Underground water level prediction method and system based on multi-source data

Abstract

The invention provides an underground water level prediction method and system based on multi-source data, and relates to the technical field of underground water level prediction.The underground water level prediction method comprises the steps that by integrating the multi-source data such as meteorology, hydrology, geology and human activities, three types of key indexes including natural supply parameters, natural loss parameters and artificial disturbance parameters are constructed; and parameters are corrected based on data such as seasons and cumulative amount of historical data, and a water level prediction model is established by using a deep learning network. According to the method, the rainfall intensity, the river water level, the evaporation intensity, the underground runoff index, the mining amount and other data are collected in real time, high-precision and high-adaptability underground water level dynamic prediction is achieved, and the prediction accuracy under the complex natural and man-made coupling effect is remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of groundwater level prediction technology, specifically to a groundwater level prediction method and system based on multi-source data. Background Technology

[0002] With the increasing demand for water resource management, groundwater level prediction plays a crucial role in agricultural irrigation, urban water supply, and geological disaster prevention. Traditional prediction methods often rely on single hydrological or meteorological data, failing to fully consider the combined impact of multi-source data, resulting in limited prediction accuracy and poor adaptability. Especially in areas with frequent human activity, groundwater systems are affected by the coupling of natural and anthropogenic factors, and traditional models often cannot accurately reflect their dynamic changes, limiting their practical application effectiveness.

[0003] In the prior art, CN117575085A discloses a method, system, device, and storage medium for predicting tidal flat groundwater levels based on neural networks. This method involves collecting time-series data of tidal flat groundwater levels and corresponding tidal flat rainfall; dividing the time-series data and rainfall into training and validation sets; standardizing the time-series data of tidal flat groundwater levels in the training set; performing high-dimensional location encoding on the standardized time-series data and rainfall in the training set; training a pre-constructed CsL neural network model using the processed training set; validating the performance of the trained CsL neural network model using the validation set; and finally, inputting the current tidal flat rainfall and current tidal flat groundwater level time-series data into the final CsL neural network model to obtain the predicted tidal flat groundwater level for the next time period.

[0004] The main problem with the above scheme is that the dynamic change of the tidal flat groundwater level is a complex process affected by multiple factors. The rise or fall of the groundwater level is caused by a variety of actual activities, and different activities produce different effects. It is impossible to effectively describe the situation by relying solely on precipitation and historical water levels, resulting in inaccurate predictions that fail to reflect actual data.

[0005] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] The purpose of this invention is to provide a groundwater level prediction method and system based on multi-source data to solve the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: A groundwater level prediction method based on multi-source data, comprising the following steps: Step 1: Collect water level data, meteorological data, hydrological data, geological data, remote sensing data, and human activity data for the target area over previous time periods; Step 2: Calculate the area ratio of different types of land in the target area, and generate natural replenishment parameters for the target area based on meteorological data, hydrological data, and the area ratio of different types of land; calculate the vegetation water consumption evaluation index based on remote sensing data, and then calculate the groundwater evaporation loss index, and combine the evaporation loss index with geological data to generate natural loss parameters. Step 3: Assign impervious area proportion weights to different types of land in the target area based on permeability; generate the overall impervious area proportion of the region based on the area proportions of different types of land and the impervious area proportion weights; and generate artificial disturbance parameters based on human activity data and the overall impervious area proportion of the region. Step 4: Correct the natural recharge parameters based on the average values ​​of meteorological and hydrological data, and correct the artificial disturbance parameters based on the cumulative amount of artificial extraction. Step 5: Construct a deep learning network, using the natural loss parameters, corrected natural replenishment parameters, and artificial disturbance parameters from the same time period in historical data as input, and the groundwater level in the same time period as the label, to train the water level prediction model. Step 6: Input the natural loss parameters, corrected natural recharge parameters, and artificial disturbance parameters for the current time period into the water level prediction model to obtain the predicted groundwater level for the current time period.

[0008] Furthermore, the time period is one day, and the water level data, meteorological data, hydrological data, geological data, and remote sensing data are all averaged from multiple collections within one day. The meteorological data includes precipitation intensity, evaporation intensity, and ambient temperature; the hydrological data includes river water level and groundwater runoff; the geological data includes soil permeability coefficient and soil aquifer thickness; the remote sensing data represents the normalized difference vegetation index of the target area; and the human activity data includes groundwater extraction and land use types, including forest land, grassland, water area, agricultural land, and urban land. The water level data, meteorological data, and hydrological data are Z-score standardized, and all data used in subsequent calculations are Z-score standardized data.

