A groundwater overexploitation area water level early warning method and system

Abstract

The application provides a groundwater overexploitation area water level early warning method and system, relates to the water quality dynamic monitoring technical field, and the method comprises the steps of: establishing a groundwater overexploitation area water level early warning model based on the corrected overexploitation area range and overexploitation degree; inputting the real-time monitored water level change data into the groundwater overexploitation area water level early warning model, performing water level early warning, and obtaining a preliminary early warning result; monitoring the water level change data of the groundwater overexploitation area in real time, and recording relevant dynamic influence factor data, wherein the dynamic influence factor data comprises rainfall, evaporation and artificial exploitation amount; calculating a dynamic factor according to the dynamic influence factor data; correcting the preliminary early warning result through the dynamic factor to obtain a final early warning result; and according to the final early warning result, when it is predicted that the groundwater water level will drop to a warning threshold, an early warning signal is sent. The application improves the accuracy and timeliness of early warning.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of water quality dynamic monitoring, in particular to a groundwater overexploitation area water level early warning method and system. BACKGROUND

[0002] Groundwater overexploitation not only leads to the decline of groundwater level, but also causes a series of environmental problems, such as land subsidence and water quality deterioration. Therefore, it is crucial to conduct timely and accurate water level early warning in groundwater overexploitation areas.

[0003] Traditional groundwater overexploitation area water level early warning methods have many defects. First, traditional methods usually conduct early warning based on static data, ignoring the dynamic changes of groundwater systems and the comprehensive effects of multiple influencing factors. This affects the accuracy and timeliness of the early warning results, so sometimes it cannot meet the needs of modern water resource management.

[0004] Secondly, when determining the overexploitation area range and overexploitation degree, some traditional methods only rely on limited geological and hydrological data, lack comprehensive data support and scientific verification process, so this may lead to inaccurate basic data of the early warning model, and further affect the reliability of the early warning results. SUMMARY

[0005] The technical problem to be solved by the present application is to provide a groundwater overexploitation area water level early warning method and system, which improves the accuracy and timeliness of early warning.

[0006] To solve the above technical problems, the technical solution of the present application is as follows:

[0007] In a first aspect, a groundwater overexploitation area water level early warning method is provided, the method comprising:

[0008] Step 1: Collecting basic data of the groundwater overexploitation area;

[0009] Step 2: Preliminary assessment of the groundwater overexploitation area to determine the preliminary overexploitation area range and overexploitation degree; verification of the preliminary overexploitation area range and overexploitation degree by calculating the correlation degree between each correlation factor and groundwater overexploitation to obtain the corrected overexploitation area range and overexploitation degree;

[0010] Step 3: Based on the corrected overexploitation area range and overexploitation degree, establishing a groundwater overexploitation area water level early warning model;

[0011] Step 4: Inputting the real-time monitored water level change data into the groundwater overexploitation area water level early warning model to conduct water level early warning to obtain the preliminary early warning result;

[0012] Step 5, real-time monitoring of the water level change data of the groundwater overexploitation area, and recording the related dynamic influence factor data, the dynamic influence factor data including rainfall, evaporation and artificial exploitation amount; calculating the dynamic factor according to the dynamic influence factor data; correcting the preliminary warning result through the dynamic factor to obtain the final warning result;

[0013] Step 5, according to the final warning result, when it is predicted that the groundwater level will drop to the warning threshold, a warning signal is issued.

[0014] Further, the groundwater overexploitation area is preliminarily evaluated to determine the preliminary overexploitation area range and overexploitation degree, including:

[0015] Pretreating the basic data of the groundwater overexploitation area to obtain the pretreated basic data of the groundwater overexploitation area;

[0016] According to the pretreated basic data of the groundwater overexploitation area, calculating the exploitation coefficient of each evaluation unit, that is, the ratio of the actual exploitation amount to the exploitable amount;

[0017] According to the historical data, determining the exploitation coefficient threshold value for judging the overexploitation degree;

[0018] Using binary coding method, encoding the exploitation coefficient as the gene of genetic algorithm; randomly generating an initial population containing multiple individuals, each individual representing an exploitation coefficient distribution;

[0019] Defining a fitness function to evaluate the pros and cons of each individual; according to the fitness function value, selecting the corresponding individual into the next generation; randomly selecting two individuals and exchanging part of the genes to generate new individuals; randomly changing the genes in the individual, repeating the selection, crossover and mutation operations until the termination condition is met, and after the genetic algorithm terminates, outputting the corresponding individual as the final solution, which represents a final exploitation coefficient distribution;

[0020] According to the final exploitation coefficient distribution, combining the exploitation coefficient threshold value, determining the preliminary overexploitation area range and overexploitation degree.

[0021] Further, the preliminary overexploitation area range and overexploitation degree are verified, and the correlation degree between each correlation factor and groundwater overexploitation is calculated to obtain the corrected overexploitation area range and overexploitation degree, including:

[0022] Taking the groundwater overexploitation degree as the reference sequence, that is, the mother sequence; calculating the absolute difference between each correlation factor sequence and the reference sequence to form a difference sequence; finding the maximum and minimum values in the difference sequence, respectively denoted as Δ max and Δ min ;

[0023] The correlation coefficient between each correlation factor and groundwater overexploitation is calculated, and the correlation coefficient calculation formula is as follows:

[0024]

[0025] Wherein, ξ ij (k) is the correlation coefficient of the ith correlation factor and the jth overexploitation index at the kth point; Δ ij (k) is the absolute difference value of the ith correlation factor and the jth overexploitation index at the kth point; p is the resolution coefficient, and the value is between (0, 1); ω ij is the weight of the ith correlation factor to the jth overexploitation index; x i (k) and x j (k) are the values of the ith correlation factor and the jth overexploitation index at the kth point, respectively; σ ij is the standard deviation between the ith correlation factor and the jth overexploitation index;

[0026] The correlation coefficients of each correlation factor at each time point are averaged to obtain the correlation degree between each correlation factor and groundwater overexploitation;

[0027] According to the size of the correlation degree, the correlation factors are sorted to determine the influence degree of each correlation factor on groundwater overexploitation, so as to obtain the correlation degree sorting; according to the correlation degree sorting, the specific influence of each correlation factor on groundwater overexploitation is analyzed, so as to obtain the correlation analysis result;

[0028] According to the correlation analysis result, the overexploitation area range and overexploitation degree preliminarily evaluated are corrected to obtain the corrected overexploitation area range and overexploitation degree.

[0029] Further, based on the corrected overexploitation area range and overexploitation degree, a groundwater overexploitation area water level warning model is established, including:

[0030] Integrate the corrected overexploitation area range and overexploitation degree data, collect rainfall, evaporation and artificial exploitation related to groundwater level change;

[0031] Determine the neural network structure, including the number of neurons in the input layer, the hidden layer and the output layer, select the corresponding ReLU function for each layer of the neural network; use the random initialization method to initialize the weights and biases of the neural network;

[0032] Divide the corrected overexploitation area range and overexploitation degree data and the rainfall, evaporation and artificial exploitation related to the change of groundwater level into training set, validation set and test set;

[0033] The mean square error is set as the loss function and the Adam optimizer, the neural network is trained using the training set data, the neural network parameters are adjusted through the back propagation algorithm, the performance of the neural network model is evaluated on the validation set, the performance of the neural network model is evaluated using the test set data to obtain an evaluation result, and the neural network model is adjusted according to the evaluation result to obtain a trained neural network model, wherein the trained neural network model is a groundwater over-exploitation area water level warning model.

