Method, system and electronic device for comprehensive field observation of precipitation, soil water and groundwater response

Abstract

The application discloses a kind of comprehensive field observation precipitation, soil water and groundwater response method, system and electronic equipment, including four steps of data monitoring and acquisition, hydrological response simulation, characteristic data selection and preprocessing, and hydrological response prediction.Deployment precipitation monitoring station, soil moisture sensor and groundwater level monitoring well, relevant data are monitored and acquired in real time.Using GIS and numerical simulation software to construct hydrological response model, simulate soil moisture content and groundwater level change under precipitation condition.Select key characteristic data and carry out pretreatment, input into the random forest hydrological prediction model that is established and trained in advance, output groundwater level change and soil moisture content prediction result in future period.Provide scientific basis for water resources management, flood control and disaster mitigation, help to develop scientific and reasonable decision-making scheme.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of hydrological monitoring and prediction. More specifically, the present application relates to a method, system and electronic device for comprehensive field observation of precipitation, soil water and groundwater response. BACKGROUND

[0002] Groundwater, as a key link in the terrestrial water cycle, plays a crucial role in maintaining ecological balance and supporting human social and economic activities. In particular, in arid and semi-arid regions, due to the scarcity of surface water resources, groundwater has become the main source of water supply for agricultural irrigation, industrial production and daily life of residents in these regions.

[0003] Effective management of groundwater resources and ensuring the sustainable use of water resources depend on a deep understanding of the complex interaction mechanisms between precipitation, soil water and groundwater. This process involves the dynamic process of precipitation penetrating into the soil layer through the surface and then replenishing groundwater, as well as the storage, migration and discharge of groundwater in the soil and aquifer. Accurate understanding of these interaction processes is of great significance for predicting changes in groundwater level, assessing water resources, and developing reasonable water resource allocation strategies.

[0004] Currently, groundwater research mainly relies on single observation methods such as meteorological monitoring, soil moisture measurement and groundwater level monitoring. These methods can reflect the status of their respective fields to some extent, but lack comprehensiveness and systematicness. For example, meteorological monitoring stations mainly record precipitation, but cannot directly reflect the impact of precipitation on soil water and groundwater; soil moisture sensors can measure soil water content, but it is difficult to accurately assess the soil water recharge to groundwater; groundwater level gauges are mainly used to monitor changes in groundwater level, and cannot directly reflect the comprehensive impact of precipitation and soil water on groundwater level.

[0005] In summary, the existing technology still lacks a comprehensive observation system that can simultaneously monitor precipitation, soil water and groundwater response. The lack of such a system seriously hinders the understanding of the interaction mechanisms of the groundwater system and its related elements, and also affects the effective management and rational use of groundwater resources. SUMMARY

[0006] An object of the present application is to solve at least the above problems and to provide at least the advantages to be described later.

[0007] To achieve these objects and other advantages in accordance with the present application, a method for comprehensive field observation of precipitation, soil water and groundwater response is provided, comprising the following steps:

[0008] S1, data monitoring and acquisition: real-time monitoring and acquisition of future precipitation data of precipitation events, and current soil water data and groundwater data, wherein the future precipitation data includes the occurrence time, precipitation intensity and duration of the precipitation event, the soil water data includes the current soil water content, and the groundwater data includes the current groundwater level;

[0009] S2, hydrological response simulation: inputting the acquired future precipitation data, current soil water data and groundwater data as input parameters into a pre-established hydrological response model to calculate and output simulation results, wherein the hydrological response model is constructed based on a numerical simulation method, and the simulation results include future changes in soil water content and groundwater level within a basin range under future precipitation conditions;

[0010] S3, feature data selection and preprocessing: selecting key feature data from the simulation results and future precipitation data, and performing preprocessing operations on the feature data;

[0011] S4, hydrological response prediction: inputting the preprocessed feature data into a pre-established and trained hydrological prediction model to output prediction results, wherein the hydrological prediction model is established and trained using a random forest method, and the prediction results include future changes in groundwater level and soil water content.

[0012] Preferably, the following steps are further included:

[0013] S5, early warning index selection and abnormal standard setting: selecting specific judgment indexes, calculating and setting abnormal standards corresponding to each judgment index based on real-time monitoring data, historical data, and output results of the hydrological response model and the hydrological prediction model;

[0014] S6, early warning triggering mechanism: comparing the prediction results with the set abnormal standards, and issuing an early warning signal when any index value in the prediction results exceeds its corresponding abnormal standard.

[0015] Preferably, the following steps are further included:

[0016] S7, power supply: using a solar power supply method to supply power to the data monitoring and acquisition device, and automatically adjusting the power consumption of the device according to the working state of the device, the data acquisition frequency, and the real-time energy status of the solar power supply system.

[0017] Preferably, the following steps are further included:

[0018] S8, equipment state monitoring: real-time monitoring of the working state, data transmission state and energy supply state of the equipment, triggering an abnormal notification mechanism when the equipment fails, data transmission is interrupted or abnormal, and using a cloud platform method to remotely access and maintain the equipment.

[0019] Preferably, the mathematical model of the hydrological response model is specifically constructed, including:

[0020] The process of converting precipitation into soil water is simulated and calculated by using the Richard equation, the process of converting soil water into groundwater is simulated and calculated by using the Darcy law, and the dynamic change of groundwater storage is simulated and calculated by using the groundwater storage change equation.

[0021] Newton iteration method is used as a coupling solution method, and the Richard equation, Darcy law and groundwater storage change equation are numerically coupled, and the true solution is gradually approached through iterative calculation, and finally the simulation result is obtained.

[0022] A system for comprehensive field observation of precipitation, soil water and groundwater response is provided, which is used to perform the method for comprehensive field observation of precipitation, soil water and groundwater response, and the system comprises:

[0023] A data monitoring and acquisition module is configured to monitor and acquire precipitation data of future precipitation events, and soil water data and groundwater data in the current state in real time, wherein the future precipitation data includes the occurrence time, precipitation intensity and duration of the precipitation event, the soil water data includes the current soil water content, and the groundwater data includes the current groundwater level.