[0009] Furthermore, the principle underlying the generation of natural supply parameters is as follows: The land use types of the target area are classified, and the area proportion of different land types is calculated using the following formula: ; in, Indicates the first The proportion of land area of ​​type 3 to the total area of ​​the target area An index representing land types, and , Indicates the quantity of land types. Indicates the first Land area of ​​type, Indicates the total area of ​​the target region; The formula used to calculate the natural replenishment parameter is: ; in, Indicates the natural supply parameter. Indicates precipitation intensity. The weighting coefficient representing the intensity of precipitation, and , Indicates the precipitation replenishment index. Indicates the river water level. The weighting coefficient represents the river water level, and , Indicates the first Soil permeability coefficient of land-like soil Indicates the first River replenishment index for land-like terrain.

[0010] Furthermore, the principle underlying the generation of natural loss parameters is as follows: The formula used to calculate the vegetation water consumption evaluation index based on the normalized difference vegetation index is as follows: ; in, This represents the vegetation water consumption evaluation index. Indicates the normalized difference vegetation index. Indicates ambient temperature. This indicates the ambient temperature at which vegetation transpiration is strongest in the target area. The evaporation loss index is generated based on the vegetation water consumption evaluation index and evaporation intensity, using the following formula: ; in, Indicates the evaporation loss index. Indicates evaporation intensity; The seasonal correction coefficient for evaporation intensity is adjusted based on seasonal settings, and the groundwater runoff is adjusted based on the soil moisture index to generate natural loss parameters. The formula used is as follows: ; in, Indicates the natural loss parameter. Indicates the evaporation loss index. This represents the seasonal correction factor, and in summer... In winter Spring and Autumn , Indicates the first The thickness of the soil aquifer in land-like soils, These represent the weighting coefficients for the evaporation loss index and the groundwater runoff index, respectively. and .

[0011] Furthermore, the principle underlying the overall proportion of impermeable area in a given region is as follows: The land use types in the target area are classified into forest land, grassland, water area, agricultural land, and urban land. A weighted average of the impervious area proportions is assigned to each land type: forest land 0.1, grassland 0.1, water area 0.01, agricultural land 0.2, and urban land 0.8. The overall impervious area proportion for the region is then calculated by weighting the proportions of each land type with their respective impervious area proportions. The formula used is as follows: ; in, This indicates the proportion of the overall impermeable area in the region. Indicates the first Weighting of the proportion of impermeable area for each land type.

[0012] Furthermore, the mathematical expression upon which the artificial perturbation parameters are based is: ; in, Indicates the parameters of artificial perturbation. This indicates the amount of groundwater extracted. This term represents the synergistic relationship between groundwater extraction volume and the proportion of the overall impermeable area in a region. These represent the weighting coefficients of groundwater extraction volume, the proportion of the overall impermeable area in the region, and the synergistic term, respectively. ,and .

[0013] Furthermore, the principle underlying the correction of the natural replenishment parameters is as follows: For each time period, the average precipitation intensity and average evaporation intensity of the past 7 days were statistically analyzed and standardized using the Z-score. The soil moisture index was calculated based on the average precipitation intensity and average evaporation intensity using the following formula: ; in, Indicates soil moisture index, This represents the standardized average precipitation intensity. This represents the standardized average evaporation intensity; The formula for correcting the natural replenishment parameter is: ; in, This represents the corrected natural supply parameter. Indicates the natural supply parameter; The principle underlying the correction of artificial disturbance parameters is as follows: For each time period, the net groundwater extraction volume over the past 30 days is calculated to generate a cumulative effect index, based on the following formula: ; in, Indicates the cumulative effect index. This represents the sensitivity coefficient, and , This indicates the net amount of groundwater extracted over the past 30 days. Indicates the threshold for extraction volume. Let be the hyperbolic tangent function, Values ​​mapped to between; The corrected artificial disturbance parameters are: ; in, This represents the corrected artificial perturbation parameters. This represents the parameters of artificial disturbance.

[0014] This invention also provides a groundwater level prediction system based on multi-source data. The system is used to implement the above-mentioned groundwater level prediction method based on multi-source data, specifically including: The data acquisition module is used to collect water level data, meteorological data, hydrological data, geological data, remote sensing data, and human activity data of the target area over a previous time period. The natural activity calculation module is used to calculate the area ratio of different types of land in the target area, and generate natural replenishment parameters for the target area based on meteorological data, hydrological data and the area ratio of different types of land; it calculates the vegetation water consumption evaluation index based on remote sensing data, and then calculates the groundwater evaporation loss index, and combines the evaporation loss index with geological data to generate natural loss parameters. The human activity calculation module is used to allocate the proportion weight of impervious area to different types of land in the target area based on permeability, generate the comprehensive impervious area proportion of the region based on the area proportion of different types of land and the impervious area proportion weight, and generate artificial disturbance parameters based on human activity data and the comprehensive impervious area proportion of the region. The parameter correction module is used to correct natural recharge parameters based on the average values ​​of meteorological and hydrological data, and to correct artificial disturbance parameters based on the cumulative amount of artificial extraction. The model training module is used to build a deep learning network. It takes the natural loss parameters, corrected natural replenishment parameters, and artificial disturbance parameters from the same time period in historical data as inputs, and the groundwater level in the same time period as labels to train the water level prediction model. The integrated output module is used to input the natural loss parameters, corrected natural replenishment parameters, and artificial disturbance parameters of the current time period into the water level prediction model to obtain the predicted groundwater level value for the current time period.

