] After obtaining the current stage of river disturbance, the data reliability assessment module extracts multi-source water environment monitoring data for the corresponding stage. It analyzes the data over a continuous time period using a sliding analysis window, calculates the average rate of change and reliability assessment index for various monitoring data types, and determines whether the monitoring data conforms to the actual changes in the river channel. For example, during a monitoring process, if the pollutant concentration at a certain section suddenly increases sharply, while the flow velocity, water level, turbidity, and data from adjacent monitoring sections do not change significantly, the system calculates that the reliability assessment index of this monitoring data exceeds a preset threshold, determining that the data is unreliable. Further analysis suggests the anomaly may be due to sensor drift or equipment malfunction, thus automatically removing this set of abnormal data. Meanwhile, data changes at other monitoring sections are consistent with hydrodynamic changes and are therefore considered reliable data, used as input for subsequent analysis, effectively preventing abnormal data from interfering with pollution analysis results.

[0058] For data that passes the reliability assessment, the sediment pollution release contribution analysis module further combines sediment pollutant content, hydrodynamic parameters, and suspended solids concentration changes to calculate the sediment pollution release contribution amount and contribution rate. For example, when heavy rain causes a significant increase in river flow velocity, the system calculates the hydrodynamic disturbance characteristics based on flow velocity, flow rate, and water depth. Simultaneously, considering the rapidly increasing trend of suspended solids concentration, a significant sediment release impact factor is obtained, further calculating the sediment pollution release contribution amount and converting it into a sediment pollution release contribution concentration. Subsequently, this contribution concentration is compared with the pollutant concentration obtained from online monitoring to calculate the sediment pollution release contribution rate. If the calculation results show that the sediment pollution release contribution rate reaches 70% or more, it indicates that the current pollution mainly originates from endogenous sediment release rather than external pollution input. The system then marks the monitoring section as a high-risk area for endogenous pollution, providing a basis for river management.

[0059] The dredging optimization module comprehensively considers pollutant change trends, sediment pollution release contribution rates, and pollution risk levels at each monitoring section to dynamically optimize the dredging sequence. For example, if the system detects that pollutant concentrations at two midstream monitoring sections are expected to continue rising, with sediment pollution release contribution rates exceeding 75%, while pollution changes at the downstream section are relatively small, then dredging operations will be prioritized in the midstream section, while the downstream section will be designated as a subsequent treatment area. Combining construction capacity, navigation requirements, and ecological protection requirements, the system automatically generates an optimized dredging plan, including dredging priority, construction time, and dredging scope, and pushes this plan to the river management department to achieve a rational allocation of river management resources.

[0060] This invention organically combines multi-source data monitoring, river disturbance identification, data reliability assessment, sediment pollution release analysis, and dredging optimization decision-making. It not only enables real-time monitoring of river water environment changes and accurate identification of pollution characteristics at different disturbance stages, but also effectively distinguishes between endogenous and exogenous pollution in sediment, improving the accuracy of pollution source analysis. Furthermore, it dynamically optimizes dredging plans based on pollution development trends, realizing the transformation of river management from traditional experience-based decision-making to data-driven and intelligent decision-making, thereby improving the level of dynamic monitoring and refined management of the river water environment.

[0061] Example 3: A data-driven dynamic monitoring method for the water environment, comprising the following steps: Step S1: By acquiring multi-source water environment monitoring data from each monitoring section of the target river in real time, and performing synchronous preprocessing according to a unified time axis, a multi-source water environment monitoring dataset is constructed; the water environment monitoring data includes water quality monitoring data, hydrodynamic parameters, meteorological parameters, and sediment parameters; Step S2: Extract multi-source water environment features based on the multi-source water environment monitoring dataset, construct a river disturbance stage identification mechanism based on the multi-source water environment features, and capture the disturbance stage of the river. Step S3: Based on the sliding analysis window of the monitoring data, build a credibility assessment model, extract credibility assessment indicators, and analyze the credibility status of the water environment monitoring data. Step S4: Obtain multi-source water environment monitoring data that has passed the credibility assessment, input the sediment pollution release contribution analysis mechanism, and calculate the sediment pollution release contribution rate; Step S5: Dynamically optimize the dredging sequence of each monitoring section of the river based on the pollutant change trend, and determine the dredging optimization plan.

[0062] like Figure 2 The diagram shown is a flowchart of a data analysis-based dynamic monitoring method for the water environment according to an embodiment of the present invention, which can be used to execute... Figure 1 The system embodiment shown is similar in principle and technical effect, and will not be described again here.

[0063] A readable storage medium storing a computer program, which, when executed by a processor, is used to implement the data analysis-based dynamic monitoring system for the water environment as described in any of the above claims.

