Reservoir water resource information management method and system based on intelligent data

Abstract

The invention relates to the technical field of information management, in particular to a reservoir water resource information management method and system based on intelligent data. The method comprises the following steps: acquiring a reservoir surface region data set; performing data preprocessing on the reservoir surface area data set to generate a reservoir surface area preprocessing data set; discrete particle node processing is carried out on the reservoir surface layer area preprocessing data set, a loss influence factor database is constructed, and an upper layer loss influence factor database is generated; performing loss rate calculation model construction on the upper loss influence factor database to generate an upper loss rate prediction model; therefore, by constructing an intelligent data reservoir water resource information management system, the problems of information asymmetry and slow response in traditional water resource management are solved, and scientificity and pertinence of reservoir water resource loss monitoring and protection measures are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of information management, and in particular to a reservoir water resources information management method and system based on intelligent data. Background Art

[0002] The existing system lacks dynamic monitoring of the reservoir operation status and cannot respond to environmental changes and fluctuations in hydrological conditions in a timely manner, resulting in the lag of water resources management. In addition, the data analysis methods are relatively single and lack in-depth multi-dimensional analysis capabilities, making it difficult to effectively explore potential loss risks and environmental influencing factors. At the same time, traditional technologies have obvious shortcomings in data integration and sharing. The lack of interconnection between different data sources leads to the formation of information islands, which makes decision makers face the dilemma of incomplete information when formulating management strategies. In addition, the existing technologies rely on static models in the monitoring and early warning of soil erosion, and fail to fully consider the impact of environmental changes, land use changes and climate factors around the reservoir, resulting in insufficient risk assessment and early warning capabilities. Finally, the current reservoir water resources management system lacks intelligent and automated functions and fails to make full use of modern information technology, such as big data analysis, Internet of Things technology and artificial intelligence. These deficiencies limit the scientificity and accuracy of reservoir water resources information management and affect the sustainable use of water resources. Summary of the invention

[0003] Based on this, it is necessary to provide a reservoir water resources information management method and system based on intelligent data to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a reservoir water resources information management method based on intelligent data, the method comprising the following steps:

[0005] Step S1: obtaining a reservoir surface area data set; performing data preprocessing on the reservoir surface area data set to generate a reservoir surface area preprocessing data set; performing discrete particle node processing on the reservoir surface area preprocessing data set, and constructing a loss influencing factor database to generate an upper layer loss influencing factor database; constructing a loss rate calculation model for the upper layer loss influencing factor database to generate an upper layer loss rate prediction model;

[0006] Step S2: Obtain historical groundwater level data, real-time groundwater level data and surface permeability data; compare the historical groundwater level data with the real-time groundwater level data to generate groundwater level change data; combine the groundwater level change data with the surface permeability data to draw a spatial distribution map, mark high loss areas, and generate a lower reservoir area loss distribution map;

[0007] Step S3: Performing a deep particle loss relationship analysis on the upper layer loss rate prediction model and the lower layer reservoir area loss distribution map to generate upper and lower layer loss relationship result data; performing linkage model association processing on the upper layer loss rate prediction model based on the lower layer reservoir area loss distribution map to generate an upper and lower layer linkage model of the reservoir area;

[0008] Step S4: Generate a soil and water conservation strategy for the upper and lower layer linkage model of the reservoir area based on the upper and lower layer loss relationship result data, generate the upper and lower layer protection strategy of the reservoir, and thus complete the intelligent data reservoir water resources information management operation.

[0009] The beneficial effect of the present invention is that by obtaining the reservoir surface area data set and performing discrete particle node processing, the upper layer loss influencing factor database generated provides a solid data foundation for the construction of the loss rate prediction model. This process ensures the comprehensive consideration of various factors affecting the surface loss of the reservoir, thereby improving the accuracy and reliability of the loss rate prediction. By comparing the historical and real-time groundwater level data, the groundwater level change data is generated, and the spatial distribution map is drawn in combination with the surface permeability, so as to clearly identify the high loss area. This method makes the monitoring and evaluation of the loss phenomenon more intuitive, which helps to formulate corresponding management measures in a timely manner. The deep particle analysis of the relationship between the upper and lower layer losses provides the correlation data between the loss rate and the reservoir management, so that the water loss situation at different levels can be comprehensively analyzed. Through the construction of the linkage model, the mutual influence of the upper and lower layer losses is quantified, which promotes the comprehensive management and optimization of water resources. Finally, the soil and water conservation strategy generated based on the result data of the upper and lower layer loss relationship can solve the problem of serious loss areas in a targeted manner, such as vegetation restoration and cover reinforcement in the upper layer loss area, and deep water retaining or groundwater recharge measures in the lower layer seepage loss area. Such a strategy not only improves the protection effect of water and soil resources, but also enhances the ecological stability of the reservoir. Therefore, the present invention solves the problems of information asymmetry and slow response in traditional water resource management by constructing an intelligent data reservoir water resource information management system, and improves the scientificity and pertinence of reservoir water resource loss monitoring and protection measures.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: obtaining a reservoir surface area data set; performing data preprocessing on the reservoir surface area data set to generate a reservoir surface area preprocessing data set;

[0012] Step S12: performing discrete particle node processing on the preprocessed data set of the reservoir surface area to generate upper discrete particles in the reservoir area; performing coefficient calculation and analysis on the upper discrete particles in the reservoir area, and constructing a loss influencing factor database to generate an upper loss influencing factor database;

[0013] Step S13: construct a churn rate calculation model based on the upper-level churn influencing factor database to generate an upper-level churn rate prediction model.

[0014] The present invention lays the foundation for subsequent analysis by obtaining the reservoir surface area data set, ensuring the comprehensiveness and reliability of the data source. This process not only provides preliminary data support for identifying loss characteristics, but also lays the foundation for subsequent data integration and analysis. The discrete particle node processing of the reservoir surface area preprocessing data set can accurately reflect the surface hydrological characteristics and their dynamic changes related to loss by subdividing the data into smaller granularities. This refinement process not only improves the accuracy of data analysis, but also provides more detailed basic data for the in-depth calculation of loss influencing factors. By performing coefficient calculation and analysis on the upper discrete particles and constructing a loss influencing factor database, the key factors affecting the surface loss of the reservoir can be systematically summarized, thereby providing strong data support for the quantitative prediction of the loss rate. The establishment of this database enables the correlation of the loss influencing factors to be fully presented, providing sufficient basis and conditions for the subsequent loss rate calculation model. Finally, by constructing a loss rate calculation model for the upper loss influencing factor database, an accurate prediction of the reservoir surface loss rate is achieved. This model can not only effectively simulate the changes in loss under different environmental conditions, but also provide a scientific basis for the management and decision-making of reservoir water resources, helping managers to formulate reasonable soil and water conservation measures.

[0015] Preferably, step S12 comprises the following steps:

[0016] Step S121: performing discrete particle node processing on the preprocessed data set of the reservoir surface area to generate discrete particles in the upper layer of the reservoir area;

[0017] Step S122: extracting spatial position feature values ​​of upper discrete particles in the reservoir area to generate spatial position feature value data of the reservoir area; extracting loss potential feature values ​​of upper discrete particles in the reservoir area to generate loss potential feature value data of the reservoir area; extracting environmental feature values ​​of upper discrete particles in the reservoir area to generate environmental feature value data of the reservoir area;

[0018] Step S123: Calculate and analyze the rainfall erosion coefficient of the reservoir area spatial position characteristic value data and the reservoir area environmental characteristic value data to generate the surface rainfall-erosion coefficient; Calculate and analyze the wind speed loss coefficient of the reservoir area spatial position characteristic value data and the reservoir area loss potential characteristic value data to generate the wind speed-loss coefficient; Calculate the slope soil coefficient of the reservoir area loss potential characteristic value data and the reservoir area environmental characteristic value data to generate the soil type-slope coefficient;

[0019] Step S124: constructing a database of loss influencing factors based on surface rainfall-erosion coefficient, wind speed-loss coefficient and soil type-slope coefficient to generate an upper layer loss influencing factor database.