[0015] Compared with the prior art, the beneficial effects of the present invention are: This invention categorizes factors affecting groundwater levels into natural recharge, natural runoff, and human activities. The subsequent deep learning model is fed with pre-processed, high-order features, improving learning efficiency and prediction accuracy. It combines rainfall intensity with river water levels, fully considering the impact of natural rainfall and river inflow on groundwater levels. In calculating natural runoff, it takes into account real-time monitorable evaporation and runoff, and for water absorbed by vegetation—which is difficult to monitor directly—it describes the amount through vegetation growth, more accurately reflecting the actual total water loss.

[0016] This invention also corrects the calculated natural recharge parameters and artificial disturbance parameters by distinguishing the impact of different seasons on evaporation and the impact of historical data. The model is trained based on the corrected data, so that the data output by the model is more consistent with the actual situation of the groundwater system, and the effective integration and collaborative utilization of multi-source data is achieved. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the method flow of an embodiment of the present invention; Figure 2 This is a schematic diagram of the fitting curve of the vegetation water consumption evaluation index in an embodiment of the present invention. Figure 3 This is a schematic diagram of the system modules in an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0019] It should be noted that, unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0020] Example: Please see Figures 1 to 3 The present invention provides a technical solution: A groundwater level prediction method based on multi-source data, comprising the following steps: Step 1: Collect water level data, meteorological data, hydrological data, geological data, remote sensing data, and human activity data for the target area over previous time periods; In this embodiment, the time period is one day, and the water level data, meteorological data, hydrological data, geological data, and remote sensing data are all averaged values ​​collected multiple times within one day. The meteorological data includes precipitation intensity, evaporation intensity, and ambient temperature; the hydrological data includes data representing river water level and groundwater runoff; the geological data includes soil permeability coefficient and soil aquifer thickness; the remote sensing data represents the normalized difference vegetation index of the target area; the human activity data includes groundwater extraction and land use types, including forest land, grassland, water area, agricultural land, and urban land; based on groundwater monitoring wells, through... Ultrasonic water level gauges record water level changes and collect water level data; precipitation intensity is obtained through weather radar, evaporation intensity through evaporation sensors, and ambient temperature is recorded through weather station temperature sensors; river water level data is obtained through water level stations, and groundwater runoff is obtained through groundwater flow meters (both of which can be obtained from hydrological stations); soil permeability coefficients are experimentally determined based on different soil types, and soil aquifer thickness is obtained through geological boreholes; red and near-infrared band data are obtained through multispectral remote sensing satellites, and then the normalized differential vegetation index is calculated; and human groundwater extraction is calculated through well flow meters. Z-score standardization was applied to water level data, meteorological data, and hydrological data, and all data used in subsequent calculations were Z-score standardized data.

[0021] The principle behind Z-score standardization of data is as follows: Taking precipitation intensity as an example, when standardizing the precipitation intensity of any given day, the precipitation intensity data of the previous 5 days are also obtained, and the average precipitation intensity of these days is... The standard deviation of precipitation intensity is Then the standardized precipitation intensity is: ,in This represents the standardized precipitation intensity. This indicates the precipitation intensity during the current data collection period; following the above method, other data requiring standardization are then standardized.

[0022] Step 2: Calculate the area ratio of different types of land in the target area, and generate natural replenishment parameters for the target area based on meteorological data, hydrological data, and the area ratio of different types of land; calculate the vegetation water consumption evaluation index based on remote sensing data, and then calculate the groundwater evaporation loss index, and combine the evaporation loss index with geological data to generate natural loss parameters. In this embodiment, the principle underlying the generation of natural replenishment parameters is as follows: The land use types of the target area are classified, and the area proportion of different land types is calculated using the following formula: ; in, Indicates the first The proportion of land area of ​​type 3 to the total area of ​​the target area An index representing land types, and , Indicates the quantity of land types. Indicates the first Land area of ​​type, Indicates the total area of ​​the target region; Different types of land have significantly different soil types and geological data, so they will be discussed separately.

[0023] The formula used to calculate the natural replenishment parameter is: ; in, Indicates the natural supply parameter. Indicates precipitation intensity. The weighting coefficient representing the intensity of precipitation, and , Indicates the precipitation replenishment index. Indicates the river water level. The weighting coefficient represents the river water level, and , Indicates the first Soil permeability coefficient of land-like soil Indicates the first River replenishment index for land-like terrain.

