Water conservancy project water level monitoring method and system based on artificial intelligence

Abstract

The invention provides a hydraulic engineering water level monitoring method and system based on artificial intelligence. Meteorological parameters and soil humidity parameters of a cross-basin reservoir group and water level measurement parameters generated by magnetic levitation displacement induction are obtained, dynamic change rules of the parameters are analyzed, and a correlation strength coefficient reflecting the hydraulic interaction between reservoirs is calculated. And the coefficient and a water level measurement parameter are jointly coded, and a cross-reservoir dynamic association map is constructed. And synchronously acquiring real-time water level signals of each reservoir, matching the real-time water level signals with a preset fluctuation feature library, and identifying a water level abnormal interval related to the water flow path node. And in combination with a mapping relationship between the dynamic association map and the abnormal fluctuation interval, determining a water level imbalance risk level, and generating regulation and control instructions including flood discharge path optimization and water storage capacity adjustment according to the water level imbalance risk level. According to the technical scheme, the water level monitoring efficiency and accuracy of the water conservancy project can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of water level monitoring for water conservancy projects, and in particular to a water level monitoring method and system for water conservancy projects based on artificial intelligence. Background Art

[0002] Coordinated water level regulation across a network of reservoirs across a river basin is crucial for effective water resource management, particularly in the face of climate change, flood warnings, and drought management. A highly intelligent monitoring system is required to ensure coordinated operation among reservoirs and avoid the risk of floods or droughts affecting upstream and downstream areas due to improper operation of a single reservoir.

[0003] Currently, existing solutions include a water level monitoring solution based on IoT technology. This solution deploys a series of high-precision sensors at each reservoir to collect real-time water conservancy information and transmits the data to a central processing platform via wireless communication networks. The central platform then applies big data analysis algorithms to process the collected information, enabling dynamic monitoring and analysis of the overall operating status of the reservoir group. This approach not only improves the accuracy of data collection but also greatly enhances the speed and efficiency of information processing, providing strong support for making scientific and reasonable reservoir operation decisions.

[0004] Although IoT-based water level monitoring solutions have demonstrated impressive performance in improving data processing capabilities and supporting decision-making, they also have certain limitations. First, due to their reliance on a large number of sensor devices and a complex network architecture, the system's initial construction costs are high and maintenance is relatively difficult. Second, when responding to extreme weather or natural disasters, data loss may occur due to damage to some sensors or network outages, impacting the stability and reliability of the entire system. Finally, while big data analytics can provide powerful data processing capabilities, in certain circumstances, such as inappropriate model parameter settings or poor input data quality, analysis results may deviate from reality, affecting the accuracy of decision-making. These issues limit the full adoption and effectiveness of this solution in practical applications. Summary of the Invention

[0005] The present application provides a water level monitoring method and system for water conservancy projects based on artificial intelligence, which is used to solve the problems of low efficiency and poor accuracy in water level monitoring of water conservancy projects in the prior art.

[0006] In a first aspect, the present application provides a water level monitoring method for a water conservancy project based on artificial intelligence, comprising:

[0007] Obtain meteorological parameters, soil moisture parameters, and water level measurement parameters for a cross-basin reservoir group. The water level measurement parameters are generated by magnetic levitation displacement sensing and are linearly mapped to water level changes.

[0008] Based on the dynamic change patterns of the meteorological parameters and soil moisture parameters, a correlation strength coefficient reflecting the hydraulic interaction between reservoirs is obtained, and the correlation strength coefficient is jointly encoded with the water level measurement parameters to generate a dynamic correlation map across reservoirs;

[0009] Synchronously collect real-time water level signals from each reservoir, perform spatiotemporal matching on the real-time water level signals with a preset water level fluctuation feature library, and extract abnormal water level fluctuation intervals associated with flow path nodes in the cross-reservoir dynamic association map;

[0010] Determining the water level imbalance risk level of the inter-basin reservoir group through the mapping relationship between the inter-reservoir dynamic correlation map and the water level abnormal fluctuation range;

[0011] A control instruction is generated according to the water level imbalance risk level, and the control instruction includes a flood discharge path optimization plan and a water storage capacity adjustment ratio.

[0012] Optionally, the step of jointly encoding the correlation strength coefficient and the water level measurement parameter to generate a cross-reservoir dynamic correlation map includes:

[0013] Dynamically allocating a weight ratio of the meteorological parameter to the soil moisture parameter in the correlation strength coefficient according to the instantaneous change rate of the meteorological parameter and the cumulative amount of the soil moisture parameter;

[0014] The time series fluctuation amplitude of the water level measurement parameter is superimposed with the weight ratio to generate a hydraulic influence value representing the influence of the external environment on the reservoir node, and a hydraulic conduction path between the reservoir nodes is constructed based on the difference between the hydraulic influence values ​​of adjacent reservoir nodes;

[0015] Dynamically correcting the connection strength of the hydraulic conduction path based on a synchronous change trend of a water level measurement parameter in the hydraulic conduction path to obtain a corrected connection strength;

[0016] The geographical location coordinates, hydraulic conduction paths and corrected connection strengths of the reservoir nodes are data-bound to generate a cross-reservoir dynamic association map.

[0017] Optionally, the superposition of the time series fluctuation amplitude of the water level measurement parameter and the weight ratio to generate a hydraulic influence value representing the influence of the external environment on the reservoir node, and constructing a hydraulic conduction path between the reservoir nodes based on the difference between the hydraulic influence values ​​of adjacent reservoir nodes, includes:

[0018] Perform weighted processing on the rising phase and the falling phase of the time series fluctuation amplitude of the water level measurement parameter according to the weight ratio to obtain weighted rising phase time series fluctuation amplitude and falling phase time series fluctuation amplitude;

[0019] Directionally superimposing the weighted time series fluctuation amplitude in the ascending phase and the time series fluctuation amplitude in the descending phase to generate a hydraulic impact value representing the influence of the external environment on the reservoir node;

[0020] Calculating an absolute difference in hydraulic influence values ​​of adjacent reservoir nodes, comparing the absolute difference with a preset hydraulic conduction path generation threshold, and setting a preset hydraulic conduction path whose absolute difference exceeds the generation threshold as a candidate conduction path;

[0021] Screening the candidate conduction paths that meet activation conditions based on the consistency between the connection strengths of the candidate conduction paths and the fluctuation directions of the water level measurement parameters in the current time window to obtain a set of activated candidate conduction paths;

[0022] The activated candidate conduction path set is superimposed on the preset conduction path in the cross-reservoir dynamic association map to obtain a hydraulic conduction path.

[0023] Optionally, determining the water level imbalance risk level of the inter-basin reservoir group through a mapping relationship between the inter-reservoir dynamic association map and the abnormal water level fluctuation range includes:

[0024] Dynamically matching the water flow path nodes in the cross-reservoir dynamic association map with the abnormal water level fluctuation interval to determine the corresponding relationship between the connection strength of the water flow path nodes and the duration of the abnormal water level fluctuation interval;

[0025] Based on the corresponding relationship, the spatial distribution range and time cumulative effect of the abnormal water level fluctuation interval in the cross-reservoir dynamic correlation map are counted;

[0026] The spatial distribution range, time cumulative effect and preset thresholds are compared and analyzed, and the water level imbalance risk level intervals of the cross-basin reservoir group are divided according to the comparative analysis results. When the spatial distribution range and time cumulative effect exceed the preset thresholds at the same time, it is judged to be a high risk level.

[0027] Optionally, performing spatiotemporal matching of the real-time water level signal with a preset water level fluctuation feature library to extract abnormal water level fluctuation intervals associated with water flow path nodes in the cross-reservoir dynamic association map includes:

[0028] Dynamically dividing the real-time water level signal into continuous fluctuation segments according to a preset time window, wherein the length of the preset time window is adaptively adjusted according to the connection density of the water flow path nodes in the cross-reservoir dynamic association map;

[0029] Matching the continuous fluctuation segments with the fluctuation patterns in a preset water level fluctuation feature library segment by segment in a temporal and spatial order, and screening out abnormal fluctuation segments in the continuous fluctuation segments whose matching degree with the fluctuation patterns exceeds a preset threshold based on the segment-by-segment matching results;

[0030] Mapping the abnormal fluctuation segment to the water flow path node, and calculating the correlation influence strength of the abnormal fluctuation segment on the adjacent reservoir node through the connection strength of the mapped water flow path node;

[0031] According to the spatial distribution range and cumulative duration of the correlation impact intensity in the cross-reservoir dynamic correlation map, the abnormal water level fluctuation interval associated with the water flow path node is obtained.

[0032] Optionally, mapping the abnormal fluctuation segment to the water flow path node, and calculating the correlation influence strength of the abnormal fluctuation segment on the adjacent reservoir node according to the connection strength of the mapped water flow path node, includes:

[0033] Overlapping and comparing the abnormal fluctuation segment with the spatiotemporal position distribution of the water flow path nodes, and selecting the water flow path nodes with an overlap exceeding a preset ratio as the target mapping nodes to which the abnormal fluctuation segment belongs;

[0034] Calculating the initial influence of the abnormal fluctuation segment on the target mapping node according to the connection strength of the target mapping node;

[0035] Based on the connection strength ratio between the target mapping node and the adjacent reservoir nodes, the initial influence amount is distributed to each adjacent reservoir node, and the distribution amount of the initial influence amount on each adjacent reservoir node is accumulated to obtain the associated influence strength.

[0036] Optionally, generating a control instruction according to the water level imbalance risk level includes:

[0037] Determine the flood discharge priority order of each reservoir node based on the risk interval corresponding to the water level imbalance risk level, and calculate the flood discharge allocation ratio of each reservoir node according to the difference between the current water storage capacity of each reservoir node and the preset safety capacity in the flood discharge priority order;

[0038] generating a flood discharge path optimization plan based on the connection strength and spatial distribution of water flow path nodes in the cross-reservoir dynamic association map;

[0039] Based on the matching relationship between the flood discharge distribution ratio and the historical flood discharge records for the same period, combined with the water level imbalance risk level, a water storage capacity adjustment ratio is generated, and the water storage capacity adjustment ratio is associated with the flood discharge path optimization plan to generate a control instruction.

[0040] In a second aspect, the present application provides a water level monitoring system for water conservancy projects based on artificial intelligence, comprising:

[0041] An acquisition module acquires meteorological parameters, soil moisture parameters, and water level measurement parameters of a cross-basin reservoir group. The water level measurement parameters are generated by magnetic levitation displacement sensing and are linearly mapped to water level changes.