[0024] A data processing and analysis module is configured to input the acquired future precipitation data, current soil water data and groundwater data as input parameters into a pre-established hydrological response model, and calculate and output simulation results, wherein the hydrological response model is constructed based on a numerical simulation method, and the simulation results include future changes in soil water content and groundwater level in the basin under future precipitation conditions.

[0025] and for filtering key feature data from the simulation results and future precipitation data, and performing preprocessing operations on the feature data;

[0026] and for inputting the preprocessed feature data into a pre-established and trained random forest hydrological prediction model, and outputting prediction results, wherein the random forest hydrological prediction model is established and trained by using a random forest method, and the prediction results include changes in groundwater level and soil water content in a future period of time.

[0027] Preferably, the system further comprises an intelligent early warning and decision support module, which is configured to select specific judgment indicators, calculate and set abnormal standards corresponding to each judgment indicator based on real-time monitoring data, historical data and output results of the hydrological response model and the random forest prediction model, and compare the prediction results with the set abnormal standards, and issue an early warning signal when any indicator value in the prediction results exceeds the corresponding abnormal standard.

[0028] and compare the prediction results with the set abnormal standards, and issue an early warning signal when any indicator value in the prediction results exceeds the corresponding abnormal standard.

[0029] Preferably, the system further comprises a power supply module, which is configured to use a solar power supply method to supply power to the data monitoring and acquisition equipment, and automatically adjust the power consumption of the equipment according to the working state of the equipment, the data acquisition frequency and the real-time energy condition of the solar power supply system.

[0030] Preferably, the system further comprises a system monitoring and maintenance module, which is configured to monitor the working state of the equipment, the data transmission condition and the energy supply condition in real time, trigger an abnormal notification mechanism when the equipment fails, data transmission is interrupted or abnormal, and remotely access and maintain the equipment abnormally using a cloud platform method.

[0031] An electronic device is provided, comprising:

[0032] one or more processors;

[0033] a memory; and

[0034] one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the programs comprise a method for comprehensive field observation of precipitation, soil water and groundwater response.

[0035] The present application at least includes the following beneficial effects:

[0036] First, by deploying precipitation monitoring stations, soil moisture sensors and groundwater level monitoring wells within the watershed, real-time monitoring and acquisition of soil water and groundwater data under current conditions and future precipitation events can be achieved, providing accurate and real-time basic data support for subsequent simulation and prediction.

[0037] Second, the hydrological response model constructed using GIS and numerical simulation software can reflect the interaction between precipitation, soil water and groundwater within the watershed, including precipitation infiltration, soil moisture movement, groundwater recharge and discharge, and other complex processes, thereby improving the reliability of the simulation results. By importing real-time monitoring data as input parameters into the hydrological response model, the changes in soil moisture content and groundwater level within the watershed under future precipitation conditions can be simulated and calculated, providing a scientific basis for water resources management and flood control and disaster reduction.

[0038] Third, key data that significantly impact prediction results are selected from simulation results and future precipitation data, such as precipitation intensity, precipitation duration, initial soil moisture content, and initial groundwater level. This improves the accuracy and efficiency of the random forest hydrological prediction model.

[0039] Fourth, the hydrological prediction model constructed and trained using the random forest method can learn the complex relationship between feature data and changes in groundwater level and soil moisture content. It possesses powerful predictive capabilities, accurately forecasting changes in groundwater level and soil moisture content over a future period. The prediction results contribute to the development of scientific and rational water resource management and flood control and disaster reduction decision-making plans, promoting the sustainable use of water resources and ecological protection.

[0040] Other advantages, objectives and features of the present invention will become apparent in part from the following description, and in part from those skilled in the art through study and practice of the invention. Attached Figure Description

[0041] Figure 1 This is a schematic flowchart of a comprehensive field observation method for precipitation, soil water, and groundwater response, as described in one of the technical solutions of the present invention.

[0042] Figure 2 This is a schematic diagram of the system framework for comprehensive field observation of precipitation, soil water and groundwater response, as described in one of the technical solutions of the present invention. Detailed Implementation

[0043] The present invention will now be described in further detail with reference to the accompanying drawings, so that those skilled in the art can implement it based on the description.

[0044] It should be noted that, unless otherwise specified, the experimental methods described in the following embodiments are all conventional methods, and the reagents and materials described are all commercially available unless otherwise specified. In the description of this invention, the orientation or positional relationship indicated by the terms is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing this invention and simplifying the description. It does not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this invention.

[0045] like Figure 1 As shown, this invention provides a comprehensive method for field observation of precipitation, soil water, and groundwater responses, comprising the following steps:

[0046] S1, data monitoring and acquisition: real-time monitoring and acquisition of future precipitation data of precipitation events, and current soil water data and groundwater data, wherein the future precipitation data includes the occurrence time, precipitation intensity and duration of the precipitation event, the soil water data includes the current soil water content, and the groundwater data includes the current groundwater level; specifically, in a watershed, a precipitation monitoring station, a soil moisture sensor and a groundwater level monitoring well are deployed. The precipitation monitoring station can monitor the occurrence time, precipitation intensity and duration of the precipitation event in real time; the soil moisture sensor is buried in a representative soil layer for monitoring the current soil water content; the groundwater level monitoring well is used to monitor the current groundwater level. These data can be transmitted in real time to the data center through wireless transmission for subsequent analysis. Real-time and accurate precipitation, soil water and groundwater data are obtained to provide basic data support for subsequent hydrological response simulation and prediction.

[0047] S2, hydrological response simulation: the future precipitation data, current soil water data and groundwater data obtained are input into a pre-established hydrological response model as input parameters, and the simulation result is calculated and output, wherein the hydrological response model is constructed based on a numerical simulation method, and the simulation result includes the future soil water content change and groundwater level change in the watershed under the future precipitation condition; specifically, a hydrological response model reflecting the interaction relationship among precipitation, soil water and groundwater in the watershed is constructed by using GIS (geographic information system) and numerical simulation software. The hydrological response model considers multiple processes such as precipitation infiltration, soil water movement, groundwater recharge and discharge, etc. The future precipitation data, current soil water data and groundwater data obtained in step S1 are input into the hydrological response model as input parameters for calculation and simulation. The simulation result includes the future soil water content change and groundwater level change in the watershed under the future precipitation condition. Through the numerical simulation method, the hydrological response in the watershed under the future precipitation condition is predicted to provide input data for the subsequent prediction model.