[0020] The present invention processes the discrete particle nodes of the preprocessed data set of the surface area of ​​the reservoir, so that the data is more refined, which helps to capture more microscopic hydrological characteristics, and the generated upper discrete particles lay the foundation for the subsequent extraction of characteristic values. By extracting the spatial position characteristic values, loss potential characteristic values ​​and environmental characteristic values ​​of the discrete particles, a multi-dimensional characteristic system is comprehensively constructed. This process not only reflects the influence of different spatial positions on the loss, but also reveals the complex relationship between environmental conditions and loss potential, forming a systematic data support, which is convenient for subsequent analysis. The extracted characteristic values ​​are calculated and analyzed for the rainfall erosion coefficient, wind speed loss coefficient and soil type-slope coefficient, and the composition of the loss influencing factors is further refined. The calculation of the rainfall erosion coefficient can reveal the direct influence of rainfall intensity on the surface loss of the reservoir, the wind speed loss coefficient considers the influence of wind speed on soil stability, and the soil type-slope coefficient provides a quantitative basis for the loss characteristics under different soil types and slope conditions. The calculation of these coefficients makes the analysis of the loss influencing factors more accurate, thereby providing a clear guiding basis for the formulation of management measures. The above calculation results are integrated into the upper loss influencing factor database to form a structured data platform. The database not only systematically summarizes various loss influencing factors, but also provides important basic data for subsequent loss rate prediction models and management strategies. In this way, the present invention realizes in-depth analysis of reservoir surface loss characteristics, making loss monitoring and management more scientific and targeted, thereby improving the effective management and protection capabilities of water resources.

[0021] Preferably, step S13 includes the following steps:

[0022] Step S131: Divide the preset upper layer loss rate model into three layers to generate a three-layer model of reservoir area loss rate, wherein the three-layer model of reservoir area loss rate includes a first layer of reservoir area, a second layer of reservoir area and a third layer of reservoir area;

[0023] Step S132: Calculate the impact of rainfall erosion on the first layer of the reservoir area by using the surface rainfall-erosion coefficient to generate the first layer of the reservoir area loss rate; Quantify the impact of wind erosion on the first layer of the reservoir area by using the surface rainfall-erosion coefficient to generate the second layer of the reservoir area loss rate; Calculate the soil slope adaptability on the third layer of the reservoir area by using the soil type-slope coefficient to generate the third layer of the reservoir area loss rate

[0024] Step S133: assign multi-layer weight values ​​to the first layer of reservoir area loss rate, the second layer of reservoir area loss rate and the third layer of reservoir area loss rate, and reorganize the model to generate an upper layer loss rate prediction model.

[0025] The present invention forms a structured three-layer model of reservoir area loss rate by dividing the preset upper loss rate model into three layers. This hierarchical strategy not only makes the analysis of loss characteristics more systematic, but also provides a clear framework for the subsequent application of loss influencing factors at different levels. The division of the first, second and third layers of the reservoir area enables each layer to independently reflect the influence of different environmental factors on the loss, thereby improving the flexibility and adaptability of the model. The characteristic value calculation and replacement are performed for each layer, so that the loss rate model can dynamically reflect the loss characteristics under the current environmental conditions. Specifically, the application of the surface rainfall-erosion coefficient in the first layer can directly reveal the impact of rainfall on reservoir loss; the application of the wind speed-loss coefficient in the second layer considers the dynamic effect of wind speed changes on soil loss; the use of the soil type-slope coefficient in the third layer provides a quantitative basis for the loss characteristics under different soil and slope conditions. Through this hierarchical characteristic value replacement, the prediction ability of the model is significantly enhanced, and the changing trend of the loss rate can be more accurately reflected. The three-layer loss rate data is subjected to multi-layer weight value allocation and model reorganization to generate an upper loss rate prediction model. The key to this process is to allocate weights to the loss rates at different levels, so that the influence relationships between the levels can be reasonably integrated, thus forming a comprehensive and sophisticated loss rate prediction system. By combining the loss characteristics at different levels, the model can not only effectively predict the loss rate, but also provide targeted decision-making support for reservoir managers, enabling them to formulate soil and water conservation strategies more scientifically.

[0026] Preferably, step S2 comprises the following steps:

[0027] Step S21: acquiring historical groundwater level data, real-time groundwater level data and surface permeability data; comparing the historical groundwater level data and the real-time groundwater level data to generate groundwater level change data;

[0028] Step S22: spatially process the surface permeability data to generate lower layer loss rate data; coordinate map the lower layer loss rate data to generate a lower layer groundwater infiltration distribution coordinate map;

[0029] Step S23: Draw a spatial distribution map of the groundwater level change data and the lower groundwater infiltration distribution coordinate map to generate a lower reservoir area loss distribution map.

[0030] The present invention establishes a comprehensive hydrological data foundation by acquiring historical groundwater level data, real-time groundwater level data and surface permeability data. The comparative analysis of historical and real-time data not only provides a clear time series perspective for identifying groundwater level changes, but also lays a solid foundation for the evaluation of subsequent loss characteristics. The generated groundwater level change data provides an important basis for understanding the hydrological dynamics of the lower layer of the reservoir, enabling managers to grasp the fluctuation of the water level in a timely manner, thereby better predicting the risk of loss. The surface permeability data is spatially processed so that the data structure of the loss rate can be converted into more intuitive spatial information. This process not only improves the visualization of the data, but also generates a lower-layer groundwater infiltration distribution coordinate map through coordinate mapping. The generation of this map enables the spatial distribution characteristics of the loss rate to be displayed, thereby providing strong support for subsequent hydrological analysis. Through these spatial data, high-risk loss areas can be clearly identified, providing a scientific basis for relevant protection measures and decisions. The spatial distribution map of the groundwater level change data and the lower-layer groundwater infiltration distribution coordinate map is drawn, and the generated lower-layer reservoir area loss distribution map further enhances the spatial analysis capability of loss monitoring. This loss distribution map intuitively shows the relationship between loss characteristics and groundwater dynamics, allowing managers to quickly locate potential loss areas and take timely intervention measures. By spatially integrating different data levels, the loss distribution map not only improves the efficiency of loss monitoring, but also provides an important scientific basis for reservoir management decisions.

[0031] Preferably, step S23 includes the following steps:

[0032] Step S231: Calculate the loss rate of the monitoring point according to the groundwater level change data and the surface permeability data to generate the loss rate data of the lower layer monitoring point;

[0033] Step S232: using GIS technology to upload the loss rate data of the lower monitoring points to the lower groundwater infiltration distribution coordinate map to draw a spatial infiltration distribution map, and generate a lower reservoir area loss distribution map;

[0034] Step S233: marking high loss areas on the loss distribution map of the lower reservoir area to generate high loss area data for the lower reservoir area.

[0035] The present invention calculates the loss rate of the monitoring point according to the groundwater level change data and the surface permeability data to generate the loss rate data of the lower monitoring point. This process not only realizes the quantitative analysis of the loss rate, but also provides key data support for the subsequent spatial distribution and management strategy. The calculation of the loss rate of the monitoring point, combined with real-time and historical data, makes the assessment of the loss risk more scientific and reliable, and provides a basis for reservoir managers to grasp the loss dynamics in a timely manner. The loss rate data of the lower monitoring point is uploaded to the lower groundwater infiltration distribution coordinate map using GIS technology to draw the spatial infiltration distribution map. The generated loss distribution map of the lower reservoir area intuitively shows the spatial distribution of the loss characteristics. Through GIS technology, not only the visualization effect of the data is improved, but also the comparison and analysis capabilities of the loss rates between different monitoring points are enhanced. This loss distribution map can effectively reveal the spatial variation law of the loss rate, and provide an intuitive reference basis for reservoir managers to formulate targeted protection measures. The high loss area of ​​the lower reservoir area loss distribution map is marked to generate the high loss area data of the lower reservoir area. This marking process makes the focus of erosion monitoring clearer, helping managers quickly identify and concentrate resources on high-risk areas, thereby improving the efficiency and effectiveness of erosion management. By combining erosion rate data with spatial distribution maps, the high-erosion area data formed provides a scientific basis for subsequent soil and water conservation strategies, allowing intervention measures for different erosion characteristics to be accurately implemented.

[0036] Preferably, step S3 comprises the following steps:

[0037] Step S31: using factor analysis to analyze the relationship between the upper layer loss rate prediction model and the lower layer reservoir area loss distribution map, and generate upper and lower layer loss relationship result data;

[0038] Step S32: Based on the data of high loss areas in the lower reservoir area, the upper loss rate prediction model is used to identify the relationship between soil and water loss, and generate spatial characteristic data of different loss areas in the reservoir area;

[0039] Step S33: using different loss spatial characteristic data of the reservoir area and the loss distribution map of the lower reservoir area to perform a deep particle loss relationship analysis on the upper layer loss rate prediction model, and generate upper and lower layer loss relationship result data;

[0040] Step S34: Based on the loss distribution map of the lower reservoir area, the upper layer loss rate prediction model is subjected to linkage model association processing to generate an upper and lower layer linkage model of the reservoir area.