[0042] an encoding module, which obtains a correlation strength coefficient reflecting the hydraulic interaction between reservoirs based on the dynamic change law of the meteorological parameters and the soil moisture parameters, and jointly encodes the correlation strength coefficient with the water level measurement parameters to generate a dynamic correlation map across reservoirs;

[0043] An extraction module synchronously collects real-time water level signals from each reservoir, performs spatiotemporal matching on the real-time water level signals with a preset water level fluctuation feature library, and extracts abnormal water level fluctuation intervals associated with the water flow path nodes in the cross-reservoir dynamic association map;

[0044] a mapping module for determining the water level imbalance risk level of the inter-basin reservoir group through a mapping relationship between the inter-reservoir dynamic association map and the water level abnormal fluctuation range;

[0045] A generation module generates a control instruction according to the water level imbalance risk level, and the control instruction includes a flood discharge path optimization plan and a water storage capacity adjustment ratio.

[0046] In a third aspect, an embodiment of the present application provides a computing device comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an artificial intelligence-based water level monitoring method for water conservancy projects as described in the first aspect above.

[0047] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program. When the computer program is executed by a computer, it implements a water level monitoring method for a water conservancy project based on artificial intelligence as described in the first aspect.

[0048] In the embodiment of the present application, by obtaining meteorological parameters, soil moisture parameters and water level measurement parameters of a cross-basin reservoir group, the water level measurement parameters are generated by magnetic levitation displacement sensing and are linearly mapped to water level changes. Non-contact high-precision collection of water level parameters can be achieved through magnetic levitation displacement sensing, and combined with the fusion of meteorological and soil moisture multi-source data, the limitations of traditional single-point monitoring are broken through, and the real-time performance and environmental adaptability of data collection are improved; based on the dynamic change law of the meteorological parameters and soil moisture parameters, a correlation strength coefficient reflecting the hydraulic interaction between reservoirs is obtained, and the correlation strength coefficient is jointly encoded with the water level measurement parameters to generate a cross-reservoir dynamic correlation map, which can be constructed based on the dynamic weight distribution of the correlation strength coefficient and the joint encoding of the water level parameters to achieve quantitative expression and visual presentation of complex hydrological correlations; by synchronously collecting the real-time water level signals of each reservoir, the real-time water level signals are compared with the preset water level signals, and the real-time water level signals are compared with the preset water level signals. The water level fluctuation feature library is matched in time and space, and the abnormal water level fluctuation intervals associated with the water flow path nodes in the cross-reservoir dynamic association map are extracted. The water level signal can be matched in time and space with the feature library in real time, and the abnormal fluctuation areas associated with the water flow path nodes can be accurately located, solving the problem of delayed detection of sudden water level mutations by traditional methods. The water level imbalance risk level of the cross-basin reservoir group is determined through the mapping relationship between the cross-reservoir dynamic association map and the abnormal water level fluctuation intervals. Based on the dynamic mapping relationship between the map and the abnormal fluctuation intervals, a multi-dimensional risk assessment model can be established to achieve graded early warning and traceability analysis of the water level imbalance risk of the cross-basin reservoir group. Control instructions are generated according to the water level imbalance risk level. The control instructions include a flood discharge path optimization plan and a water storage capacity adjustment ratio. The risk level can be combined with the spatial distribution characteristics of the dynamic map to generate a flood discharge path optimization plan and a water storage capacity adjustment instruction, thereby improving the accuracy and execution efficiency of multi-objective coordinated control.

[0049] Furthermore, based on the dynamic weighting ratios assigned to the instantaneous rate of change of meteorological parameters and the accumulated soil moisture, the temporal fluctuation amplitudes of water level parameters are superimposed with the weights to generate hydraulic impact values. A hydraulic conduction path is constructed based on the differences in impact values ​​between adjacent nodes, and the connection strength of the path is dynamically corrected based on the synchronous water level change trend. Finally, a dynamic cross-reservoir correlation map is generated by data binding of node coordinates, conduction paths, and corrected strengths. This method effectively reflects the changes in hydraulic influence between different reservoir nodes caused by external environmental factors. By constructing and dynamically correcting hydraulic conduction paths, it not only enhances understanding of the interactions between reservoir nodes but also provides data support for precise regulation, enhancing the scientific and rational nature of coordinated water level regulation across reservoir groups across a river basin.

[0050] These and other aspects of the present application will become more readily apparent from the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0052] Figure 1 A flow chart of a water level monitoring method for a water conservancy project based on artificial intelligence provided by the present application is shown;

[0053] Figure 2 The present invention provides a schematic diagram of a water level monitoring system for water conservancy projects based on artificial intelligence.

[0054] Figure 3 A schematic structural diagram of a computing device provided by the present application is shown. DETAILED DESCRIPTION

[0055] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0056] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this document or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to being different types.

[0057] Researchers have found that existing water level monitoring methods for inter-basin reservoir groups have difficulty in dynamically quantifying the hydraulic interactions between reservoirs and lack a multi-source data fusion mechanism, resulting in delayed identification of water level mutation propagation paths and insufficient precision in multi-objective collaborative regulation. Based on this, a water level monitoring method for water conservancy projects based on artificial intelligence is provided. Specifically, first, a data foundation is constructed by collecting meteorological parameters, soil moisture parameters, and water level measurement parameters generated by magnetic levitation displacement sensing for inter-basin reservoir groups. Next, the correlation strength coefficient is calculated based on these parameters and jointly encoded with the water level measurement parameters to generate a dynamic correlation map across reservoirs, while also identifying abnormal water level fluctuation intervals. Then, based on the mapping relationship between the dynamic correlation map and the abnormal water level fluctuation interval, the water level imbalance risk level is assessed and determined. Finally, control instructions are automatically generated based on the risk level to optimize the flood discharge path and adjust the water storage capacity, thereby achieving scientific and reasonable water level regulation.

[0058] This method generates a dynamic correlation map by fusing magnetic levitation displacement sensing with meteorological and soil parameters, and accurately locates the abnormal fluctuation range by combining real-time water level signal spatiotemporal matching. It also adaptively generates flood discharge and water storage control instructions based on risk levels to achieve scientific and reasonable control of the water level of the reservoir group, improve the ability to respond to water level changes and extreme weather events, and ensure the safe and efficient use of water resources.

[0059] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0060] Figure 1 The present invention provides a flow chart of a water level monitoring method for a water conservancy project based on artificial intelligence, as shown in FIG. Figure 1 As shown, the method includes:

[0061] 101. Obtain meteorological parameters, soil moisture parameters, and water level measurement parameters of a cross-basin reservoir group, wherein the water level measurement parameters are generated by magnetic levitation displacement sensing and are linearly mapped to water level changes;

[0062] In this step, meteorological parameters refer to data reflecting changes in the atmospheric environment, including rainfall intensity, wind speed, evaporation, etc.

[0063] Soil moisture parameters refer to the water content data collected by soil sensors, which characterize the surface infiltration and water storage capacity.

[0064] The water level measurement parameter refers to the non-contact water level signal generated by the magnetic levitation displacement sensing device. The vertical displacement of the magnetic levitation ball triggers the Hall element to generate an electrical signal. The strength of the electrical signal is linearly mapped to the water level change.

[0065] Magnetic levitation displacement sensing is a technology that accurately measures the position or displacement of an object based on changes in the magnetic field. It is used in scenarios that require high-precision position detection. In this solution, it is used to measure water level changes.

[0066] The linear mapping relationship of water level change means that there is a direct and proportional relationship between the output signal measured by the magnetic levitation displacement sensor and the actual water level height.

[0067] In an embodiment of the present application, first, meteorological parameters (precipitation, evaporation, etc.) are acquired through weather stations (such as automatic rain gauges, temperature and humidity sensors) and satellite remote sensing. Soil moisture parameters are acquired using a soil moisture sensor (such as a TDR probe) or radar inversion technology, and water level measurement parameters are recorded in real time using a magnetic levitation displacement sensor (based on the Hall effect principle). The analog signal (such as voltage) output by the sensor is then digitized through a conversion module and calibrated to a water level height value. Kalman filtering is used to eliminate noise from meteorological parameters and soil moisture parameters (such as eliminating abnormal evaporation data points). Finally, linear regression is applied to the water level measurement parameters to verify the linear mapping relationship (R 2 >0.99 is considered valid).

[0068] In a certain province, a cluster of reservoirs called B has deployed an array of automatic weather stations and soil moisture sensors covering the entire basin. These devices monitor meteorological data such as precipitation, temperature, and wind speed, as well as soil moisture content, in real time, and upload this data to a central database via wireless communication modules. Furthermore, magnetic displacement sensors have been installed at each reservoir to accurately measure water level changes. For example, one day, the water level at Reservoir C rose rapidly due to continuous rainfall. The magnetic displacement sensors captured this change in real time and transmitted the relevant data to the system. After initial cleaning and formatting, all data is integrated into the global positioning system, providing a clear spatial distribution map for subsequent analysis.

[0069] 102. Based on the dynamic variation patterns of the meteorological parameters and soil moisture parameters, a correlation strength coefficient reflecting the hydraulic interaction between reservoirs is obtained, and the correlation strength coefficient is jointly encoded with the water level measurement parameters to generate a dynamic correlation map across reservoirs;

[0070] In this step, hydraulic interaction refers to the mutual influence and effect caused by the exchange of water flow and water volume between different water bodies in the water resource system, especially in the cross-basin or multi-reservoir system.

[0071] The correlation strength coefficient refers to the degree of influence of quantitative meteorological and soil moisture parameters on the hydraulic interaction between reservoirs, which is generated by dynamic calculation of the instantaneous change rate (meteorological) and the cumulative amount (soil moisture).

[0072] Joint encoding refers to the integration of multiple different types of data sources or data features into a unified representation through specific methods or algorithms to facilitate further processing, analysis or model training.

[0073] The cross-reservoir dynamic association graph describes the hydraulic connection relationship of a reservoir group using a graph structure, where the nodes are reservoirs and the edge weights are the association strength coefficients.