[0048] S3, feature data selection and preprocessing: key feature data is selected from the simulation result and future precipitation data, and the feature data is preprocessed; specifically, from the simulation result of step S2 and the future precipitation data, feature data that has an important influence on the prediction result is selected, such as precipitation intensity, precipitation duration, initial soil water content, initial groundwater level, etc. The feature data is preprocessed, including data cleaning (removing outliers and filling missing values), data normalization (converting data to the same order of magnitude), etc., to ensure data quality and consistency of model input. Through the selection and preprocessing of the feature data, the accuracy and efficiency of the random forest hydrological prediction model are improved, and the influence of redundant information on the prediction result is reduced.

[0049] S4, hydrological response prediction: input the pre-processed feature data into the pre-established and trained random forest hydrological prediction model, output the prediction results, wherein the hydrological prediction model is established and trained by random forest method, and the prediction results include the changes of groundwater level and soil moisture content in the future period. A hydrological prediction model is constructed and trained using the random forest method. The pre-processed feature data in step S3 is used as input to train the hydrological prediction model to learn the complex relationship between feature data and groundwater level change and soil moisture content. After training, input new feature data into the model to output prediction results, including changes in groundwater level and soil moisture content in the future period. Using the powerful prediction ability of the random forest model, the changes in groundwater level and soil moisture content in the future period are accurately predicted, providing scientific basis for water resources management, flood control and disaster reduction.

[0050] In the above technical solution, by combining real-time monitoring data and numerical simulation method, and the powerful prediction ability of random forest model, the changes of groundwater level and soil moisture content in the future period can be accurately predicted. It provides scientific basis for water resources management, flood control and disaster reduction, and helps to make scientific and reasonable decision-making scheme. Through real-time monitoring and prediction, problems in water resources management can be found and solved in time, promoting sustainable utilization of water resources and ecological protection.

[0051] In the above technical solution, the core task of hydrological response simulation is to use the pre-established hydrological response model to input real-time monitoring of future precipitation data, current soil water data and groundwater data as input parameters for calculation and simulation. This process is mainly based on numerical simulation method, aiming to reflect the interaction and dynamic change of precipitation, soil water and groundwater in the basin. The results of simulation usually include the changes of soil moisture content and groundwater level in the future under the condition of future precipitation in the basin. These results are calculated by the model, which provides quantitative description of future hydrological response.

[0052] The core task of feature data selection and preprocessing is to select the feature data that has important influence on the prediction results from the results of hydrological response simulation and future precipitation data, and to perform preprocessing operation on these data. This process aims to improve the accuracy and efficiency of the prediction model, and reduce the influence of redundant information on the prediction results. After selection and preprocessing, the feature data is used as input for the subsequent prediction model. These feature data usually include precipitation intensity, precipitation duration, initial soil moisture content, initial groundwater level and other key information.

[0053] In summary, steps S2 and S3 play different roles in the process of hydrological response prediction, and they cooperate with each other to provide accurate and efficient input data for the subsequent prediction model.

[0054] The core task of hydrological response prediction is to input the preprocessed feature data into the pre-established and trained random forest hydrological prediction model for calculation and prediction. The powerful prediction ability of the random forest model is used to accurately predict the changes of groundwater level and soil moisture content in the future period, providing scientific basis for water resources management, flood control and disaster reduction. Step S2 and step S4 cooperate and complement each other, and together constitute a complete hydrological response prediction system. Step S2 focuses on understanding the hydrological response mechanism in the basin through numerical simulation method, while step S4 focuses on accurate prediction by using random forest model, and provides scientific basis for water resources management, flood control and disaster reduction and other fields.

[0055] In another technical solution, the following steps are further included:

[0056] S5, early warning index selection and abnormal standard setting: selecting specific judgment indexes, calculating and setting the abnormal standards corresponding to each judgment index based on real-time monitoring data, historical data and the output results of the hydrological response model and the random forest prediction model; specifically, in the S5 step, the following judgment indexes can be selected: soil moisture content change rate, groundwater level rising rate, and precipitation intensity. Based on these indexes, first, collect real-time monitoring data (such as current soil moisture content, groundwater level, real-time precipitation intensity, etc.), and historical data (soil moisture content, groundwater level, precipitation intensity and their change trend under the same condition in the past period). At the same time, the soil moisture content change, groundwater level change and predicted precipitation intensity in the future period are calculated by using the hydrological response model in step S2 and the random forest prediction model in step S4. According to the historical data and the model output results, statistical methods (such as mean plus or minus standard deviation, percentile method, etc.) are used to set the abnormal standards for each judgment index. For example, for the soil moisture content change rate, when the change rate exceeds a certain percentile (such as 90% or 95% percentile) of the historical data, it is considered to reach the abnormal standard; for the groundwater level rising rate and the precipitation intensity, similar methods can also be used to set the abnormal standards. Step S5 selects appropriate judgment indexes and sets reasonable abnormal standards for each index based on real-time monitoring data, historical data and model output results. These abnormal standards will be used in the subsequent early warning triggering mechanism to determine whether the prediction result meets the early warning condition.

[0057] S6, early warning trigger mechanism: compare the prediction results with the set abnormal standards, when any index value in the prediction results exceeds its corresponding abnormal standard, send an early warning signal. Specifically, in step S6, the prediction results (soil moisture content change and groundwater level change in the future period) obtained in step S4 are compared with the abnormal standards set in step S5. Specifically, check the soil moisture content change rate, groundwater level rising rate and other indicators in the prediction results one by one, and judge whether they exceed their corresponding abnormal standards. Once any index value in the prediction results exceeds its corresponding abnormal standard, an early warning signal is immediately sent. This early warning signal can be a simple alarm prompt, or an early warning report containing detailed information (such as the over-standard index, over-standard degree, predicted impact, etc.). Step S6 compares the prediction results with the abnormal standards, identifies and sends early warning signals in time. When the prediction results show that hydrological anomalies (such as rapid change of soil moisture content, abnormal rise of groundwater level, etc.) may occur in the future, the early warning signal can remind relevant departments and personnel to take timely measures to reduce or avoid potential disaster impact.