[0034] Further, the corrected over-exploitation area range and over-exploitation degree data, and the rainfall, evaporation and artificial exploitation amount related to the change of the groundwater level are divided into a training set, a validation set and a test set, including:

[0035] The corrected over-exploitation area range and over-exploitation degree data, and the rainfall, evaporation and artificial exploitation amount data are sorted;

[0036] An evaluation function is defined for evaluating the performance of the neural network model under different data division schemes;

[0037] The parameters of the differential evolution algorithm are set, including the population size NP, the crossover factor, the scaling factor and the maximum number of iterations; the population is initialized, that is, NP random data division schemes are generated as initial solutions;

[0038] For each individual in the population, the neural network model is trained using the training set and the performance is evaluated on the validation set; the evaluation value of each individual is calculated according to the evaluation function; enter the iteration process, for each iteration:

[0039] Randomly select three different individuals, generate a new trial individual according to the rules of the differential evolution algorithm; evaluate the trial individual, that is, train the model using the new training set and evaluate the performance on the validation set; if the evaluation value of the trial individual is better than that of the target individual, replace the target individual, update the individuals in the population, until the maximum number of iterations is reached;

[0040] According to the final individual found by the differential evolution algorithm, the final training set, validation set and test set division scheme is determined.

[0041] Further, the neural network parameters are adjusted through the back propagation algorithm, including:

[0042] The parameters of the neural network are initialized, including the weights and biases;

[0043] Input a sample in the training data set, perform forward propagation calculation through the network, that is, according to the current weights and biases, calculate the activation value of each layer of neurons until the output of the network is obtained;

[0044] The mean square error value between the network output and the actual label is calculated;

[0045] From the output layer, the gradient of the mean square error value to the activation value of each neuron in each layer is calculated by the chain rule, that is, the partial derivative;

[0046] According to the calculated gradient, the weights and biases of each layer of neurons are updated using the gradient descent algorithm until the stopping condition is met, the performance of the model during training is evaluated using the validation dataset, and the learning rate is adjusted, the number of network layers is increased or decreased as needed to continuously adjust the parameters of the neural network.

[0047] Further, the basic data of the groundwater overexploitation area includes groundwater exploitation amount, exploitable amount, water level dynamic change data, and related data of geological environmental problems.

[0048] In a second aspect, a water level early warning system for a groundwater overexploitation area includes:

[0049] The collection module is configured to collect basic data of the groundwater overexploitation area.

[0050] The evaluation module is configured to preliminarily evaluate the groundwater overexploitation area to determine a preliminary overexploitation area range and overexploitation degree, and to verify the preliminary overexploitation area range and overexploitation degree by calculating the correlation degree between each correlation factor and groundwater overexploitation to obtain a corrected overexploitation area range and overexploitation degree.

[0051] The establishment module is configured to establish a water level early warning model for the groundwater overexploitation area based on the corrected overexploitation area range and overexploitation degree.

[0052] The early warning module is configured to input real-time monitored water level change data into the water level early warning model for the groundwater overexploitation area to perform water level early warning and obtain a preliminary early warning result.

[0053] The calculation module is configured to monitor water level change data of the groundwater overexploitation area in real time and record relevant dynamic influence factor data, including rainfall, evaporation, and human exploitation amount, calculate a dynamic factor based on the dynamic influence factor data, and correct the preliminary early warning result based on the dynamic factor to obtain a final early warning result.

[0054] The judgment module is configured to issue an early warning signal when it is predicted that the groundwater level will drop to a warning threshold based on the final early warning result.

[0055] In a third aspect, a computing device includes:

[0056] one or more processors;

[0057] a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method.

[0058] In a fourth aspect, a computer readable storage medium stores a program, which when executed by a processor, implements the method.

[0059] The above scheme of the present application at least includes the following beneficial effects:

[0060] By collecting the basic data of the overexploited area of groundwater, accurate data support can be provided for subsequent steps, including but not limited to geological structure, hydrogeological conditions, historical exploitation data, etc., which are crucial for accurately assessing the scope and degree of overexploitation.

[0061] By preliminarily evaluating the overexploited area of groundwater, the scope and degree of overexploitation can be roughly determined, and the verification process further improves the accuracy of the evaluation by calculating the correlation degree between each correlation factor and groundwater overexploitation, ensuring that the early warning model is based on more accurate data.

[0062] Based on the corrected scope and degree of overexploitation, the early warning model can more accurately predict the trend of groundwater level changes. Such a model can consider a variety of factors, including geological conditions, exploitation history, etc., thereby improving the accuracy and reliability of the early warning.

[0063] By monitoring the real-time water level change data, the dynamic changes of the groundwater level can be understood in a timely manner, and by inputting these data into the early warning model, preliminary early warning results can be obtained quickly to provide information support for timely response to possible water level decline problems.

[0064] Real-time monitoring and recording of dynamic influencing factor data such as rainfall, evaporation, and human exploitation can provide a more comprehensive understanding of factors affecting groundwater level changes. By calculating dynamic factors and correcting preliminary early warning results, the accuracy and timeliness of early warning can be further improved, ensuring that the early warning results are more realistic.

[0065] When it is predicted that the groundwater level will drop to the early warning threshold, an early warning signal is sent in a timely manner to remind relevant departments and personnel to take measures to prevent further decline in the groundwater level, thereby protecting groundwater resources and reducing environmental problems caused by overexploitation. BRIEF DESCRIPTION OF DRAWINGS

[0066] Figure 1 is a flowchart of a groundwater overexploited area water level early warning method provided by an embodiment of the present application.

[0067] Figure 2 is a schematic diagram of a groundwater overexploited area water level early warning system provided by an embodiment of the present application. DETAILED DESCRIPTION

[0068] Exemplary embodiments of the present disclosure will be described in greater detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be embodied in various forms without being limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be thoroughly and completely understood, and will fully convey the scope of the present disclosure to those skilled in the art.

[0069] As Figure 1 indicated, the embodiment of the present application proposes a water level early warning method for groundwater overexploitation area, which comprises the following steps:

[0070] Step 1, collecting the basic information of the groundwater overexploitation area, the basic information of the groundwater overexploitation area including the groundwater exploitation amount, exploitable amount, water level dynamic change data and related information of geological environmental problems;

[0071] Step 2, preliminarily evaluating the groundwater overexploitation area to determine the preliminary overexploitation area range and overexploitation degree; verifying the preliminary overexploitation area range and overexploitation degree, and obtaining the corrected overexploitation area range and overexploitation degree by calculating the correlation degree between each correlation factor and groundwater overexploitation;

[0072] Step 3, based on the corrected overexploitation area range and overexploitation degree, establishing a water level early warning model for the groundwater overexploitation area;

[0073] Step 4, inputting the real-time monitored water level change data into the water level early warning model for the groundwater overexploitation area to perform water level early warning, so as to obtain a preliminary early warning result;

[0074] Step 5, real-time monitoring the water level change data of the groundwater overexploitation area and recording the related dynamic influence factor data, the dynamic influence factor data including rainfall, evaporation and artificial exploitation amount; calculating the dynamic factor according to the dynamic influence factor data; correcting the preliminary early warning result by the dynamic factor to obtain a final early warning result;

[0075] Step 5, according to the final early warning result, when it is predicted that the groundwater level will drop to the early warning threshold, an early warning signal is issued.