[0074] In an embodiment of the present application, first, meteorological parameters and soil moisture parameters are extracted from the data obtained in step 101, and a time series analysis algorithm is used to identify their change patterns over time. Then, based on these change patterns, the correlation strength coefficients between different reservoirs are calculated. This step usually involves statistical methods or machine learning algorithms (such as decision trees, random forests) to quantify the degree of water flow interaction between reservoirs. Finally, combined with water level measurement parameters, deep learning techniques (such as convolutional neural networks) are applied for joint encoding to construct a cross-reservoir dynamic correlation map that reflects the complex relationship between reservoirs. This map not only shows the physical connection between reservoirs, but also reflects the complex dynamic interactions between reservoirs.

[0075] Using the historical data from step 101, the system performed a time series analysis of precipitation, soil moisture, and water level changes in the B reservoir group. For example, it was found that a specific seasonal rainfall pattern would cause Reservoir D to send more runoff to Reservoir E downstream. Based on this, the system calculated the correlation strength coefficient between each reservoir, combined it with the water level measurement parameters, and used a deep learning model to generate a cross-reservoir dynamic correlation map. The cross-reservoir dynamic correlation map shows that when Reservoir D discharges flood water, it will have a significant impact on the water level of Reservoir E, while Reservoir F is relatively independent. The cross-reservoir dynamic correlation map lays the foundation for the next step of extracting abnormal fluctuation ranges.

[0076] 103. Synchronously collect real-time water level signals from each reservoir, perform spatiotemporal matching on the real-time water level signals with a preset water level fluctuation feature library, and extract abnormal water level fluctuation intervals associated with flow path nodes in the cross-reservoir dynamic association map;

[0077] In this step, the water level fluctuation feature library is a predefined normal / abnormal water level pattern (such as a flood peak waveform and a drought period flat curve).

[0078] Real-time water level signal refers to the information of the current water level height directly obtained from water bodies (such as rivers, lakes, reservoirs, etc.) through various sensors and technical means.

[0079] The abnormal water level fluctuation range refers to the time period that deviates from the characteristic library pattern (such as the water level rise rate exceeds the threshold for 2 consecutive hours).

[0080] In the embodiment of the present application, the real-time water level signals of each reservoir are first synchronized at a frequency of minutes through the Internet of Things device. Then, the dynamic time warping algorithm is used to match the real-time water level signal with the preset water level fluctuation feature library. If the matching gap exceeds the threshold, it is marked as an abnormal interval (such as a sudden rise of 1.8m in the water level within 2 hours). Finally, the cross-reservoir dynamic correlation map is extracted, and the upstream nodes of the abnormal reservoir are traced back (such as the flood discharge of Reservoir A causes the abnormality of Reservoir C), and the abnormal water level fluctuation interval of the key water flow path is located.

[0081] One day, the water level at Reservoir C rose rapidly due to heavy rainfall upstream. The system simultaneously collected real-time water level signals from various reservoirs and performed a spatiotemporal match with a pre-set database of water level fluctuation characteristics. Using sliding window technology and the isolation forest algorithm, the system identified that the water level at Reservoir C exceeded the normal fluctuation range and marked it as an abnormal fluctuation range. Further analysis, combined with dynamic correlation graphs, revealed that this was a chain reaction caused by a large-scale flood discharge from Reservoir D upstream in a short period of time. This result was passed on to the next step to assess the overall risk level.

[0082] 104. Determine the water level imbalance risk level of the inter-basin reservoir group based on the mapping relationship between the inter-reservoir dynamic association map and the abnormal water level fluctuation range;

[0083] In this step, the water level imbalance risk level refers to the risk level (such as low / medium / high) divided according to the degree of abnormal fluctuation and the topological structure of the map.

[0084] In the embodiment of the present application, first, the topological importance of each reservoir node in the cross-reservoir dynamic association map is calculated based on the algorithm (for example, the hub node weight is 0.9). Then, the abnormal amplitude (Z value), association strength and node importance of the abnormal water level fluctuation interval are integrated, and the risk is quantified by the weighted formula (risk value = node weight × abnormal Z value × association strength). Finally, the risk level is divided according to the preset threshold (for example, >0.8 is high risk), and the water level imbalance risk level of the reservoir group is output.

[0085] Based on the results of step 103, the system combines the dynamic correlation map across reservoirs and uses a Bayesian network model to assess the overall risk of reservoir group B. For example, it finds that abnormal fluctuations in reservoir C may cause downstream reservoir G to face the risk of overflow, while the other reservoirs are within a safe range. Ultimately, the system classifies the risk levels into high risk (reservoir C), medium risk (reservoir G), and low risk (the remaining reservoirs). It also issues an early warning to the management team, recommending that measures be taken to alleviate the pressure on reservoir C as a priority.

[0086] 105. Generate a control instruction according to the water level imbalance risk level, wherein the control instruction includes a flood discharge path optimization plan and a water storage capacity adjustment ratio.

[0087] In this step, control instructions are specific operational guidelines or commands generated in the water resources management system based on the analysis of current hydrological conditions, weather forecasts and historical data. They aim to optimize the allocation and management of water resources, ensure the safe operation of water conservancy facilities, and respond to potential risks such as floods or droughts.

[0088] The flood discharge path optimization plan refers to the dynamic adjustment of the flood discharge gate opening and the target reservoir based on the risk level.

[0089] The water storage capacity adjustment ratio refers to the redistribution of water storage according to the load of upstream and downstream reservoirs (e.g. the capacity of downstream reservoirs is expanded by 5%).

[0090] In the embodiment of the present application, first, the correlation strength coefficient in the dynamic correlation map is converted into a path weight (weight = 1 / correlation strength), and an algorithm is used to search the map for the flood discharge path optimization scheme that has the least impact on the downstream (for example, avoiding the hub node C and selecting the A→D→river path). Then, a linear programming model is constructed, and the total reservoir capacity safety threshold is used as a constraint condition to dynamically allocate the water storage capacity adjustment ratio of each reservoir according to the risk level. Finally, the system automatically controls the gate opening, executes the flood discharge path optimization scheme, adjusts the water pumping volume to achieve the water storage capacity target, and generates a control instruction.

[0091] Based on the risk classification in step 104, the system automatically generates control instructions. For example, given the high risk level of Reservoir C, the system recommends increasing its flood discharge to Reservoir H downstream while reducing water storage in other reservoirs to free up space. Furthermore, the system optimizes flood discharge paths, prioritizing channels with minimal downstream impact. These instructions are sent directly to the operating facilities of the relevant reservoirs via the automated control system, successfully preventing the possibility of an overflow at Reservoir C and ensuring the safe operation of the entire reservoir complex.

[0092] In summary, steps 101 to 105 form a complete closed-loop management process, from data collection and dynamic correlation analysis to risk assessment and control instruction generation. In practical scenarios, this approach can monitor water level changes across reservoirs in real time, quickly identify potential risks, and generate scientifically sound control plans, significantly improving the efficiency and safety of water resources management and ensuring the smooth implementation of flood control and drought relief efforts.

[0093] In order to further improve the dynamics and environmental adaptability of the cross-reservoir dynamic correlation map, the weight ratio is first dynamically adjusted according to the instantaneous change rate of meteorological parameters and the accumulated amount of soil moisture to enhance the model's response to sudden weather and long-term infiltration. Then, the temporal fluctuation amplitude of the water level parameters is superimposed with the weight to generate a hydraulic impact value that characterizes the impact of the external environment, and a preliminary hydraulic conduction path is constructed based on the difference in the impact values ​​of adjacent nodes. The path connection strength is further dynamically corrected based on the synchronization of water level changes to ensure the timeliness and accuracy of the conduction relationship. Finally, the reservoir geographic coordinates, corrected path and strength data are bound to form a cross-reservoir dynamic correlation map, providing spatial topological support for coordinated management of the watershed. In some embodiments, the correlation strength coefficient and the water level measurement parameter are jointly encoded in step 102 to generate a cross-reservoir dynamic correlation map, including:

[0094] 201. Dynamically assigning a weight ratio of the meteorological parameter to the soil moisture parameter in the correlation strength coefficient according to the instantaneous change rate of the meteorological parameter and the cumulative amount of the soil moisture parameter;

[0095] In step 201, the instantaneous rate of change of meteorological parameters refers to the real-time gradient of meteorological factors such as temperature and rainfall. The cumulative value of the soil moisture parameter refers to the integral value of the soil moisture parameter over a set time period (e.g., 24 hours). Weight allocation refers to adjusting the contribution ratio of meteorological and soil moisture to the correlation strength through an adaptive algorithm.

[0096] In an embodiment of the present application, a sliding window mechanism is first used to calculate the instantaneous rate of change of meteorological parameters (such as the hourly rainfall differential value), and an integral algorithm is used to accumulate the soil moisture parameter sensor data over time to calculate the cumulative amount. Then, the two types of parameters are mapped to the [0,1] interval through normalization processing, and the weight ratio is dynamically assigned based on an adaptive weighting model (such as the entropy weight method). For example, when the meteorological change rate exceeds the threshold, its weight ratio is increased to 70%, and the soil moisture weight is reduced to 30%. The final output weight ratio is used for the subsequent calculation of the hydraulic impact value.

[0097] 202. Superimposing the time series fluctuation amplitude of the water level measurement parameter with the weight ratio to generate a hydraulic influence value representing the influence of the external environment on the reservoir node, and constructing a hydraulic conduction path between the reservoir nodes based on the difference between the hydraulic influence values ​​of adjacent reservoir nodes;

[0098] In step 202, the time series fluctuation amplitude refers to the standard deviation or range of the water level measurement parameter over the time series, reflecting the severity of changes in reservoir water storage. The hydraulic impact value is a comprehensive indicator that integrates environmental weights and water level fluctuations, quantifying the impact of the external environment on reservoir nodes. The hydraulic conduction path refers to the directed edges constructed based on the gradient differences in the hydraulic impact values ​​of adjacent reservoirs, representing the direction of water potential energy transmission.

[0099] In an embodiment of the present application, the time series fluctuation amplitude of the reservoir water level sensor is first extracted, and the time series fluctuation amplitude of the water level measurement parameter (such as the variance of the water level change within 24 hours) is calculated after filtering and denoising. This fluctuation amplitude is linearly superimposed with the weight ratio output in step 201. Subsequently, the spatial adjacency relationship of the reservoir nodes is determined based on the triangulation algorithm, and the difference (ΔH) in the hydraulic influence value between adjacent nodes is calculated. If the difference is greater than a preset threshold, a hydraulic conduction path from the high-value node to the low-value node is constructed, and an initial connection strength (such as the absolute value of ΔH) is assigned.

