Hydrological monitoring point dynamic planning method and system

Abstract

The invention discloses a hydrological monitoring point dynamic planning method and system, and relates to the technical field of hydrological monitoring, and the method comprises the steps: collecting hydrological monitoring point parameters of a target region, and making an initial point planning scheme; and performing hydrological dynamic prediction on the region based on prediction of a future time zone to obtain a hydrological prediction result. And according to the result, performing redundancy adjustment on the initial point location scheme to generate a first adjustment scheme. And based on the monitoring demand and the prediction result, correcting the point location blind area to form a second adjustment scheme. And in combination with the geographic feature data and the damage risk threshold, compensation adjustment of the damaged point location is carried out, and a third adjustment scheme is generated. And integrating the above adjustment schemes, carrying out global optimization, and generating an optimized hydrological monitoring point layout. The technical problems of poor planning flexibility and low precision of the hydrological monitoring point positions in the prior art are solved, and the technical effects of improving the planning flexibility and precision of the hydrological monitoring point positions and improving the hydrological monitoring quality are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of hydrological monitoring, and in particular to a method and system for dynamic planning of hydrological monitoring points. Background Art

[0002] In the application scenarios of hydrological monitoring, with the increasing intensification of climate change and human activities, the dynamic changes of hydrological conditions in the region are becoming more and more complex, and the problems of traditional monitoring point layout are becoming increasingly prominent. The reasonable layout of hydrological monitoring points is the key to accurately capturing regional hydrological dynamics, but the traditional point layout often relies on historical data and lacks predictions of future hydrological trends, resulting in redundancy, blind spots, and point damage in the layout of monitoring points. The existing hydrological monitoring system fails to fully consider the regional geographical characteristics and future changes in hydrological dynamics when planning points, making it difficult to respond to sudden hydrological events in real time, and therefore cannot effectively optimize resource allocation and ensure the comprehensiveness and accuracy of monitoring data.

[0003] At the current stage, relevant technologies have technical problems such as poor planning flexibility and low accuracy of hydrological monitoring points. Summary of the invention

[0004] The present application provides a method and system for dynamic planning of hydrological monitoring points, which collects the parameters of the hydrological monitoring points in the target area and formulates an initial point planning scheme. Based on the prediction of the future time zone, a hydrological dynamic prediction is made for the area to obtain the hydrological prediction results. According to the results, the initial point plan is adjusted for redundancy to generate a first adjustment plan. Based on the monitoring needs and the prediction results, the point blind spots are corrected to form a second adjustment plan. Combining the geographic feature data and the damage risk threshold, compensatory adjustments are made to the damaged points to generate a third adjustment plan. The above adjustment plans are integrated, the initial plan is globally optimized, and the optimized hydrological monitoring point layout is generated, which realizes multi-dimensional and flexible adjustment of the hydrological monitoring points through the hydrological dynamic prediction results, and achieves the technical effect of improving the planning flexibility and accuracy of the hydrological monitoring points and improving the quality of hydrological monitoring.

[0005] The present application provides a method for dynamic planning of hydrological monitoring points, including:

[0006] Collect the parameters of the hydrological monitoring points in the target area to obtain an initial point planning scheme; perform hydrological dynamic prediction on the target area based on a preset future time zone to obtain a hydrological dynamic prediction result; perform redundancy adjustment on the hydrological monitoring points in the initial point planning scheme based on the hydrological dynamic prediction result to obtain a first adjustment scheme for the point planning; based on the hydrological dynamic prediction result, perform blind spot correction on the hydrological monitoring points in the initial point planning scheme according to the monitoring demand analysis channel and the decision channel for adding hydrological monitoring points to obtain a second adjustment scheme for the point planning; based on the regional geographic feature data set of the target area and the hydrological dynamic prediction result, perform damage compensation on the hydrological monitoring points in the initial point planning scheme according to the point damage risk threshold to obtain a third adjustment scheme for the point planning; perform global optimization on the initial point planning scheme according to the first adjustment scheme for the point planning, the second adjustment scheme for the point planning and the third adjustment scheme for the point planning to generate an optimization result for the hydrological monitoring points.

[0007] The present application also provides a hydrological monitoring point dynamic planning system, including:

[0008] An initial point planning scheme acquisition module is used to collect the hydrological monitoring point parameters of the target area to obtain an initial point planning scheme; a hydrological dynamic prediction result acquisition module is used to perform hydrological dynamic prediction on the target area based on a preset future time zone to obtain a hydrological dynamic prediction result; a point planning first adjustment scheme acquisition module is used to perform redundancy adjustment of the hydrological monitoring points of the initial point planning scheme based on the hydrological dynamic prediction result to obtain a first adjustment scheme for point planning; a second adjustment scheme acquisition module is used to adjust the hydrological monitoring points according to the monitoring needs based on the hydrological dynamic prediction result. The analysis channel and the decision channel for adding hydrological monitoring points correct the blind spots of the initial point planning scheme to obtain the second adjustment plan of the point planning; the third adjustment plan acquisition module is used to compensate for the damage of the hydrological monitoring points of the initial point planning scheme according to the point damage risk threshold based on the regional geographic feature data set of the target area and the hydrological dynamic prediction result, and obtain the third adjustment plan of the point planning; the global optimization module is used to globally optimize the initial point planning scheme according to the first adjustment plan of the point planning, the second adjustment plan of the point planning and the third adjustment plan of the point planning, and generate the optimization result of the hydrological monitoring points.

[0009] The present application proposes a method and system for dynamic planning of hydrological monitoring points. First, the parameters of the hydrological monitoring points in the target area are collected to formulate an initial point planning scheme. Based on the prediction of the future time zone, a hydrological dynamic prediction is made for the area to obtain the hydrological prediction results. According to the results, the initial point plan is adjusted for redundancy to generate a first adjustment plan. Based on the monitoring needs and the prediction results, the point blind spots are corrected to form a second adjustment plan. Combining the geographic feature data and the damage risk threshold, compensatory adjustments are made to the damaged points to generate a third adjustment plan. The above adjustment plans are integrated, the initial plan is globally optimized, and the optimized hydrological monitoring point layout is generated. The hydrological monitoring points are flexibly adjusted in multiple dimensions through the hydrological dynamic prediction results, thereby achieving the technical effect of improving the planning flexibility and accuracy of the hydrological monitoring points and improving the quality of hydrological monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0011] Figure 1 A schematic diagram of a flow chart of a method for dynamic planning of hydrological monitoring points provided in an embodiment of the present application;

[0012] Figure 2 A schematic diagram of the structure of a dynamic planning system for hydrological monitoring points provided in an embodiment of the present application.

[0013] Explanation of the reference numerals: initial point planning scheme acquisition module 10, hydrological dynamic prediction result acquisition module 20, point planning first adjustment scheme acquisition module 30, second adjustment scheme acquisition module 40, third adjustment scheme acquisition module 50, global optimization module 60. DETAILED DESCRIPTION

[0014] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0015] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0016] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0017] The present application embodiment provides a method for dynamic planning of hydrological monitoring points, such as Figure 1 As shown, the method includes:

[0018] Step S100, collect the hydrological monitoring point parameters of the target area, and obtain the initial point planning scheme. Specifically, when collecting the hydrological monitoring point parameters of the target area to obtain the initial point planning scheme, first clarify the scope of the target area and the monitoring elements, select the appropriate equipment type, measurement range and accuracy requirements according to the elements, and consult relevant information to obtain the historical monitoring point distribution, hydrological data change trend and regional geographical information. Then conduct field data collection, use GPS to accurately measure the latitude and longitude and altitude of the point, record the location information in the river, record the equipment model, parameters, installation time, operating status and maintenance history in detail, observe and record the surrounding environmental information such as land use type, vegetation coverage, pollution source and position relationship with other geographical elements. Then classify and organize the collected data into a database, classify them according to the dimensions of monitoring elements, ensure that the data can be queried, and then use GIS software or drawing tools to draw the initial point planning map and mark the relevant information, conduct a preliminary evaluation of the scheme from the aspects of the rationality of the point distribution and the coverage of the hydrological characteristic area, mark the problem area, and finally obtain the initial point planning scheme.