[0041] The present invention uses factor analysis to perform deep particle loss relationship analysis on the upper loss rate prediction model and the lower reservoir area loss distribution map, thereby generating upper and lower layer loss relationship result data. This process not only reveals the dynamic relationship between the upper and lower layer losses, but also provides data support for the identification of loss characteristics, so that managers can scientifically understand the mutual influence of losses at different levels and provide a basis for loss management decisions. Based on the data of high loss areas in the lower reservoir area, the upper loss rate prediction model is used to identify the relationship between soil and water loss, and different spatial feature data of loss in the reservoir area are generated. The generation of this data makes the spatial characteristics of loss clear, thereby achieving a comprehensive understanding of the loss phenomenon and improving the efficiency of formulating management strategies for high loss areas. Through this analysis, the changing law of loss rate under different environmental conditions can be identified, which provides an important reference for the subsequent design of protection measures. Using the different spatial feature data of loss in the reservoir area and the loss distribution map of the lower reservoir area, the upper loss rate prediction model is used to perform deep particle loss relationship analysis, and further generate upper and lower layer loss relationship result data. This link not only deepens the understanding of the relationship between upper and lower layer losses, but also provides more abundant data support for loss risk assessment. By analyzing the relationship between different spatial characteristics and loss, potential risk areas can be identified more effectively, providing a scientific basis for precise intervention. Based on the loss distribution map of the lower reservoir area, the upper loss rate prediction model is linked to the model to generate a linkage model of the upper and lower layers of the reservoir area. The generation of this model enables managers to comprehensively consider the loss relationship between the upper and lower layers, so as to formulate more effective management strategies and achieve coordinated prevention and control of soil and water loss. By linking the loss characteristics of the upper and lower layers, the ability to monitor the overall loss situation can be improved, providing strong data support for the sustainable management of water resources.

[0042] Preferably, step S4 comprises the following steps:

[0043] Step S41: Based on the upper and lower layer loss relationship result data, the upper and lower layer linkage model of the reservoir area is evaluated for loss potential, and the upper and lower layer loss potential evaluation data of the reservoir area are generated; the upper and lower layer linkage factor results are generated for the upper and lower layer loss potential evaluation data of the reservoir area, and the upper and lower layer linkage factor result data are generated, wherein the upper and lower layer linkage factor result data includes the upper layer loss serious result and the lower layer infiltration serious result;

[0044] Step S42: generating soil and water conservation strategies for the upper and lower layer linkage factor result data, and generating upper and lower layer protection strategies for reservoirs;

[0045] Step S43: Using the upper and lower layer protection strategies of the reservoir to complete the reservoir information management operation.

[0046] The present invention generates the upper and lower layer linkage factor results for the upper and lower layer linkage model of the reservoir area based on the upper and lower layer loss relationship result data, and the generated upper and lower layer linkage factor result data specifically include the upper layer loss serious result and the lower layer infiltration serious result. This process not only realizes the accurate identification of the loss characteristics between the upper and lower layers, but also lays a data foundation for the subsequent formulation of protection strategies. By analyzing the upper and lower layer linkage factors, the severity of the loss at different levels can be clarified, providing managers with an intuitive understanding of the loss status of different areas of the reservoir, thereby helping to formulate more targeted management measures. The generation of soil and water conservation strategies for the upper and lower layer linkage factor result data forms a reservoir upper and lower layer protection strategy. The formulation of this strategy not only relies on scientific data analysis, but also combines a deep understanding of the loss characteristics to ensure the effectiveness and feasibility of the protection measures. By accurately identifying the loss problems of the upper and lower layers, managers can consider the characteristics of different levels when formulating strategies, thereby achieving overall coordination and optimization of soil and water loss prevention and control. Especially in the face of a complex natural environment, the strategy can more effectively deal with potential loss risks and improve the ecological safety of the reservoir. The reservoir upper and lower layer protection strategy is used to complete the reservoir information management operation. The implementation of this link makes the entire reservoir management system more complete and efficient, ensuring the smooth progress of information management operations. By combining protection strategies with actual management operations, the water and soil resources of the reservoir can be effectively maintained under scientific guidance, thereby promoting the sustainable use of water resources. In addition, the implementation of the strategy can provide timely feedback on the effects of loss management, further enrich data, and promote the optimization and adjustment of subsequent management measures, thus forming a dynamic management system.

[0047] Preferably, step S42 includes the following steps:

[0048] Step S421: Generate soil and water conservation strategies for the upper and lower layer linkage factor result data, and generate reservoir upper and lower layer protection strategies, wherein the reservoir upper and lower layer protection strategies include reservoir area upper layer protection strategies and reservoir area lower layer protection strategies;

[0049] Step S422: When the result data of the upper and lower layer linkage factor is a result of serious upper layer loss, the reservoir area upper layer protection strategy is applied to extract and analyze the reservoir area environmental characteristic value data to generate upper layer soil type data; based on the upper layer soil type data, the covering plants are screened to generate the reservoir area upper layer reinforcement plant type data, and an alarm message is sent, thereby completing the reservoir area upper layer protection strategy;

[0050] Step S423: When the result data of the upper and lower layer linkage factor is a serious result of lower layer infiltration, the reservoir area lower layer protection strategy is applied, and the lower layer loss rate data is used to screen deep water retaining materials to generate lower layer water retaining material data; artificial water replenishment path generation is performed based on the lower layer reservoir area high loss area data to generate lower layer high loss area water replenishment path data, and the lower layer water retaining material data and the lower layer high loss area water replenishment path data are sent as disaster protection information, thereby completing the reservoir area lower layer protection strategy.

[0051] The present invention generates a water and soil conservation strategy for the upper and lower layer linkage factor result data, and the formed upper and lower layer protection strategies of the reservoir are respectively aimed at the upper and lower layer loss problems, thereby realizing the comprehensive protection of the reservoir ecological environment. This two-level protection strategy not only improves the prevention and control capabilities of soil and water loss, but also can effectively cope with complex changes in natural conditions, laying the foundation for the sustainable management of the reservoir. When it is identified that the upper and lower layer linkage factor result data is a serious result of upper layer loss, the upper layer protection strategy of the reservoir area is immediately applied, and the upper layer soil type data is generated by extracting and analyzing the soil type of the environmental characteristic value data. The implementation of this process not only concretizes the soil characteristic data, but also provides a scientific basis for the subsequent screening of covering plants. Screening covering plants based on the generated upper layer soil type data can select the most suitable plant type for soil reinforcement, and this method effectively enhances the soil's anti-erosion ability. In addition, the mechanism of sending alarm information ensures that when the risk of loss increases, the relevant managers can respond in time and take corresponding measures, further improving the real-time and flexibility of the protection strategy. When the result data of the upper and lower layer linkage factor is a serious result of lower layer infiltration, the reservoir area lower layer protection strategy is applied to screen the deep water retaining materials based on the lower layer loss rate data to generate the lower layer water retaining material data. This process not only selects suitable water retaining materials based on data science, but also provides necessary data support for the subsequent generation of artificial water replenishment paths. By generating a water replenishment path based on the high loss area data, it ensures that the water resources in the reservoir area are effectively replenished and enhances the overall benefits of soil and water conservation. The lower layer water retaining material data and the water replenishment path data are sent for disaster protection information, forming a dynamic prevention and control mechanism for potential soil and water loss risks, ensuring comprehensive monitoring and protection of the reservoir.