[0076] In the embodiments of the present application, by comprehensively collecting detailed information of groundwater overexploitation areas, including exploitation amount, exploitable amount, water level dynamic change data and related information of geological environmental problems, these data can help to more accurately understand the current situation and problems of overexploitation areas, so as to develop more effective early warning and management strategies. Preliminary assessment of the scope and degree of overexploitation can help to quickly identify problem areas, and through the verification process, the preliminary assessment results are corrected by using correlation degree calculation, which improves the accuracy and reliability of the assessment, which helps to ensure the accuracy of the subsequent early warning model and reduce the possibility of false positives and false negatives. Based on the corrected scope and degree of overexploitation, the early warning model can more accurately predict and evaluate the dynamic changes of groundwater level, which helps to respond to potential water level decline risks in a timely manner. By monitoring water level changes in real time and inputting data into the early warning model, preliminary early warning results can be quickly obtained, which is important for timely response and prevention of groundwater overexploitation, and helps to protect groundwater resources and the ecological environment. According to the dynamic factors such as rainfall, evaporation and human exploitation, the actual situation of groundwater level change can be more comprehensively reflected, and by calculating dynamic factors and correcting the preliminary warning results, the accuracy and pertinence of the warning are further improved, which helps managers make more informed decisions to cope with changing environmental conditions. When it is predicted that the groundwater level will drop to the warning threshold, timely warning signals can remind relevant departments and personnel to take action quickly, which helps to prevent excessive decline of groundwater level, protect groundwater resources, and reduce environmental problems caused by it. A timely and effective early warning system is an important guarantee for water resources management and ecological environment protection.

[0077] Step 1: Collecting basic information of groundwater overexploitation areas comprehensively and systematically, the following is a detailed explanation of this step:

[0078] Groundwater exploitation amount data:

[0079] This part of the data records the exploitation from history to now in the groundwater overexploitation area, including the location of exploitation well, exploitation time, exploitation amount, etc. Understanding the exploitation amount helps to analyze the water resource consumption speed of the overexploitation area and judge whether the exploitation activity exceeds the renewable capacity of groundwater.

[0080] Exploitable amount data:

[0081] Exploitable amount refers to the maximum amount of water that can be extracted from groundwater without affecting the sustainable use of groundwater and the ecological environment. Collecting this data helps to assess whether the current exploitation activity exceeds the safety threshold, thereby judging the potential risk of overexploitation.

[0082] Water level dynamic change data:

[0083] Water level dynamic change data records the spatio-temporal changes of groundwater level, including seasonal fluctuations, interannual variations, etc.

[0084] Geological environment related information:

[0085] Geological environment problems such as land subsidence and water quality deterioration are closely related to groundwater overexploitation. Collecting these data helps to understand the impact of overexploitation on the geological environment.

[0086] In summary, step 1 collects various basic data of the groundwater overexploitation area, providing solid data support for subsequent water level warning work. The accuracy and completeness of these data directly affect the reliability of the warning model and the accuracy of the warning results.

[0087] In a preferred embodiment of the present application, the groundwater overexploitation area is preliminarily evaluated to determine the preliminary overexploitation area range and overexploitation degree, including:

[0088] The basic data of the groundwater overexploitation area is preprocessed to obtain the preprocessed basic data of the groundwater overexploitation area, specifically including: collecting the basic data of the groundwater overexploitation area, including the exploitation amount, exploitable amount, water level change, etc.; removing duplicate, incorrect or incomplete data to ensure the accuracy and consistency of the data; converting the data into a unified format for subsequent analysis and processing; for missing data, using interpolation, regression and other methods to fill in, and standardizing the data to eliminate dimensional differences for comparison between different indicators.

[0089] According to the preprocessed basic data of the groundwater overexploitation area, the exploitation coefficient of each evaluation unit is calculated, that is, the ratio of the actual exploitation amount to the exploitable amount, specifically including: dividing the groundwater overexploitation area into several evaluation units, each unit as an independent analysis object, for each evaluation unit, statistics its actual exploitation amount and exploitable amount, and calculating the exploitation coefficient of each evaluation unit, that is, the ratio of the actual exploitation amount to the exploitable amount, which reflects the exploitation intensity of the unit.

[0090] According to the historical data, the exploitation coefficient threshold is determined to judge the overexploitation degree, specifically including: analyzing the historical exploitation data to understand the impact of different exploitation coefficients on the groundwater system; based on historical data, set one or more exploitation coefficient thresholds to judge the overexploitation degree. For example, set the exploitation coefficient greater than 1 as overexploitation, and less than or equal to 1 as non-overexploitation.

[0091] Adopt binary coding mode, and encode the mining coefficient as the gene of the genetic algorithm; randomly generate an initial population containing multiple individuals, and each individual represents a mining coefficient distribution, specifically including: adopting binary coding mode, and encoding the mining coefficient as the gene of the genetic algorithm, and each gene represents a specific mining coefficient value; randomly generating an initial population containing multiple individuals, and each individual is composed of a group of genes (i.e., mining coefficients) and represents a possible mining coefficient distribution.

[0092] Define the fitness function to evaluate the pros and cons of each individual; according to the fitness function value, select the corresponding individual to enter the next generation; randomly select two individuals and exchange part of the genes to generate new individuals; randomly change the genes in the individual, and repeat the selection, crossover and mutation operations until the termination condition is met, and after the genetic algorithm terminates, output the corresponding individual as the final solution, which represents a final mining coefficient distribution, specifically including:

[0093] Determine the evaluation criteria, and define a fitness function to calculate the fitness value of each individual based on the evaluation criteria, which should be able to quantify the pros and cons of the individual (i.e., the mining coefficient distribution); for each individual in the population, use the fitness function to calculate its fitness value; sort all individuals according to their fitness values, and use a selection strategy (such as roulette selection) to select the corresponding individuals to enter the next generation, and in the selection process, the probability of the individual with a higher fitness value being selected should be greater; according to the selection strategy, select a certain number of individuals from the current population to form the next generation population; randomly select two individuals from the new generation population for pairing, and randomly select one or more crossover points, which will determine which genes will be exchanged; at the selected crossover points, exchange the genes of the two individuals to generate two new individuals, which simulates the natural crossbreeding of organisms; set a mutation probability, which determines the likelihood of each gene being mutated; for each individual in the population, randomly select a portion of genes for mutation according to their gene length and mutation probability; randomly change the selected genes, which in binary coding usually means changing 0 to 1 or 1 to 0; repeat the selection, crossover and mutation operations until the termination condition is met, and a new population is generated after each operation, and after the algorithm terminates, select the individual with the highest fitness value from the last generation population as the final solution; decode the genes (i.e., the binary coded mining coefficient) of the final solution into the actual mining coefficient distribution, and output the mining coefficient distribution of the final solution, which represents the optimized groundwater mining strategy. The calculation formula of the fitness function is:

[0094]

[0095] Where N is the total number of mining coefficients; c iis the exploitation coefficient of the i th evaluation unit; is the average value of all exploitation coefficients; ∈ is a very small constant, used to avoid the error of division by zero; max i (c i ) represents the maximum value among all exploitation coefficients; T is a preset maximum allowed exploitation coefficient threshold; α and β are weight coefficients.

[0096] According to the final exploitation coefficient distribution, in combination with the exploitation coefficient threshold, the preliminary overexploitation area range and overexploitation degree are determined, specifically including: according to the final exploitation coefficient distribution output by the genetic algorithm, the exploitation situation of each evaluation unit is analyzed, in combination with the exploitation coefficient threshold, the evaluation units with exploitation coefficients exceeding the threshold are demarcated as overexploitation areas, and the overexploitation areas are classified according to the size of the exploitation coefficient, and the overexploitation degree of each area is quantified. For example, the area with an exploitation coefficient greater than a certain value can be divided into a serious overexploitation area, and the area with an exploitation coefficient less than another value can be divided into a mild overexploitation area, and the like.