[0024] Natural recharge parameters reflect the contribution of natural factors (mainly precipitation and river infiltration) to groundwater recharge over a period of time. Precipitation is the most significant source of groundwater recharge, while river level reflects the state of surface water bodies. Higher river levels promote river infiltration and recharge of groundwater along the banks. This infiltration is influenced by the soil permeability coefficient; the higher the soil permeability coefficient, the greater the contribution of river infiltration. The precipitation recharge index reflects the direct contribution of precipitation to groundwater recharge. Precipitation is the most direct influencing factor on groundwater recharge; the greater the precipitation, the greater the contribution, and the two have an approximately linear relationship. Precipitation intensity always has a positive promoting effect on groundwater recharge, hence the weighting coefficient for precipitation intensity... The value is positive, and it is impossible to completely prevent rainwater infiltration, therefore The lower limit is set at 0.5 to avoid the situation where "precipitation has no impact on the groundwater level at all", and the upper limit is set at 2, which means that the contribution of precipitation is allowed to be amplified by 100%, while preventing a single feature from becoming too dominant. The river recharge index represents the non-linear effect of river water level on groundwater recharge. When river water level is very low, there is no direct correlation between river water level and groundwater changes; at this point, the contribution of river water level is zero. When a certain threshold is exceeded, the river begins to infiltrate and recharge groundwater, and this infiltration intensifies as the river water level rises. Furthermore, the infiltration effect of rivers on groundwater is influenced by the soil permeability coefficient. Different soil permeability coefficients are determined for different types of land. The soil permeability coefficient represents the velocity of water flowing through soil pores under a unit hydraulic gradient. The higher the soil permeability coefficient, the stronger the land's ability to infiltrate water, and the stronger the river's influence on groundwater recharge. River water level has a positive effect on groundwater recharge, allowing its contribution to be very small. Moreover, the effect of river recharge is affected by distance, geological conditions, etc., and is generally weaker than the effect of direct precipitation. The range of values ​​is ; The principle underlying the generation of natural loss parameters is as follows: The formula used to calculate the vegetation water consumption evaluation index based on the normalized difference vegetation index is as follows: ; in, This represents the vegetation water consumption evaluation index. Indicates the normalized difference vegetation index. Indicates ambient temperature. This indicates the ambient temperature at which vegetation transpiration is strongest in the target area. The vegetation water consumption evaluation index reflects the ability of vegetation to consume groundwater through transpiration. The Normalized Difference Vegetation Index (NDVI) measures vegetation cover and growth status. The higher the value, the more lush the vegetation, the stronger the overall transpiration of the vegetation, the greater the water consumption, and the higher the vegetation water consumption evaluation index. It is inversely proportional to the vegetation water consumption evaluation index and inversely proportional to the vegetation water consumption. The vegetation water consumption evaluation index is used to reflect the impact of temperature on vegetation transpiration. The temperature at which vegetation transpiration is strongest is used as the benchmark. The closer the actual ambient temperature is to this benchmark (i.e., the higher the actual ambient temperature), the higher the vegetation water consumption. The vegetation water consumption evaluation index is directly proportional to the ambient temperature and inversely proportional to the temperature difference, where the temperature difference represents the difference between the actual ambient temperature and the ambient temperature corresponding to the peak of vegetation transpiration. Table 1 shows the changes in the vegetation water consumption evaluation index with the normalized difference vegetation index and ambient temperature. It can be seen The smaller the value, the greater the vegetation water consumption evaluation index.

[0025] Table 1. Variation of Vegetation Water Consumption Evaluation Index with NDVI and Ambient Temperature

[0026] The evaporation loss index is generated based on the vegetation water consumption evaluation index and evaporation intensity, using the following formula: ; in, Indicates the evaporation loss index. Indicates evaporation intensity; The evaporation loss index reflects the total evaporation intensity of groundwater in a target area, including evaporation from the surface and evaporation from vegetation; it is measured by evaporation intensity. The amount of water evaporating from the Earth's surface is evaluated, and the evaporation intensity is regulated by the transpiration of vegetation.

[0027] The seasonal correction coefficient for evaporation intensity is adjusted based on seasonal settings, and the groundwater runoff is adjusted based on the soil moisture index to generate natural loss parameters. The formula used is as follows: ; in, Indicates the natural loss parameter. Indicates the evaporation loss index. This represents the seasonal correction factor, and in summer... In winter Spring and Autumn , Indicates the first The thickness of the soil aquifer in land-like soils, These represent the weighting coefficients for the evaporation loss index and the groundwater runoff index, respectively. and .