[0052] In this specification, a reservoir water resources information management system based on intelligent data is provided, which is used to execute the above-mentioned reservoir water resources information management method based on intelligent data. The reservoir water resources information management system based on intelligent data:

[0053] Upper data collection and integration module: used to obtain reservoir surface area data set; perform data preprocessing on reservoir surface area data set to generate reservoir surface area preprocessing data set; perform discrete particle node processing on reservoir surface area preprocessing data set, and construct loss influencing factor database to generate upper loss influencing factor database; construct loss rate calculation model on upper loss influencing factor database to generate upper loss rate prediction model;

[0054] Lower groundwater monitoring and analysis module: used to obtain historical groundwater level data, real-time groundwater level data and surface permeability data; compare historical groundwater level data with real-time groundwater level data to generate groundwater level change data; combine groundwater level change data with surface permeability data to draw a spatial distribution map, mark high loss areas, and generate a lower reservoir area loss distribution map;

[0055] Upper and lower layer loss relationship analysis module: used to perform deep particle loss relationship analysis on the upper layer loss rate prediction model and the lower layer reservoir area loss distribution map, and generate upper and lower layer loss relationship result data; based on the lower layer reservoir area loss distribution map, the upper layer loss rate prediction model is linked to the model association process, and the upper and lower layer linkage model of the reservoir area is generated;

[0056] Soil and water conservation strategy generation module: used to generate soil and water conservation strategies for the upper and lower layer linkage model of the reservoir area based on the upper and lower layer loss relationship result data, generate reservoir upper and lower layer protection strategies, and thus complete the intelligent data reservoir information management operation.

[0057] The beneficial effect of the present invention is that by obtaining the reservoir surface area data set and performing discrete particle node processing, the upper layer loss influencing factor database generated provides a solid data foundation for the construction of the loss rate prediction model. This process ensures the comprehensive consideration of various factors affecting the surface loss of the reservoir, thereby improving the accuracy and reliability of the loss rate prediction. By comparing the historical and real-time groundwater level data, the groundwater level change data is generated, and the spatial distribution map is drawn in combination with the surface permeability, so as to clearly identify the high loss area. This method makes the monitoring and evaluation of the loss phenomenon more intuitive, which helps to formulate corresponding management measures in a timely manner. The deep particle analysis of the relationship between the upper and lower layer losses provides the correlation data between the loss rate and the reservoir management, so that the water loss situation at different levels can be comprehensively analyzed. Through the construction of the linkage model, the mutual influence of the upper and lower layer losses is quantified, which promotes the comprehensive management and optimization of water resources. Finally, the soil and water conservation strategy generated based on the result data of the upper and lower layer loss relationship can solve the problem of serious loss areas in a targeted manner, such as vegetation restoration and cover reinforcement in the upper layer loss area, and deep water retaining or groundwater recharge measures in the lower layer seepage loss area. Such a strategy not only improves the protection effect of water and soil resources, but also enhances the ecological stability of the reservoir. Therefore, the present invention solves the problems of information asymmetry and slow response in traditional water resource management by constructing an intelligent data reservoir information management system, and improves the scientificity and pertinence of reservoir water resource loss monitoring and protection measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 A schematic diagram of the steps of the reservoir water resources information management method based on intelligent data;

[0059] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0060] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0061] Figure 4 for Figure 1 Detailed implementation steps of step S4 in FIG.

[0062] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0063] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0064] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0065] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0066] To achieve this, please refer to Figures 1 to 4 , a reservoir water resources information management method based on intelligent data, the method comprising the following steps:

[0067] Step S1: obtaining a reservoir surface area data set; performing data preprocessing on the reservoir surface area data set to generate a reservoir surface area preprocessing data set; performing discrete particle node processing on the reservoir surface area preprocessing data set, and constructing a loss influencing factor database to generate an upper layer loss influencing factor database; constructing a loss rate calculation model for the upper layer loss influencing factor database to generate an upper layer loss rate prediction model;

[0068] Step S2: Obtain historical groundwater level data, real-time groundwater level data and surface permeability data; compare the historical groundwater level data with the real-time groundwater level data to generate groundwater level change data; combine the groundwater level change data with the surface permeability data to draw a spatial distribution map, mark high loss areas, and generate a lower reservoir area loss distribution map;

[0069] Step S3: Performing a deep particle loss relationship analysis on the upper layer loss rate prediction model and the lower layer reservoir area loss distribution map to generate upper and lower layer loss relationship result data; performing linkage model association processing on the upper layer loss rate prediction model based on the lower layer reservoir area loss distribution map to generate an upper and lower layer linkage model of the reservoir area;

[0070] Step S4: Generate a soil and water conservation strategy for the upper and lower layer linkage model of the reservoir area based on the upper and lower layer loss relationship result data, generate an upper and lower layer protection strategy for the reservoir, and thus complete the intelligent data reservoir information management operation.

[0071] The beneficial effect of the present invention is that by obtaining the reservoir surface area data set and performing discrete particle node processing, the upper layer loss influencing factor database generated provides a solid data foundation for the construction of the loss rate prediction model. This process ensures the comprehensive consideration of various factors affecting the surface loss of the reservoir, thereby improving the accuracy and reliability of the loss rate prediction. By comparing the historical and real-time groundwater level data, the groundwater level change data is generated, and the spatial distribution map is drawn in combination with the surface permeability, so as to clearly identify the high loss area. This method makes the monitoring and evaluation of the loss phenomenon more intuitive, which helps to formulate corresponding management measures in a timely manner. The deep particle analysis of the relationship between the upper and lower layer losses provides the correlation data between the loss rate and the reservoir management, so that the water loss situation at different levels can be comprehensively analyzed. Through the construction of the linkage model, the mutual influence of the upper and lower layer losses is quantified, which promotes the comprehensive management and optimization of water resources. Finally, the soil and water conservation strategy generated based on the result data of the upper and lower layer loss relationship can solve the problem of serious loss areas in a targeted manner, such as vegetation restoration and cover reinforcement in the upper layer loss area, and deep water retaining or groundwater recharge measures in the lower layer seepage loss area. Such a strategy not only improves the protection effect of water and soil resources, but also enhances the ecological stability of the reservoir. Therefore, the present invention solves the problems of information asymmetry and slow response in traditional water resource management by constructing an intelligent data reservoir information management system, and improves the scientificity and pertinence of reservoir water resource loss monitoring and protection measures.

[0072] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of the reservoir water resources information management method based on intelligent data of the present invention. In this example, the reservoir water resources information management method based on intelligent data includes the following steps:

[0073] Step S1: obtaining a reservoir surface area data set; performing data preprocessing on the reservoir surface area data set to generate a reservoir surface area preprocessing data set; performing discrete particle node processing on the reservoir surface area preprocessing data set, and constructing a loss influencing factor database to generate an upper layer loss influencing factor database; constructing a loss rate calculation model for the upper layer loss influencing factor database to generate an upper layer loss rate prediction model;

[0074] In the embodiment of the present invention, obtaining the reservoir surface area data set is the first step of the data processing process. This data set contains multi-dimensional information such as terrain, soil type, precipitation, vegetation cover and hydrological characteristics. The comprehensive analysis of this information is the basis of the loss influencing factors. In the subsequent data preprocessing stage, data processing techniques such as standardization, denoising and normalization are used to ensure the consistency and comparability of the data, thereby generating the reservoir surface area preprocessing data set. This process is crucial and provides reliable input data for subsequent analysis. Discrete particle node processing is performed on the reservoir surface area preprocessing data set. This step involves converting continuous geographic information into discrete particle nodes, which represent the characteristics of soil and water loss in a specific geographical location. Through methods such as spatial interpolation technology and cluster analysis, the spatial position of the particle nodes can be accurately determined so that it can better reflect the soil and water loss situation in the region. Subsequently, based on the characteristics of these particle nodes, a database of loss influencing factors is constructed, and key factors affecting soil and water loss, such as rainfall intensity, soil moisture, terrain slope, etc., are extracted through multi-factor analysis. The generation of this database provides a necessary variable basis for the calculation of the loss rate. Based on the upper loss influencing factor database, the loss rate calculation model is constructed, and a combination of statistical modeling and machine learning methods, such as regression analysis, random forest or neural network, is used to predict the loss rate in the reservoir area. By taking various influencing factors as input, the model can learn the influence of different factors on the loss rate, and then generate an upper loss rate prediction model.