[0064] The readable storage medium can be a computer storage medium or a communication medium. A communication medium includes any medium that facilitates the transfer of computer programs from one location to another. A computer storage medium can be any available medium accessible to a general-purpose or special-purpose computer. For example, a readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application-Specific Integrated Circuit (ASIC). Alternatively, the ASIC can be located in a user equipment. Of course, the processor and the readable storage medium can also exist as discrete components in a communication device. The readable storage medium can be a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0065] The present invention also provides a program product including executable instructions stored in a readable storage medium. At least one processor of the device can read the executable instructions from the readable storage medium, and the at least one processor executes the executable instructions to cause the device to implement the methods provided in the various embodiments described above.

[0066] In the embodiments of the above-described device, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0067] Through the above embodiments, this invention improves the real-time performance, accuracy, and scientific rigor of river water environment monitoring and governance decisions by integrating multi-source water environment monitoring data and data analysis technology. By simultaneously acquiring multi-dimensional information such as water quality, hydrodynamics, meteorology, sediment, and river operation through a multi-source data monitoring module, it overcomes the limitations of traditional water environment monitoring that relies on a single pollution indicator. This allows the system to more comprehensively reflect the actual operating status of the river and improves its ability to perceive river conditions under complex environments. By incorporating a river disturbance stage identification module, the system can promptly identify different degrees of disturbance to the river based on dynamic changes in rainfall, water level, flow velocity, flow rate, and turbidity, avoiding the lag caused by judging abnormal river conditions solely based on changes in pollutant concentration. This method can detect potential risks such as rainstorm erosion, pollution diffusion, and sediment resuspension in advance, providing early warning for subsequent pollution prevention and control. The data reliability assessment module dynamically evaluates the quality of monitoring data, effectively reducing the impact of sensor malfunctions, data transmission errors, and localized fluctuations on analysis results. It not only determines the reliability of monitoring data but also analyzes the sources of anomalies by considering data change patterns, enabling the system to distinguish between real environmental changes and equipment malfunctions, thus improving the reliability of pollution analysis results. The sediment pollution release contribution analysis module further analyzes the sources of river pollution by combining hydrodynamic conditions, suspended solids changes, and sediment pollution status. It quantitatively calculates the contribution ratio of sediment pollution to water pollution concentration. Compared to traditional methods that only judge pollution levels based on water concentration, this approach effectively identifies the impact of endogenous pollution, providing a more accurate basis for determining whether dredging is necessary and avoiding resource waste from indiscriminate dredging. The dredging optimization and determination module dynamically adjusts the dredging sequence based on pollution trends and pollution risk levels, enabling priority implementation of treatment measures in severely polluted areas, shifting from traditional periodic dredging to predictive and precise dredging. This approach improves river management efficiency, reduces costs, and minimizes the impact of unnecessary engineering disturbances on the river's ecological environment.

[0068] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

[0069] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A water environment dynamic monitoring system based on data analysis, characterized in that, It includes a multi-source data monitoring module, a river disturbance stage identification module, a data credibility assessment module, a sediment pollution release contribution analysis module, and a dredging optimization determination module; The multi-source data monitoring module is used to acquire multi-source water environment monitoring data from various monitoring sections of the target river in real time, perform synchronous preprocessing according to a unified time axis, and construct a multi-source water environment monitoring dataset; the water environment monitoring data includes water quality monitoring data, hydrodynamic parameters, meteorological parameters, and sediment parameters; The river disturbance stage identification module is used to extract multi-source water environment features based on multi-source water environment monitoring datasets, construct a river disturbance stage identification mechanism based on multi-source water environment features, and capture the disturbance stage of the river. The data credibility assessment module is used to build a credibility assessment model based on the sliding analysis window of monitoring data, extract credibility assessment indicators, and analyze the credibility status of water environment monitoring data. The sediment pollution release contribution analysis module is used to acquire multi-source water environment monitoring data that has passed the credibility assessment, input the sediment pollution release contribution analysis mechanism, and calculate the sediment pollution release contribution rate. The dredging optimization determination module is used to dynamically optimize the dredging sequence of each monitoring section of the river based on the pollutant change trend, and to determine the dredging optimization scheme.

2. The water environment dynamic monitoring system based on data analysis according to claim 1, characterized in that, The river disturbance stage identification module is used to extract multi-source water environment features based on multi-source water environment monitoring datasets, and to construct a river disturbance stage identification mechanism based on these features to capture the disturbance stage of the river, as detailed below: Multi-source water environment features are extracted from multi-source water environment monitoring data, and a water environment feature vector is constructed. The multi-source water environment features include rainfall intensity growth rate, water level change rate, flow velocity change rate, turbidity change rate, and flow rate change rate. Based on the characteristics of multi-source water environment, a mechanism for identifying river disturbance stages is constructed, and a comprehensive river disturbance index is built to determine the river disturbance stage.