[0028] Natural loss parameters reflect the intensity of groundwater evaporation loss and runoff loss within the target area. This reflects groundwater evaporation. The evaporation loss index is adjusted for different seasons. Summer has the strongest average solar radiation of the year, and plants are mostly in their vigorous growth period, leading to peak evaporation. Therefore, the actual evaporation in summer is much higher than the annual average. A seasonal correction factor is used to amplify the base evaporation loss index by 20% to capture this seasonally enhanced evaporation effect. Winter has weak solar radiation, low temperatures, and vegetation is mostly dormant. Soil may also freeze, resulting in evaporation far below the annual average. Therefore, the base evaporation loss index is reduced by 20% to reflect the seasonal inhibition effect. Spring and autumn have relatively moderate temperatures and sunshine, and evaporation is close to the annual average. No additional adjustments will be made. This reflects the reduction of groundwater caused by groundwater runoff. This process is mainly affected by the thickness of the soil aquifer. The thicker the aquifer, the stronger its water storage capacity, the greater the flow resistance, and the slower the runoff rate. Conversely, the thinner the aquifer, the weaker its water storage capacity, the easier it is for water to flow out, and the faster the runoff rate. Runoff loss is inversely proportional to aquifer thickness. Different land types have different aquifer thicknesses; therefore, the groundwater runoff index is calculated separately for each land type and summed to reflect the overall groundwater runoff intensity of the target area. Evaporation is the main pathway for groundwater loss. ,Pick , .

[0029] Step 3: Assign impervious area proportion weights to different types of land in the target area based on permeability; generate the overall impervious area proportion of the region based on the area proportions of different types of land and the impervious area proportion weights; and generate artificial disturbance parameters based on human activity data and the overall impervious area proportion of the region. In this embodiment, the principle underlying the generation of the overall impermeable area ratio is as follows: The land use types in the target area are classified into forest land, grassland, water area, agricultural land, and urban land. A weighted average of the impervious area proportions is assigned to each land type: forest land 0.1, grassland 0.1, water area 0.01, agricultural land 0.2, and urban land 0.8. The overall impervious area proportion for the region is then calculated by weighting the proportions of each land type with their respective impervious area proportions. The formula used is as follows: ; in, This indicates the proportion of the overall impermeable area in the region. Indicates the first Weighting of the proportion of impermeable area for each land type.

[0030] The regional comprehensive impervious area ratio reflects the degree of decline in surface permeability caused by changes in land use due to human activities, i.e., it reflects the impact of different types of land on surface runoff and groundwater recharge capacity. A higher impervious area ratio indicates that the surface is less susceptible to water infiltration, resulting in less groundwater recharge. The weighting of the impervious area ratio is based on the land's permeability. This is used to quantify the ability of different land types to impede precipitation infiltration. The value is between 0 and 1, and The smaller the value, the weaker the surface's ability to prevent rainwater infiltration, the more rainwater seeps into the ground, and the more it replenishes the groundwater. The larger the area, the stronger the surface's ability to impede rainwater infiltration, making it more difficult for rainwater to penetrate the ground. In areas with high human activity, such as urban land, the surface is often covered by materials with extremely poor permeability, such as cement and asphalt, making it difficult for rainwater to infiltrate. Therefore, the proportion of impermeable area in such land has a higher weighting. In natural environments such as woodlands and grasslands, the surface is mostly soil and vegetation, offering almost no obstruction to rainwater replenishment; therefore, the proportion of impermeable area has a lower weighting. The overall proportion of impermeable area in the target area is calculated by combining all land types within the target area. , The larger the value, the stronger the ability of the target area to prevent rainwater from seeping into the ground.

[0031] The mathematical expression upon which the artificial perturbation parameters are based is: ; in, Indicates the parameters of artificial perturbation. This indicates the amount of groundwater extracted. This term represents the synergistic relationship between groundwater extraction volume and the proportion of the overall impermeable area in a region. These represent the weighting coefficients of groundwater extraction volume, the proportion of the overall impermeable area in the region, and the synergistic term, respectively. ,and .

[0032] Artificial disturbance parameters reflect the direct impact of human activities on the groundwater system, mainly including groundwater extraction and changes in land type caused by human activities, which in turn affect precipitation infiltration. This reflects the negative impact of direct mining on groundwater levels. This indicates the amount of groundwater extracted. The larger the value, the more groundwater is extracted and the more severe the impact of human activities. This reflects the indirect impact of land use type on the groundwater system. The higher the proportion of impermeable area, the weaker the rainwater infiltration capacity, the less natural recharge, which indirectly leads to a drop in the groundwater level. This reflects the synergistic effect of groundwater extraction and impermeable area. Higher elevations generally indicate higher levels of urbanization. In these areas, groundwater extraction makes groundwater regeneration more difficult, thus amplifying the impact of human activities. While direct extraction directly affects groundwater, the overall proportion of impermeable surface area in a region indirectly impacts groundwater levels. ,Pick , , .