[0075] Step S2: Obtain historical groundwater level data, real-time groundwater level data and surface permeability data; compare the historical groundwater level data with the real-time groundwater level data to generate groundwater level change data; combine the groundwater level change data with the surface permeability data to draw a spatial distribution map, mark high loss areas, and generate a lower reservoir area loss distribution map;

[0076] In the embodiment of the present invention, it is necessary to obtain historical groundwater level data, real-time groundwater level data and surface permeability data, which are collected by an automatic monitoring system and hydrological stations to ensure the timeliness and accuracy of the data. The historical groundwater level data provides a time series background for analysis, while the real-time groundwater level data reflects the current dynamic changes in the water level. The surface permeability data is an important indicator for evaluating soil erosion and groundwater recharge capacity. After the data is acquired, a comparative analysis of the historical groundwater level data and the real-time groundwater level data is performed, and time series analysis techniques such as the moving average method and the exponential smoothing method are used to extract the differences and change trends between the two. The groundwater level change data generated by this process can reflect the rise and fall of the groundwater level in different time periods, laying the foundation for subsequent loss analysis. The generated groundwater level change data is combined with the surface permeability data, and a spatial distribution map is drawn using a spatial analysis technique (such as a geographic information system GIS). In this process, the discrete monitoring point data is converted into a continuous spatial distribution map by an interpolation method (such as Kriging interpolation or inverse distance weighted interpolation), thereby generating a loss distribution map of the lower reservoir area. The spatial distribution map can not only visually display the spatial relationship between groundwater level changes and surface permeability, but also mark high loss areas through comparative analysis, which indicate that soil and water loss is serious and needs priority protection. The generated lower reservoir area loss distribution map provides an important basis for the implementation of soil and water conservation measures.

[0077] Step S3: Performing a deep particle loss relationship analysis on the upper layer loss rate prediction model and the lower layer reservoir area loss distribution map to generate upper and lower layer loss relationship result data; performing linkage model association processing on the upper layer loss rate prediction model based on the lower layer reservoir area loss distribution map to generate an upper and lower layer linkage model of the reservoir area;

[0078] In an embodiment of the present invention, a deep particle loss relationship analysis is performed on the upper layer loss rate prediction model and the lower layer reservoir area loss distribution map. This process involves the use of deep learning algorithms, especially a combination of particle swarm optimization (PSO) and convolutional neural network (CNN) to achieve feature extraction and association analysis in complex data sets. By comprehensively considering various loss factors (such as rainfall intensity, soil type and vegetation coverage) contained in the model, the algorithm can capture the potential relationship between the upper layer loss rate and the lower layer loss situation, and then generate upper and lower layer loss relationship result data. These result data not only include the change in the loss rate, but also reflect the spatial distribution characteristics of the influencing factors. Based on the lower layer reservoir area loss distribution map, the upper layer loss rate prediction model is subjected to linkage model association processing. The linkage model here uses algorithms such as multivariate linear regression or support vector machine (SVM) to associate key features (such as high loss areas and soil and water conservation conditions) in the lower layer loss distribution map with the upper layer loss rate. The purpose of this process is to explore the mutual influence and dynamic relationship between the two, so as to establish a more accurate upper and lower layer linkage model. The generation of linkage model relies on cross-validation and data fusion technology of multiple data sources, including but not limited to geographic information system (GIS), time series data analysis and multidimensional statistical analysis, to ensure that the model has good prediction ability and reliability. The generated upper and lower linkage model of reservoir area can not only provide a basis for future soil erosion prediction, but also provide scientific guidance for reservoir management and decision support system.

[0079] Step S4: Generate a soil and water conservation strategy for the upper and lower layer linkage model of the reservoir area based on the upper and lower layer loss relationship result data, generate an upper and lower layer protection strategy for the reservoir, and thus complete the intelligent data reservoir information management operation.

[0080] In the embodiment of the present invention, based on the result data of the relationship between the upper and lower layers, it is first necessary to conduct an in-depth analysis of the upper and lower layer linkage model of the reservoir area to generate an effective soil and water conservation strategy. This process relies on the comprehensive use of multiple data analysis technologies, including decision tree algorithms, random forest models, and deep learning models, etc., to achieve intelligent generation of soil and water conservation measures. By analyzing the relationship data between the upper and lower layers, serious loss areas and potential risk points can be identified, and visualized through spatial data analysis technology (such as geographic information system GIS) to more intuitively understand the dynamics of soil and water loss in the reservoir area. Based on the generated upper and lower layer linkage model, an optimization algorithm (such as genetic algorithm or particle swarm optimization) is used to explore the effects of different soil and water conservation strategies. This optimization process evaluates the potential of various strategies in reducing soil and water loss by simulating the implementation effects of different protection measures, such as vegetation restoration, soil reinforcement, and construction of water dams. By quantitatively analyzing the implementation effect of each strategy, specific suggestions for the upper and lower layer protection strategies of the reservoir are generated, including corresponding measures for upper layer soil loss and lower layer infiltration problems.

[0081] Preferably, step S1 comprises the following steps:

[0082] Step S11: obtaining a reservoir surface area data set; performing data preprocessing on the reservoir surface area data set to generate a reservoir surface area preprocessing data set;

[0083] Step S12: performing discrete particle node processing on the preprocessed data set of the reservoir surface area to generate upper discrete particles in the reservoir area; performing coefficient calculation and analysis on the upper discrete particles in the reservoir area, and constructing a loss influencing factor database to generate an upper loss influencing factor database;

[0084] Step S13: construct a churn rate calculation model based on the upper-level churn influencing factor database to generate an upper-level churn rate prediction model.

[0085] In the embodiment of the present invention, a reservoir surface area data set is obtained by means of sensors, remote sensing technology and field surveys, and these data include multi-dimensional information such as soil type, vegetation coverage, precipitation and human activities. Next, data preprocessing is performed to improve the accuracy and availability of the data. This step involves data cleaning, missing value filling and outlier processing. By applying statistical methods and data interpolation techniques, the integrity and consistency of the data set are ensured, thereby generating a reservoir surface area preprocessing data set. Discrete particle node processing is performed on the preprocessed data set to divide the reservoir area into several small units. This method helps to capture spatial heterogeneity and dynamic changes. Through spatial analysis techniques, such as Kriging interpolation or grid analysis, upper discrete particles in the reservoir area can be generated, and then the coefficients of environmental characteristics and loss potential of each particle are calculated and analyzed. This process uses regression analysis or machine learning methods to establish a loss influencing factor database, and generates an upper loss influencing factor database, which includes various factors that affect soil loss such as rainfall intensity, slope, soil type and vegetation coverage. The upper loss influencing factor database is applied to the construction of the loss rate calculation model. By using models such as multivariate linear regression, decision tree or random forest, multiple influencing factors are correlated with the churn rate to generate an upper-level churn rate prediction model.

[0086] Preferably, step S12 comprises the following steps:

[0087] Step S121: performing discrete particle node processing on the preprocessed data set of the reservoir surface area to generate discrete particles in the upper layer of the reservoir area;

[0088] Step S122: extracting spatial position feature values ​​of upper discrete particles in the reservoir area to generate spatial position feature value data of the reservoir area; extracting loss potential feature values ​​of upper discrete particles in the reservoir area to generate loss potential feature value data of the reservoir area; extracting environmental feature values ​​of upper discrete particles in the reservoir area to generate environmental feature value data of the reservoir area;

[0089] Step S123: Calculate and analyze the rainfall erosion coefficient of the reservoir area spatial position characteristic value data and the reservoir area environmental characteristic value data to generate the surface rainfall-erosion coefficient; Calculate and analyze the wind speed loss coefficient of the reservoir area spatial position characteristic value data and the reservoir area loss potential characteristic value data to generate the wind speed-loss coefficient; Calculate the slope soil coefficient of the reservoir area loss potential characteristic value data and the reservoir area environmental characteristic value data to generate the soil type-slope coefficient;

[0090] Step S124: constructing a database of loss influencing factors based on surface rainfall-erosion coefficient, wind speed-loss coefficient and soil type-slope coefficient to generate an upper layer loss influencing factor database.