[0019] Step S200, based on the preset future time zone, the target area is subjected to hydrological dynamic prediction to obtain the hydrological dynamic prediction result. Specifically, firstly, a hydrological monitoring sensor network is deployed in the target area to collect real-time hydrological data and pre-process it, and at the same time, the meteorological forecast data of the preset future time zone is obtained from the meteorological agency, including precipitation, temperature, wind speed and direction, etc., and matched with the location of the hydrological monitoring station, and then the geographical feature data such as topography, water system distribution, soil type, etc. are summarized and digitally processed so as to be integrated and analyzed on the geographic information system platform. Then, a suitable hydrological model is selected according to the regional characteristics and research purpose, and the parameters are determined and verified using historical hydrological and meteorological data, and then different scenarios of the future time zone are set in combination with the meteorological forecast data. Then, the real-time hydrological, meteorological and geographical data are input into the model to simulate and calculate according to the set scenario, and the operating status is monitored during the process to predict the future change trend of factors such as water level, flow, and water quality. Finally, the statistical indicators of the prediction results are analyzed, and the influence range of various factors is considered through visual display and uncertainty analysis, so as to obtain the hydrological dynamic prediction results, which provides a basis for subsequent work.

[0020] In a possible implementation, the target area is subjected to a hydrological dynamic prediction based on a preset future time zone to obtain a hydrological dynamic prediction result, and step S200 further includes step S210, collecting real-time hydrological parameters of the target area to obtain real-time hydrological status information. Specifically, advanced hydrological monitoring equipment is installed at key locations in the target area, such as the intersection of the mainstream and tributaries of the river, the inlet and outlet of the reservoir, and typical observation wells of groundwater. For water level monitoring, high-precision pressure sensors or ultrasonic sensors are used. These sensors can sense small changes in water levels in real time and collect and transmit data at a high frequency (e.g., once per second). For flow monitoring, Doppler flowmeters or ADCP (Acoustic Doppler Current Profiler) are used to accurately measure the velocity profile of water flow and calculate real-time flow data based on the cross-sectional information of the river. For water quality monitoring, multi-parameter water quality monitors are used to synchronously monitor the temperature, pH, dissolved oxygen, conductivity and other parameters of the water body. The collected data is sent to the data center via wired or wireless transmission. During the data collection process, the equipment is monitored for quality in real time. Once abnormal data fluctuations or transmission interruptions are found, the fault diagnosis and repair procedures are immediately started to ensure the continuity and accuracy of the data. The real-time hydrological parameters collected are summarized and integrated to build a real-time hydrological database. The data are preliminarily analyzed and processed, such as calculating the rate of change of water level and instantaneous change of flow, so as to obtain the characteristic information of real-time hydrological status. By drawing the real-time data change curve, the changing trend of parameters such as water level and flow over time is intuitively displayed, which helps analysts to quickly understand the dynamic characteristics of the current hydrological status. At the same time, the data mining algorithm is used to compare and analyze the hydrological data of the same period in history to find out the abnormal points or potential laws of the current data, so as to provide basic information for the subsequent hydrological dynamic prediction.

[0021] Step S220, loading the weather forecast data of the target area based on the preset future time zone. Specifically, the meteorological forecast data of the target area in the preset future time zone is obtained from professional meteorological departments, meteorological data service platforms or numerical weather forecast models. The data sources usually provide data in multiple formats, which need to be unified and converted to make them compatible with hydrological data and geographical feature data. The data includes precipitation forecast information, such as the time distribution of rainfall, the size of rainfall and the spatial distribution; temperature forecast, covering the highest temperature, the lowest temperature and its changing trend; wind direction and wind speed forecast, clarifying the changes in wind direction and wind speed at different altitudes. The data interface technology is used to realize the automatic download and loading of meteorological data to ensure the timeliness and integrity of the data. The loaded meteorological forecast data is preprocessed to remove possible erroneous data or outliers. For example, data points that obviously deviate from the laws of historical meteorological data or do not conform to meteorological principles are marked and corrected. The data accuracy and reliability are improved by comparing and verifying with the data of meteorological stations in the surrounding areas. At the same time, a quality assessment index system for meteorological data is established to quantitatively evaluate the accuracy and resolution of the data, so as to consider the influencing factors of data quality in subsequent hydrological dynamic predictions, and appropriately adjust the weight of the parts with low data quality or use data interpolation, smoothing and other methods to optimize the processing.

[0022] Step S230, based on the real-time hydrological status information and the meteorological forecast data, perform hydrological dynamic prediction according to the regional geographic feature data set to obtain the hydrological dynamic prediction result. Specifically, the real-time hydrological status information, meteorological forecast data and regional geographic feature data set are fused and processed, and according to the geographic information system (GIS) technology, the hydrological data and meteorological data are spatially matched and associated with the geographic feature data to build an integrated data model. For example, precipitation data is combined with terrain data to analyze the precipitation distribution and runoff formation process in different terrain parts, and the data is standardized to meet the input requirements of the hydrological prediction model, including data format, unit unification, data range adjustment and other operations. At the same time, according to the prediction target and time scale, the data is reasonably divided and reorganized into time series so that the model can accurately capture the time correlation and causal relationship between the data, and select the appropriate hydrological data according to the hydrogeological characteristics, meteorological conditions and prediction needs of the target area. Dynamic prediction models. Common models include hydrological models based on physical mechanisms, statistical models, and artificial intelligence models. For models based on physical mechanisms, such as SWAT (Soil and Water Assessment Tool) and MIKESHE, it is necessary to set model parameters according to the actual situation of the region, such as soil permeability, vegetation interception parameters, river roughness coefficient, etc. Statistical models need to determine appropriate statistical distribution functions and model parameters, such as the autoregressive order and moving average order in ARIMA (autoregressive moving average model). Artificial intelligence models such as neural network models need to set network structure, training algorithm parameters, etc., use historical data to pre-train the model and optimize parameters to improve the model's prediction performance and adaptability, input the prepared data into the selected prediction model, and start the model for calculation. During the operation of the model, the calculation status of the model and the rationality of the output results are monitored in real time. The intermediate results of the model output are analyzed and verified to ensure the accuracy of the model calculation process. According to the preset future time zone, the model gradually calculates the changes in hydrological elements at different time steps, such as the rising or falling trend of water level, the increase or decrease in flow rate, and the prediction of water quality changes. The results of the model output are post-processed, including data inversion, error correction and visualization of results. The hydrological dynamic prediction results are presented by drawing charts of the prediction results, generating prediction reports, etc., providing a scientific basis for related decision-making and research.

[0023] Step S300, based on the hydrological dynamic prediction results, the initial point planning scheme is adjusted for redundancy of hydrological monitoring points to obtain the first adjustment scheme for point planning. Specifically, firstly, the relevant data of each monitoring point is extracted from the hydrological dynamic prediction results and the historical monitoring data of the initial point is sorted out, and the data archive is established after cleaning and preprocessing. Then, a suitable fitting model is selected, such as linear regression or time series analysis, and the historical and predicted data are fitted and analyzed to obtain the fitting relationship and parameters. Then, twin identification is performed based on the fitting results, and the twin degree is calculated by correlation coefficient method or similarity index method, the twin point cluster is determined, and the position proximity analysis of the points in the cluster is performed, and the redundancy coefficient is calculated by comprehensive multi-factors, and it is judged whether the threshold is reached to determine the redundant points. Then, an adjustment strategy is formulated according to the redundant detection results, and the points are retained in the key areas and the parameters or functions are adjusted. The redundant points in the non-key areas are considered to be removed or the functions are transferred. The initial plan is adjusted according to the strategy to generate the first adjustment plan, and then the rationality is verified and optimized through simulation analysis and expert evaluation, so as to ensure that the monitoring needs are met, redundancy is avoided, and efficiency and resource utilization are improved.