[0100] 203. Dynamically correct the connection strength of the hydraulic conduction path based on the synchronous change trend of the water level measurement parameter in the hydraulic conduction path to obtain a corrected connection strength;

[0101] In step 203, the synchronization trend refers to the correlation between multiple reservoir water level parameters in the time dimension, which is quantified by covariance or dynamic time warping algorithm. Connection strength modification refers to strengthening or weakening the weight of the transmission path based on the synchronization analysis results.

[0102] In an embodiment of the present application, for a reservoir node with a hydraulic conduction path, a time series segment of its water level measurement parameter is extracted, and a correlation coefficient algorithm is used to calculate the synchronization index. If the correlation coefficient is greater than 0.8, the connection strength is enhanced by an exponential weighting method (such as strength = original strength * (1 + correlation coefficient)). If the correlation coefficient is less than 0.3, an attenuation function is used to reduce the strength. At the same time, a time lag analysis (such as a cross-correlation function) is introduced to determine the conduction delay and dynamically adjust the path direction. For example, if the water level change of reservoir A lags behind that of reservoir B by 2 hours, the conduction path direction is corrected to A→B. Finally, the corrected connection strength is obtained.

[0103] 204. Bind the geographical location coordinates, hydraulic conduction paths, and corrected connection strengths of the reservoir nodes to generate a cross-reservoir dynamic association map.

[0104] In step 204, geographic coordinates refer to a set of numerical values ​​used to determine the precise location of a reservoir node on the Earth's surface. Data binding encapsulates spatial coordinates, path topology, and intensity values ​​into a graph data structure. The cross-reservoir dynamic association graph is a multidimensional relationship network stored in a graph database, supporting real-time updates and visual queries.

[0105] In this embodiment, the geographic coordinates of the reservoir nodes are first imported into a geographic information system and spatially aligned with the corrected hydraulic conduction path from step 203. Next, a graph modeling tool is used to construct a weighted directed graph with node attributes (coordinates, current water level) and edge attributes (connection strength, conduction direction). Finally, an interactive, dynamic cross-reservoir graph is generated using WebGL technology, supporting the time-sliced ​​display of the coupling relationship between environmental parameters and hydraulic conduction.

[0106] Here's a specific example:

[0107] During a prolonged summer drought in a certain province's reservoir group, the system detected abnormal water level fluctuations in 15 reservoirs due to agricultural irrigation. In step 201, meteorological parameters indicated a 30-day, instantaneous rainfall rate of only 2 mm / h (below the historical average of 8 mm / h), while cumulative soil moisture in the irrigated area reached 1200 mm (exceeding the threshold of 800 mm). Using an entropy weighting method, the system dynamically assigned a soil moisture weight of 65% and a meteorological weight of 35%. In step 202, based on water level sensor data, the system found that upstream reservoir P experienced a daily water level fluctuation standard deviation of 0.8 (impact value 78) due to farmland pumping, while downstream reservoir Q experienced smaller fluctuations due to river recharge (impact value 52). Triangulation was used to determine the adjacency of the two reservoirs, and a hydraulic conduction path (initial strength 26) was generated from P to Q. In step 203, dynamic time warping analysis revealed strong synchronization (correlation coefficient 0.91) and a 40-minute lag between the P and Q water levels during the daily irrigation peak at 3:00 a.m. The connection strength was adjusted to 50, and the delayed conduction relationship was annotated. Step 204 imports the BeiDou coordinates and the corrected path into the platform, generating a thermal map showing a deep red, high-intensity path from P to Q. By overlaying the soil moisture distribution, the core area affected by agricultural water use is identified. Based on this, the water department diverts 2 million cubic meters of water to Q, successfully mitigating the risk of drying up in the P reservoir area.

[0108] In summary, steps 201 to 204, through dynamic weight allocation, hydraulic conduction path construction and intensity correction, and multidimensional data binding, enable this solution to accurately quantify and visualize cross-reservoir relationships. In this example, the system successfully identified the primary risk conduction paths during a typhoon and issued a two-hour advance warning of the overflow risk at downstream reservoir Y. Compared to static correlation models, this method improves the accuracy of environmental coupling analysis and enhances emergency response efficiency, providing real-time decision support for integrated watershed management.

[0109] In order to further improve the time-series sensitivity and dynamic screening accuracy of hydraulic conduction path construction, the rising and falling stages of water level fluctuations are first weighted separately to distinguish the differentiated driving effects of the external environment on water storage and loss. Subsequently, a hydraulic impact value is generated by directional superposition to highlight the net water storage trend. The absolute difference in the impact values ​​of adjacent nodes is calculated and compared with the threshold to screen out candidate paths with significant conduction potential. Combined with the consistency of the water level fluctuation direction in the current time window, logical conflict paths are eliminated and effective conduction relationships are activated. Finally, the activated path is superimposed with the historical preset path to form a hydraulic conduction network with both dynamic response and empirical laws. In some embodiments, the time-series fluctuation amplitude of the water level measurement parameter and the weight ratio are superimposed in step 202 to generate a hydraulic influence value that characterizes the influence of the external environment on the reservoir node, and based on the difference between the hydraulic influence values ​​of adjacent reservoir nodes, a hydraulic conduction path between reservoir nodes is constructed, including:

[0110] 301. Perform weighted processing on the rising phase and the falling phase of the time series fluctuation amplitude of the water level measurement parameter according to the weight ratio to obtain weighted rising phase time series fluctuation amplitude and falling phase time series fluctuation amplitude;

[0111] In step 301, the time series fluctuation amplitude in the rising phase refers to the fluctuation amount in the continuous rising interval of the water level time series curve (such as the extreme difference in water level change during the period with slope > 0). The time series fluctuation amplitude in the falling phase refers to the fluctuation amount in the continuous falling interval of the water level time series curve (such as the extreme difference in water level change during the period with slope < 0). Weighted processing refers to assigning differentiated weights to the rising / falling phases according to the weight ratio. For example, when the meteorological weight is high, the rising phase (rainstorm inflow) is strengthened, and when the soil moisture weight is high, the falling phase (infiltration loss) is strengthened.

[0112] In an embodiment of the present application, the inflection point of the time series fluctuation amplitude curve of the water level measurement parameter is first detected by the differential method, and the complete sequence is divided into alternating rising stages and falling stages. The fluctuation amplitude (such as the difference between the maximum and minimum values ​​in the stage) is calculated for each stage. Then, according to the weight ratio dynamically assigned in step 201 (such as meteorological weight α, soil moisture weight β), the amplitude of the rising stage is multiplied by (α+β×0.5) and the amplitude of the falling stage is multiplied by (β+α×0.5), respectively, to reflect the dominant difference of environmental parameters on the rise and fall of water levels. Finally, the weighted rising stage time series fluctuation amplitude and the falling stage time series fluctuation amplitude are output.

[0113] 302. Directionally superimpose the weighted time series fluctuation amplitude in the ascending phase and the time series fluctuation amplitude in the descending phase to generate a hydraulic impact value representing the influence of the external environment on the reservoir node;

[0114] In step 302, directional superposition refers to physically combining the weighted amplitudes of the rising and falling phases. For example, positive superposition of rising amplitudes reflects the inflow contribution, while negative superposition of falling amplitudes reflects the runoff effect. The hydraulic impact value is a scalar value generated by directional superposition, with the sign indicating the net storage trend of the reservoir node (positive for increased storage, negative for increased runoff).

[0115] In this embodiment, the weighted rising phase and falling phase fluctuation amplitudes output in step 301 are accumulated. For example, if a reservoir has two rising phases (weighted amplitudes of +8m and +5m) and one falling phase (weighted amplitude of -6m) within 12 hours, the hydraulic impact value is +7m. This value, through both symbolic and numerical representation, represents the hydraulic impact value of the reservoir node affected by the external environment and is used in subsequent transmission path construction.

[0116] 303. Calculate the absolute difference of hydraulic influence values ​​of adjacent reservoir nodes, compare the absolute difference with a preset hydraulic conduction path generation threshold, and set the preset hydraulic conduction path whose absolute difference exceeds the generation threshold as a candidate conduction path;

[0117] In step 303, the absolute difference refers to the absolute difference in hydraulic impact values ​​between adjacent reservoir nodes, which is used to quantify the difference in conduction potential energy. The generation threshold refers to a preset conduction path trigger threshold (e.g., ΔH ≥ 5m) to filter out low-strength connections. Candidate conduction paths are the set of directed edges that satisfy ΔH ≥ the threshold, preliminarily characterizing the potential direction of water energy transfer.

[0118] In this embodiment, the neighbor relationship of the reservoir nodes is first determined based on a spatial proximity algorithm. For each pair of adjacent reservoir nodes, ΔH = |H1-H2| is calculated. If ΔH ≥ a generation threshold T (e.g., 4m), a candidate conductive path is generated from the high-H value node to the low-H value node, and ΔH is used as the initial connection strength. For example, if reservoir A has H = +10m and adjacent reservoir B has H = +3m, ΔH = 7m ≥ T, resulting in a candidate conductive path from A to B with a strength of 7.

[0119] 304. Filter the candidate conduction paths that meet activation conditions based on consistency between the connection strengths of the candidate conduction paths and the fluctuation directions of the water level measurement parameters in the current time window, to obtain a set of activated candidate conduction paths.

[0120] In step 304, the consistency of the fluctuation direction refers to the matching of the water level change trends of the nodes at both ends of the candidate path within the current time window (such as both rising or both falling). The activation condition refers to the logical matching of the path strength and the fluctuation direction (such as the upstream rises and the downstream rises, or the upstream falls and the downstream falls with a lag). The candidate conduction path set refers to the set of potential hydraulic conduction paths that are preliminarily screened according to certain standards and calculation methods in the process of analyzing the dynamic association between the internal and adjacent reservoir nodes of the reservoir system. The connection strength refers to a quantitative indicator that measures the degree of interaction or influence between adjacent reservoir nodes in the context of the hydraulic conduction path between reservoir nodes. The water level measurement parameters within the time window refer to the data set obtained by monitoring and recording the reservoir water level within a specific time period (i.e., the "time window").