[0058] In the above technical solution, by monitoring precipitation, soil water and groundwater data in real time, using hydrological response model and random forest prediction model for simulation and prediction, selecting specific judgment indexes and setting abnormal standards, a complete early warning trigger mechanism is finally established. This mechanism can monitor and predict hydrological anomalies in real time, and send early warning signals in time when the prediction results reach the early warning conditions, providing scientific basis and technical support for water resources management, flood control and disaster reduction and other fields.

[0059] In another technical solution, the following steps are further included:

[0060] S7, Power supply: using solar power supply method to power the data monitoring and acquisition equipment, and according to the working state of the equipment, the data acquisition frequency and the real-time energy condition of the solar power supply system, automatically adjusting the power consumption of the equipment. Specifically, in step S7, a solar panel is used as the main power source for the data monitoring and acquisition equipment. The solar panel is installed in a well-lit area near the equipment, and converts sunlight into electrical energy to provide continuous power supply for the equipment. At the same time, a smart power consumption management system is designed, which can automatically adjust the power consumption of the equipment according to the working state of the equipment (such as data acquisition, data transmission, standby, etc.), the data acquisition frequency and the real-time energy condition of the solar power supply system (such as battery capacity, solar panel output power, etc.). For example, when the equipment is in the data acquisition state, the smart power consumption management system will increase the power supply voltage and current of the equipment to ensure the accuracy and stability of data acquisition; when the equipment is in standby state, the smart power consumption management system will reduce the power supply voltage and current of the equipment to reduce unnecessary energy consumption. In addition, when the solar power supply system is low in power, the smart power consumption management system will automatically reduce the power consumption of the equipment or suspend non-critical functions to prolong the running time of the equipment. Step S7 can ensure that the data monitoring and acquisition equipment can run continuously and stably, and at the same time, make full use of renewable energy (solar energy) to power the equipment and reduce dependence on traditional energy. Through the smart power consumption management system to automatically adjust the power consumption of the equipment, it can further improve the energy utilization efficiency of the equipment, prolong the running time of the equipment and reduce the maintenance cost.

[0061] In another technical solution, the following steps are further included:

[0062] S8, device state monitoring: real-time monitoring of the working state, data transmission state and energy supply state of the device, triggering an abnormal notification mechanism when the device fails, data transmission is interrupted or abnormal, and using a cloud platform method to remotely access and maintain the device. Specifically, in step S8, a device state monitoring system is designed to monitor the working state, data transmission state and energy supply state of the device in real time. When the device fails, data transmission is interrupted or energy supply is abnormal, an abnormal notification mechanism is triggered immediately, and an abnormal notification is sent to relevant personnel through SMS, email or cloud platform. The cloud platform method is used to remotely access the device state monitoring system to realize remote monitoring and maintenance of the device. Through the cloud platform, the running state, historical data, abnormal records and other information of the device can be viewed in real time, and the device can be remotely configured, upgraded and fault checked. For example, when the device fails, the cloud platform will immediately display the fault information and prompt the relevant personnel to handle it. The relevant personnel can remotely access the device through the cloud platform to view detailed fault logs and diagnostic information, and then take appropriate measures to repair or maintain it. Step S8 can ensure the stability and reliability of data monitoring and acquisition equipment, and timely discover and handle device failures or data transmission abnormalities. Through the cloud platform method to remotely access the device state monitoring system, remote monitoring and maintenance of the device can be realized, the maintenance efficiency and reliability of the device can be improved, and the maintenance cost can be reduced.

[0063] In another technical scheme, the mathematical model of the hydrological response model is specifically constructed as follows:

[0064] The Richard equation is used to simulate and calculate the process of converting precipitation into soil water, the Darcy law is used to simulate and calculate the process of converting soil water into groundwater, and the groundwater storage change equation is used to simulate and calculate the dynamic change of groundwater storage.

[0065] The Newton iteration method is used as a coupling solution method to numerically couple the Richard equation, the Darcy law and the groundwater storage change equation, and the true solution is gradually approached through iterative calculation, and finally the simulation result is obtained.

[0066] In the above technical solution, in the first step, the Richard equation is used to simulate and calculate the process of precipitation transforming into soil water. Specifically, the soil types, precipitation data, initial soil water content, and other parameters in the watershed area are collected. Then, these parameters are substituted into the Richard equation, and the numerical solution method (such as finite difference method) is used to simulate the precipitation infiltration process, and the distribution of soil water content with time is obtained. The Richard equation is a basic equation for describing the movement of water in unsaturated soil, which can reflect the influence of precipitation infiltration, soil evaporation, and plant transpiration on soil water. By simulating the process of precipitation transforming into soil water, the dynamic changes of soil water can be understood, and scientific basis can be provided for agricultural irrigation, drainage, and soil management. The Richard equation is as follows:

[0067]

[0068] where: θ is the soil water content (m 3 / m 3 ); h is the soil water head (m); K(θ) is the soil hydraulic conductivity (dependent on water content θ); S is the source term (such as precipitation, evaporation, etc.).

[0069] In the second step, Darcy's law is used to simulate and calculate the process of soil water transforming into groundwater. Specifically, based on the first step, Darcy's law is used to describe the flow process of soil water through the soil bottom to the aquifer. By collecting the hydraulic conductivity of the soil bottom, soil water pressure, and other parameters, substituting them into Darcy's law for numerical solution, the rate and amount of soil water transforming into groundwater can be obtained. Darcy's law is a basic law for describing the flow of fluid in porous media, which is used to describe the transformation process of soil water to groundwater. By simulating this process, the recharge of groundwater resources can be understood, and data support can be provided for groundwater resource management and protection. Darcy's Law is as follows:

[0070]

[0071] where: q is the groundwater flow (m 3 / s); K(θ) is the groundwater permeability coefficient, which is equivalent to the soil hydraulic conductivity; is the gradient of groundwater head.