[0097] In the embodiments of the present application, through cleaning, integration and standardization of the original data, the quality and availability of the data are improved; the exploitation coefficient as a key index for measuring the groundwater exploitation intensity, its calculation helps to intuitively understand the exploitation situation of each evaluation unit, and provides a quantitative basis for the determination of the overexploitation degree; the exploitation coefficient threshold set based on the historical data provides a scientific standard for defining the overexploitation area and the non-overexploitation area, so that the judgment of the overexploitation degree is more objective and accurate; through binary coding, the complex exploitation coefficient problem is simplified into a gene form that can be processed by the genetic algorithm, which facilitates efficient operation of the algorithm, and the initial population generated randomly increases the diversity of the search space, which helps the algorithm to find the optimal solution in the global range; the design of the fitness function can quantify the advantages and disadvantages of each individual, and provide clear guidance for the selection operation; the selection, crossover and mutation operations simulate the process of natural evolution, and through continuous iteration optimization, the individuals in the population gradually approach the optimal solution, and the application of the genetic algorithm can efficiently and accurately search for the optimal exploitation coefficient distribution; in combination with the final exploitation coefficient distribution and the exploitation coefficient threshold, the range of the overexploitation area can be accurately demarcated, and the overexploitation degree of each area can be quantified.

[0098] In a preferred embodiment of the present application, the preliminary overexploitation area range and overexploitation degree are verified, and the correlation degree between each correlation factor and groundwater overexploitation is calculated to obtain the corrected overexploitation area range and overexploitation degree, including:

[0099] The groundwater overexploitation degree is taken as a reference sequence, i.e., a mother sequence; the absolute difference between each correlation factor sequence and the reference sequence is calculated to form a difference sequence; the maximum value and the minimum value in the difference sequence are found out and recorded as Δ max and Δ minSpecifically, it includes: determining the mother sequence, clarifying the data on groundwater over-exploitation, which will be the reference sequence, also called the mother sequence. Assuming that there are groundwater over-exploitation data at n time points, it can be expressed as a sequence M = {m1, m2, ..., m n}, where m n represents the degree of groundwater overdraft at the nth time point. Next, determine the data series of various factors that may be related to the degree of groundwater overdraft. Assuming there are p related factors, each factor has data at n time points, then the data of each related factor can be represented as a sequence F j ={f j1 , f j2 ,…,f jn}, where j = 1, 2, ... p represents the jth correlation factor, f jn Represents the value of the jth correlation factor at the nth time point; for each correlation factor sequence Fj, calculate the absolute difference between it and the parent sequence M to form a new difference sequence D j ={d j1 , d j2 ,…,d jn}, where d ji =|f ji -m i |, represents the absolute difference between the jth correlation factor and the degree of groundwater overexploitation at the i-th time point.

[0100] In all difference sequences D j Find the maximum value Δ max and minimum value Δ min , these two values ​​will be used to calculate the correlation coefficient later. Specifically, we can traverse all the elements in the difference sequence and find the maximum value as Δ max , and similarly find the minimum value as Δ min .

[0101] The correlation coefficient between each correlation factor and groundwater overexploitation was calculated. The correlation coefficient calculation formula is as follows:

[0102]

[0103] Among them, ξ ij (k) is the correlation coefficient between the i-th correlation factor and the j-th overexploitation index at the k-th point; Δ ij (k) is the absolute difference between the i-th correlation factor and the j-th overexploitation index at the k-th point; ρ is the resolution coefficient, which takes a value between (0, 1); ω ij is the weight of the i-th correlation factor on the j-th overexploitation indicator; x i (k) and x j(k) is the value of the ith correlation factor and the jth overexploitation indicator at the kth point; σ ij is the standard deviation between the ith correlation factor and the jth overexploitation indicator;

[0104] The correlation coefficients of each correlation factor at each time point are averaged to obtain the correlation degree between each correlation factor and groundwater overexploitation, specifically including:

[0105] For each correlation factor, the average of its correlation coefficients at all time points is calculated, and the correlation coefficient of each correlation factor at each time point is calculated according to the correlation coefficient of each correlation factor at each time point calculated in the previous step ij (k), where i represents the index of the correlation factor, j represents the index of the overexploitation indicator, and k represents the index of the time point, and the formula for calculating the correlation degree is:

[0106]

[0107] where n is the total number of time points, R i represents the correlation degree between the ith correlation factor and groundwater overexploitation; t k is the kth time point, μ is the time center point, and σ is a parameter controlling the width of the weight distribution; s ik is the standardized value of the ith correlation factor at the kth time point; log e (s ik +1) is the logarithmic function.

[0108] According to the size of the correlation degree, the correlation factors are sorted to determine the influence degree of each correlation factor on groundwater overexploitation, to obtain the correlation degree ranking; according to the correlation degree ranking, the specific influence of each correlation factor on groundwater overexploitation is analyzed to obtain the results of the correlation analysis, specifically including: after calculating the correlation degrees of all correlation factors, the correlation factors can be sorted according to the size of the correlation degrees, and the sorting can be from large to small, so that it can be more intuitive to see which factors have the greatest influence on groundwater overexploitation. The sorted result can be represented as an ordered list, where each element contains the name of the correlation factor and its corresponding correlation degree; according to the sorting result of the correlation degree, the specific influence of each correlation factor on groundwater overexploitation can be analyzed, and factors with high correlation degrees indicate that they have stronger correlation with groundwater overexploitation and may be the main cause of overexploitation. For each high-correlation-degree factor, further analyze the reasons and mechanisms behind it to better understand how they affect groundwater overexploitation.

[0109] According to the results of the correlation analysis, the scope and degree of overexploitation of the preliminary evaluation are corrected to obtain the corrected scope and degree of overexploitation, which specifically includes: based on the results of the correlation analysis, the scope and degree of overexploitation of the preliminary evaluation can be corrected, especially for those factors highly related to groundwater overexploitation, the relevant overexploitation area delimitation standards and overexploitation degree evaluation methods need to be reexamined and adjusted. For example, if it is found that agricultural irrigation activities in a certain area are highly related to groundwater overexploitation, stricter standards may be needed when delimiting the overexploitation area in that area, and appropriate management measures may be taken to reduce the overexploitation of groundwater resources by irrigation. The corrected scope and degree of overexploitation should more scientifically and accurately reflect the actual situation, providing a stronger basis for subsequent groundwater management and protection work.

[0110] In the embodiments of the present application, by comprehensively considering the influence of multiple correlation factors on groundwater overexploitation and using correlation degree for quantitative analysis, the scope of overexploitation area and the degree of overexploitation can be more accurately determined. This method considers multiple correlation factors that may affect groundwater overexploitation, and by calculating the correlation degree between each factor and groundwater overexploitation, it can more comprehensively understand the contribution of each factor to groundwater overexploitation, so as to develop more comprehensive management and protection measures. By sorting the correlation factors, it can be clear which factors have the greatest impact on groundwater overexploitation, allowing managers to take targeted measures to reduce overexploitation, optimize resource allocation, and improve management efficiency. This method allows the weights of correlation factors to be adjusted according to actual conditions to adapt to different regions and different time points, and this flexibility allows the method to be widely applied to groundwater overexploitation evaluation under various geological and environmental conditions, and by correcting the scope and degree of overexploitation, it helps to develop more reasonable groundwater exploitation plans, thereby promoting the sustainable use of groundwater resources.