[0033] Step 4: Correct the natural recharge parameters based on the average values ​​of meteorological and hydrological data, and correct the artificial disturbance parameters based on the cumulative amount of artificial extraction. In this embodiment, the principle underlying the correction of the natural replenishment parameter is as follows: For each time period, the average precipitation intensity and average evaporation intensity of the past 7 days were statistically analyzed and standardized using the Z-score. The soil moisture index was calculated based on the average precipitation intensity and average evaporation intensity using the following formula: ; in, Indicates soil moisture index, This represents the standardized average precipitation intensity. This represents the standardized average evaporation intensity; The soil moisture index is calculated based on the current dryness and wetness of the soil, using historical data on average precipitation intensity and average evaporation intensity. Higher precipitation intensity indicates higher soil moisture, but also a lower amount of water that the soil can absorb, meaning more precipitation is used to replenish groundwater rather than being absorbed by the soil. Conversely, lower precipitation intensity indicates lower soil moisture, but also a higher amount of water that the soil can absorb, meaning a larger portion of precipitation is absorbed by the soil and does not flow into the ground. Soil moisture is calculated based on average precipitation intensity and average evaporation intensity; a higher average precipitation intensity indicates a higher soil moisture index and more moist soil. The formula for correcting the natural replenishment parameter is: ; in, This represents the corrected natural supply parameter. Indicates the natural supply parameter; This represents a correction factor for the natural recharge parameter, based on the soil moisture index. A higher soil moisture index indicates that, under the influence of precipitation and evaporation over the past 7 days, more water from natural recharge has entered the groundwater system rather than the dry soil. The calculated... The closer the soil moisture index is to the true value, the smaller the correction required. A lower soil moisture index indicates drier soil; naturally replenished water is preferentially absorbed by the drier soil before entering groundwater. Therefore, the calculated... To reduce the size further, the soil's ability to absorb water should be taken into account.

[0034] The principle underlying the correction of artificial disturbance parameters is as follows: For each time period, the net groundwater extraction volume over the past 30 days is calculated to generate a cumulative effect index, based on the following formula: ; in, Indicates the cumulative effect index. This represents the sensitivity coefficient, and , This indicates the net amount of groundwater extracted over the past 30 days. Indicates the threshold for extraction volume. Let be the hyperbolic tangent function, Values ​​mapped to between; The corrected artificial disturbance parameters are: ; in, This represents the corrected artificial perturbation parameters. This represents the parameters of artificial disturbance.

[0035] The purpose of correcting for artificial disturbance parameters is to reflect the cumulative effect of groundwater extraction activities, that is, the continuous impact of long-term extraction on the groundwater system. This represents the cumulative intensity of human mining activities over the past 30 days, calculated as total extraction minus reinjection. It is a preset threshold, determined based on the sustainable exploitable volume of groundwater. The purpose is to Limited to Between, the cumulative effect coefficient The value is ,when When this occurs, it indicates that the net groundwater extraction is positive, the cumulative effect of extraction is enhanced, and the artificial disturbance parameters are amplified. hour, This indicates that there is no cumulative effect over the past 30 days, and no correction is required. This indicates that there is still backflow. The impact of human activities on the groundwater system has been mitigated.

[0036] Step 5: Construct a deep learning network, using the natural loss parameters, corrected natural replenishment parameters, and artificial disturbance parameters from the same time period in historical data as input, and the groundwater level in the same time period as the label, to train the water level prediction model. In this embodiment, the constructed deep learning network structure is as follows: Input layer: Contains 3 neurons, used to input natural loss parameters, as well as corrected natural replenishment parameters and artificial perturbation parameters; The first hidden layer contains 64 neurons, activated using the ReLU activation function; The second hidden layer contains 32 neurons, activated using the ReLU activation function; The third hidden layer contains 16 neurons, activated using the ReLU activation function; Output layer: Contains 1 neuron, used to output the groundwater level; The following natural loss parameters, corrected natural replenishment parameters, and corrected artificial disturbance parameters from the same time period in historical data are used as input features, and the actual observed groundwater level at the corresponding time is used as the label. Daily data from the past few years (e.g., 3-5 years) are used as the training set to ensure coverage of different seasons and extreme climate conditions. The mean squared error function is used as the loss function, and the loss function is minimized through backpropagation. The most recent year's data is selected from the historical data as the validation set, and the loss is calculated using the validation set. Training stops when the loss on the validation set no longer decreases, and the current model is saved.

[0037] Step 6: Input the natural loss parameters, corrected natural recharge parameters, and artificial disturbance parameters for the current time period into the water level prediction model to obtain the predicted groundwater level for the current time period.