[0091] In the embodiment of the present invention, the pre-processed data set of the surface area of ​​the reservoir is processed by discrete particle nodes to convert the data set into a spatially analyzable particle form. This discretization process uses spatial analysis technology to subdivide the entire area into multiple particle units, so that the subsequent analysis can be more accurate and capture the spatial heterogeneity of the reservoir area. For the generated upper discrete particles in the reservoir area, the spatial position characteristics of each particle, such as coordinates, adjacency, etc., are extracted by spatial position feature value extraction, and geometric and topological analysis methods are used. In addition, loss potential feature value extraction and environmental feature value extraction are also performed. These features are determined by multivariate statistical analysis or machine learning methods (such as principal component analysis) to determine the loss potential and environmental impact corresponding to each particle, and generate reservoir area loss potential feature value data and environmental feature value data, which provide basic data for subsequent loss coefficient calculation. Combined with the spatial position feature value data and environmental feature value data of the reservoir area, the rainfall erosion coefficient calculation and analysis are carried out. This process uses a regression model or environmental simulation software to calculate the soil erosion potential under rainfall conditions and generate a surface rainfall-erosion coefficient. Combining the spatial location characteristic value data and the loss potential characteristic value data, the influence of wind speed on soil loss is calculated to generate the wind speed-loss coefficient. In addition, by combining the loss potential characteristic value with the environmental characteristic value, the slope soil coefficient is calculated, the loss characteristics of different soil types under slope changes are extracted, and the soil type-slope coefficient is generated. The above three types of coefficients (rainfall-erosion coefficient, wind speed-loss coefficient, soil type-slope coefficient) are integrated to construct a database of loss influencing factors and generate a database of upper layer loss influencing factors.

[0092] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0093] Step S21: acquiring historical groundwater level data, real-time groundwater level data and surface permeability data; comparing the historical groundwater level data and the real-time groundwater level data to generate groundwater level change data;

[0094] Step S22: spatially process the surface permeability data to generate lower layer loss rate data; coordinate map the lower layer loss rate data to generate a lower layer groundwater infiltration distribution coordinate map;

[0095] Step S23: Draw a spatial distribution map of the groundwater level change data and the lower groundwater infiltration distribution coordinate map to generate a lower reservoir area loss distribution map.

[0096] In the embodiment of the present invention, data acquisition is to construct a comprehensive data set by integrating historical groundwater level data, real-time groundwater level data and surface permeability data. The historical groundwater level data provides a time series background for the study, while the real-time groundwater level data reflects the current state. The comparative analysis of the two can reveal the dynamic changes of the groundwater level, thereby generating groundwater level change data. This process uses statistical analysis tools to calculate the water level differences between different time points, and then evaluate the trend and amplitude of hydrological changes. The spatial processing of surface permeability data is a key step, involving spatial interpolation methods, such as Kriging or inverse distance weighted method, to convert discrete permeability data into a continuous spatial distribution model, thereby generating lower layer loss rate data. In addition, coordinate mapping of the lower layer loss rate data is to combine spatial data with actual geographic coordinates. This process relies on geographic information system (GIS) technology to display the data in a spatial coordinate system and generate a lower layer groundwater infiltration distribution coordinate map. The combination of groundwater level change data and the lower layer groundwater infiltration distribution coordinate map is visualized by drawing a spatial distribution map using GIS technology. This step uses spatial analysis tools, combined with relevant data sets, to perform overlay analysis and generate a distribution map of water loss in the lower reservoir area, which can clearly show the relationship between groundwater level changes and soil erosion.

[0097] Preferably, step S23 includes the following steps:

[0098] Step S231: Calculate the loss rate of the monitoring point according to the groundwater level change data and the surface permeability data to generate the loss rate data of the lower layer monitoring point;

[0099] Step S232: using GIS technology to upload the loss rate data of the lower monitoring points to the lower groundwater infiltration distribution coordinate map to draw a spatial infiltration distribution map, and generate a lower reservoir area loss distribution map;

[0100] Step S233: marking high loss areas on the loss distribution map of the lower reservoir area to generate high loss area data for the lower reservoir area.

[0101] In the embodiment of the present invention, it is key to calculate the loss rate of the monitoring point according to the groundwater level change data and the surface permeability data. The loss rate calculation formula is used to combine the groundwater level change of the monitoring point with the corresponding surface permeability to quantify the loss rate of each monitoring point. This process involves a variety of statistical methods and calculation models. By setting different loss thresholds, the loss rate data of the lower monitoring point is generated, thereby providing basic data for subsequent analysis. Using GIS technology to upload the loss rate data of the lower monitoring point to the lower groundwater infiltration distribution coordinate map and draw the spatial infiltration distribution map is one of the core links of the process. The GIS system can effectively process and display spatial data, and map the loss rate data to the corresponding geographical location through spatial analysis tools, thereby generating a loss distribution map of the lower reservoir area. This process includes spatial interpolation of data, generation of heat maps, and superposition of vector layers, ensuring that the generated loss distribution map is not only scientific, but also intuitively displays the spatial characteristics of soil erosion. Marking high loss areas on the loss distribution map of the lower reservoir area is an important link in the application of analysis results. By setting a threshold for the churn rate, spatial analysis technology is used to automatically identify and mark high churn areas. This process includes clustering analysis or classification algorithms based on distribution maps to form high churn area data.

[0102] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0103] Step S31: using factor analysis to analyze the relationship between the upper layer loss rate prediction model and the lower layer reservoir area loss distribution map, and generate upper and lower layer loss relationship result data;

[0104] Step S32: Based on the data of high loss areas in the lower reservoir area, the upper loss rate prediction model is used to identify the relationship between soil and water loss, and generate spatial characteristic data of different loss areas in the reservoir area;

[0105] Step S33: using different loss spatial characteristic data of the reservoir area and the loss distribution map of the lower reservoir area to perform a deep particle loss relationship analysis on the upper layer loss rate prediction model, and generate upper and lower layer loss relationship result data;

[0106] Step S34: Based on the loss distribution map of the lower reservoir area, the upper layer loss rate prediction model is subjected to linkage model association processing to generate an upper and lower layer linkage model of the reservoir area.

[0107] In the embodiment of the present invention, the factor analysis method is used to perform a deep particle loss relationship analysis on the upper layer loss rate prediction model and the lower layer reservoir area loss distribution map. This process requires the extraction of the main factors affecting soil and water loss from multiple variables by statistical methods. Factor analysis can effectively reduce the dimension of data, find out the potential factors affecting loss, and generate the upper and lower layer loss relationship result data, which provides a clear direction and basis for subsequent analysis. Based on the data of the high loss area in the lower reservoir area, the upper layer loss rate prediction model is used to identify the soil and water loss relationship. In this process, it is first necessary to accurately locate the high loss area, and then combine the characteristic data of these areas with the upper layer loss rate prediction model, and identify the relationship between the two through comparative analysis. The generated reservoir area different loss space characteristic data will provide a scientific basis for subsequent management measures and help identify areas with higher loss risks under specific conditions. The upper layer loss rate prediction model is again used to perform a deep particle loss relationship analysis using the different loss space characteristic data of the reservoir area and the lower layer reservoir area loss distribution map. This process is actually a further verification and deepening of the previous analysis results. By comparing and analyzing the influence of different spatial characteristics, the loss relationship between the upper and lower layers is confirmed again. The new round of upper and lower layer loss relationship result data generated further improved the model, making it more accurate and reliable in practical applications. The upper layer loss rate prediction model was linked to the linkage model based on the lower layer reservoir area loss distribution map. The key to this process is to use the spatial characteristics of the lower layer loss distribution to link the upper and lower layer models through the linkage mechanism, so that they can interact and feedback, thereby generating an upper and lower layer linkage model for the reservoir area.

[0108] As an example of the present invention, refer to Figure 4 As shown, in this example, step S4 includes:

[0109] Step S41: Based on the upper and lower layer loss relationship result data, the upper and lower layer linkage model of the reservoir area is evaluated for loss potential, and the upper and lower layer loss potential evaluation data of the reservoir area are generated; the upper and lower layer linkage factor results are generated for the upper and lower layer loss potential evaluation data of the reservoir area, and the upper and lower layer linkage factor result data are generated, wherein the upper and lower layer linkage factor result data includes the upper layer loss serious result and the lower layer infiltration serious result;

[0110] Step S42: generating soil and water conservation strategies for the upper and lower layer linkage factor result data, and generating upper and lower layer protection strategies for reservoirs;

[0111] Step S43: Using the upper and lower layer protection strategies of the reservoir to complete the reservoir information management operation.