[0024] In a possible implementation, the initial point planning scheme is adjusted for redundancy of hydrological monitoring points based on the hydrological dynamic prediction results to obtain a first adjustment plan for the point planning. Step S300 further includes step S310, which is to fit the monitoring parameters of each hydrological monitoring point in the initial point planning scheme based on the hydrological dynamic prediction results to determine multiple point monitoring fitting results. Specifically, a rich data resource is obtained from the hydrological dynamic prediction results, including information such as water level change predictions, flow change trends, and water quality component fluctuations at different time steps. For each hydrological monitoring point in the initial point planning scheme, the relevant prediction data is extracted, and the existing historical monitoring data of each point is sorted out. The data is quality checked to eliminate abnormal values ​​caused by instrument failures, environmental interference, and other factors. The data is standardized to have a unified dimension and format to facilitate subsequent analysis and calculation. For example, the water level data is uniformly converted to meters, and the flow data is converted to cubic meters per second. The historical data and predicted data are arranged and combined according to the time series to construct a data set for each point, so as to prepare for the subsequent fitting work. According to the characteristics of the hydrological data and the research purpose, the appropriate fitting method is selected. The common linear fitting method is suitable for the case where the data presents a relatively simple linear relationship; for data with periodic or seasonal variation characteristics, harmonic analysis fitting or seasonal ARIMA model can be used for fitting. Each monitoring point is taken as the object to build the corresponding fitting model. For example, for a water level monitoring point, if its water level data shows obvious seasonal variation in a year, a seasonal ARIMA model can be constructed to determine the parameters of the model (such as seasonal cycle, autoregressive order, moving average order, etc.). Through optimization algorithms such as the least squares method, the model parameters are estimated so that the model can describe the relationship between the historical monitoring data and the predicted data as accurately as possible. After the model calculation, the monitoring parameter fitting curve of each point and the coefficients of the fitting equation are obtained, which constitute the fitting results of multiple point monitoring and provide basic data for subsequent redundant detection.

[0025] Step S320, based on the monitoring fitting results of the multiple points, the initial point planning scheme is subjected to redundancy detection, and monitoring point redundancy detection results are generated. Specifically, based on the monitoring fitting results of the multiple points, similarity analysis is performed between each point. The correlation coefficient is used as a measurement indicator to calculate the correlation coefficient between each two point monitoring fitting results. The correlation coefficient can reflect the similarity between the two data sequences in terms of change trend and amplitude. For flow monitoring points, if the correlation coefficient of the flow fitting data sequences of the two points is close to 1, it indicates that they are very similar in flow change pattern. In addition to the correlation coefficient, other similarity indicators can also be calculated, such as Euclidean distance, dynamic time warping distance, etc. The Euclidean distance can measure the numerical difference between the monitoring data of two points at the same time point; the dynamic time warping distance is suitable for processing situations where the data sequence may be stretched or offset on the time axis, and more accurately evaluate the similarity of the data. By comprehensively using these similarity indicators, a comprehensive quantitative analysis of the similarity between each point is performed. According to the calculation results of the similarity index, a reasonable threshold is set to determine whether there is redundancy. If the correlation coefficient between two points is greater than or equal to the set point monitoring predetermined twin degree threshold, and the geographical location is also relatively close, it is preliminarily determined that there may be redundant point pairs. Further analysis and verification of the possible redundant points is carried out, combined with regional geographical characteristics, hydrological function requirements and other factors. For example, in an area with relatively stable water flow and relatively uniform hydrological characteristics, if the monitoring data of two points are highly similar and the locations are adjacent, then these two points are likely to be redundant. After detailed analysis and judgment, the specific information of the redundant points is determined, and the redundant detection results of the monitoring points are generated to clarify which points may be redundant and the degree of redundancy, providing an accurate basis for subsequent adjustments.

[0026] Step S330, perform redundancy adjustment based on the redundant detection results of the monitoring points, and generate the first adjustment plan for the point planning. Specifically, a scientific and reasonable redundant adjustment strategy is formulated based on the redundant detection results of the monitoring points. For points determined to be redundant, it is necessary to comprehensively consider various factors to decide the adjustment method. If the area where the redundant points are located has important hydrological research value or special hydrological changes may occur, even if there is redundancy, one of the points can be retained, and its monitoring equipment can be upgraded or the monitoring parameter settings can be optimized. For example, in an area close to the source of a river and with sensitive ecological environment, although the monitoring data of the two points are similar, in order to more comprehensively grasp the impact of hydrological changes at the source on the downstream, one point can be retained and the monitoring of water quality microbial indicators can be increased. For those points in non-critical areas with more obvious redundancy, it can be considered Remove it or adjust it to a location that needs more monitoring. When formulating the adjustment strategy, it is also necessary to consider cost factors, data continuity, and the impact on the layout of the entire monitoring network. According to the formulated adjustment strategy, the initial point planning scheme is actually adjusted, and the redundant points determined to be removed are deleted from the plan, and the retained points are adjusted accordingly. Parameters or functions are optimized. After the adjustment is completed, the new point planning scheme is comprehensively checked and evaluated to ensure that the adjusted scheme meets the needs of hydrological monitoring while achieving a reasonable layout of monitoring points and reducing redundancy. After repeated inspections and optimizations, the first adjustment plan for the point planning is finally generated, providing a more scientific and efficient point layout basis for subsequent hydrological monitoring work.

[0027] In one possible implementation, the initial point planning scheme is subjected to redundancy detection based on the multiple point monitoring fitting results to generate monitoring point redundancy detection results, and step S320 further includes step S321, performing twin identification in pairs based on the multiple point monitoring fitting results to obtain multiple point monitoring twin degrees. Specifically, from the multiple point monitoring fitting results, extract the key characteristic parameters of each point, such as data change trend, fluctuation amplitude, mean value and other information. Arrange these parameters into a format that can be calculated and compared, and prepare data for the subsequent calculation of twin degrees. For each hydrological monitoring point, it is compared with other points one by one to ensure that no combination is missed. During the comparison process, considering that different types of monitoring data (such as water level, flow, water quality, etc.) may have different dimensions and ranges of variation, data standardization or normalization is required to make different data comparable. A suitable calculation method is used to determine the twin degree of point monitoring. A commonly used method is to calculate the similarity of two point monitoring data in the feature space based on the data similarity algorithm. For example, the similarity of data change trends can be measured by calculating the Pearson correlation coefficient. If the change trends of the water level data sequences of the two points are highly consistent in the same time interval, the Pearson correlation coefficient will approach 1. At the same time, combined with the similarity calculation of other characteristic parameters, such as the similarity of fluctuation amplitude can be evaluated by calculating the difference in standard deviation, and the mean similarity directly compares the data mean. Combining these factors, the twin degree value of each point combination is obtained by weighted summation or constructing a comprehensive indicator function, thereby obtaining the twin degree of multiple point monitoring.

[0028] Step S322, determine whether the twin degrees of the multiple point monitoring are greater than or equal to the predetermined twin degrees of the point monitoring, and determine multiple twin point clusters that are greater than or equal to the predetermined twin degrees of the point monitoring. Specifically, compare the calculated twin degrees of the multiple point monitoring with the preset predetermined twin degrees of the point monitoring. The predetermined twin degree is a measurement standard determined based on experience, historical data statistical analysis, or expert knowledge, and is used to determine which point combinations have a higher similarity. Check each twin degree value one by one. If it is greater than or equal to the predetermined twin degree, the corresponding two points are classified as a twin point cluster. For example, if the predetermined twin degree is 0.8, when the twin degree of the two points is 0.9, the two points are classified into the same twin point cluster. After comparing and screening all point combinations, multiple twin point clusters are determined, and each cluster contains two hydrological monitoring points with a higher similarity.

[0029] Step S323 , performing proximity analysis of intra-cluster point locations according to the plurality of twin point clusters to determine a plurality of intra-cluster point redundancy coefficients. Specifically, the precise geographical location information of the two hydrological monitoring points in each twin point cluster is obtained, including longitude and latitude coordinates, altitude, etc. For points in linear geographical environments such as rivers, it is also necessary to clarify their relative positional relationship with upstream and downstream, river banks, etc., and digitize the location information for subsequent calculation and analysis. For example, the longitude and latitude coordinates are converted into coordinate values ​​in a plane rectangular coordinate system to facilitate the calculation of location proximity indicators such as the distance between the two points. The redundancy coefficient of the points within the cluster is determined based on factors such as the actual distance between the points, the relative orientation, and the geographical environment characteristics. If the two points are close to each other and are in a similar geographical environment (such as both on the same side of the river bank, the same section of a gentle river channel, etc.), the redundancy coefficient will be higher. The redundancy coefficient can be calculated by establishing a mathematical model. For example, parameters such as distance weight and environmental similarity weight are set, and a redundancy coefficient value between 0 and 1 is calculated by weighted summation. Such calculations are performed on the points in each twin point cluster to determine the redundancy coefficients of multiple points within the cluster.