[0121] In this embodiment, the candidate conduction path is first extracted for consistency in the direction of fluctuations in water level measurement parameters at the nodes at both ends of the candidate conduction path within a recent time window (e.g., 3 hours) (increases are marked as +1, decreases as -1). If the directions are consistent (e.g., A↑ and B↑), the candidate conduction path is retained and the original connection strength is maintained. Then, if the directions are opposite but the downstream lags the upstream (using cross-correlation analysis to detect a lag time of ≤1 hour), the strength is adjusted according to the lag coefficient (e.g., 0.7). Otherwise, the candidate conduction path is eliminated. For example, if C in a candidate path C→D has recently increased (+1) and D has decreased (-1), with no lag correlation, the path is considered invalid. Finally, a set of activated candidate conduction paths is obtained.

[0122] 305. Superimpose the activated candidate conduction path set with the preset conduction path in the cross-reservoir dynamic association map to obtain a hydraulic conduction path.

[0123] In step 305, the pre-set conduction path refers to a fixed conduction relationship (e.g., a natural river channel connection) predefined based on historical hydrological data or manual experience. A hydraulic conduction path is an effective path for water flow to flow or interact between different reservoir nodes within a reservoir system, determined based on analysis of water level changes and their influencing factors.

[0124] In this embodiment, a preset conduction path (e.g., a fixed connection E→F) is first loaded from the cross-reservoir dynamic association map. The set of candidate conduction paths activated in step 304 is then overlaid with the preset conduction paths. If both a dynamic conduction path and a preset conduction path exist for the same node pair, the dynamic conduction path is retained and its strength is updated. If only a single type exists, it is retained. Finally, the hydraulic conduction path is obtained. For example, if the dynamic path G→H (strength 9) conflicts with the preset conduction path H→G (strength 5), only the G→H path is retained in the final map.

[0125] Here's a specific example:

[0126] In a scenario where reservoir group B in a certain province was responding to Typhoon Haikui, the water level of Reservoir J ​​fluctuated dramatically due to the typhoon's heavy rainfall. In step 301, the system weighted the amplitude of its temporal fluctuations based on a meteorological weight of 90% and a soil moisture weight of 10%, calculating a weighted amplitude of 15m in the rising phase (dominated by heavy rain) and a weighted amplitude of 2m in the falling phase (with a weak infiltration effect). Due to lower rainfall intensity, the adjacent reservoir K had an amplitude of 6m in the rising phase and 8m in the falling phase (with a significant influence from soil moisture). In step 302, hydraulic impact values ​​were generated through directional superposition. The net water storage trend of J was +13m (15-2), while the impact value of K due to the runoff effect was -2m (6-8). Step 303 calculated the absolute difference between the two, ΔH = 15m (exceeding the threshold of 4m), generated a candidate conduction path from J to K, and assigned an initial strength of 15. Step 304 further verifies that the water level at J continues to rise within the current time window, and that K rises synchronously with the floodgate opening, one hour later. The rise is consistent in direction and with a reasonable delay, activating the J→K path. In step 305, the system dynamically overrides the pre-set dry season water diversion path, K→J, prioritizing the high-intensity J→K conduction path. Based on this, the flood control command center initiates emergency flood diversion from J to K, lowering the J reservoir water level by 1.5 meters within two hours, successfully mitigating the risk of dam failure and ensuring downstream safety.

[0127] In summary, steps 301 to 305, through directional weighting of time-series fluctuations, dynamic path activation screening, and multi-source path fusion, allow this solution to accurately identify the J→K abnormal transmission path in typhoon emergency scenarios, overriding historical reverse flow preset paths. This shortens flood diversion decision-making response time and successfully prevents flooding of downstream towns. Compared to traditional static models, the dynamic transmission path has a lower false alarm rate, providing highly reliable topological support for coordinated river basin regulation under extreme weather conditions.

[0128] In order to further improve the dynamics and spatial linkage of the risk assessment of water level imbalance in a group of inter-basin reservoirs, the water flow path nodes in the dynamic map are first matched with the water level anomaly intervals to establish a correlation between the path intensity and the duration of the anomaly. The spatial distribution density and the cumulative effect of abnormal fluctuations in time are statistically analyzed to quantify the risk diffusion range and persistence. By comparing the spatial distribution range and the cumulative effect in time with the preset thresholds, low, medium and high risk levels are divided. In particular, when the two indicators exceed the limit at the same time, it is determined to be a high risk, realizing multi-dimensional risk coupling analysis and providing a basis for hierarchical management and control. In some embodiments, the water level imbalance risk level of the inter-basin reservoir group is determined by the mapping relationship between the inter-reservoir dynamic correlation map and the water level abnormal fluctuation interval described in step 104, including:

[0129] 401. Dynamically match the water flow path nodes in the cross-reservoir dynamic association map with the abnormal water level fluctuation interval to determine the corresponding relationship between the connection strength of the water flow path nodes and the duration of the abnormal water level fluctuation interval;

[0130] In step 401, the water flow path node refers to the node in the dynamic association map that represents the hydraulic conduction relationship between reservoirs, including the connection strength (quantified conduction capacity) and conduction direction attributes. The abnormal water level fluctuation interval refers to the continuous time period when the reservoir water level exceeds the historical normal range (such as ±2 times the standard deviation), and its start and end time and fluctuation amplitude are recorded. Dynamic matching refers to aligning the time attributes of the water flow path node (such as the conduction path activation period) with the time window of the water level abnormal interval to establish a mapping relationship between path strength and abnormal duration;

[0131] In the embodiment of the present application, all activated water flow path nodes (such as A→B) in the cross-reservoir dynamic association map are first extracted, and their connection strength and activation time period are recorded. At the same time, the abnormal water level fluctuation interval of each reservoir (such as continuous over-threshold fluctuation for 3 hours) is detected from the water level monitoring data. Through the time series alignment algorithm (such as dynamic time warping), the activation period of the path node is matched with the abnormal interval. For each path node, the overlapping time of its activation period and the abnormal interval of the upstream and downstream nodes is calculated, and a mapping relationship table is established to record the corresponding relationship between the path connection strength and the overlapping time.

[0132] 402. Based on the corresponding relationship, the spatial distribution range and time cumulative effect of the abnormal water level fluctuation range in the cross-reservoir dynamic correlation map are counted.

[0133] In step 402, the spatial distribution range refers to the geographic coverage of abnormal water level fluctuations within the basin, calculated by the spatial density of abnormal reservoir nodes. The temporal cumulative effect refers to the combined effect of the persistence and transmission delay of abnormal fluctuations in the temporal dimension, quantified by the weighted accumulation of the abnormal duration.

[0134] In the embodiment of the present application, the abnormal reservoir node in the abnormal water level fluctuation range is firstly taken as the center, and the kernel density estimation algorithm is used to generate the spatial distribution range, and the density of abnormal nodes per unit area is calculated (e.g. 8 / 100km 2 ) and weighted by path connection strength (density value × average strength). For each abnormal node, the overlap duration of its associated paths is accumulated (for example, if library X is associated with three paths, the total overlap duration is 6 hours), and an exponential decay function is introduced to calculate the cumulative effect over time. This generates a spatial distribution range and cumulative effect over time, identifying high-risk clusters.

[0135] 403. Compare and analyze the spatial distribution range and time cumulative effect with the preset threshold value, and divide the water level imbalance risk level interval of the cross-basin reservoir group according to the comparative analysis results. When the spatial distribution range and the time cumulative effect exceed the preset threshold value at the same time, it is determined to be a high risk level.

[0136] In step 403, the preset threshold value includes a spatial density threshold value (e.g., 5 / 100km2 ) and a cumulative time threshold (e.g., 8 hours) are set based on historical disaster data. Risk levels are divided into high risk (double thresholds exceeded), medium risk (single threshold exceeded and lasting for >30 minutes), and low risk (single threshold exceeded and lasting for <10 minutes).

[0137] In this embodiment, the spatial distribution range and cumulative effect of abnormal fluctuations are first compared with preset thresholds. When the spatial density reaches or exceeds the preset threshold of 5 abnormal nodes per 100 square kilometers, and the cumulative effect reaches or exceeds 8 hours, the risk level is marked as high. Conversely, if only one or both of these thresholds are below the threshold, the risk level is classified as medium or low, depending on the specific situation.

[0138] Here's a specific example:

[0139] During the period when reservoir group B in a certain province was responding to the passage of Typhoon Mangkhut, three of the six reservoirs (X, Y, and Z) experienced significant abnormal water level fluctuations. According to step 401, two conduction paths were first identified and activated in the cross-reservoir dynamic association map: Reservoir X → Y (connection strength of 18, activation period of 12:00-15:00) and Reservoir Y → Z (connection strength of 12, activation period of 13:30-16:00). Further analysis revealed that the abnormal fluctuation period for Reservoir X was 12:00-14:30, for Reservoir Y it was 13:00-16:00, and for Reservoir Z it was 14:00-17:00. The matching results showed that the overlap time between the X → Y path and the abnormal fluctuation period was 2.5 hours, while the overlap time for the Y → Z path was 2 hours. Then, in step 402, it is calculated that the spatial density of the abnormal fluctuation range in the entire reservoir group is 8 abnormal nodes per 100 square kilometers (the threshold is set to 5), and the time cumulative effect reaches 10 hours (the threshold is set to 8 hours). These data show that not only is the affected area extensive, but the abnormal fluctuation also lasts for a long time, posing a threat to the stability of the entire system. Finally, in step 403, the above-mentioned spatial distribution range and time cumulative effect are compared and analyzed with the preset risk level threshold. Since both indicators exceed their respective thresholds, the system automatically determines that this event belongs to a high-risk level and triggers a full-area flood diversion plan. Accordingly, the water resources management system initiated emergency dispatch measures for the three reservoirs X, Y, and Z, adjusting the storage capacity to alleviate flood pressure and ensure the safety of downstream areas. This series of precise and timely response measures effectively mitigated the impact of the disaster and protected the safety of people's lives and property.

[0140] In summary, steps 401 to 403, by combining the mapping relationship between the cross-reservoir dynamic correlation map and the abnormal water level fluctuation range, can accurately identify and quantitatively assess water level imbalance risk areas within a cross-basin reservoir group. This approach not only improves the precision of water resource management but also enhances the ability to respond to sudden hydrological events, helping to develop more scientific and reasonable reservoir operation strategies and ensure the security and stability of regional water resources.