[0038] Please see Figure 3 The present invention also provides a groundwater level prediction system based on multi-source data. The system is used to implement the above-mentioned groundwater level prediction method based on multi-source data, specifically including: The data acquisition module is used to collect water level data, meteorological data, hydrological data, geological data, remote sensing data, and human activity data of the target area over a previous time period. The natural activity calculation module is used to calculate the area ratio of different types of land in the target area, and generate natural replenishment parameters for the target area based on meteorological data, hydrological data and the area ratio of different types of land; it calculates the vegetation water consumption evaluation index based on remote sensing data, and then calculates the groundwater evaporation loss index, and combines the evaporation loss index with geological data to generate natural loss parameters. The human activity calculation module is used to allocate the proportion weight of impervious area to different types of land in the target area based on permeability, generate the comprehensive impervious area proportion of the region based on the area proportion of different types of land and the impervious area proportion weight, and generate artificial disturbance parameters based on human activity data and the comprehensive impervious area proportion of the region. The parameter correction module is used to correct natural recharge parameters based on the average values ​​of meteorological and hydrological data, and to correct artificial disturbance parameters based on the cumulative amount of artificial extraction. The model training module is used to build a deep learning network. It takes the natural loss parameters, corrected natural replenishment parameters, and artificial disturbance parameters of the same time period in historical data as inputs, and the groundwater level at the corresponding time as the label to train the water level prediction model. The integrated output module is used to calculate the natural loss parameters, corrected natural replenishment parameters, and artificial disturbance parameters in real time based on the steps of the natural activity calculation module, human activity calculation module, and parameter correction module. It inputs the three real-time parameters into the water level prediction model and outputs the real-time groundwater level prediction value.

[0039] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0040] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0041] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0042] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A groundwater level prediction method based on multi-source data, characterized in that, The specific steps include: Step 1: Collect water level data, meteorological data, hydrological data, geological data, remote sensing data, and human activity data for the target area over previous time periods; Step 2: Calculate the area ratio of different types of land in the target area, and generate natural replenishment parameters for the target area based on meteorological data, hydrological data, and the area ratio of different types of land; calculate the vegetation water consumption evaluation index based on remote sensing data, and then calculate the groundwater evaporation loss index, and combine the evaporation loss index with geological data to generate natural loss parameters. Step 3: Assign impervious area proportion weights to different types of land in the target area based on permeability; generate the overall impervious area proportion of the region based on the area proportions of different types of land and the impervious area proportion weights; and generate artificial disturbance parameters based on human activity data and the overall impervious area proportion of the region. Step 4: Correct the natural recharge parameters based on the average values ​​of meteorological and hydrological data, and correct the artificial disturbance parameters based on the cumulative amount of artificial extraction. Step 5: Construct a deep learning network, using the natural loss parameters, corrected natural replenishment parameters, and artificial disturbance parameters from the same time period in historical data as input, and the groundwater level in the same time period as the label, to train the water level prediction model. Step 6: Input the natural loss parameters, corrected natural recharge parameters, and artificial disturbance parameters for the current time period into the water level prediction model to obtain the predicted groundwater level for the current time period.

2. The groundwater level prediction method based on multi-source data according to claim 1, characterized in that: In step 1, the time period is one day, and the water level data, meteorological data, hydrological data, geological data, and remote sensing data are all averaged from multiple collections within one day. The meteorological data includes precipitation intensity, evaporation intensity, and ambient temperature; the hydrological data includes river water level and groundwater runoff; the geological data includes soil permeability coefficient and soil aquifer thickness; the remote sensing data represents the normalized difference vegetation index of the target area; and the human activity data includes groundwater extraction and land use types, including forest land, grassland, water area, agricultural land, and urban land. The water level data, meteorological data, and hydrological data are Z-score standardized, and all data used in subsequent calculations are Z-score standardized data.

3. The groundwater level prediction method based on multi-source data according to claim 2, characterized in that: The principle underlying the generation of natural replenishment parameters in step 2 is as follows: The land use types of the target area are classified, and the area proportion of different land types is calculated using the following formula: ； in, Indicates the first The proportion of land area of ​​type 3 to the total area of ​​the target area An index representing land types, and , Indicates the quantity of land types. Indicates the first Land area of ​​type, Indicates the total area of ​​the target region; The formula used to calculate the natural replenishment parameter is: ； in, Indicates the natural supply parameter. Indicates precipitation intensity. The weighting coefficient representing the intensity of precipitation, and , Indicates the precipitation replenishment index. Indicates the river water level. The weighting coefficient represents the river water level, and , Indicates the first Soil permeability coefficient of land-like soil Indicates the first River replenishment index for land-like terrain.