[0030] Step S324, determine whether the multiple intra-cluster point redundancy coefficients are greater than or equal to the intra-cluster point redundancy threshold, and determine the marked intra-cluster point redundancy coefficients greater than or equal to the intra-cluster point redundancy threshold. Specifically, compare the calculated multiple intra-cluster point redundancy coefficients with the intra-cluster point redundancy threshold. The threshold is also a standard determined based on experience, data analysis, etc., and is used to determine whether the point is redundant. If a certain intra-cluster point redundancy coefficient is greater than or equal to the threshold, it is identified as a coefficient with redundant characteristics. All redundant coefficients are checked and identified, and a marked intra-cluster point redundancy coefficient greater than or equal to the intra-cluster point redundancy threshold is determined.

[0031] Step S325, point mapping is performed on the initial point planning scheme based on the redundancy coefficient of the points within the identified cluster to obtain the redundant detection result of the monitoring points. Specifically, point mapping is performed on the initial point planning scheme based on the redundancy coefficient of the points within the identified cluster. Points with redundant characteristics are marked and associated in the planning scheme, and their relevant information, such as point number, location information, size of redundancy coefficient, etc., are recorded. Through mapping, the redundant point situation existing in the initial point planning scheme is fully reflected, thereby obtaining the redundant detection result of the monitoring points. The result provides an accurate basis for subsequent point adjustment and optimization, which helps to improve the rationality and scientificity of the layout of hydrological monitoring points.

[0032] Step S400, based on the hydrological dynamic prediction results, the initial point planning scheme is corrected for the blind spots of the hydrological monitoring points according to the monitoring demand analysis channel and the decision channel for adding hydrological monitoring points, and the second adjustment plan for the point planning is obtained. Specifically, the hydrological dynamic prediction results are used to detect hydrological fluctuations at each location, and the fluctuation coefficient reflecting the hydrological instability of each location is calculated. At the same time, the hydrological risk prediction is carried out in combination with historical data, geographic information, human activities and other factors to obtain the risk coefficient. The fluctuation coefficient and risk coefficient are input into the monitoring demand analysis channel, and the hydrological monitoring demand at each location is calculated based on the predetermined fluctuation weight and risk weight. Then, it is determined whether the demand reaches the predetermined value, and a demand distribution map is drawn in the geographic information system to determine the area with low demand as a potential blind spot. The blind spot is confirmed by combining historical data and field surveys, and then remote sensing and field measurements are used to collect the geographical feature data of the blind spot, including terrain height, slope, vegetation cover, soil type and hydrological related information. Then, based on the blind spot detection results and geographic feature data, the location, quantity and type of new points are determined by adding decision channels, such as setting up water level monitoring points in low-lying areas and water quality monitoring points in areas with dense vegetation. The number of new points is reasonably planned in combination with the blind spot situation. Finally, the information of the new points is incorporated into the initial plan and simulated for verification. After optimization and adjustment, the second adjustment plan for the point planning is generated to improve the layout of the monitoring points.

[0033] In a possible implementation, based on the hydrological dynamic prediction results, the initial point planning scheme is corrected for the blind spots of the hydrological monitoring points according to the monitoring demand analysis channel and the decision channel for adding hydrological monitoring points, and a second adjustment plan for the point planning is obtained. Step S400 further includes step S410, based on the monitoring demand analysis channel, the hydrological monitoring demand analysis is performed according to the hydrological dynamic prediction results to determine the hydrological monitoring demand of multiple locations. Specifically, key information is extracted from the hydrological dynamic prediction results, including data such as the predicted values ​​of water level changes, flow change trends, and the possibility of water quality changes at different locations at different time points in the future. The data is classified and sorted, and grouped according to the location information so that the demand analysis can be performed for each location later. At the same time, the data is smoothed and outliers are removed to improve the accuracy and reliability of the data. For example, some obviously unreasonable data points caused by short-term sensor failures or model errors are corrected or deleted. The monitoring demand analysis channel is used, and the algorithm model built based on historical monitoring data and expert experience is included in the channel. The sorted hydrological data of each location is input into the channel, and the demand analysis calculation process is started. In the monitoring demand analysis, the data is analyzed and the demand analysis calculation process is started. In the analysis channel, firstly, the water level change intensity index of each location is calculated according to the water level change prediction data, such as using statistical quantities such as standard deviation to measure. For the flow change trend, its rate and amplitude of change are analyzed. Combined with the law of flow change under different seasons and climatic conditions, corresponding weights are assigned for comprehensive evaluation. In terms of water quality changes, factors such as the possible spread of pollution sources, the self-purification capacity of water bodies, and the degree of impact on the surrounding ecological environment and human activities are considered. The factors are integrated according to a predetermined algorithm, combined with the predetermined hydrological fluctuation weight and the predetermined hydrological risk weight, and through mathematical operations such as weighted summation, the hydrological monitoring demand of multiple locations is accurately calculated. Each location corresponds to a demand value, which reflects the urgency of hydrological monitoring at that location.

[0034] Step S420, determine whether the hydrological monitoring requirements of the multiple locations are greater than or equal to the predetermined hydrological monitoring requirements, and generate a hydrological monitoring requirement location distribution. Specifically, the calculated hydrological monitoring requirements of the multiple locations are compared with the predetermined hydrological monitoring requirements one by one. The predetermined hydrological monitoring requirement is a standard value determined based on the hydrological importance level classification of the target area, water resources management goals, and relevant policies and regulations. For those locations whose requirements are greater than or equal to the predetermined value, record them, and integrate the location information that meets the conditions by marking them on the Geographic Information System (GIS) platform to form a hydrological monitoring requirement location distribution. In the marking process, different colors or symbols can be used to distinguish according to the level of requirements, so as to intuitively show the spatial distribution differences of the requirements. For example, areas with higher requirements can be marked in red, and areas with lower requirements but still meeting the conditions can be marked in yellow, so as to clearly show which areas have more prominent needs for hydrological monitoring.

[0035] Step S430, based on the hydrological monitoring demand location distribution, the initial point planning scheme is used to identify the vacant monitoring points, and the point blind spot detection results are obtained. Specifically, the generated hydrological monitoring demand location distribution is superimposed and compared with the initial point planning scheme, and the monitoring coverage of each position in the demand location distribution in the initial point planning scheme is carefully checked. For those locations that exist in the demand location distribution but have no corresponding monitoring points in the initial point planning scheme or the monitoring points are sparse and cannot meet the monitoring needs, they are identified as vacant monitoring points. Through precise geographic coordinate matching and spatial analysis algorithms, the specific location information and range of these vacant points are determined to obtain the point blind spot detection results. This process needs to consider factors such as the effective monitoring radius of the monitoring point, the monitoring accuracy, and the monitoring requirements of different hydrological elements. For example, for water quality monitoring, it is necessary to consider the diffusion range of the pollution source and the mixing of the water flow to determine a reasonable monitoring blind area range.

[0036] Step S440, based on the point blind spot detection result, geographic feature collection is performed to obtain geographic feature data of the point blind spot. Specifically, based on the point blind spot detection result, the specific areas where geographic feature collection is required are determined. For these areas, a variety of geographic information collection technologies are comprehensively used, and satellite remote sensing images are used to obtain macroscopic geographic feature information, such as the overall form of the topography, the coverage and type of vegetation, etc., and more accurate terrain height, slope and other data are obtained through ground measurement equipment, such as GPS measuring instruments, topographic mapping instruments, etc. For information such as groundwater level, soil texture and permeability that are closely related to hydrology, groundwater monitoring wells, soil sampling and analysis, etc. can be used for collection. During the collection process, targeted sampling is performed according to a certain grid density or according to the topographic and geomorphic characteristics to ensure that the collected data can accurately reflect the geographical features of the point blind spot, and real-time quality control is performed on the collected data to check the accuracy and completeness of the data, and supplementary collection or data correction is performed in a timely manner.