3. The water environment dynamic monitoring system based on data analysis according to claim 2, characterized in that, Based on the characteristics of multi-source water environment, a river disturbance stage identification mechanism is constructed. The comprehensive river disturbance index is analyzed to determine the river disturbance stage. The specific steps are as follows: The characteristics of multi-source water environment are obtained and normalized, and weighting coefficients are assigned according to the degree of influence of each multi-source water environment characteristic on rainstorm disturbance. The characteristics of multi-source water environment and their corresponding weighting coefficients are input into the river disturbance stage identification mechanism. Based on the comprehensive river disturbance index, the stage of river disturbance is determined.

4. The water environment dynamic monitoring system based on data analysis according to claim 3, characterized in that, The determination of the river disturbance stage is as follows: The comprehensive river disturbance index is compared with a preset disturbance threshold range. If the comprehensive river disturbance index is greater than the upper limit of the preset disturbance threshold range, the river is in a first-level disturbance stage, where the river disturbance is severe. If the comprehensive river disturbance index is within the preset disturbance threshold range, the river is in a second-level disturbance stage, where the river is undisturbed. If the comprehensive river disturbance index is less than the lower limit of the preset disturbance threshold range, the river is in a third-level disturbance stage, where the river is undisturbed.

5. The water environment dynamic monitoring system based on data analysis according to claim 1, characterized in that, The data credibility assessment module is used to extract multi-source water environment monitoring data corresponding to the disturbance stage of the river channel, conduct credibility assessment, obtain monitoring credibility coefficients, and analyze the sources of anomalies in the monitoring data, as detailed below: Extract multi-source water environment monitoring data corresponding to the disturbance stage of the river channel and construct a sliding analysis window for the monitoring data; Based on the sliding analysis window of the monitoring data, credibility assessment indicators are extracted, a credibility assessment model is built based on the credibility assessment indicators, and the monitoring credibility coefficient is calculated. An anomaly source analysis model is constructed based on the credibility coefficient to analyze the sources of anomalies in the monitoring data and generate a credibility evaluation result for the monitoring data.

6. The water environment dynamic monitoring system based on data analysis according to claim 1, characterized in that, The data credibility assessment module is used to build a credibility assessment model based on a sliding analysis window of monitoring data, extract credibility assessment indicators, and analyze the credibility status of water environment monitoring data, as detailed below: Reliability assessment indicators are extracted based on a sliding analysis window of monitoring data; Based on the credibility assessment index, the credibility status of water environment monitoring data is judged and analyzed. The credibility assessment index is compared with the preset credibility threshold. If the credibility assessment index is greater than or equal to the preset credibility threshold, the credibility of the water environment monitoring data is unqualified. If the credibility assessment index is less than the preset credibility threshold, the credibility of the water environment monitoring data is qualified.

7. The water environment dynamic monitoring system based on data analysis according to claim 6, characterized in that, The credibility assessment index is specifically as follows: the characteristics of the multi-source water environment are calculated per unit time using water environment monitoring data, the average rate of change of monitoring data within the sliding analysis window is analyzed, and the credibility assessment index is constructed based on the characteristics of the multi-source water environment and the average rate of change of monitoring data.

8. The water environment dynamic monitoring system based on data analysis according to claim 1, characterized in that, The sediment pollution release contribution analysis module is used to acquire multi-source water environment monitoring data that has passed the reliability assessment, input the sediment pollution release contribution analysis mechanism, and calculate the sediment pollution release contribution rate, as detailed below: Obtain multi-source water environment monitoring data with acceptable reliability, input the multi-source water environment monitoring data into the sediment pollution release contribution analysis mechanism, calculate the sediment pollution release contribution amount, calculate the sediment pollution release contribution concentration based on the sediment pollution release contribution amount, and calculate the sediment pollution release contribution rate based on the ratio of sediment pollution release contribution concentration to pollutant concentration.

9. A data-based dynamic monitoring method for the water environment, applied to the data-based dynamic monitoring system for the water environment as described in any one of claims 1-8, characterized in that, Includes the following steps: By acquiring multi-source water environment monitoring data from various monitoring sections of the target river in real time, and performing synchronous preprocessing according to a unified timeline, a multi-source water environment monitoring dataset is constructed. The water environment monitoring data includes water quality monitoring data, hydrodynamic parameters, meteorological parameters, and sediment parameters. Based on the multi-source water environment monitoring dataset, multi-source water environment characteristics are extracted, and a river disturbance stage identification mechanism is constructed according to the multi-source water environment characteristics to capture the disturbance stage of the river. A credibility assessment model was built based on a sliding analysis window of monitoring data to extract credibility assessment indicators and analyze the credibility status of water environment monitoring data. Acquire multi-source water environment monitoring data that have passed the credibility assessment, input them into the sediment pollution release contribution analysis mechanism, and calculate the sediment pollution release contribution rate. Based on the changing trends of pollutants, the dredging sequence of each monitoring section of the river is dynamically optimized, and the dredging optimization plan is determined.

10. A readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it is used to implement the data analysis-based dynamic monitoring system for the water environment as described in any one of claims 1-8.

Images