[0072] Third step, the change equation of groundwater storage is used to simulate and calculate the dynamic change of groundwater storage. Based on the second step, the change equation of groundwater storage is used to describe the change of groundwater storage. By collecting the parameters of groundwater recharge, exploitation, and aquifer storage capacity, the change equation of groundwater storage is substituted into the numerical solution to obtain the dynamic change of groundwater storage. The change equation of groundwater storage can reflect the dynamic balance state of the groundwater system, including the influence of recharge, exploitation, and storage capacity on groundwater storage. By simulating the dynamic change of groundwater storage, the sustainable utilization of groundwater resources can be understood, and the decision basis for the rational development and protection of groundwater resources is provided. The change equation of groundwater storage is as follows:

[0073]

[0074] Where: R is the recharge source term of groundwater (e.g., precipitation, seepage of upper soil water, etc.).

[0075] Fourth step, coupling solution and iterative calculation. Based on the above three steps, Newton iteration method is used as the coupling solution method to numerically couple Richard equation, Darcy's law, and the change equation of groundwater storage. Through iterative calculation, the real solution is gradually approached, and the simulation result is finally obtained. In the specific implementation process, reasonable iteration step and convergence condition are set to ensure the accuracy and stability of the iterative calculation. The boundary conditions are set, including the flow rate, water level, precipitation, evaporation, and other external input conditions of the watershed boundary. The initial conditions are set, including the initial soil water content, groundwater level, soil humidity, and other state variables at the initial time. The purpose of coupling solution and iterative calculation is to integrate multiple mathematical models into a unified framework for solving, to reflect the overall dynamic change process of the precipitation-soil water-groundwater system. Through coupling solution and iterative calculation, more accurate and reliable simulation results can be obtained, providing more scientific basis for water resources management and protection.

[0076] In the above technical solution, by using Richard equation, Darcy's law, and the change equation of groundwater storage, and combining Newton iteration method as the coupling solution method, the simulation and calculation of the transformation of precipitation into soil water, soil water into groundwater, and the dynamic change of groundwater storage are realized. It can fully reflect the dynamic change process of the precipitation-soil water-groundwater system, and provide scientific basis for water resources management and protection. Through simulation and calculation, the dynamic change of soil moisture, the recharge and storage change of groundwater resources, and other information can be understood, providing decision support for agricultural irrigation, drainage, soil management, groundwater resource development and protection, etc.

[0077] As Figure 2As shown, based on the same inventive concept, the present application also provides a system for comprehensive field observation of precipitation, soil water and groundwater response, which is used to perform the method for comprehensive field observation of precipitation, soil water and groundwater response, and the system comprises:

[0078] A data monitoring and acquisition module is configured to monitor and acquire precipitation data of a future precipitation event, soil water data and groundwater data in a current state in real time, wherein the precipitation data of the future precipitation event includes occurrence time, precipitation intensity and duration of the precipitation event, the soil water data includes current soil water content, and the groundwater data includes current groundwater level; the data monitoring and acquisition module includes a sensor module and a data acquisition and transmission module, and the data acquisition and transmission module mainly includes a data acquisition unit, a wireless data transmission unit and a data storage and backup unit. Specifically, the data monitoring and acquisition module is configured to monitor in real time by using a high-precision sensor network. The sensor network includes a precipitation sensor, a soil moisture sensor and a groundwater level sensor. The precipitation sensor is installed at a high point of an observation area and can accurately measure the occurrence time, precipitation intensity and duration of the precipitation event. For example, the precipitation sensor mainly includes a high-precision rain gauge (such as a Tipping Bucket rain gauge, an optical rain gauge sensor and a rain gauge cylinder) and a transmission line, wherein the rain gauge can accurately record the occurrence time, intensity and duration of the precipitation event and transmit the information to the data acquisition and transmission module through the transmission line, thereby realizing real-time monitoring of precipitation and precipitation intensity. The soil moisture sensor is uniformly distributed in the soil layer of the observation area to monitor and acquire soil water content at different depths in real time. For example, the soil moisture sensor mainly includes a transmission line, a soil moisture sensor body and a soil air zone, wherein one soil moisture sensor is arranged in the soil air zone every 10-20 cm until the phreatic surface, and the soil moisture sensor transmits soil moisture content information of different soil types, different wet conditions and different soil depths to the data acquisition and transmission module through the transmission line, thereby realizing real-time dynamic monitoring of soil moisture variation in the air zone. The groundwater level sensor is installed in a groundwater well to monitor the change of the groundwater level in real time. For example, the groundwater level and water temperature sensor mainly includes a transmission line, a groundwater monitoring well, a well cover and a groundwater level and water temperature sensor, the groundwater level and water temperature sensor is vertically placed in the groundwater monitoring well until the phreatic surface, a well cover with a screw hole is installed at the well mouth of the groundwater monitoring well, one end of the transmission line is connected to the groundwater level and water temperature sensor, and the other end is connected to the data acquisition and transmission module through the screw hole of the well cover, and the groundwater level information is transmitted to the data acquisition and transmission module in real time through the transmission line. Thus, the fluctuation of the groundwater level can be continuously monitored to help analyze the influence of precipitation on groundwater recharge.For example, the data acquisition and transmission module (responsible for collecting, storing and transmitting the data collected by the sensor, its main feature is that it can run independently with self-powered supply without external power supply, ensuring long-term stable data transmission) includes a data acquisition unit, a wireless data transmission unit, a data storage and backup unit, the data acquisition unit integrates a multi-channel data acquisition system, supports high-frequency sampling, and can collect data from different sensors in real time; The wireless data transmission unit uses advanced wireless communication technology (such as 4G / 5G, LoRa, NB-IoT, Wi-Fi, etc.), to ensure that even in remote areas and without network conditions, monitoring data can still be efficiently transmitted; The data storage and backup unit has local storage function, can temporarily store data in case of network disconnection, and automatically upload after network recovery, to ensure the integrity of the data. The purpose of the data monitoring and acquisition module is to obtain real-time and accurate data related to future precipitation events and current soil water and groundwater data. These data are the basis for subsequent data processing and analysis, and are also important input parameters for building hydrological response models and random forest hydrological prediction models.