[0037] Step S450, based on the point blind spot detection result and the geographical feature data of the point blind spot, according to the hydrological monitoring point, a decision channel is added to generate a second adjustment plan for the point planning. Specifically, a large amount of historical hydrological monitoring data, geographical feature data and corresponding successful point addition case data are collected. The historical hydrological monitoring data include actual monitoring records of water level, flow and water quality in different periods and regions; the geographical feature data cover topography, vegetation, soil and other information; the point addition case data record in detail the circumstances under which the point was added, the location and type of the added point, and the subsequent effects. Key features are extracted from the collected data, such as the hydrological characteristics corresponding to different terrain types (mountains, plains, river valleys, etc.), the correlation characteristics between vegetation coverage and water quality changes, the characteristics of the impact of soil properties on water flow, etc. Each case is annotated, and the annotated content includes whether it is an effective point addition case (that is, whether it improves the monitoring effect, meets specific needs, etc.), and the annotated data is used for model training. Machine learning algorithms, such as neural network algorithms or decision tree algorithms, are used for training. In the neural network training, appropriate parameters such as the number of network layers, the number of nodes and the learning rate are set. By inputting feature data and corresponding annotation information, the network weights are continuously adjusted so that the model can learn the relationship between different feature combinations and the addition of points. The decision tree algorithm constructs decision branches based on indicators such as information gain, and corresponds various feature condition combinations to point addition strategies. Through repeated training and verification, the model parameters are optimized to improve the accuracy and generalization ability of the model. The point blind spot detection results and geographic feature data are input into the trained model. The model makes analysis and decisions based on the learned knowledge and experience and comprehensively considers various factors. For example, in the point blind spot in the mountainous area, if the terrain is steep, the vegetation is sparse, and the groundwater level changes greatly, the model will recommend adding flow and water level monitoring points at key locations such as the valley exit based on the rules and patterns obtained from the training. According to the decision results output by the model, the initial point planning scheme is adjusted and optimized to generate the second adjustment plan for the point planning. In the adjustment process, the collaborative work of the new points and the original points is fully considered to ensure the rationality and effectiveness of the entire monitoring network and improve the overall level of hydrological monitoring.

[0038] In a possible implementation, based on the monitoring demand analysis channel, the hydrological monitoring demand analysis is performed according to the hydrological dynamic prediction results to determine the hydrological monitoring demand of multiple locations. Step S410 further includes step S411, performing hydrological fluctuation detection on each location of the target area according to the hydrological dynamic prediction results to obtain hydrological fluctuation coefficients of multiple locations. Specifically, detailed data about each location of the target area is obtained from the hydrological dynamic prediction results, including a data series of changes in water level, flow, water quality and other elements over time. For each location, these data are arranged in chronological order and preprocessed to remove possible outliers, such as data points that are obviously inconsistent with the actual situation due to instrument failure or data transmission errors. The noise interference in the data is reduced by a data smoothing algorithm to improve the accuracy and reliability of the data. Taking water level data as an example, if the water level data at a certain moment is too different from the data at the previous and next adjacent moments and does not conform to the law of water flow changes, further inspection and verification or correction is required, using appropriate statistical methods. To calculate the hydrological fluctuation coefficient, for water level fluctuation, calculate the standard deviation or variance of water level changes within a certain period of time. The larger the standard deviation, the more drastic the water level fluctuation. For example, select one month as the time period, and calculate the standard deviation of daily water level data at a certain location within this month as the water level fluctuation coefficient. For flow fluctuation, the average value of the flow change rate or the coefficient of variation of the flow can be calculated. In the calculation process, the influence of different seasons, climatic conditions and geographical environmental factors on the fluctuation is taken into account. For example, the river flow fluctuation in rainy season is usually larger, and corrections are made by setting seasonal adjustment factors, etc., to more accurately reflect the actual hydrological fluctuation situation at each location, thereby obtaining hydrological fluctuation coefficients for multiple locations.

[0039] Step S412, based on the hydrological dynamic prediction results, the hydrological risk of each location in the target area is predicted to obtain hydrological risk coefficients for multiple locations. Specifically, based on the hydrological dynamic prediction results, various factors that may cause hydrological risks are deeply analyzed. In terms of flood risk, factors such as rainfall, topography, river basin characteristics, and water conservancy engineering facilities are considered. If the predicted rainfall exceeds the carrying capacity of a river in a certain area in a short period of time, and the area is low-lying and the river channel is narrow, then the flood risk will be high. In terms of water quality risk, attention is paid to factors such as the distribution of pollution sources, water flow conditions, and surrounding human activities. For example, locations close to industrial areas and with slow water flow may face a higher risk of water pollution. For drought risk, analysis is performed in combination with rainfall forecasts, soil types, groundwater levels, and vegetation coverage conditions, such as soil water retention capacity. The drought risk is high in areas with poor water quality, low groundwater level and sparse vegetation. A corresponding risk assessment model is constructed to calculate the hydrological risk coefficient. For flood risk, a flood simulation model based on hydrological principles can be used in combination with historical flood event data for calculation. By inputting data such as rainfall and topography, the possibility of flood occurrence and inundation range can be simulated, and the flood risk coefficient is determined based on the simulation results. For water quality risk, a pollutant diffusion model is used in combination with parameters such as pollution source intensity and water body self-purification capacity for calculation. Drought risk can be determined by establishing a drought indicator system and comprehensively considering factors such as rainfall, evaporation, and soil moisture content. After calculation, the hydrological risk coefficients of multiple locations in the target area are obtained.

[0040] Step S413, input the hydrological fluctuation coefficients of the multiple locations and the hydrological risk coefficients of the multiple locations into the monitoring demand analysis channel to obtain the hydrological monitoring demand of the multiple locations, wherein the monitoring demand analysis channel includes predetermined hydrological fluctuation weights and predetermined hydrological risk weights. Specifically, the calculated hydrological fluctuation coefficients of the multiple locations and the hydrological risk coefficients of the multiple locations are input into the monitoring demand analysis channel, which pre-sets predetermined hydrological fluctuation weights and predetermined hydrological risk weights. The weights are determined based on the assessment of the importance of different hydrological factors and past monitoring experience, etc. For example, if an area often suffers from flood disasters, the weights related to flood risks may be set relatively high. Different weight values ​​are reasonably determined through expert evaluation, data analysis, historical case summary and other methods to reflect the different degrees of impact of hydrological fluctuations and risks on monitoring needs in specific areas or situations. In the monitoring demand analysis channel, the fluctuation coefficients and the hydrological risk coefficients are adjusted according to the set weights. The risk coefficient is weightedly calculated by using the mathematical method of weighted summation. The hydrological fluctuation coefficient of each location is multiplied by the predetermined hydrological fluctuation weight, and the hydrological risk coefficient is multiplied by the predetermined hydrological risk weight. The two are then added together to obtain the hydrological monitoring demand at each location. For example, the hydrological fluctuation coefficient of a certain location is 0.6, and the predetermined hydrological fluctuation weight is 0.4; the hydrological risk coefficient is 0.8, and the predetermined hydrological risk weight is 0.6. The hydrological monitoring demand at this location is 0.6×0.4+0.8×0.6=0.72. Through this calculation method, the corresponding hydrological monitoring demand is determined for each location in the target area, so that subsequent point planning adjustments and other work can be carried out according to the demand.