4. The groundwater level prediction method based on multi-source data according to claim 3, characterized in that: The principle underlying the generation of natural loss parameters in step 2 is as follows: The formula used to calculate the vegetation water consumption evaluation index based on the normalized difference vegetation index is as follows: ； in, This represents the vegetation water consumption evaluation index. Indicates the normalized difference vegetation index. Indicates ambient temperature. This indicates the ambient temperature at which vegetation transpiration is strongest in the target area. The evaporation loss index is generated based on the vegetation water consumption evaluation index and evaporation intensity, using the following formula: ； in, Indicates the evaporation loss index. Indicates evaporation intensity; The seasonal correction coefficient for evaporation intensity is adjusted based on seasonal settings, and the groundwater runoff is adjusted based on the soil moisture index to generate natural loss parameters. The formula used is as follows: ； in, Indicates the natural loss parameter. Indicates the evaporation loss index. This represents the seasonal correction factor, and in summer... In winter Spring and Autumn , Indicates the first The thickness of the soil aquifer in land-like soils, These represent the weighting coefficients for the evaporation loss index and the groundwater runoff index, respectively. and .

5. The groundwater level prediction method based on multi-source data according to claim 3, characterized in that: The principle underlying the generation of the overall impermeable area ratio in step 3 is as follows: The land use types in the target area are classified into forest land, grassland, water area, agricultural land, and urban land. A weighted average of the impervious area proportions is assigned to each land type: forest land 0.1, grassland 0.1, water area 0.01, agricultural land 0.2, and urban land 0.

8. The overall impervious area proportion for the region is then calculated by weighting the proportions of each land type with their respective impervious area proportions. The formula used is as follows: ； in, This indicates the proportion of the overall impermeable area in the region. Indicates the first Weighting of the proportion of impermeable area for each land type.

6. The groundwater level prediction method based on multi-source data according to claim 5, characterized in that: The mathematical expression used to generate the artificial disturbance parameters in step 3 is as follows: ； in, Indicates the parameters of artificial perturbation. This indicates the amount of groundwater extracted. This term represents the synergistic relationship between groundwater extraction volume and the proportion of the overall impermeable area in a region. These represent the weighting coefficients of groundwater extraction volume, the proportion of the overall impermeable area in the region, and the synergistic term, respectively. ,and .

7. The groundwater level prediction method based on multi-source data according to claim 2, characterized in that: The principle underlying the correction of the natural supply parameters in step 4 is as follows: For each time period, the average precipitation intensity and average evaporation intensity of the past 7 days were statistically analyzed and standardized using the Z-score. The soil moisture index was calculated based on the average precipitation intensity and average evaporation intensity using the following formula: ； in, Indicates soil moisture index, This represents the standardized average precipitation intensity. This represents the standardized average evaporation intensity; The formula for correcting the natural replenishment parameter is: ； in, This represents the corrected natural supply parameter. Indicates the natural supply parameter; The principle underlying the correction of artificial disturbance parameters is as follows: For each time period, the net groundwater extraction volume over the past 30 days is calculated to generate a cumulative effect index, based on the following formula: ； in, Indicates the cumulative effect index. This represents the sensitivity coefficient, and , This indicates the net amount of groundwater extracted over the past 30 days. Indicates the threshold for extraction volume. Let be the hyperbolic tangent function, Values ​​mapped to between; The corrected artificial disturbance parameters are: ； in, This represents the corrected artificial perturbation parameters. This represents the parameters of artificial disturbance.

8. A groundwater level prediction system based on multi-source data, characterized in that: The system is used to implement the groundwater level prediction method based on multi-source data as described in any one of claims 1-7, specifically including: The data acquisition module is used to collect water level data, meteorological data, hydrological data, geological data, remote sensing data, and human activity data of the target area over a previous time period. The natural activity calculation module is used to calculate the area ratio of different types of land in the target area, and generate natural replenishment parameters for the target area based on meteorological data, hydrological data and the area ratio of different types of land; it calculates the vegetation water consumption evaluation index based on remote sensing data, and then calculates the groundwater evaporation loss index, and combines the evaporation loss index with geological data to generate natural loss parameters. The human activity calculation module is used to allocate the proportion weight of impervious area to different types of land in the target area based on permeability, generate the comprehensive impervious area proportion of the region based on the area proportion of different types of land and the impervious area proportion weight, and generate artificial disturbance parameters based on human activity data and the comprehensive impervious area proportion of the region. The parameter correction module is used to correct natural recharge parameters based on the average values ​​of meteorological and hydrological data, and to correct artificial disturbance parameters based on the cumulative amount of artificial extraction. The model training module is used to build a deep learning network. It takes the natural loss parameters, corrected natural replenishment parameters, and artificial disturbance parameters from the same time period in historical data as inputs, and the groundwater level in the same time period as labels to train the water level prediction model. The integrated output module is used to input the natural loss parameters, corrected natural replenishment parameters, and artificial disturbance parameters of the current time period into the water level prediction model to obtain the predicted groundwater level value for the current time period.

Images