[0079] The data processing and analysis module is used to input the obtained future precipitation data, current soil water data and groundwater data as input parameters into the pre-established hydrological response model, calculate the output to obtain simulation results, wherein the hydrological response model is constructed based on numerical simulation method, and the simulation results include future soil water content change and groundwater level change within the basin range under future precipitation conditions; Specifically, the data processing and analysis module receives data from the data monitoring and acquisition module, and performs data cleaning and verification to ensure the accuracy and integrity of the data. Then, the cleaned data is imported into the pre-established hydrological response model. The hydrological response model is constructed based on numerical simulation method, which can simulate the influence of precipitation events on soil water content and groundwater level. Through model calculation, the future soil water content change and groundwater level change within the basin range under future precipitation conditions are output.

[0080] And for screening key feature data from simulation results and future precipitation data, and performing preprocessing operation on the feature data; Specifically, the data processing and analysis module is also responsible for screening key feature data such as precipitation intensity, precipitation duration, soil water content change rate, groundwater level change rate, etc. from simulation results and future precipitation data. Preprocessing operations are performed on these feature data, such as normalization, standardization, etc., so as to be subsequently input into the random forest hydrological prediction model. The data processing and analysis module converts the real-time monitored data into useful information, simulates the future soil water content change and groundwater level change through the hydrological response model, and screens out key feature data for subsequent prediction analysis.

[0081] and input the preprocessed feature data into a pre-established and trained random forest hydrological prediction model to output a prediction result, wherein the random forest hydrological prediction model is established and trained by using the random forest method, and the prediction result includes the change of groundwater level and soil moisture content in a future period of time. Specifically, the random forest hydrological prediction model is established and trained by using the random forest method. In the model training stage, historical precipitation data, soil water data and groundwater data are used as the training set, and the model parameters are optimized through multiple iterations and cross-validation. After training, the preprocessed feature data is input into the model to output the prediction result. The prediction result includes the change of groundwater level and soil moisture content in a future period of time. The purpose of the random forest hydrological prediction model is to predict the future change of groundwater level and soil moisture content by using historical data and key feature data. By using the random forest method, the model can automatically learn the rules and patterns in the data, improving the accuracy and robustness of the prediction.

[0082] In the above technical solution, the data monitoring and acquisition module is responsible for real-time monitoring and acquiring relevant data; the data processing and analysis module is responsible for data cleaning, verification, simulation and feature selection; and the random forest hydrological prediction model is responsible for prediction analysis using feature data. Real-time monitoring and prediction analysis of precipitation, soil water and groundwater can be achieved, providing a scientific basis for water resource management and environmental protection. Through real-time monitoring data, changes in hydrological conditions can be understood in a timely manner; through the hydrological response model and the random forest hydrological prediction model, future trends of hydrological changes can be predicted to provide support for decision-making. In addition, it has the advantages of high precision, real-time performance and scalability, and can be widely applied to different regions and different types of water resource management practices.

[0083] In another technical solution, an intelligent early warning and decision support module is also included, which is used to select specific judgment indicators, calculate and set the abnormal standards corresponding to each judgment indicator based on real-time monitoring data, historical data, and the output results of the hydrological response model and the random forest prediction model, and compare the prediction results with the set abnormal standards, and issue a warning signal when any index value in the prediction results exceeds the corresponding abnormal standard. Specifically, the intelligent early warning and decision support module mainly includes an early warning system unit and a decision support unit. Specifically, the intelligent early warning and decision support module selects specific judgment indicators according to actual needs. These indicators can include the rate of change of soil moisture content, the amplitude of groundwater level rise and fall, the combined effect of precipitation intensity and duration, etc. Based on real-time monitoring data, historical data, and the output results of the hydrological response model and the random forest prediction model, the module calculates and sets the abnormal standards corresponding to each judgment indicator through statistical analysis and other methods. The setting of abnormal standards is a dynamic adjustment process, which can be fine-tuned according to factors such as seasonal changes, geographical location, soil type, and groundwater conditions. For example, in the dry season, the rate of decline of soil moisture content can be considered as an important indicator of abnormality; while in the rainy season, more attention can be paid to the combined effect of precipitation intensity and duration on groundwater level. Once the abnormal standards are set, the intelligent early warning and decision support module compares the output results of the random forest prediction model with these standards. If any index value in the prediction results exceeds the corresponding abnormal standard, the module will immediately issue a warning signal and notify relevant personnel through SMS, email, APP push, etc. It also has decision support function. When the warning signal is issued, the module will provide targeted suggestions or measures for relevant personnel according to the pre-set emergency plan or decision tree to cope with the impending hydrological abnormal event. The intelligent early warning and decision support module, through real-time monitoring data and prediction results, issues a warning signal in a timely manner before or when a hydrological abnormal event occurs, provides decision support for relevant personnel, and reduces the impact of hydrological abnormal events on human society and the natural environment.

[0084] Specifically, as preferred, based on the judgment index anomaly standard of hydrological analysis and prediction results, precipitation, soil moisture content and groundwater level are selected as the main judgment index. Based on real-time data and historical trends, the abnormal standard is dynamically calculated. According to the change rate of precipitation, the fluctuation rate of soil moisture content and other dynamic setting judgment standards, the prediction results of the model are compared with the measured data, and the deviation exceeds a certain standard, which is judged as abnormal. For example, if the predicted flow rate deviates from the actual flow rate by more than 20%, it is considered that the prediction of the model is abnormal. Analyze the trend change of hydrological indicators (such as soil moisture content, precipitation, etc.), if the trend changes suddenly, it may mean the occurrence of extreme hydrological events. Early warning and response: once the hydrological index is abnormal, the system should trigger the early warning and report to the decision maker. The early warning content includes: flood, drought, etc. The duration and range of prediction (the time period and the range of influence that the abnormal event may last), the response measure suggestion (based on the model and historical data, the possible response measures are suggested, such as evacuation, water reduction, reservoir regulation, etc.), multi-level response (according to the severity of the abnormality, different levels of response measures can be set. For example, slight abnormality may only need to issue a reminder, while more serious abnormality may need to start the emergency plan).