[0041] Step S500, based on the regional geographic feature data set of the target area and the hydrological dynamic prediction results, the initial point planning scheme is compensated for the damage to the hydrological monitoring points according to the point damage risk threshold, and the third adjustment plan for the point planning is obtained. Specifically, the target area geographic feature data set and the hydrological dynamic prediction results are first integrated, and information related to the risk of point damage such as terrain, soil, vegetation, etc. is extracted from the geographic data set. Combined with the water level, flow changes and extreme weather information in the hydrological prediction, a data file is established for each monitoring point. Then, a point damage risk prediction model is constructed, integrating the influencing mechanism of geographical and hydrological factors, using machine learning or physical models, and after historical data training and verification, the risk of damage is predicted for each point to obtain a risk coefficient. Then these coefficients are compared with the set threshold, and the points that are greater than or equal to the threshold are marked to determine the distribution of predicted damaged points, and a comprehensive judgment is made in combination with the specific geographical environment. After that, the geographical environment around the damaged points is analyzed based on the geographic feature dataset, and compensation strategies are formulated for different situations such as complex terrain, unstable geology or large flood impact, such as relocating points, strengthening foundations or adding flood control facilities. The initial plan is adjusted according to the strategy to generate a third adjustment plan. Finally, GIS and hydrological models are used to simulate the safety and monitoring effects of the points under different conditions. If there are any problems, they are optimized and improved until the safety and monitoring needs are met, and the final plan is determined.

[0042] In one possible implementation, based on the regional geographic feature data set of the target area and the hydrological dynamic prediction results, the initial point planning scheme is compensated for damage to the hydrological monitoring points according to the point damage risk threshold, and a third adjustment plan for the point planning is obtained. Step S500 further includes step S510, based on the hydrological dynamic prediction results, a damage risk prediction is performed on each hydrological monitoring point in the initial point planning scheme to obtain multiple point damage risk coefficients. Specifically, various key information is extracted from the hydrological dynamic prediction results, including but not limited to the prediction of water level change amplitude, flow peak prediction, and the probability and intensity prediction of extreme weather events (such as heavy rain, floods, hurricanes, etc.). For each hydrological monitoring point in the initial point planning scheme, the surrounding geographical environment data is obtained, such as the geographical feature information such as the terrain height, slope, geological structure stability, and the distance information from rivers, lakes and other water bodies. At the same time, the records of events related to point damage that have occurred in the point and the surrounding areas in history are sorted out, such as the water level height that has been impacted by floods, the impact range when geological disasters occur, and other data, which are integrated as reference data. These data are processed in a unified data format to ensure the accuracy and completeness of the data, so as to make full preparations for subsequent risk prediction calculations and construct a point damage risk prediction model, which comprehensively considers the impact of multiple factors on the point damage risk. For example, a relationship model between the water level change amplitude and the point damage probability is established using statistical analysis methods. If the predicted water level rise exceeds a certain threshold and the point is located in a low-lying area, the damage risk will increase accordingly. For flow peak prediction, the impact of water flow on the point is analyzed in combination with factors such as the width, depth and water flow speed of the river, and the damage risk is then assessed. When considering extreme weather events, the probability distribution of damage caused to the point by weather events such as rainstorms and hurricanes of different intensities is statistically calculated based on historical data and incorporated into the model calculation. The collected data is input into the model, and through the calculation logic of the model, the weight relationship of various factors is comprehensively considered to calculate a quantitative damage risk coefficient for each hydrological monitoring point, thereby obtaining damage risk coefficients for multiple points. These coefficients can intuitively reflect the degree of damage risk that each point may face in the future.

[0043] Step S520, determine whether the damage risk coefficients of the multiple points are greater than or equal to the damage risk threshold of the point, and establish a predicted distribution of damaged points. Specifically, the calculated damage risk coefficients of the multiple points are compared and analyzed one by one with the pre-set damage risk threshold of the point. The damage risk threshold of the point is a measurement standard determined comprehensively based on engineering experience, industry standards, and historical data statistical analysis. If the damage risk coefficient of a certain point is greater than or equal to the threshold, it means that the point is more likely to be damaged in the future. The points that meet the conditions are recorded and sorted, and marked on a map or geographic information system (GIS) according to the geographical location information of the points. The information of these points is integrated to form a predicted distribution of damaged points. The distribution of these points with higher damage risks is displayed in a visual way, so that it can be clearly seen which areas of monitoring points have greater safety hazards, and provide a clear target area for subsequent targeted point layout compensation.

[0044] Step S530, based on the regional geographic feature data set, point layout compensation is performed according to the predicted damaged point distribution to generate a third adjustment plan for the point planning. Specifically, based on the regional geographic feature dataset, a detailed geographic feature analysis is conducted on each point in the predicted distribution of damaged points and its surrounding environment. For points in mountainous areas with large terrain slopes and unstable geological structures, engineering measures are considered for reinforcement, such as building slope protection and retaining walls, to enhance the stability of the points and prevent geological disasters such as landslides from causing damage to the points. For points near rivers that are prone to floods, the points are moved to higher terrain or safer locations, or flood control facilities are built for the points, such as building flood control embankments and installing waterproof protective covers, based on the historical flood data of the river, river topography, and water flow direction. For areas with loose soil texture and prone to settlement, foundation reinforcement measures are taken to ensure the stability of the foundation of the points. At the same time, according to the monitoring function requirements of the points and the characteristics of the surrounding geographical environment, the installation method and layout of the monitoring equipment are replanned to improve the adaptability and reliability of the points in complex geographical environments. According to the formulated point layout compensation strategy, the initial point planning scheme is adjusted and optimized. The points that need to be relocated will be rearranged in new safe locations and equipped with appropriate monitoring equipment; the points that need to be reinforced or have additional protective facilities will be subject to corresponding engineering renovations and equipment updates. During the adjustment process, tools such as geographic information systems and hydrological simulation software will be used to simulate and verify the adjusted plan, simulating the feasibility and monitoring effect of the new point layout plan under different hydrological conditions and geographical environments, to check whether it can effectively reduce the risk of point damage and ensure the accuracy and continuity of hydrological monitoring data. If problems are found during the simulation process, such as the existence of new monitoring blind spots or unsatisfactory compensation measures, the plan will be further optimized and adjusted in a timely manner. After repeated verification and improvement, the third adjustment plan for the point planning will be generated to make the layout of hydrological monitoring points more scientific, reasonable, safe and reliable.

[0045] Step S600, according to the first adjustment scheme of the point planning, the second adjustment scheme of the point planning and the third adjustment scheme of the point planning, the initial point planning scheme is globally optimized to generate the optimization result of the hydrological monitoring point. Specifically, firstly, the data of the first, second and third adjustment schemes of the point planning are summarized, cleaned and standardized, and a comprehensive evaluation index system is established, covering aspects such as monitoring coverage, data accuracy, reasonable points, and cost-effectiveness. The evaluation score is calculated by determining the weights to construct a mathematical model. Then, the conflicts in the integration process are handled, such as analyzing the basis of the objectives of each plan, using GIS to visualize the conflicting areas, and coordinating and solving them after comprehensive evaluation, such as adjusting the location, parameters or functions of the points. Then, through iterative optimization, the hydrological model is used to simulate the working conditions of the optimized points under different hydrological conditions and actual environments, and the deficiencies are adjusted according to the simulation results, and it is iterated repeatedly until the target is met. Finally, the optimization scheme of the hydrological monitoring points is determined, the detailed information is sorted and archived, the results are displayed visually, and the lessons learned are summarized by comparing with the initial scheme, providing a reference for subsequent work, and completing the optimization and improvement of the layout of the hydrological monitoring points.

[0046] The embodiment of the present application adopts the method of collecting the parameters of the hydrological monitoring points in the target area and formulating the initial point planning scheme. Based on the prediction of the future time zone, the hydrological dynamic prediction is performed on the area to obtain the hydrological prediction results. According to the results, the initial point plan is adjusted for redundancy to generate a first adjustment plan. Based on the monitoring needs and the prediction results, the point blind spots are corrected to form a second adjustment plan. Combining the geographic feature data and the damaged risk threshold, compensatory adjustments are made to the damaged points to generate a third adjustment plan. The above adjustment plans are integrated, the initial plan is globally optimized, and the optimized hydrological monitoring point layout is generated. The hydrological monitoring points are flexibly adjusted in multiple dimensions through the hydrological dynamic prediction results, thereby achieving the technical effect of improving the planning flexibility and accuracy of the hydrological monitoring points and improving the quality of hydrological monitoring.