[0111] In a preferred embodiment of the present application, based on the corrected scope and degree of overexploitation, a groundwater overexploitation area water level warning model is established, including:

[0112] Integrate the corrected scope and degree of overexploitation data, collect rainfall, evaporation and human exploitation related to groundwater level changes, specifically including: integrating the corrected scope and degree of overexploitation data to ensure consistency in geographical space and time scale; cleaning the integrated data to remove outliers, missing values or duplicate data to ensure data quality; collecting rainfall data closely related to groundwater level changes, which may include historical rainfall records from weather stations, satellite remote sensing or public data sets. Collect evaporation data, which can be obtained from weather observation stations or relevant research institutions. Collect human exploitation data, including agricultural, industrial and residential water exploitation records, which may come from water management departments or relevant statistical data sets.

[0113] The number of neurons in the input layer, the hidden layer and the output layer of the neural network structure is determined, a corresponding ReLU function is selected for each layer of the neural network, the weights and biases of the neural network are initialized using a random initialization method, specifically including: determining the number of layers of the neural network (including the input layer, the hidden layer and the output layer), determining the number of neurons in each layer, which needs to be tried and adjusted according to experience to find the best network structure; selecting a ReLU (Rectified Linear Unit) activation function for each layer of the neural network to increase the nonlinear expression ability of the network; using a random initialization method (such as He initialization, Xavier initialization, etc.) to assign initial values to the weights and biases of the neural network, to ensure that the initialized weights and biases have appropriate distribution and range, to avoid the problem of gradient vanishing or explosion in the training process.

[0114] The corrected over-exploitation area range and over-exploitation degree data and the rainfall, evaporation and artificial exploitation related to the change of groundwater level are divided into a training set, a validation set and a test set;

[0115] The mean square error is set as a loss function and an Adam optimizer, the neural network is trained using the training set data, the neural network parameters are adjusted through a back propagation algorithm, the performance of the neural network model is evaluated on the validation set, the performance of the neural network model is evaluated using the test set data to obtain an evaluation result, the neural network model is adjusted according to the evaluation result to obtain a trained neural network model, wherein the trained neural network model is a groundwater over-exploitation area water level early warning model, specifically including:

[0116] The mean squared error (MSE) is selected as the loss function to measure the difference between the predicted value and the true value of the model; the Adam optimizer is selected as the parameter update algorithm in the training process, which combines the ideas of AdaGrad and RMSProp, and can adaptively adjust the learning rate. The training set data is used to train the neural network, the predicted value and the loss function value are calculated by forward propagation, and then the network weights and biases are updated by the back propagation algorithm. During the training process, the performance of the model can be evaluated regularly using the validation set data, and the learning rate, batch size and other training parameters can be adjusted as needed. The performance of the neural network is evaluated on the validation set, the trend of the loss function value and the prediction accuracy of the model are observed, and the trained neural network model is finally evaluated using the test set data to obtain the generalization performance evaluation result of the model. According to the evaluation result obtained, the neural network model is adjusted and optimized, which includes adjusting the network structure (increasing or decreasing the number of layers, the number of neurons, etc.), adjusting the activation function type, modifying the learning rate strategy, etc. The training and evaluation process is repeated until a satisfactory model performance is obtained. The finally trained neural network model is the groundwater over-exploitation area water level warning model.

[0117] In the embodiment of the present application, by integrating the corrected over-exploitation area range and over-exploitation degree data, and collecting multi-dimensional information such as rainfall, evaporation and artificial exploitation closely related to groundwater level changes, the model can more comprehensively reflect the dynamic changes of the groundwater system, thereby improving the accuracy of the warning. The neural network structure is adopted, and a large amount of actual data is used for training and optimization, so that the model can learn the complex nonlinear relationship between the data. This data-driven method provides a scientific basis for groundwater management decision-making, and helps to realize the rational use of resources and environmental protection. Through accurate warning, the risk areas of groundwater over-exploitation can be found in time, so as to guide relevant departments to reasonably allocate and adjust water resources exploitation plan, avoid ecological problems caused by over-exploitation, and ensure the sustainable use of groundwater. The warning model can quickly respond to abnormal changes of groundwater level, provide timely information support for emergency management departments, and help to improve the ability and efficiency of responding to groundwater crisis. Groundwater is an important part of the ecological system, and the establishment of a scientific warning model helps to protect groundwater resources, maintain ecological balance, and promote the in-depth development of ecological civilization construction. By dividing the training set, validation set and test set, and using the mean squared error as the loss function and the Adam optimizer for training, the model overfitting can be effectively prevented, and its generalization ability in different scenarios can be enhanced. At the same time, the model can be adjusted according to the evaluation result to further optimize the performance of the model.

[0118] In a preferred embodiment of the present application, the revised over-exploitation area range and over-exploitation degree data, as well as the rainfall, evaporation and artificial exploitation data related to the change of groundwater level, are divided into training set, validation set and test set, including:

[0119] The revised over-exploitation area range and over-exploitation degree data, as well as the rainfall, evaporation and artificial exploitation data, are sorted, specifically including: collecting the revised over-exploitation area range and over-exploitation degree data, as well as the related rainfall, evaporation and artificial exploitation data, to ensure that these data are consistent in time and spatial scales. Clean the data to remove outliers, missing values or duplicate values, and standardize or normalize the data to eliminate the dimensional differences between different features; convert the data into a format suitable for neural network model input, such as organizing the data into two-dimensional arrays or tensors and saving them in appropriate file formats (such as CSV, NumPy arrays, etc.).

[0120] Define an evaluation function to evaluate the performance of the neural network model under different data partition schemes, where the evaluation function is the mean square error.

[0121] Set the parameters of the differential evolution algorithm, including population size NP, crossover factor, scaling factor and maximum number of iterations; initialize the population, that is, generate NP random data partition schemes as initial solutions, specifically including: setting the parameters of the differential evolution algorithm, including population size (NP, the number of individuals), crossover factor (used to control the generation of new individuals), scaling factor (used to control the scaling degree of difference vectors) and maximum number of iterations (the maximum number of algorithm running rounds); according to the population size, randomly generate NP data partition schemes as initial solutions, each scheme should contain the partition proportion or specific index of training set, validation set and test set.

[0122] For each individual in the population, train the neural network model using the training set and evaluate the performance on the validation set; calculate the evaluation value of each individual according to the evaluation function; enter the iteration process, for each iteration, specifically including:

[0123] Randomly select three different individuals, generate a new trial individual according to the rules of the differential evolution algorithm; evaluate the trial individual, that is, train the model using the new training set and evaluate the performance on the validation set; if the evaluation value of the trial individual is better than that of the target individual, replace the target individual, update the individuals in the population, until the maximum number of iterations is reached, which specifically includes: for each individual in the population (i.e. data partition scheme), train the neural network model using the training set and evaluate its performance on the validation set. Calculate the evaluation value of each individual according to the evaluation function; in each iteration, randomly select three different individuals (denoted as X1, X2, X3), generate a new trial individual according to the rules of the differential evolution algorithm (such as DE / rand / 1 / bin strategy), which usually involves differential operation and crossover operation on the selected individuals; evaluate the generated trial individual, that is, train the neural network model using the new training set and evaluate its performance on the validation set, if the evaluation value of the trial individual is better than that of the target individual (i.e. better performance), replace the target individual with the trial individual. After a round of iteration, update the individuals in the population, retain the individuals with better performance, eliminate the individuals with poor performance, and determine whether the maximum number of iterations is reached. If so, stop iteration; otherwise, return to step four and continue the iteration process.

[0124] According to the final individual found by the differential evolution algorithm, determine the final training set, validation set and test set partition scheme, which specifically includes: after the iteration is completed, select the individual with the best evaluation value from the population as the final data partition scheme; according to the final data partition scheme, divide the original data set into training set, validation set and test set, ensure that the three sets are consistent in data distribution and independent of each other, save the final data partition scheme and the corresponding training set, validation set and test set data.