[0085] In another technical solution, a power supply module is also included, which is used to power the data monitoring and acquisition device by using a solar power supply method, and automatically adjusts the power consumption of the device according to the working state of the device, the data acquisition frequency and the real-time energy condition of the solar power supply system. Specifically, the power supply module mainly includes a solar power supply unit and an energy efficiency optimization unit. Specifically, the power supply module uses a solar panel as the main energy source, cooperates with a high-efficiency battery pack, and provides stable and reliable power supply for the data monitoring and acquisition device. The solar panel is installed at the best light position of the observation point to ensure that it can capture sunlight and convert it into electric energy to the maximum extent. At the same time, the energy efficiency optimization unit is built-in with an intelligent power management system, which can automatically adjust the power consumption of the device according to the working state of the device, the data acquisition frequency and the real-time energy condition of the solar power supply system. For example, during the day when the sunlight is sufficient, the solar panel generates sufficient electric energy, and the intelligent power management system will increase the operating power of the device to collect data at a higher frequency; while at night or on rainy days, the solar power supply capacity is weakened, and the intelligent power management system will automatically reduce the power consumption of the device and reduce the data acquisition frequency to prolong the endurance time of the battery. The power supply module provides continuous and stable power supply for the data monitoring and acquisition device, and automatically adjusts the power consumption according to the environmental conditions and device requirements to ensure the long-term stable operation of the device and the continuity of data acquisition.

[0086] In another technical solution, the system monitoring and maintenance module is further configured to monitor the working state of the device, the data transmission state, and the energy supply state in real time, trigger an abnormal notification mechanism when the device fails, data transmission is interrupted, or an abnormality occurs, and remotely access and maintain the device abnormally by using a cloud platform method. Specifically, the system monitoring and maintenance module mainly includes a system state monitoring unit and a remote maintenance unit. Specifically, the system monitoring and maintenance module realizes real-time monitoring of the working state of the device, the data transmission state, and the energy supply state by integrating Internet of Things technology and cloud platform technology. The system monitoring and maintenance module collects various operating parameters of the device through sensors and communication modules, including but not limited to device temperature, humidity, power voltage, current, and the like, and indexes such as data transmission integrity, delay, and packet loss rate. When the device fails, data transmission is interrupted, or an abnormality occurs, the system monitoring and maintenance module will immediately trigger an abnormal notification mechanism, and notify relevant personnel through short message, email, APP push, and the like. In addition, the system monitoring and maintenance module has a remote access function, and by using a cloud platform method, the real-time state of the device can be viewed at any time and anywhere, and fault diagnosis and abnormal maintenance can be performed. For example, when an abnormality or power failure of a sensor is detected, an alarm information is automatically generated and sent to the mobile phone of the designated maintenance personnel. The maintenance personnel can log in to the cloud platform through a mobile phone APP or a computer browser to view the detailed state and alarm record of the device, and then perform remote debugging or dispatch on-site maintenance personnel according to the actual situation. The system monitoring and maintenance module can ensure the stable operation of the data monitoring and acquisition system and the reliability of data transmission, timely discover and handle device faults and data abnormalities, and improve the availability and maintenance efficiency of the system.

[0087] The division of the modules in the embodiments of the present application is illustrative, and is only a logical function division. In actual implementation, another division manner can be used. In addition, each function module in each embodiment of the present application can be integrated in one processor, or can be physically separated, or two or more modules can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of a software function module.

[0088] Based on the same inventive concept, the present application further provides an electronic device, comprising:

[0089] one or more processors;

[0090] a memory; and

[0091] One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs comprising a method for performing the comprehensive field observation of precipitation, soil water and groundwater response. Specifically, the electronic device can be any one of a smartphone, a notebook computer, a desktop computer, a tablet computer or a vehicle-mounted computer, etc. These electronic devices are all equipped with one or more high-performance processors for performing complex computing tasks, and a large-capacity memory for storing operating systems, application programs and user data. In this embodiment, a smartphone is taken as an example for detailed description. The smartphone is built-in with a special application program, which is designed to perform the comprehensive field observation of precipitation, soil water and groundwater response. The program is pre-installed in the memory of the smartphone, or downloaded and installed by the user through the application store. When the user starts the program, it will use the sensors of the smartphone (such as GPS locator, accelerometer, etc., although these sensors may not be directly involved in hydrological observation, but can be used for auxiliary positioning and data recording) and wireless communication modules (such as 4G / 5G, Wi-Fi, etc.) to communicate with the hydrological monitoring equipment deployed in the field. The program can receive and process data from these devices, including precipitation, soil moisture, groundwater level, etc. information. Then, the program will use the built-in algorithm to process and analyze these data to generate real-time hydrological condition report and prediction results. In addition, the program also supports uploading the processed data to the cloud server for higher-level data analysis and long-term storage. Users can access the data and analysis results on the cloud server through the browser or special application of the smartphone, realizing remote monitoring and management. The purpose of this embodiment is to provide a convenient and efficient electronic device for performing the comprehensive field observation of precipitation, soil water and groundwater response. By integrating these complex hydrological observation and analysis tasks into terminal devices such as smartphones, users can access and process hydrological data anytime and anywhere, thereby improving the efficiency and accuracy of water resource management.

[0092] Although the embodiments of the present application have been disclosed as above, they are not limited to the applications listed in the specification and embodiments, and can be fully applied to various fields suitable for the present application, and additional modifications can be easily made by those skilled in the art, and therefore the present application is not limited to specific details and the figures shown and described herein, without departing from the general concept defined by the claims and equivalent scope.