[0141] In order to further improve the spatiotemporal correlation and dynamic adaptability of the extraction of abnormal water level fluctuation intervals, the time window length is first adaptively adjusted according to the connection density of the water flow path nodes to achieve high-frequency monitoring of high-density areas and global coverage of low-density areas. The segmented fluctuation segments are dynamically time-regularized and matched with the abnormal forms in the preset feature library to screen out abnormal segments with high similarity. By mapping to the water flow path nodes and calculating the correlation influence intensity, the abnormal fluctuation interval is defined in combination with the spatial distribution and cumulative duration to ensure the spatiotemporal correlation and conduction logic consistency of anomaly detection. In some embodiments, step 103 is described in which the real-time water level signal is spatiotemporally matched with the preset water level fluctuation feature library to extract the abnormal water level fluctuation interval associated with the water flow path nodes in the cross-reservoir dynamic correlation map, including:

[0142] 501. Dynamically segmenting the real-time water level signal into continuous fluctuation segments according to a preset time window, wherein the length of the preset time window is adaptively adjusted according to the connection density of the water flow path nodes in the cross-reservoir dynamic association map;

[0143] In step 501, the real-time water level signal refers to the time series data collected in real time by the reservoir water level sensor, with a time resolution of up to minutes. The preset time window refers to the length of the period for dynamically segmenting the data, with an initial value of 1 hour, which is adaptively adjusted according to the connection density of the water path nodes (the number of conduction paths per unit area). The continuous fluctuation segment refers to a continuous sequence of water level change data segmented from the real-time water level signal within a specific time window. The connection density refers to the number of activated water flow paths within a unit geographical area. The higher the density, the more complex the conduction relationship, and the time window needs to be shortened to improve the analysis accuracy.

[0144] In an embodiment of the present application, first, the currently activated water flow path nodes are extracted from the cross-reservoir dynamic association map, and the spatial connection density of these nodes is calculated. The spatial connection density reflects the number of water flow paths activated within a unit geographical range. The higher the density, the more complex the conduction relationship. Based on the spatial connection density value, the time window length is dynamically adjusted. If the connection density is high (for example, more than 8 per 100 square kilometers), a shorter time window (such as 0.5 hours) is set to improve the analysis accuracy. If the connection density is low, a longer time window (such as 1 hour) is used. Then, the real-time water level signal is segmented into continuous fluctuation segments using a sliding window method. For example, for a 24-hour data set, if a 0.5-hour time window is used for segmentation, 48 segments can be obtained, each of which contains a 30-minute water level change curve.

[0145] 502. Match the continuous fluctuation segments with the fluctuation patterns in a preset water level fluctuation feature library segment by segment in a temporal and spatial order, and screen out abnormal fluctuation segments in the continuous fluctuation segments whose matching degree with the fluctuation patterns exceeds a preset threshold based on the segment-by-segment matching results;

[0146] In step 502, the fluctuation morphology refers to the historical abnormal fluctuation pattern (such as a sudden rise type and a slow fall type) stored in the preset feature library, including morphological curves and time series characteristics. The water level fluctuation feature library is a data set containing a variety of typical water level change patterns, which is used to identify and classify the changes in reservoir water levels monitored in real time. Segment-by-segment matching refers to aligning the real-time fluctuation segments with the feature library morphology in chronological order and calculating the similarity. The matching threshold refers to a preset similarity judgment standard used to screen abnormal segments. An abnormal fluctuation segment refers to a continuous water level change data with significant abnormal characteristics identified by comparing and analyzing the typical patterns in the preset water level fluctuation feature library when monitoring the reservoir water level.

[0147] In an embodiment of the present application, various typical abnormal fluctuation patterns are read from a preset water level fluctuation feature library as templates. Then, for each continuous fluctuation segment, a dynamic time warping algorithm is used to match it with the abnormal fluctuation pattern template and calculate the similarity. Based on the segment-by-segment matching results, it is possible to find which continuous fluctuation segments are closest to the known abnormal fluctuation patterns. If the minimum distance between a continuous fluctuation segment and the template is lower than a set threshold (e.g., 0.3), the segment is marked as an abnormal fluctuation segment.

[0148] 503. Map the abnormal fluctuation segment to the water flow path node, and calculate the correlation influence strength of the abnormal fluctuation segment on the adjacent reservoir node based on the connection strength of the mapped water flow path node;

[0149] In step 503, the association impact intensity refers to the degree of transmission of the abnormal fluctuation through the flow path nodes to adjacent reservoirs. This is calculated by combining the path connection strength and the abnormal amplitude. Abnormal fluctuation segment mapping involves associating the abnormal segment with the flow path node of the reservoir in which it resides and spreading the impact along the transmission direction.

[0150] In this embodiment, the abnormal fluctuation segments marked in the previous step are first matched with the flow path nodes in the cross-reservoir dynamic association map to identify the specific reservoir locations and upstream and downstream associated paths where these abnormal fluctuation segments are located. Then, the association impact strength on each path is calculated according to a formula based on the path connection strength of the mapped flow path nodes and the abnormal fluctuation amplitude.

[0151] 504. Obtain an abnormal water level fluctuation interval associated with the water flow path node according to the spatial distribution range and cumulative duration of the correlation impact intensity in the cross-reservoir dynamic correlation map.

[0152] In step 504, the spatial distribution range refers to the geographic area affected by the abnormal fluctuation, quantified using kernel density estimation. The cumulative duration refers to the duration of the abnormal fluctuation along its impact path, calculated using a weighted total duration. The abnormal water level fluctuation interval refers to a specific time period with significant abnormal characteristics identified through reservoir water level monitoring and analysis.

[0153] In this embodiment, the correlation impact strength is first calculated using a kernel density estimation method to calculate the spatial distribution of the geographic area affected by the abnormal fluctuation to quantify the impact range of the abnormal fluctuation. Next, for each affected water flow path, the duration of the abnormal fluctuation is accumulated, and the weighted cumulative duration is calculated, taking into account the decreasing impact effect over time. Finally, if the calculated spatial distribution density and cumulative duration both exceed the preset threshold, it is determined to be an abnormal water level fluctuation interval.

[0154] Here's a specific example:

[0155] Reservoir group B in a certain province experienced regional heavy rainfall during the plum rain season, resulting in a significant water level rise in Reservoir X. In step 501, due to the high connection density (12 per 100 square kilometers), a 0.5-hour time window was selected, and the real-time data from Reservoir X was segmented into multiple segments. One segment showed a 1.2-meter water level rise between 12:00 and 12:30. In step 502, this data segment was compared with the "sudden rise" pattern. The result showed a distance of 0.25, which was below the set threshold and was therefore marked as an anomaly. In step 503, this abnormal fluctuation was mapped to the flow paths X→Y and X→Z, and the respective impact strengths were calculated. Finally, in step 504, after evaluating the spatial density and cumulative duration, an abnormal fluctuation interval was identified, and coordinated flood discharge measures were initiated accordingly, effectively reducing the flood risk. This approach not only improves the accuracy of early warnings but also accelerates response time, significantly enhancing flood control capabilities.

[0156] In summary, steps 501 to 504, by performing spatiotemporal matching of real-time water level signals with a pre-defined water level fluctuation signature database, can accurately identify abnormal water level fluctuation intervals within the cross-reservoir dynamic correlation map, providing an efficient method for monitoring and providing early warning of potential water level imbalance risks. This approach not only improves the accuracy and timeliness of water resource management but also enhances the ability to respond to emergencies, facilitates the development of more scientific and rational scheduling strategies, and ensures the safe operation of a reservoir cluster.

[0157] In order to further improve the accuracy and spatial conductivity of the calculation of the intensity of abnormal fluctuation impact, the water flow path nodes that are highly correlated with the abnormal fragments are first screened through spatiotemporal overlap calculation to ensure the accuracy of the mapping target. The initial impact amount is calculated based on the connection strength of the target node and the abnormal fluctuation amplitude to reflect the direct effect intensity. The initial impact amount is further allocated according to the connection strength ratio between the target node and the adjacent nodes, and the correlation impact intensity is obtained by accumulating the multi-path contribution value to realize the spatial diffusion modeling and quantitative evaluation of the abnormal conduction effect. In some embodiments, the step 503 maps the abnormal fluctuation fragment to the water flow path node, and calculates the correlation impact intensity of the abnormal fluctuation fragment on the adjacent reservoir node through the connection strength of the mapped water flow path node, including:

[0158] 601. Perform an overlap comparison between the abnormal fluctuation segment and the spatiotemporal position distribution of the water flow path nodes, and select the water flow path nodes with an overlap exceeding a preset ratio as target mapping nodes to which the abnormal fluctuation segment belongs;

[0159] In step 601, the spatiotemporal location distribution refers to the geographic location (latitude and longitude) and activation time period of the flow path node in the dynamic association map. The overlap percentage refers to the intersection of the spatiotemporal range of the abnormal fluctuation segment (e.g., the coordinate range of 12:30-13:30) and the spatiotemporal range of the flow path node. The target mapping node refers to the flow path node with an overlap of 50% or more with the abnormal fluctuation segment.

[0160] In an embodiment of the present application, first, the spatiotemporal range information of the abnormal fluctuation segment is extracted from the abnormal fluctuation segment, including the specific activation time period and geographic coordinate range. Then, this information is overlapped and compared with the spatiotemporal position distribution of all water flow path nodes in the dynamic association map. The time overlap duration and spatial intersection area between each water flow path node and the abnormal fluctuation segment are calculated. Finally, based on the calculated time overlap duration and spatial intersection area, the degree of overlap between the abnormal fluctuation segment and the water flow path node is evaluated. If the overlap reaches or exceeds 50%, the node is marked as a target mapping node.

[0161] 602. Calculate the initial influence of the abnormal fluctuation segment on the target mapping node according to the connection strength of the target mapping node;

[0162] In step 602, the initial impact refers to the direct impact strength of the abnormal fluctuation segment on the target mapping node, which is calculated by combining the node connection strength and the abnormal fluctuation amplitude. The connection strength refers to the quantitative value of the conduction capacity of the water path node.

[0163] In the embodiment of the present application, the maximum water level change amplitude is first extracted from the abnormal fluctuation segment (e.g., the water level rises by 1.5 meters within 2 hours). Then, the initial impact is calculated based on the connection strength of the target mapping node corresponding to the maximum water level change amplitude. Finally, combined with the connection strength of the target mapping node (e.g., a strength value of 20), the initial impact is calculated by multiplication (20×1.5=30).

[0164] 603. Based on the connection strength ratio between the target mapping node and the adjacent reservoir nodes, the initial influence amount is distributed to each adjacent reservoir node, and the distribution amount of the initial influence amount on each adjacent reservoir node is accumulated to obtain the associated influence strength.