[0125] In the embodiments of the present application, by carefully dividing the data set, it can be ensured that the training set contains enough diverse data samples, so that the neural network model can fully learn the inherent rules of the data. At the same time, the effective division of the validation set and the test set helps to accurately evaluate the generalization ability of the model and avoid overfitting or underfitting problems. As an efficient optimization algorithm, the differential evolution algorithm can automatically find the best data division scheme in the search space. Through continuous iteration and evolution, the algorithm can gradually approach the global optimal solution, thereby significantly improving the performance of the neural network model. In the data division process, various factors related to the change of groundwater level (such as rainfall, evaporation and human exploitation) are considered, which makes the trained neural network model better adapt to complex and variable actual situations. Therefore, the model has stronger robustness and prediction ability when facing new data. Traditional data division methods often rely on the experience and subjective judgment of experts, while the present process divides data through an automated algorithm, reducing the influence of human factors on the performance of the model, which not only improves work efficiency, but also ensures the objectivity and consistency of data division.

[0126] In a preferred embodiment of the present application, the neural network parameters are adjusted by the back propagation algorithm, including:

[0127] Initializing the parameters of the neural network, including weights and biases, specifically including: randomly initializing the weight matrix for each layer of the neural network (except the output layer), common initialization methods include random decimal initialization (such as sampling from a normal distribution with a mean of 0 and a variance of 1), Xavier initialization (automatically adjusting the variance according to the number of input and output neurons) or He initialization (an initialization method optimized for ReLU activation function and its variants); the bias is initialized to 0 or a small number close to 0, because the main role of the bias is to adjust the activation threshold of the neuron, rather than introducing additional feature transformation.

[0128] Inputting a sample in the training data set, performing forward propagation calculation through the network, that is, calculating the activation value of each layer of neurons according to the current weight and bias until the output of the network is obtained, specifically including: receiving a training sample as input and passing it to the first hidden layer; for each hidden layer, calculate the activation value of each neuron in the current layer according to the weight and bias of the current layer and the activation value of the previous layer. This is usually done through matrix multiplication and addition operations, and then an activation function (such as ReLU, Sigmoid or Tanh) is applied to introduce nonlinearity; the calculation method of the last layer (usually the output layer) is similar to that of the hidden layer, but no activation function needs to be applied (this depends on the specific task, for example, it may not be needed in regression tasks), and the activation value of the output layer is the predicted output of the network.

[0129] Calculating the mean square error value between the network output and the actual label;

[0130] From the output layer, the gradient of the mean square error with respect to the activation values of each layer of neurons is calculated by the chain rule, specifically including: calculating the gradient of the output layer activation value with respect to the mean square error, which is usually done by derivation operation, to obtain the error gradient corresponding to each output neuron; then, starting from the output layer, the gradient of the hidden layer neurons is calculated layer by layer back, which is realized by the chain rule, that is, using the gradient passed down from the last layer and the weight of the current layer to calculate the gradient of the neurons in the current layer; During backpropagation, the gradient values corresponding to each weight and bias need to be accumulated in order to update the parameters subsequently.

[0131] According to the calculated gradient, the weights and biases of each layer of neurons are updated using the gradient descent algorithm until the stopping condition is met, and the performance of the model during training is evaluated using the validation dataset, and the learning rate is adjusted, the number of network layers is increased or decreased, to continuously adjust the parameters of the neural network, specifically including: according to the calculated gradient value and the set learning rate, the weights and biases of each layer of neurons are updated using the gradient descent algorithm; Set a stop condition, such as reaching the maximum number of iterations, the loss function value converging to a certain threshold or the performance of the validation set no longer improving, etc., when the stopping condition is met, stop iteration and save the current network parameters, during the training process, the performance of the model is evaluated regularly using the validation dataset. This helps to detect whether the model is overfitting or underfitting, and adjusts the learning rate, the number of network layers and other hyperparameters accordingly.

[0132] In the embodiments of the present application, the backpropagation algorithm calculates the gradient and updates the network parameters, so that the prediction error of the model on the training data gradually decreases. This helps to improve the fitting ability of the model on the training data, and further optimizes its generalization performance on unseen data. Through the gradient descent algorithm, the neural network can automatically adjust its weights and biases to adapt to different training samples. This self-adaptive learning ability enables the neural network to handle complex nonlinear problems and continuously improve its performance during the learning process. The backpropagation algorithm is an efficient optimization method that uses the chain rule to pass error signals layer by layer, avoiding the direct calculation of the gradient of all parameters of the entire network, thereby reducing the computational complexity, which enables the neural network to achieve fast learning and optimization under limited computational resources. During the training process, the structure of the neural network can be adjusted according to the performance evaluation results of the validation dataset, such as increasing or decreasing the number of network layers. This flexibility enables the neural network to be customized for different problems and datasets to further improve model performance. The learning rate is an important parameter in the gradient descent algorithm, which determines the step size of parameter updates. By dynamically adjusting the learning rate according to the performance changes during training, the model can quickly converge in the early stage and make more precise adjustments in the later stage to achieve better optimization results.

[0133] In a preferred embodiment of the present application, step 4, the real-time monitored water level change data is input into the groundwater overexploitation area water level warning model to perform water level warning, to obtain preliminary warning results, including:

[0134] Real-time collection of water level change data in the groundwater overexploitation area using a sensor network; preprocessing of the collected data, including noise removal, outlier detection and processing, data format conversion, etc., to ensure data quality and consistency. Convert the preprocessed data into a format suitable for input into the neural network model, for example, organize the data into a two-dimensional array or tensor. Load the trained groundwater overexploitation area water level warning model; input the preprocessed real-time monitoring data into the warning model, which usually involves passing the data to the input layer of the model; after the model receives the input data, it will perform forward propagation calculations, and in the forward propagation process, the model will calculate the activation values of neurons layer by layer according to the current weights and biases until it reaches the output layer; in the output layer, the model will output a specific numerical value as the preliminary warning result, which represents the model's prediction of the current water level change trend, and according to the specific numerical value, it can be known whether there is an overexploitation risk.

[0135] In a preferred embodiment of the present application, step 5, real-time monitoring of water level change data in the groundwater overexploitation area and recording of relevant dynamic influencing factor data, including rainfall, evaporation, and human exploitation, specifically including:

[0136] The water level in the overexploited groundwater area is continuously and automatically monitored by sensor networks, water level monitoring stations or other monitoring devices. These devices can transmit water level data to the data processing center or early warning system periodically (e.g., every hour, every day) or in real time. The received real-time water level data needs to be preprocessed, including noise removal, outlier detection and processing, to ensure the accuracy and reliability of the data. In addition to water level change data, some dynamic factors that affect the change of groundwater level also need to be recorded. These factors include rainfall, evaporation and human exploitation. Rainfall is an important source of groundwater recharge, and changes in rainfall will directly affect the level of groundwater. Historical rainfall records can be obtained through meteorological stations, satellite remote sensing or public data sets, and real-time rainfall can be monitored. Evaporation is an important way of groundwater consumption, and an increase in evaporation will lead to a decrease in groundwater level. Evaporation data can be obtained through meteorological observation stations or relevant research institutions. Human activities such as agricultural irrigation, industrial water and residential water consumption are also important factors affecting groundwater exploitation, and these data are usually obtained from water management departments or relevant statistical data sets. For the above dynamic influence factor data, a corresponding monitoring and recording system needs to be established. This can be achieved by installing sensors, collecting public data or cooperating with other departments. The collected data needs to be preprocessed, including outlier removal, missing value processing and data format conversion, to ensure the quality and consistency of the data. The collected dynamic influence factor data needs to be stored in a database or file for subsequent analysis and use. At the same time, a data management system needs to be established to ensure the integrity, security and accessibility of the data. By monitoring the water level change data in real time and recording the relevant dynamic influence factor data, a more comprehensive understanding of the change trend and influencing factors of the groundwater level can be obtained, thereby improving the accuracy of the early warning system. Through timely monitoring and early warning, overexploitation of groundwater can be prevented.