Claims

1. A comprehensive method for field observation of precipitation, soil water, and groundwater responses, characterized in that, Includes the following steps: S1. Data monitoring and acquisition: Real-time monitoring and acquisition of precipitation data for future precipitation events, as well as current soil water and groundwater data. The future precipitation data includes the occurrence time, intensity, and duration of the precipitation event; the soil water data includes the current soil moisture content; and the groundwater data includes the current groundwater level. S2. Hydrological Response Simulation: The acquired future precipitation data, current soil water data, and groundwater data are used as input parameters and imported into a pre-established hydrological response model. The simulation results are calculated and output. The hydrological response model is constructed based on numerical simulation methods. The simulation results include changes in soil moisture content and groundwater level within the watershed under future precipitation conditions. S3. Feature Data Selection and Preprocessing: Select key feature data from simulation results and future precipitation data, and perform preprocessing operations on the feature data; S4. Hydrological Response Prediction: The preprocessed feature data is input into the pre-established and trained hydrological prediction model, and the prediction results are output. The hydrological prediction model is established and trained using the random forest method. The prediction results include changes in groundwater level and soil moisture content over a future period. The mathematical model of the hydrological response model is specifically constructed as follows: Richard's equation was used to simulate and calculate the process of precipitation transforming into soil water, Darcy's law was used to simulate and calculate the process of soil water transforming into groundwater, and the groundwater storage change equation was used to simulate and calculate the dynamic changes in groundwater storage. The Newton-Raphson iteration method is used as a coupled solution method. The Richard equation, Darcy's law and the groundwater storage change equation are numerically coupled. The simulation results are obtained by gradually approximating the true solution through iterative calculation.

2. The method for comprehensive field observation of precipitation, soil water, and groundwater response as described in claim 1, characterized in that, It also includes the following steps: S5. Selection of early warning indicators and setting of abnormal standards: Select specific judgment indicators, and calculate and set the abnormal standards corresponding to each judgment indicator based on real-time monitoring data, historical data, and the output results of the hydrological response model and the hydrological prediction model. S6. Early warning triggering mechanism: The prediction results are compared with the set abnormality standards. When any indicator value in the prediction results exceeds its corresponding abnormality standard, an early warning signal is issued.

3. The method for comprehensive field observation of precipitation, soil water, and groundwater response as described in claim 1, characterized in that, It also includes the following steps: S7. Power Supply: The device is powered by solar energy, and its power consumption is automatically adjusted according to the device's operating status, data acquisition frequency, and the real-time energy status of the solar power system.

4. The method for comprehensive field observation of precipitation, soil water, and groundwater response as described in claim 3, characterized in that, It also includes the following steps: S8. Equipment Status Monitoring: Real-time monitoring of equipment operating status, data transmission status, and energy supply status. When equipment malfunctions, data transmission is interrupted, or abnormalities occur, an abnormal notification mechanism is triggered. Additionally, remote access and maintenance of equipment abnormalities can be performed using a cloud platform.

5. A comprehensive system for field observation of precipitation, soil water, and groundwater responses, characterized in that: The system is used to perform the method according to any one of claims 1 to 4, the system comprising: The data monitoring and acquisition module is used to monitor and acquire precipitation data of future precipitation events in real time, as well as soil water data and groundwater data under the current conditions. The future precipitation data includes the occurrence time, precipitation intensity and duration of the precipitation event, the soil water data includes the current soil moisture content, and the groundwater data includes the current groundwater level. The data processing and analysis module is used to take the acquired future precipitation data, current soil water data and groundwater data as input parameters, import them into a pre-established hydrological response model, calculate and output simulation results, wherein the hydrological response model is constructed based on numerical simulation methods, and the simulation results include future changes in soil moisture content and groundwater level within the watershed under future precipitation conditions; And for screening key feature data from simulation results and future precipitation data, and for preprocessing feature data; And for inputting the preprocessed feature data into a pre-established and trained random forest hydrological prediction model, and outputting prediction results, wherein the random forest hydrological prediction model is established and trained using the random forest method, and the prediction results include groundwater level changes and soil moisture content over a future period of time; The mathematical model of the hydrological response model is specifically constructed as follows: Richard's equation was used to simulate and calculate the process of precipitation transforming into soil water, Darcy's law was used to simulate and calculate the process of soil water transforming into groundwater, and the groundwater storage change equation was used to simulate and calculate the dynamic changes in groundwater storage. The Newton-Raphson iteration method is used as a coupled solution method. The Richard equation, Darcy's law and the groundwater storage change equation are numerically coupled. The simulation results are obtained by gradually approximating the true solution through iterative calculation.

6. The comprehensive field observation system for precipitation, soil water, and groundwater response as described in claim 5, characterized in that, It also includes an intelligent early warning and decision support module, which is used to select specific judgment indicators, calculate and set the abnormality standards corresponding to each judgment indicator based on real-time monitoring data, historical data, and the output results of the hydrological response model and the random forest hydrological prediction model. It is also used to compare the prediction results with the set anomaly criteria, and to issue an early warning signal when any indicator value in the prediction results exceeds its corresponding anomaly criteria.

7. The comprehensive field observation system for precipitation, soil water, and groundwater response as described in claim 5, characterized in that, It also includes a power supply module, which is used to power the data monitoring and acquisition equipment using solar power, and to automatically adjust the power consumption of the equipment according to the working status of the equipment, the data acquisition frequency and the real-time energy status of the solar power system.

8. The comprehensive field observation system for precipitation, soil water, and groundwater response as described in claim 5, characterized in that, Also includes: The system monitoring and maintenance module is used to monitor the working status of the equipment, data transmission status, and energy supply status in real time. When the equipment fails, data transmission is interrupted, or there is an anomaly, an anomaly notification mechanism is triggered. In addition, the system can remotely access and perform anomaly maintenance on the equipment using a cloud platform.

9. An electronic device, characterized in that, include: One or more processors; Memory; as well as One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs comprising methods for performing any one of claims 1 to 4.

Images