[0047] In the above, refer to Figure 1 A method for dynamic planning of hydrological monitoring points according to an embodiment of the present invention is described in detail. Figure 2 A hydrological monitoring point dynamic planning system according to an embodiment of the present invention is described.

[0048] A hydrological monitoring point dynamic planning system according to an embodiment of the present invention is used to solve the technical problems of poor planning flexibility and low precision of hydrological monitoring points in the prior art, and to flexibly adjust the hydrological monitoring points in multiple dimensions through hydrological dynamic prediction results, thereby achieving the technical effect of improving the planning flexibility and precision of hydrological monitoring points and improving the quality of hydrological monitoring. A hydrological monitoring point dynamic planning system includes: an initial point planning scheme acquisition module 10, a hydrological dynamic prediction result acquisition module 20, a point planning first adjustment scheme acquisition module 30, a second adjustment scheme acquisition module 40, a third adjustment scheme acquisition module 50, and a global optimization module 60.

[0049] The initial point planning scheme acquisition module 10 is used to collect the hydrological monitoring point parameters of the target area and obtain the initial point planning scheme.

[0050] The hydrological dynamic prediction result acquisition module 20 is used to perform hydrological dynamic prediction on the target area based on a preset future time zone to obtain a hydrological dynamic prediction result.

[0051] The point planning first adjustment scheme acquisition module 30 is used to perform redundancy adjustment of the hydrological monitoring points on the initial point planning scheme based on the hydrological dynamic prediction result to obtain the point planning first adjustment scheme.

[0052] The second adjustment scheme acquisition module 40 is used to correct the blind spots of the hydrological monitoring points of the initial point planning scheme based on the hydrological dynamic prediction results, according to the monitoring demand analysis channel and the hydrological monitoring point addition decision channel, to obtain the second adjustment scheme of the point planning.

[0053] The third adjustment scheme acquisition module 50 is used to compensate for the damage to the hydrological monitoring points in the initial point planning scheme based on the regional geographic feature data set of the target area and the hydrological dynamic prediction results according to the point damage risk threshold, and obtain the third adjustment scheme for the point planning.

[0054] The global optimization module 60 is used to globally optimize the initial point planning scheme according to the first point planning adjustment scheme, the second point planning adjustment scheme and the third point planning adjustment scheme, and generate hydrological monitoring point optimization results.

[0055] The specific configuration of the hydrological dynamic prediction result acquisition module 20 will be described in detail below. As described above, the hydrological dynamic prediction is performed on the target area based on the preset future time zone to obtain the hydrological dynamic prediction result. The hydrological dynamic prediction result acquisition module 20 further includes: a real-time hydrological state information acquisition unit, the real-time hydrological state information acquisition unit is used to collect real-time hydrological parameters of the target area and obtain real-time hydrological state information; a meteorological forecast data loading unit, the meteorological forecast data loading unit is used to load the meteorological forecast data of the target area based on the preset future time zone; a hydrological dynamic prediction unit, the hydrological dynamic prediction unit is used to perform hydrological dynamic prediction according to the regional geographical feature data set based on the real-time hydrological state information and the meteorological forecast data, and obtain the hydrological dynamic prediction result.

[0056] The specific configuration of the point planning first adjustment scheme acquisition module 30 will be described in detail below. As described above, the initial point planning scheme is adjusted for redundancy of the hydrological monitoring points based on the hydrological dynamic prediction results to obtain the first adjustment scheme of the point planning. The point planning first adjustment scheme acquisition module 30 further includes: a monitoring fitting result determination unit, the monitoring fitting result determination unit is used to perform monitoring parameter fitting on each hydrological monitoring point in the initial point planning scheme based on the hydrological dynamic prediction results to determine multiple point monitoring fitting results; a redundancy detection unit, the redundancy detection unit is used to perform redundancy detection on the initial point planning scheme based on the multiple point monitoring fitting results to generate a monitoring point redundancy detection result; a redundancy adjustment unit, the redundancy adjustment unit is used to perform redundancy adjustment based on the monitoring point redundancy detection result to generate the first adjustment scheme of the point planning.

[0057] Among them, based on the fitting results of the monitoring of the multiple points, the initial point planning scheme is subjected to redundancy detection to generate redundant detection results of the monitoring points. The redundant detection unit further includes: a twin identification subunit, the twin identification subunit is used to perform twin identification in pairs according to the fitting results of the monitoring of the multiple points, and obtain multiple twin degrees of monitoring of the points; a predetermined twin degree monitoring subunit, the predetermined twin degree monitoring subunit is used to determine whether the twin degrees of the monitoring of the multiple points are greater than or equal to the predetermined twin degrees of the monitoring of the points, and determine multiple twin point clusters that are greater than or equal to the predetermined twin degrees of the monitoring of the points; proximity analysis Subunit, the proximity analysis subunit is used to perform proximity analysis of the point positions within the cluster according to the multiple twin point clusters, and determine multiple redundancy coefficients of the points within the cluster; a redundancy coefficient judgment subunit, the redundancy coefficient judgment subunit is used to judge whether the multiple redundancy coefficients of the points within the cluster are greater than or equal to the redundancy threshold of the points within the cluster, and determine the redundancy coefficient of the points within the cluster that is greater than or equal to the redundancy threshold of the points within the cluster; a point mapping subunit, the point mapping subunit is used to perform point mapping on the initial point planning scheme based on the redundancy coefficient of the points within the cluster to obtain the redundant detection result of the monitoring points.

[0058] Next, the specific configuration of the second adjustment scheme acquisition module 40 will be described in detail. As described above, based on the hydrological dynamic prediction results, the initial point planning scheme is corrected for the blind spots of the hydrological monitoring points according to the monitoring demand analysis channel and the decision channel for adding hydrological monitoring points, and the second adjustment scheme for the point planning is obtained. The second adjustment scheme acquisition module 40 further includes: a location hydrological monitoring demand determination unit, which is used to perform hydrological monitoring demand analysis based on the monitoring demand analysis channel and the hydrological dynamic prediction results to determine the hydrological monitoring demand of multiple locations; a hydrological monitoring demand location distribution generation unit, which is used to determine whether the hydrological monitoring demand of the multiple locations is greater than or equal to the predetermined hydrological monitoring demand. The unit is used to identify the missing monitoring points in the initial point planning scheme based on the hydrological monitoring demand position distribution, and obtain the point blind spot detection results; the unit is used to collect geographical features based on the point blind spot detection results, and obtain the geographical feature data of the point blind spots; the unit is used to generate the second adjustment plan for the point planning, and the unit is used to generate the second adjustment plan for the point planning based on the point blind spot detection results and the geographical feature data of the point blind spots, according to adding a decision channel to the hydrological monitoring point.

[0059] Wherein, based on the monitoring demand analysis channel, the hydrological monitoring demand analysis is performed according to the hydrological dynamic prediction result, and the hydrological monitoring demand of multiple locations is determined. The location hydrological monitoring demand determination unit further includes: a location hydrological fluctuation coefficient acquisition subunit, the location hydrological fluctuation coefficient acquisition subunit is used to perform hydrological fluctuation detection at each location of the target area according to the hydrological dynamic prediction result, and obtain multiple location hydrological fluctuation coefficients; a location hydrological risk coefficient acquisition subunit, the location hydrological risk coefficient acquisition subunit is used to perform hydrological risk prediction at each location of the target area according to the hydrological dynamic prediction result, and obtain multiple location hydrological risk coefficients; a location hydrological monitoring demand acquisition subunit, the location hydrological monitoring demand acquisition subunit is used to input the multiple location hydrological fluctuation coefficients and the multiple location hydrological risk coefficients into the monitoring demand analysis channel, and obtain the multiple location hydrological monitoring demand, wherein the monitoring demand analysis channel includes a predetermined hydrological fluctuation weight and a predetermined hydrological risk weight.