[0137] In a preferred embodiment of the present application, in step 5, a dynamic factor is calculated according to the dynamic influence factor data, wherein the calculation formula of the dynamic factor D is:

[0138]

[0139] wherein R represents the current rainfall (unit: mm / day); the historical average rainfall (the same unit as the current rainfall); σ R represents the standard deviation of rainfall, which is used to measure the volatility of rainfall; E represents the current evaporation (unit: mm / day); represents the historical average evaporation (the same unit as the current evaporation); σ E represents the standard deviation of evaporation, which is used to measure the volatility of evaporation; X represents the current human exploitation (unit: m 3 / day); represents the historical average human exploitation (unit is the same as the current exploitation) ; σ X represents the standard deviation of human exploitation, used to measure the volatility of exploitation; a, b, c, d, e and f are weight and index coefficients.

[0140] In a preferred embodiment of the present application, in step 5, the preliminary warning result is corrected by a dynamic factor to obtain the final warning result, wherein after the dynamic factor is calculated, it can be used to correct the preliminary warning result, and the correction formula can be:

[0141]

[0142] wherein t represents the current time; T represents the period; represents the phase shift; n represents the number of time points used to calculate the moving average; P i represents the warning result at the i-th time point in the past; R, E and X represent the current rainfall, evaporation and human exploitation, respectively; respectively represent the historical average rainfall, evaporation, human exploitation; σ R , σ E , σ X respectively represent the standard deviation of rainfall, evaporation and human exploitation; A, B and C represent weight coefficients; F w represents the final warning result, the value after dynamic factor correction; W represents the preliminary warning result, a value indicating the over-exploitation risk.

[0143] In a preferred embodiment of the present application, in step 5, according to the final warning result, it is judged that the underground water is predicted to be, specifically including:

[0144] Collect and analyze the basic data of the over-exploitation area of underground water, including:

[0145] Geological and hydrogeological data, including the distribution, thickness, permeability and water storage capacity of the groundwater layer, which helps to understand the natural recharge and discharge conditions of groundwater.

[0146] Historical water level data, collect long time series of water level monitoring data in the over-exploitation area of underground water, including interannual variation, seasonal fluctuation, etc., which is the basis for determining the warning threshold.

[0147] Exploitation data, record the exploitation activities in the over-exploitation area of underground water, including exploitation amount, location of exploitation well, exploitation time, etc., which helps to evaluate the influence of exploitation activities on groundwater level.

[0148] Environmental data, collect environmental data related to groundwater overexploitation, such as rainfall, evaporation, surface water recharge, etc. These data help understand the recharge sources and consumption pathways of groundwater.

[0149] Reference standard for determining early warning threshold, specifically including:

[0150] Safe water level, according to the principle of sustainable utilization of groundwater resources, determine a safe water level, that is, the lowest water level that can be reached without affecting the sustainable utilization of groundwater and the ecological environment.

[0151] Historical minimum water level, analyze historical water level data, find the lowest point of groundwater level as one of the references for the early warning threshold.

[0152] Based on the safe water level, combined with the specific situation of the groundwater overexploitation area, determine an early warning threshold slightly lower than the safe water level, so as to give early warning when the groundwater level approaches the dangerous level. If the historical minimum water level is significantly lower than the safe water level, consider setting the early warning threshold between the historical minimum water level and the safe water level to reflect the actual situation of the groundwater level and the historical impact of exploitation activities.

[0153] Compare the final warning result calculated with the pre-set early warning threshold. If the final warning result exceeds the early warning threshold, it means that the groundwater level has the risk of falling to a dangerous level. According to the gap between the final warning result and the early warning threshold, determine the level of warning. For example, multiple warning levels (such as level one warning, level two warning, level three warning, etc.) can be set, each level corresponds to different early warning thresholds and response measures. When it is determined that early warning is needed, according to the warning level, through appropriate channels (such as SMS, email, online platform, alarm system, etc.), send early warning signals to relevant departments, enterprises and the public, the early warning signal contains the information of warning level, warning area, warning reason, suggested response measures, etc. so that the recipient can take appropriate action in time.

[0154] As shown in Figure 2 , the embodiment of the present application also provides a groundwater overexploitation area water level early warning system, comprising:

[0155] The collection module is used for collecting the basic data of the groundwater overexploitation area;

[0156] The evaluation module is used for preliminary evaluation of the groundwater overexploitation area, to determine the preliminary overexploitation area range and overexploitation degree; verify the preliminary overexploitation area range and overexploitation degree by calculating the correlation degree between each correlation factor and groundwater overexploitation to obtain the corrected overexploitation area range and overexploitation degree;

[0157] The establishment module is used for establishing a groundwater overexploitation area water level early warning model based on the corrected overexploitation area range and overexploitation degree;

[0158] The early warning module is configured to input the monitored water level change data in real time into a water level early warning model of the overexploited groundwater area, perform water level early warning, and obtain a preliminary early warning result.

[0159] The calculation module is configured to monitor water level change data of the overexploited groundwater area in real time, record relevant dynamic influence factor data, and calculate a dynamic factor according to the dynamic influence factor data.

[0160] The judgment module is configured to judge, according to the final early warning result, when the predicted water level of the overexploited groundwater area will drop to a warning threshold, and issue an early warning signal.

[0161] It should be noted that the system corresponds to the method described above, and all implementation manners in the method embodiment are applicable to the embodiment and can achieve the same technical effects.

[0162] Embodiments of the present application also provide a computing device, comprising a processor and a memory storing a computer program, wherein the computer program is executed by the processor to perform the method described above.

[0163] Embodiments of the present application also provide a computer readable storage medium storing instructions, wherein the instructions are executed on a computer to make the computer perform the method described above. All implementation manners in the method embodiment are applicable to the embodiment and can achieve the same technical effects.

Claims

1. A groundwater level early warning method for over-exploitation areas, characterized in that: The method comprises: Step 1: Collect basic data on groundwater overexploitation areas; Step 2: Conduct a preliminary assessment of the groundwater overexploitation area to determine the preliminary scope and degree of overexploitation; verify the preliminary scope and degree of overexploitation, and calculate the correlation between each correlation factor and groundwater overexploitation to obtain the revised scope and degree of overexploitation, including: taking the groundwater overexploitation degree as a reference sequence, i.e., the parent sequence; calculating the absolute difference between each correlation factor sequence and the reference sequence to form a difference sequence; finding the maximum and minimum values ​​in the difference sequence, which are recorded as and ; Calculate the correlation coefficient between each correlation factor and groundwater overexploitation; average the correlation coefficients of each correlation factor at each time point to obtain the degree of correlation between each correlation factor and groundwater overexploitation; rank the correlation factors according to the magnitude of the correlation degree, determine the degree of influence of each correlation factor on groundwater overexploitation, and obtain a correlation ranking; analyze the specific influence of each correlation factor on groundwater overexploitation based on the correlation ranking to obtain the results of the correlation analysis; based on the results of the correlation analysis, revise the initially assessed overexploitation area and overexploitation degree to obtain a revised overexploitation area and overexploitation degree; Step 3: Based on the revised over-exploitation area range and over-exploitation degree, establish a groundwater level early warning model for over-exploitation areas; Step 4: Input the real-time monitored water level change data into the groundwater over-exploitation area water level early warning model to perform water level early warning to obtain preliminary early warning results; Step 5: Real-time monitoring of water level changes in the groundwater over-exploitation zone and recording of relevant dynamic influencing factor data, including rainfall, evaporation, and artificial extraction. Based on the dynamic influencing factor data, dynamic factors are calculated. The initial warning results are corrected using the dynamic factors to obtain the final warning results. Step 6: Based on the final warning result, when it is predicted that the groundwater level will drop to the warning threshold, a warning signal is issued.