[0112] In the embodiment of the present invention, environmental variables such as soil moisture, rainfall, wind speed, groundwater level, etc. in the reservoir area are obtained in real time through a variety of sensors and monitoring equipment. In the loss potential assessment stage, statistical analysis and machine learning algorithms are used to conduct in-depth analysis of the collected multidimensional data, and a prediction model of the upper and lower layer loss relationship is established using a decision tree or random forest method. This process aims to quantify the dynamic relationship between upper layer loss and lower layer infiltration, and generate upper and lower layer loss potential assessment data by calculation to identify loss risk areas. Once the loss potential assessment data is generated, the upper and lower layer linkage factors can be further extracted and generated. By analyzing the upper and lower layer loss relationship result data, the key factors affecting soil and water loss in the reservoir area are identified, and linkage factor result data including severe upper layer loss results and severe lower layer infiltration results are generated. In the strategy generation stage, by integrating the upper and lower layer linkage factor result data, the decision support system is used to formulate corresponding soil and water conservation measures. These measures include the selection of covering plants, soil improvement plans, rainwater management strategies, etc. Finally, relying on the generated reservoir upper and lower layer protection strategies, comprehensive management of reservoir information is achieved.

[0113] Preferably, step S42 includes the following steps:

[0114] Step S421: Generate soil and water conservation strategies for the upper and lower layer linkage factor result data, and generate reservoir upper and lower layer protection strategies, wherein the reservoir upper and lower layer protection strategies include reservoir area upper layer protection strategies and reservoir area lower layer protection strategies;

[0115] Step S422: When the result data of the upper and lower layer linkage factor is a result of serious upper layer loss, the reservoir area upper layer protection strategy is applied to extract and analyze the reservoir area environmental characteristic value data to generate upper layer soil type data; based on the upper layer soil type data, the covering plants are screened to generate the reservoir area upper layer reinforcement plant type data, and an alarm message is sent, thereby completing the reservoir area upper layer protection strategy;

[0116] Step S423: When the result data of the upper and lower layer linkage factor is a serious result of lower layer infiltration, the reservoir area lower layer protection strategy is applied, and the lower layer loss rate data is used to screen deep water retaining materials to generate lower layer water retaining material data; artificial water replenishment path generation is performed based on the lower layer reservoir area high loss area data to generate lower layer high loss area water replenishment path data, and the lower layer water retaining material data and the lower layer high loss area water replenishment path data are sent as disaster protection information, thereby completing the reservoir area lower layer protection strategy.

[0117] In the embodiment of the present invention, the upper and lower layer protection strategies of the reservoir are generated by comprehensive analysis of the result data of the upper and lower layer linkage factors. This process adopts multi-factor analysis and decision support system to ensure the scientific nature and pertinence of the protection strategy. The formulation of the upper and lower layer protection strategies of the reservoir area is based on the in-depth study of hydrological and meteorological data, soil characteristic data and historical loss conditions, so that the protection measures can effectively respond to the loss risks at different levels. When the result data of the upper and lower layer linkage factors indicate that the upper layer loss is serious, the upper layer protection strategy of the reservoir area is implemented. At this time, the soil type extraction and analysis of the environmental characteristic value data of the reservoir area is performed to generate the upper layer soil type data. This process mainly relies on geographic information system (GIS) technology and soil classification standards. Subsequently, based on the extracted soil type data, the covering plant screening is performed to generate the upper layer reinforcement plant type data of the reservoir area. This step combines ecological principles and plant physiological characteristics to select plants suitable for local environmental conditions and soil types for covering. At the same time, the system also has a real-time monitoring function, which can send alarm information in time to notify relevant management personnel to take necessary measures to ensure the implementation of the upper layer protection strategy. When the result data of the upper and lower layer linkage factors indicate that the lower layer seepage is serious, the reservoir area lower layer protection strategy is adopted. In this process, the deep water retaining material is screened by analyzing the lower layer loss rate data to generate the lower layer water retaining material data. This step uses materials science and engineering technology to select suitable water retaining materials to reduce soil erosion. In addition, based on the data of high loss areas in the lower reservoir area, artificial water replenishment paths are generated to ensure that high loss areas receive timely water resources replenishment. Finally, the lower layer water retaining material data and water replenishment path data are integrated, and disaster protection information is sent to form a closed-loop management.

[0118] In this specification, a reservoir water resources information management system based on intelligent data is provided, which is used to execute the above-mentioned reservoir water resources information management method based on intelligent data. The reservoir water resources information management system based on intelligent data:

[0119] Upper data collection and integration module: used to obtain reservoir surface area data set; perform data preprocessing on reservoir surface area data set to generate reservoir surface area preprocessing data set; perform discrete particle node processing on reservoir surface area preprocessing data set, and construct loss influencing factor database to generate upper loss influencing factor database; construct loss rate calculation model on upper loss influencing factor database to generate upper loss rate prediction model;

[0120] Lower groundwater monitoring and analysis module: used to obtain historical groundwater level data, real-time groundwater level data and surface permeability data; compare historical groundwater level data with real-time groundwater level data to generate groundwater level change data; combine groundwater level change data with surface permeability data to draw a spatial distribution map, mark high loss areas, and generate a lower reservoir area loss distribution map;

[0121] Upper and lower layer loss relationship analysis module: used to perform deep particle loss relationship analysis on the upper layer loss rate prediction model and the lower layer reservoir area loss distribution map, and generate upper and lower layer loss relationship result data; based on the lower layer reservoir area loss distribution map, the upper layer loss rate prediction model is linked to the model association process, and the upper and lower layer linkage model of the reservoir area is generated;

[0122] Soil and water conservation strategy generation module: used to generate soil and water conservation strategies for the upper and lower layer linkage model of the reservoir area based on the upper and lower layer loss relationship result data, generate reservoir upper and lower layer protection strategies, and thus complete the intelligent data reservoir water resources information management operation.

[0123] The beneficial effect of the present invention is that by obtaining the reservoir surface area data set and performing discrete particle node processing, the upper layer loss influencing factor database generated provides a solid data foundation for the construction of the loss rate prediction model. This process ensures the comprehensive consideration of various factors affecting the surface loss of the reservoir, thereby improving the accuracy and reliability of the loss rate prediction. By comparing the historical and real-time groundwater level data, the groundwater level change data is generated, and the spatial distribution map is drawn in combination with the surface permeability, so as to clearly identify the high loss area. This method makes the monitoring and evaluation of the loss phenomenon more intuitive, which helps to formulate corresponding management measures in a timely manner. The deep particle analysis of the relationship between the upper and lower layer losses provides the correlation data between the loss rate and the reservoir management, so that the water loss situation at different levels can be comprehensively analyzed. Through the construction of the linkage model, the mutual influence of the upper and lower layer losses is quantified, which promotes the comprehensive management and optimization of water resources. Finally, the soil and water conservation strategy generated based on the result data of the upper and lower layer loss relationship can solve the problem of serious loss areas in a targeted manner, such as vegetation restoration and cover reinforcement in the upper layer loss area, and deep water retaining or groundwater recharge measures in the lower layer seepage loss area. Such a strategy not only improves the protection effect of water and soil resources, but also enhances the ecological stability of the reservoir. Therefore, the present invention solves the problems of information asymmetry and slow response in traditional water resource management by constructing an intelligent data reservoir information management system, and improves the scientificity and pertinence of reservoir water resource loss monitoring and protection measures.

[0124] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0125] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A reservoir water resources information management method based on intelligent data, characterized in that: The following steps are involved: Step S1: obtaining a reservoir surface area data set; performing data preprocessing on the reservoir surface area data set to generate a reservoir surface area preprocessing data set; performing discrete particle node processing on the reservoir surface area preprocessing data set, and constructing a loss influencing factor database to generate an upper layer loss influencing factor database; The upper-level churn influencing factor database is used to construct a churn rate calculation model to generate an upper-level churn rate prediction model; Step S2: Obtain historical groundwater level data, real-time groundwater level data and surface permeability data; compare the historical groundwater level data with the real-time groundwater level data to generate groundwater level change data; combine the groundwater level change data with the surface permeability data to draw a spatial distribution map, mark high loss areas, and generate a lower reservoir area loss distribution map; Step S3: Performing a deep particle loss relationship analysis on the upper layer loss rate prediction model and the lower layer reservoir area loss distribution map to generate upper and lower layer loss relationship result data; performing linkage model association processing on the upper layer loss rate prediction model based on the lower layer reservoir area loss distribution map to generate an upper and lower layer linkage model of the reservoir area; Step S4: Generate a soil and water conservation strategy for the upper and lower layer linkage model of the reservoir area based on the upper and lower layer loss relationship result data, generate the upper and lower layer protection strategy of the reservoir, and thus complete the intelligent data reservoir water resources information management operation.