[0060] The specific configuration of the third adjustment scheme acquisition module 50 will be described in detail below. As described above, based on the regional geographic feature data set of the target area and the hydrological dynamic prediction result, the initial point planning scheme is compensated for the damage of the hydrological monitoring points according to the point damage risk threshold, and the point planning third adjustment scheme is obtained. The third adjustment scheme acquisition module 50 further includes: a damage risk prediction unit, the damaged risk prediction unit is used to predict the damage risk of each hydrological monitoring point in the initial point planning scheme based on the hydrological dynamic prediction result, and obtain multiple point damage risk coefficients; a predicted damaged point distribution establishment unit, the predicted damaged point distribution establishment unit is used to determine whether the multiple point damage risk coefficients are greater than or equal to the point damage risk threshold, and establish a predicted damaged point distribution; a point layout compensation unit, the point layout compensation unit is used to perform point layout compensation based on the regional geographic feature data set and the predicted damaged point distribution, and generate the third adjustment scheme of the point planning.

[0061] A hydrological monitoring point dynamic planning system provided by an embodiment of the present invention can execute a hydrological monitoring point dynamic planning method provided by any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0062] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0063] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for dynamic planning of hydrological monitoring points, characterized in that: The method comprises: Collect the hydrological monitoring point parameters of the target area and obtain the initial point planning scheme; Performing hydrological dynamic prediction on the target area based on a preset future time zone to obtain a hydrological dynamic prediction result; Based on the hydrological dynamic prediction result, the initial point planning scheme is adjusted for hydrological monitoring point redundancy to obtain a first adjustment scheme for the point planning; Based on the hydrological dynamic prediction result, the initial point planning scheme is corrected for the blind area of ​​the hydrological monitoring point according to the monitoring demand analysis channel and the decision channel for adding hydrological monitoring points, so as to obtain a second adjustment plan for the point planning; Based on the regional geographic feature data set of the target area and the hydrological dynamic prediction result, the initial point planning scheme is compensated for the hydrological monitoring point damage according to the point damage risk threshold, so as to obtain a third adjustment scheme for the point planning; According to the first adjustment plan for the point planning, the second adjustment plan for the point planning and the third adjustment plan for the point planning, the initial point planning plan is globally optimized to generate hydrological monitoring point optimization results.

2. The method according to claim 1, characterized in that Performing hydrological dynamic prediction on the target area based on a preset future time zone to obtain hydrological dynamic prediction results, including: Collecting real-time hydrological parameters of the target area to obtain real-time hydrological status information; Based on the preset future time zone, loading weather forecast data for the target area; Based on the real-time hydrological status information and the meteorological forecast data, hydrological dynamic prediction is performed according to the regional geographic feature data set to obtain the hydrological dynamic prediction result.

3. The method according to claim 1, characterized in that Based on the hydrological dynamic prediction result, the initial point planning scheme is adjusted for hydrological monitoring point redundancy to obtain a first adjustment scheme for point planning, including: Based on the hydrological dynamic prediction results, monitoring parameters of each hydrological monitoring point in the initial point planning scheme are fitted to determine multiple point monitoring fitting results; Based on the multiple point monitoring fitting results, the initial point planning scheme is subjected to redundancy detection to generate monitoring point redundancy detection results; Redundancy adjustment is performed based on the redundant detection result of the monitoring points to generate a first adjustment plan for the point planning.

4. The method according to claim 3, characterized in that Based on the multiple point monitoring fitting results, the initial point planning scheme is subjected to redundancy detection to generate monitoring point redundancy detection results, including: Perform twin identification on a pair-by-two basis according to the multiple point monitoring fitting results to obtain multiple point monitoring twin degrees; Determining whether the twinning degrees of the plurality of point monitoring are greater than or equal to the predetermined twinning degree of the point monitoring, and determining a plurality of twin point clusters having a twinning degree greater than or equal to the predetermined twinning degree of the point monitoring; Performing proximity analysis of intra-cluster point locations according to the plurality of twin point clusters to determine a plurality of intra-cluster point redundancy coefficients; Determine whether the plurality of intra-cluster point redundancy coefficients are greater than or equal to an intra-cluster point redundancy threshold, and determine an intra-cluster point redundancy coefficient greater than or equal to the intra-cluster point redundancy threshold; The initial point planning scheme is point mapped based on the point redundancy coefficient within the identification cluster to obtain the monitoring point redundancy detection result.

5. The method according to claim 1, characterized in that Based on the hydrological dynamic prediction result, the initial point planning scheme is corrected for the hydrological monitoring point blind area according to the monitoring demand analysis channel and the hydrological monitoring point additional decision channel to obtain the second adjustment plan of the point planning, including: Based on the monitoring demand analysis channel, the hydrological monitoring demand analysis is performed according to the hydrological dynamic prediction result to determine the hydrological monitoring demand of multiple locations; Determining whether the hydrological monitoring requirements of the multiple locations are greater than or equal to a predetermined hydrological monitoring requirement, and generating a hydrological monitoring requirement location distribution; Based on the location distribution of the hydrological monitoring requirements, the initial point planning scheme is used to identify the missing monitoring points to obtain the point blind spot detection results; Based on the point blind spot detection result, geographic feature collection is performed to obtain geographic feature data of the point blind spot; Based on the point blind spot detection result and the geographical feature data of the point blind spot, a second adjustment plan for the point planning is generated according to the additional establishment of a decision channel at the hydrological monitoring point.

6. The method according to claim 5, characterized in that Based on the monitoring demand analysis channel, the hydrological monitoring demand analysis is performed according to the hydrological dynamic prediction result to determine the hydrological monitoring demand of multiple locations, including: Perform hydrological fluctuation detection at each location in the target area according to the hydrological dynamic prediction result to obtain hydrological fluctuation coefficients at multiple locations; According to the hydrological dynamic prediction result, hydrological risk prediction is performed at each location in the target area to obtain hydrological risk coefficients of multiple locations; The hydrological fluctuation coefficients of the multiple locations and the hydrological risk coefficients of the multiple locations are input into the monitoring demand analysis channel to obtain the hydrological monitoring demand degrees of the multiple locations, wherein the monitoring demand analysis channel includes a predetermined hydrological fluctuation weight and a predetermined hydrological risk weight.

7. The method according to claim 1, characterized in that Based on the regional geographic feature data set of the target area and the hydrological dynamic prediction result, the initial point planning scheme is compensated for hydrological monitoring point damage according to the point damage risk threshold, and a third adjustment scheme for the point planning is obtained, including: Based on the hydrological dynamic prediction results, damage risk prediction is performed on each hydrological monitoring point in the initial point planning scheme to obtain damage risk coefficients of multiple points; Determine whether the damage risk coefficients of the multiple points are greater than or equal to the damage risk threshold of the point, and establish a predicted damaged point distribution; Based on the regional geographic feature data set, point layout compensation is performed according to the predicted damaged point distribution to generate a third adjustment plan for the point planning.

8. A hydrological monitoring point dynamic planning system, characterized in that: The system is used to implement a hydrological monitoring point dynamic programming method according to any one of claims 1 to 7, and the system comprises: An initial point planning scheme acquisition module is used to collect hydrological monitoring point parameters of the target area to obtain an initial point planning scheme; A hydrological dynamic prediction result acquisition module, which is used to perform hydrological dynamic prediction on the target area based on a preset future time zone to obtain a hydrological dynamic prediction result; A first adjustment scheme acquisition module for point planning, wherein the first adjustment scheme acquisition module for point planning is used to perform redundancy adjustment of hydrological monitoring points on the initial point planning scheme based on the hydrological dynamic prediction result to obtain a first adjustment scheme for point planning; A second adjustment scheme acquisition module, which is used to correct the blind spots of the hydrological monitoring points of the initial point planning scheme based on the hydrological dynamic prediction result and the monitoring demand analysis channel and the decision channel for adding hydrological monitoring points, so as to obtain a second adjustment scheme for the point planning; A third adjustment scheme acquisition module, the third adjustment scheme acquisition module is used to compensate for the damage of the hydrological monitoring points in the initial point planning scheme according to the point damage risk threshold based on the regional geographic feature data set of the target area and the hydrological dynamic prediction result, and obtain a third adjustment scheme for the point planning; A global optimization module is used to globally optimize the initial point planning scheme according to the first adjustment scheme of the point planning, the second adjustment scheme of the point planning and the third adjustment scheme of the point planning, and generate optimization results of the hydrological monitoring points.

Images