[0165] In step 603, the connection strength ratio refers to the proportion of the connection strength between the target mapping node and each adjacent node. The allocation refers to the distribution of the impact of abnormal fluctuations across different flow path nodes, calculated according to a specific algorithm or rule. The associated impact strength refers to the cumulative value of the initial impact amounts allocated to adjacent nodes, reflecting the transmission effect of the abnormal fluctuations.

[0166] In an embodiment of the present application, the proportion of each path is first calculated based on the connection strength ratio of all adjacent paths of the target mapping node. For example, the target mapping node has two adjacent paths with strengths of 12 and 8, respectively, and the proportions are 60% and 40%. Then, the initial influence amount (such as 30) is proportionally distributed to the adjacent reservoir nodes (30×60%=18, 30×40%=12). Finally, the initial influence amounts received by each adjacent reservoir node from different paths are accumulated (such as a node has received 15 through other paths, the total strength is 18+15=33) to obtain the final association influence strength.

[0167] Here's a specific example:

[0168] During the typhoon response period of the B reservoir group in a certain province, Reservoir P experienced abnormal water level fluctuations (rising by 2 meters) from 12:00 to 13:00. First, the system extracted the spatiotemporal range of the abnormal segment (12:00-13:00, region A) and performed a spatiotemporal comparison with the activation period (12:00-14:00) and coverage area (region B) of the water flow path node P→S. The calculation time overlap was 1 hour and the spatial intersection was 80%. After the overlap was determined to meet the standard, P→S was marked as the target mapping node. Next, based on the connection strength of 18 at the P→S node and the abnormal amplitude of 2 meters, the initial impact was calculated to be 36. Then, based on the connection strength ratio of P→S's adjacent nodes S→T (strength 10) and S→U (strength 8) (55.6% and 44.4%), the initial impact was distributed as 20 for S→T and 16 for S→U. Finally, the accumulated historical impact of the S→T node is 15, and the total correlation strength reaches 35, triggering an automatic flood discharge command, lowering the reservoir P water level by 1.8 meters within 2 hours, effectively mitigating the dam break risk.

[0169] In summary, steps 601 to 603 accurately assess the transmission effects of abnormal fluctuations on the entire reservoir system by mapping abnormal fluctuation segments to flow path nodes and calculating the initial impact and distribution based on the node connection strength. This approach not only improves understanding of the impact of abnormal fluctuations but also provides strong support for the development of precise emergency response strategies. In the typhoon scenario, the successful quantification of the abnormal transmission effect of P→S→T / U enabled downstream reservoirs to initiate flood diversion measures in advance, reducing direct economic losses and improving the accuracy and efficiency of emergency response. Overall, this method significantly enhances water resource management and flood prevention and early warning capabilities.

[0170] In order to further improve the accuracy and coordination of the generation of control instructions for reservoir groups, the priority of flood discharge is first determined according to the risk level, and the proportion of flood discharge is allocated based on the difference between the current water storage capacity of the reservoir and the safety threshold to ensure rapid flood discharge in key areas. Generate a flood discharge path optimization plan based on the path connection strength and spatial distribution in the dynamic map, taking into account both efficiency and risk avoidance. Combine historical flood discharge data for the same period to match current needs, dynamically adjust the reservoir safety capacity threshold, and bind the adjustment ratio to the optimized path to form a complete set of control instructions for storage and discharge coordination, and realize global optimization scheduling of cross-reservoir resources. This method realizes the coordinated linkage of flood discharge priority, path optimization and historical data, ensures the scientific nature and pertinence of control measures, and improves the emergency response efficiency of cross-basin reservoir groups. In some embodiments, the generation of control instructions according to the water level imbalance risk level described in step 105 includes:

[0171] 701. Determine a flood discharge priority order for each reservoir node based on the risk interval corresponding to the water level imbalance risk level, and calculate a flood discharge allocation ratio for each reservoir node based on the difference between the current water storage capacity of each reservoir node and a preset safety capacity in the flood discharge priority order;

[0172] In step 701, the flood discharge priority order refers to the ranking of reservoir flood discharge urgency based on risk level, with high-risk reservoirs being prioritized for flood discharge. Risk intervals are typically used to describe the risk of reservoir water level imbalance and to formulate appropriate regulatory measures accordingly. The difference in preset safety capacity refers to the difference between a reservoir's current water storage and its preset safety capacity; a larger difference requires more flood discharge. The flood discharge allocation ratio refers to the proportion of flood discharge allocated to each reservoir based on priority and capacity difference.

[0173] In the embodiment of the present application, the risk interval is first divided according to the water level imbalance risk level (such as high risk corresponds to emergency flood discharge, low risk corresponds to slow discharge). Then, the difference between the current water storage capacity of each reservoir node and the preset safety capacity is calculated. The larger the difference, the more flood discharge is required. Then, combined with the flood discharge priority order, a higher proportion of flood discharge is allocated to high-risk nodes. For example, if the risk level of reservoir X is high and the capacity difference is 1 million cubic meters, and reservoir Y is medium risk and the difference is 500,000 cubic meters, then the flood discharge ratio of X is higher than that of Y. Finally, the flood discharge distribution ratio of each reservoir node is obtained.

[0174] 702. Generate a flood discharge path optimization plan based on the connection strength and spatial distribution of the water flow path nodes in the cross-reservoir dynamic association map;

[0175] In step 702, the flood discharge path optimization solution involves selecting the flood discharge route with the highest conduction efficiency based on the strength and spatial distribution of the water flow paths in the dynamic association map. Connection strength refers to the quantitative value of the conduction capacity of the path nodes; higher strength indicates higher flood discharge efficiency.

[0176] In an embodiment of the present application, all possible flood discharge path nodes and their connection strengths are first extracted from the cross-reservoir dynamic association map. Then, based on the spatially distributed data, high-risk areas or congested paths are excluded. For example, if a path has low connection strength and needs to pass through a geologically fragile area, it is excluded. Next, a graph theory algorithm (such as the shortest path or maximum flow algorithm) is used to optimize path selection, giving priority to paths with high connection strength and reasonable geographical distribution. Finally, an optimized flood discharge path plan is generated.

[0177] 703. Based on the matching relationship between the flood discharge volume allocation ratio and the historical flood discharge records for the same period, combined with the water level imbalance risk level, a water storage capacity adjustment ratio is generated, the water storage capacity adjustment ratio is associated with the flood discharge path optimization plan, and a control instruction is generated.

[0178] In step 703, the water storage capacity adjustment ratio refers to the dynamic adjustment of the reservoir water storage safety threshold according to the matching results of historical flood discharge records and the current risk level. Association binding refers to associating the flood discharge path with the adjusted water storage capacity to ensure the coordination of the control instructions. The flood discharge path optimization plan refers to the selection of the optimal flood discharge path and flow distribution strategy by analyzing the connection strength, spatial distribution and other relevant factors of the water flow path nodes in order to effectively deal with the risks brought by excessively high reservoir water levels in the water resources management and flood prevention early warning system. The control instruction is a specific operation command issued to the reservoir system (including a single reservoir or a group of multiple reservoirs) to guide on-site management personnel to perform corresponding adjustment and control actions.

[0179] In an embodiment of the present application, the current flood discharge allocation ratio is first matched with the historical flood discharge records for the same period, and the flood discharge effect under similar risk levels is analyzed. For example, if historical data shows that a reservoir can effectively lower the water level by discharging 50% of its water when the risk is high, a similar ratio is currently used. Then, the ratio is adjusted in combination with the water level imbalance risk level, such as increasing the flood discharge ratio when the risk is high. Finally, the water storage capacity adjustment ratio is bound to the path optimization plan to generate a control instruction (such as "X reservoir discharges 30% of its water through path X→Y→Z, with a flow limit of 100 cubic meters / second") to ensure that the flood discharge volume and the path plan are executed in coordination.

[0180] Here's a specific example:

[0181] During Typhoon Haiyan, three reservoirs, X, Y, and Z, were identified as high-risk in a certain province's reservoir group B. In step 701, based on the risk ranking (X>Y>Z) and the difference between each reservoir's current storage capacity and its safe capacity (X exceeded the limit by 8 million cubic meters, Y exceeded the limit by 6 million cubic meters, and Z exceeded the limit by 2 million cubic meters), flood discharge proportions were allocated according to priority: X accounted for 50% of the total flood discharge, Y accounted for 30%, and Z accounted for 20%. Step 702, based on the cross-reservoir dynamic correlation map, extracted high-connectivity paths (X→A: strength 25, Y→B: strength 18, Z→C: strength 10). Combined with spatial distribution analysis, X→A (downstream of the flood discharge area, 90% efficiency) and Y→B (avoiding residential areas, 85% efficiency) were prioritized as flood discharge paths. Step 703 matches historical high-risk data for the same period and reduces the safety capacity of X and Y by 15%. Finally, a control instruction is generated: X discharges 4 million cubic meters of flood water through the X→A path at a ratio of 50% (8 million × 50%), and Y discharges 1.8 million cubic meters of flood water through the Y→B path (6 million × 30%). This ensures that the flood discharge volume is accurately bound to the path plan, achieving rapid risk response and efficient resource allocation.

[0182] In summary, steps 701 to 703, through multi-level linkage of flood discharge priority calculation, path optimization, and historical data matching, significantly improve the efficiency of regulating water level imbalances across a cluster of reservoirs across a river basin. In typhoon scenarios, the system accurately allocates flood discharge and selects the optimal path, avoiding the risk of downstream flooding and reducing resource waste. Compared with traditional methods, flood discharge response time is shortened and the risk level is reduced by one level, effectively ensuring the safety of the reservoir cluster and downstream areas, and providing intelligent decision-making support for flood prevention and disaster reduction.