2. The method for early warning of groundwater level in over-exploitation areas according to claim 1, characterized in that: Conduct a preliminary assessment of groundwater overexploitation areas to determine the initial scope and extent of overexploitation, including: Preprocessing the basic data of the groundwater over-exploitation area to obtain preprocessed basic data of the groundwater over-exploitation area; Based on the pre-processed basic data of groundwater over-exploitation areas, the extraction coefficient, i.e. the ratio of actual extraction volume to extractable volume, is calculated for each assessment unit; Based on historical data, the mining coefficient threshold is determined to judge the degree of over-exploitation; The mining coefficient is encoded as the gene of the genetic algorithm using binary coding. An initial population consisting of multiple individuals is randomly generated, and each individual represents a mining coefficient distribution. Define a fitness function to evaluate the quality of each individual; select the corresponding individual to enter the next generation based on the fitness function value; randomly select two individuals and exchange some of their genes to generate a new individual; randomly change the genes in the individual, and repeat the selection, crossover, and mutation operations until the termination condition is met. After the genetic algorithm terminates, the corresponding individual is output as the final solution, which represents a final mining coefficient distribution; Based on the final mining coefficient distribution and combined with the mining coefficient threshold, the preliminary over-exploitation area and over-exploitation degree are determined.

3. A groundwater level early warning method for over-exploitation areas according to claim 2, characterized in that: Based on the revised over-exploitation area and over-exploitation degree, a groundwater level early warning model for over-exploitation areas is established, including: Integrate revised data on the extent and degree of overexploitation, collecting rainfall, evaporation, and anthropogenic extraction data related to groundwater level changes; Determine the neural network structure, including the number of neurons in the input layer, hidden layer, and output layer, and select the corresponding ReLU function for each layer of the neural network; use random initialization method to initialize the weights and bias of the neural network; The corrected over-exploitation area and over-exploitation degree data, as well as rainfall, evaporation and anthropogenic extraction data related to groundwater level changes were divided into training, validation and test sets. The mean square error is set as the loss function and Adam optimizer, the neural network is trained using the training set data, and the neural network parameters are adjusted through the back propagation algorithm; the performance of the neural network model is evaluated on the validation set, and the performance of the neural network model is evaluated using the test set data to obtain the evaluation results; the neural network model is adjusted according to the evaluation results to obtain the trained neural network model, where the trained neural network model is a groundwater over-exploitation area water level warning model.

4. A groundwater level early warning method for over-exploitation areas according to claim 3, characterized in that: The corrected over-exploitation area and over-exploitation degree data, as well as rainfall, evaporation, and anthropogenic extraction data related to groundwater level changes, are divided into training, validation, and test sets, including: Compile and update data on the extent and degree of over-exploitation, as well as rainfall, evaporation, and anthropogenic extraction; Define an evaluation function to evaluate the performance of the neural network model under different data partitioning schemes; Set the parameters of the differential evolution algorithm, including the population size NP, crossover factor, scaling factor, and maximum number of iterations; initialize the population, that is, generate NP random data partitioning schemes as the initial solution; For each individual in the population, the neural network model is trained using the training set and the performance is evaluated on the validation set. The evaluation value of each individual is calculated according to the evaluation function. The iterative process is entered. For each iteration: Three different individuals are randomly selected and a new test individual is generated according to the rules of the differential evolution algorithm. The test individual is evaluated, that is, the model is trained using the new training set and the performance is evaluated on the validation set. If the evaluation value of the test individual is better than the evaluation value of the target individual, the target individual is replaced and the individuals in the population are updated until the maximum number of iterations is reached. According to the final individuals found by the differential evolution algorithm, the final training set, validation set and test set division scheme is determined.

5. A groundwater over-exploitation area water level early warning method according to claim 4, characterized in that: Adjust the neural network parameters through the back-propagation algorithm, including: Initialize the parameters of the neural network, including weights and biases; Input a sample from the training data set and perform forward propagation calculations through the network. That is, based on the current weights and biases, calculate the activation values ​​of each layer of neurons until the network output is obtained; Calculate the mean square error between the network output and the actual label; Starting from the output layer, the gradient of the mean square error value with respect to the activation value of each neuron in each layer, i.e. the partial derivative, is calculated by the chain rule. According to the calculated gradient, the gradient descent algorithm is used to update the weights and biases of each layer of neurons until the stopping condition is met. The validation dataset is used to evaluate the performance of the model during training, and the learning rate is adjusted as needed, and the number of network layers is increased or decreased to continuously adjust the parameters of the neural network.

6. A groundwater level early warning method for over-exploitation areas according to claim 5, characterized in that: The basic data of groundwater over-exploitation areas include groundwater extraction volume, exploitable volume, water level dynamic change data and relevant data on geological environmental issues.

7. A groundwater over-exploitation area water level early warning system, characterized in that: include: Collection module, used to collect basic data on groundwater over-exploitation areas; The assessment module is used to conduct a preliminary assessment of the groundwater over-exploitation area, determine the preliminary over-exploitation area range and over-exploitation degree; verify the preliminary over-exploitation area range and over-exploitation degree, and obtain the revised over-exploitation area range and over-exploitation degree by calculating the correlation between each correlation factor and groundwater over-exploitation, including: taking the groundwater over-exploitation degree as a reference sequence, that is, the parent sequence; calculating the absolute difference between each correlation factor sequence and the reference sequence to form a difference sequence; finding the maximum and minimum values ​​in the difference sequence, which are recorded as and ; Calculate the correlation coefficient between each correlation factor and groundwater overexploitation; average the correlation coefficient of each correlation factor at each time point to obtain the correlation degree between each correlation factor and groundwater overexploitation; rank the correlation factors according to the size of the correlation degree, determine the degree of influence of each correlation factor on groundwater overexploitation, and obtain the correlation degree ranking; analyze the specific influence of each correlation factor on groundwater overexploitation according to the correlation degree ranking, and obtain the result of the correlation analysis; according to the result of the correlation analysis, revise the initially assessed overexploitation area and overexploitation degree to obtain the revised overexploitation area and overexploitation degree; Establish a module for establishing a groundwater level early warning model for overexploited areas based on the revised overexploited area range and overexploitation degree; The early warning module is used to input the real-time monitored water level change data into the groundwater over-exploitation area water level early warning model to carry out water level early warning and obtain preliminary early warning results; The calculation module is used to monitor the water level change data of the groundwater over-exploitation area in real time and record the relevant dynamic influencing factor data, including rainfall, evaporation and artificial extraction; calculate the dynamic factor based on the dynamic influencing factor data; and use the dynamic factor to correct the preliminary warning results to obtain the final warning results; The judgment module is used to determine, based on the final warning result, when it is predicted that the groundwater level will drop to the warning threshold and issue a warning signal.

8. A computing device, characterized in that include: one or more processors; A storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a program, which, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images