2. The reservoir water resources information management method based on intelligent data according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: obtaining a reservoir surface area data set; performing data preprocessing on the reservoir surface area data set to generate a reservoir surface area preprocessing data set; Step S12: performing discrete particle node processing on the preprocessed data set of the reservoir surface area to generate upper discrete particles in the reservoir area; performing coefficient calculation and analysis on the upper discrete particles in the reservoir area, and constructing a loss influencing factor database to generate an upper loss influencing factor database; Step S13: construct a churn rate calculation model based on the upper-level churn influencing factor database to generate an upper-level churn rate prediction model.

3. The reservoir water resources information management method based on intelligent data according to claim 2 is characterized in that: Step S12 includes the following steps: Step S121: performing discrete particle node processing on the preprocessed data set of the reservoir surface area to generate discrete particles in the upper layer of the reservoir area; Step S122: extracting spatial position feature values ​​of upper discrete particles in the reservoir area to generate spatial position feature value data of the reservoir area; extracting loss potential feature values ​​of upper discrete particles in the reservoir area to generate loss potential feature value data of the reservoir area; extracting environmental feature values ​​of upper discrete particles in the reservoir area to generate environmental feature value data of the reservoir area; Step S123: Calculate and analyze the rainfall erosion coefficient of the reservoir area spatial position characteristic value data and the reservoir area environmental characteristic value data to generate the surface rainfall-erosion coefficient; Calculate and analyze the wind speed loss coefficient of the reservoir area spatial position characteristic value data and the reservoir area loss potential characteristic value data to generate the wind speed-loss coefficient; Calculate the slope soil coefficient of the reservoir area loss potential characteristic value data and the reservoir area environmental characteristic value data to generate the soil type-slope coefficient; Step S124: constructing a database of loss influencing factors based on surface rainfall-erosion coefficient, wind speed-loss coefficient and soil type-slope coefficient to generate an upper layer loss influencing factor database.

4. The reservoir water resources information management method based on intelligent data according to claim 2 is characterized in that: Step S13 includes the following steps: Step S131: Divide the preset upper layer loss rate model into three layers to generate a three-layer model of reservoir area loss rate, wherein the three-layer model of reservoir area loss rate includes a first layer of reservoir area, a second layer of reservoir area and a third layer of reservoir area; Step S132: Calculate the impact of rainfall erosion on the first layer of the reservoir area by using the surface rainfall-erosion coefficient to generate the first layer of the reservoir area loss rate; Quantify the impact of wind erosion on the first layer of the reservoir area by using the surface rainfall-erosion coefficient to generate the second layer of the reservoir area loss rate; Calculate the soil slope adaptability on the third layer of the reservoir area by using the soil type-slope coefficient to generate the third layer of the reservoir area loss rate Step S133: assign multi-layer weight values ​​to the first layer of reservoir area loss rate, the second layer of reservoir area loss rate and the third layer of reservoir area loss rate, and reorganize the model to generate an upper layer loss rate prediction model.

5. The reservoir water resources information management method based on intelligent data according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: acquiring historical groundwater level data, real-time groundwater level data and surface permeability data; comparing the historical groundwater level data and the real-time groundwater level data to generate groundwater level change data; Step S22: spatially process the surface permeability data to generate lower layer loss rate data; coordinate map the lower layer loss rate data to generate a lower layer groundwater infiltration distribution coordinate map; Step S23: Draw a spatial distribution map of the groundwater level change data and the lower groundwater infiltration distribution coordinate map to generate a lower reservoir area loss distribution map.

6. The reservoir water resources information management method based on intelligent data according to claim 5 is characterized in that: Step S23 includes the following steps: Step S231: Calculate the loss rate of the monitoring point according to the groundwater level change data and the surface permeability data to generate the loss rate data of the lower layer monitoring point; Step S232: using GIS technology to upload the loss rate data of the lower monitoring points to the lower groundwater infiltration distribution coordinate map to draw a spatial infiltration distribution map, and generate a lower reservoir area loss distribution map; Step S233: marking high loss areas on the loss distribution map of the lower reservoir area to generate high loss area data for the lower reservoir area.

7. The reservoir water resources information management method based on intelligent data according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: using factor analysis to analyze the relationship between the upper layer loss rate prediction model and the lower layer reservoir area loss distribution map, and generate upper and lower layer loss relationship result data; Step S32: Based on the data of high loss areas in the lower reservoir area, the upper loss rate prediction model is used to identify the relationship between soil and water loss, and generate spatial characteristic data of different loss areas in the reservoir area; Step S33: using different loss spatial characteristic data of the reservoir area and the loss distribution map of the lower reservoir area to perform a deep particle loss relationship analysis on the upper layer loss rate prediction model, and generate upper and lower layer loss relationship result data; Step S34: Based on the loss distribution map of the lower reservoir area, the upper layer loss rate prediction model is subjected to linkage model association processing to generate an upper and lower layer linkage model of the reservoir area.

8. The reservoir water resources information management method based on intelligent data according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: Based on the upper and lower layer loss relationship result data, the upper and lower layer linkage model of the reservoir area is evaluated for loss potential, and the upper and lower layer loss potential evaluation data of the reservoir area are generated; the upper and lower layer linkage factor results are generated for the upper and lower layer loss potential evaluation data of the reservoir area, and the upper and lower layer linkage factor result data are generated, wherein the upper and lower layer linkage factor result data includes the upper layer loss serious result and the lower layer infiltration serious result; Step S42: generating soil and water conservation strategies for the upper and lower layer linkage factor result data, and generating upper and lower layer protection strategies for reservoirs; Step S42: Using the upper and lower layer protection strategies of the reservoir to complete the reservoir information management operation.

9. The reservoir water resources information management method based on intelligent data according to claim 8 is characterized in that: Step S42 includes the following steps: Step S421: Generate soil and water conservation strategies for the upper and lower layer linkage factor result data, and generate reservoir upper and lower layer protection strategies, wherein the reservoir upper and lower layer protection strategies include reservoir area upper layer protection strategies and reservoir area lower layer protection strategies; Step S422: When the result data of the upper and lower layer linkage factor is a result of serious upper layer loss, the reservoir area upper layer protection strategy is applied to extract and analyze the reservoir area environmental characteristic value data to generate upper layer soil type data; based on the upper layer soil type data, the covering plants are screened to generate the reservoir area upper layer reinforcement plant type data, and an alarm message is sent, thereby completing the reservoir area upper layer protection strategy; Step S423: When the result data of the upper and lower layer linkage factor is a serious result of lower layer infiltration, the reservoir area lower layer protection strategy is applied, and the lower layer loss rate data is used to screen deep water retaining materials to generate lower layer water retaining material data; artificial water replenishment path generation is performed based on the lower layer reservoir area high loss area data to generate lower layer high loss area water replenishment path data, and the lower layer water retaining material data and the lower layer high loss area water replenishment path data are sent as disaster protection information, thereby completing the reservoir area lower layer protection strategy.

10. A reservoir water resources information management system based on intelligent data, characterized in that: Used to execute the reservoir water resources information management method based on intelligent data as claimed in claim 1, the reservoir water resources information management system based on intelligent data comprises: Upper data collection and integration module: used to obtain reservoir surface area data set; perform data preprocessing on reservoir surface area data set to generate reservoir surface area preprocessing data set; perform discrete particle node processing on reservoir surface area preprocessing data set, and construct loss influencing factor database to generate upper loss influencing factor database; construct loss rate calculation model on upper loss influencing factor database to generate upper loss rate prediction model; Lower groundwater monitoring and analysis module: used to obtain historical groundwater level data, real-time groundwater level data and surface permeability data; compare historical groundwater level data with real-time groundwater level data to generate groundwater level change data; combine groundwater level change data with surface permeability data to draw a spatial distribution map, mark high loss areas, and generate a lower reservoir area loss distribution map; Upper and lower layer loss relationship analysis module: used to perform deep particle loss relationship analysis on the upper layer loss rate prediction model and the lower layer reservoir area loss distribution map, and generate upper and lower layer loss relationship result data; based on the lower layer reservoir area loss distribution map, the upper layer loss rate prediction model is linked to the model association process, and the upper and lower layer linkage model of the reservoir area is generated; Soil and water conservation strategy generation module: used to generate soil and water conservation strategies for the upper and lower layer linkage model of the reservoir area based on the upper and lower layer loss relationship result data, generate reservoir upper and lower layer protection strategies, and thus complete the intelligent data reservoir water resources information management operation.

Images