[0183] Figure 2 The present invention provides a structural diagram of a water level monitoring system for a water conservancy project based on artificial intelligence, as shown in FIG. Figure 2 As shown, the system includes:

[0184] An acquisition module 21 acquires meteorological parameters, soil moisture parameters, and water level measurement parameters of a cross-basin reservoir group, wherein the water level measurement parameters are generated by magnetic levitation displacement sensing and are linearly mapped to water level changes;

[0185] The encoding module 22 obtains a correlation strength coefficient reflecting the hydraulic interaction between reservoirs based on the dynamic change pattern of the meteorological parameters and the soil moisture parameters, and jointly encodes the correlation strength coefficient with the water level measurement parameters to generate a dynamic correlation map across reservoirs;

[0186] An extraction module 23 synchronously collects real-time water level signals from each reservoir, performs spatiotemporal matching of the real-time water level signals with a preset water level fluctuation feature library, and extracts abnormal water level fluctuation intervals associated with flow path nodes in the cross-reservoir dynamic association map;

[0187] A mapping module 24 determines the water level imbalance risk level of the inter-basin reservoir group through a mapping relationship between the inter-reservoir dynamic association map and the water level abnormal fluctuation range;

[0188] The generating module 25 generates a control instruction according to the water level imbalance risk level, wherein the control instruction includes a flood discharge path optimization plan and a water storage capacity adjustment ratio.

[0189] Figure 2 The water level monitoring system for water conservancy projects based on artificial intelligence can be executed Figure 1 The implementation principle and technical effects of the artificial intelligence-based water level monitoring method for water conservancy projects described in the illustrated embodiment will not be elaborated on here. The specific manner in which each module and unit performs operations in the artificial intelligence-based water level monitoring system for water conservancy projects in the above embodiment has been described in detail in the embodiments of the method and will not be elaborated on here.

[0190] In one possible design, Figure 2 The water level monitoring system for a hydraulic project based on artificial intelligence in the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0191] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0192] The processing component 32 is used for the above Figure 1 The embodiment provides a water level monitoring method for a water conservancy project based on artificial intelligence.

[0193] The processing component 32 may include one or more processors to execute computer instructions to perform all or part of the steps in the above method. Of course, the processing component may also be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0194] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0195] Of course, a computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0196] The input / output interface provides an interface between the processing component and the peripheral interface module, which can be an output device, an input device, etc.

[0197] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0198] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0199] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The embodiment shown is a water level monitoring method for a water conservancy project based on artificial intelligence.

[0200] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0201] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0202] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0203] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A water level monitoring method for water conservancy projects based on artificial intelligence, characterized in that: include: Obtain meteorological parameters, soil moisture parameters, and water level measurement parameters for a cross-basin reservoir group. The water level measurement parameters are generated by magnetic levitation displacement sensing and are linearly mapped to water level changes. Based on the dynamic change patterns of the meteorological parameters and soil moisture parameters, a correlation strength coefficient reflecting the hydraulic interaction between reservoirs is obtained, and the correlation strength coefficient is jointly encoded with the water level measurement parameters to generate a dynamic correlation map across reservoirs; Synchronously collect real-time water level signals from each reservoir, perform spatiotemporal matching on the real-time water level signals with a preset water level fluctuation feature library, and extract abnormal water level fluctuation intervals associated with flow path nodes in the cross-reservoir dynamic association map; Determining the water level imbalance risk level of the inter-basin reservoir group through the mapping relationship between the inter-reservoir dynamic correlation map and the water level abnormal fluctuation range; A control instruction is generated according to the water level imbalance risk level, and the control instruction includes a flood discharge path optimization plan and a water storage capacity adjustment ratio.

2. The method according to claim 1, characterized in that The step of jointly encoding the correlation strength coefficient and the water level measurement parameter to generate a cross-reservoir dynamic correlation map includes: Dynamically allocating a weight ratio of the meteorological parameter to the soil moisture parameter in the correlation strength coefficient according to the instantaneous change rate of the meteorological parameter and the cumulative amount of the soil moisture parameter; The time series fluctuation amplitude of the water level measurement parameter is superimposed with the weight ratio to generate a hydraulic influence value representing the influence of the external environment on the reservoir node, and a hydraulic conduction path between the reservoir nodes is constructed based on the difference between the hydraulic influence values ​​of adjacent reservoir nodes; Dynamically correcting the connection strength of the hydraulic conduction path based on a synchronous change trend of a water level measurement parameter in the hydraulic conduction path to obtain a corrected connection strength; The geographical location coordinates, hydraulic conduction paths and corrected connection strengths of the reservoir nodes are data-bound to generate a cross-reservoir dynamic association map.

3. The method according to claim 2, characterized in that The method comprises superimposing the time series fluctuation amplitude of the water level measurement parameter and the weight ratio to generate a hydraulic influence value representing the influence of the external environment on the reservoir node, and constructing a hydraulic conduction path between the reservoir nodes based on the difference between the hydraulic influence values ​​of adjacent reservoir nodes, including: Perform weighted processing on the rising phase and the falling phase of the time series fluctuation amplitude of the water level measurement parameter according to the weight ratio to obtain weighted rising phase time series fluctuation amplitude and falling phase time series fluctuation amplitude; Directionally superimposing the weighted time series fluctuation amplitude in the ascending phase and the time series fluctuation amplitude in the descending phase to generate a hydraulic impact value representing the influence of the external environment on the reservoir node; Calculating an absolute difference in hydraulic influence values ​​of adjacent reservoir nodes, comparing the absolute difference with a preset hydraulic conduction path generation threshold, and setting a preset hydraulic conduction path whose absolute difference exceeds the generation threshold as a candidate conduction path; Screening the candidate conduction paths that meet activation conditions based on the consistency between the connection strengths of the candidate conduction paths and the fluctuation directions of the water level measurement parameters in the current time window to obtain a set of activated candidate conduction paths; The activated candidate conduction path set is superimposed on the preset conduction path in the cross-reservoir dynamic association map to obtain a water conservancy conduction path.

4. The method according to claim 1, wherein The determining of the water level imbalance risk level of the inter-basin reservoir group by the mapping relationship between the inter-reservoir dynamic association map and the abnormal water level fluctuation range includes: Dynamically matching the water flow path nodes in the cross-reservoir dynamic association map with the abnormal water level fluctuation interval to determine the corresponding relationship between the connection strength of the water flow path nodes and the duration of the abnormal water level fluctuation interval; Based on the corresponding relationship, the spatial distribution range and time cumulative effect of the abnormal water level fluctuation interval in the cross-reservoir dynamic correlation map are counted; The spatial distribution range, time cumulative effect and preset thresholds are compared and analyzed, and the water level imbalance risk level intervals of the cross-basin reservoir group are divided according to the comparative analysis results. When the spatial distribution range and time cumulative effect exceed the preset thresholds at the same time, it is judged to be a high risk level.

5. The method according to claim 1, wherein The step of performing spatiotemporal matching of the real-time water level signal with a preset water level fluctuation feature library to extract abnormal water level fluctuation intervals associated with water flow path nodes in the cross-reservoir dynamic association map includes: Dynamically dividing the real-time water level signal into continuous fluctuation segments according to a preset time window, wherein the length of the preset time window is adaptively adjusted according to the connection density of the water flow path nodes in the cross-reservoir dynamic association map; Matching the continuous fluctuation segments with the fluctuation patterns in a preset water level fluctuation feature library segment by segment in a temporal and spatial order, and screening out abnormal fluctuation segments in the continuous fluctuation segments whose matching degree with the fluctuation patterns exceeds a preset threshold based on the segment-by-segment matching results; Mapping the abnormal fluctuation segment to the water flow path node, and calculating the correlation influence strength of the abnormal fluctuation segment on the adjacent reservoir node through the connection strength of the mapped water flow path node; According to the spatial distribution range and cumulative duration of the correlation impact intensity in the cross-reservoir dynamic correlation map, the abnormal water level fluctuation interval associated with the water flow path node is obtained.

6. The method according to claim 5, characterized in that Mapping the abnormal fluctuation segment to the water flow path node, and calculating the correlation influence strength of the abnormal fluctuation segment on the adjacent reservoir node according to the connection strength of the mapped water flow path node, includes: Overlapping and comparing the abnormal fluctuation segment with the spatiotemporal position distribution of the water flow path nodes, and selecting the water flow path nodes with an overlap exceeding a preset ratio as the target mapping nodes to which the abnormal fluctuation segment belongs; Calculating the initial influence of the abnormal fluctuation segment on the target mapping node according to the connection strength of the target mapping node; Based on the connection strength ratio between the target mapping node and the adjacent reservoir nodes, the initial influence amount is distributed to each adjacent reservoir node, and the distribution amount of the initial influence amount on each adjacent reservoir node is accumulated to obtain the associated influence strength.

7. The method according to claim 1, characterized in that The generating of a control instruction according to the water level imbalance risk level includes: Determine the flood discharge priority order of each reservoir node based on the risk interval corresponding to the water level imbalance risk level, and calculate the flood discharge allocation ratio of each reservoir node according to the difference between the current water storage capacity of each reservoir node and the preset safety capacity in the flood discharge priority order; generating a flood discharge path optimization plan based on the connection strength and spatial distribution of water flow path nodes in the cross-reservoir dynamic association map; Based on the matching relationship between the flood discharge distribution ratio and the historical flood discharge records for the same period, combined with the water level imbalance risk level, a water storage capacity adjustment ratio is generated, and the water storage capacity adjustment ratio is associated with the flood discharge path optimization plan to generate a control instruction.

8. An artificial intelligence-based water level monitoring system for water conservancy projects, characterized in that: include: An acquisition module acquires meteorological parameters, soil moisture parameters, and water level measurement parameters of a cross-basin reservoir group. The water level measurement parameters are generated by magnetic levitation displacement sensing and are linearly mapped to water level changes. an encoding module, which obtains a correlation strength coefficient reflecting the hydraulic interaction between reservoirs based on the dynamic change law of the meteorological parameters and the soil moisture parameters, and jointly encodes the correlation strength coefficient with the water level measurement parameters to generate a dynamic correlation map across reservoirs; An extraction module synchronously collects real-time water level signals from each reservoir, performs spatiotemporal matching on the real-time water level signals with a preset water level fluctuation feature library, and extracts abnormal water level fluctuation intervals associated with the water flow path nodes in the cross-reservoir dynamic association map; a mapping module for determining the water level imbalance risk level of the inter-basin reservoir group through a mapping relationship between the inter-reservoir dynamic association map and the water level abnormal fluctuation range; A generation module generates a control instruction according to the water level imbalance risk level, and the control instruction includes a flood discharge path optimization plan and a water storage capacity adjustment ratio.

9. A computing device, characterized in that It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an artificial intelligence-based water level monitoring method for water conservancy projects as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that A computer program is stored, and when the computer program is executed by a computer, the water level monitoring method for a water conservancy project based on artificial intelligence as described in any one of claims 1 to 7 is implemented.

Images