Method for constructing three-dimensional geologic structure model coupling geologic structure and groundwater migration

Abstract

The invention relates to a three-dimensional geologic structure model construction method for coupling a geologic structure and underground water migration, provides machine learning, and belongs to the field of computer aided design. The method comprises the following steps: intelligently analyzing underground water transfer information corresponding to a set geographic area in a current time segment by using a transfer information intelligent analysis model corresponding to the set geographic area; and constructing a three-dimensional geologic structure model of the set geographic area in the current time interval according to an intelligent analysis result. Aiming at the technical problem that modeling of a three-dimensional geologic structure model in future time has deviation due to lack of effective underground water transfer information in future time, a transfer information intelligent analysis model which is customized and designed for a current geographic area and based on machine learning is adopted; the effective analysis of the groundwater migration information of the set geographic area in the current time segment serving as a future time segment is completed, so that the technical problem is solved.

Description

Technical Field

[0001] The machine learning proposed in this invention relates to the field of computer-aided design, and in particular to a method for constructing a three-dimensional geological structure model that couples geological structure with groundwater transport. Background Technology

[0002] Training various neural networks using machine learning to obtain artificial intelligence models capable of performing various tasks is a major design pattern used in the field of computer-aided design. For example, when coupling geological structural parameters as static data with groundwater migration information as dynamic data to perform computer-aided design of a three-dimensional geological structural model of a geographical area, both the geological structural parameters as static data and the groundwater migration information as dynamic data can be analyzed separately using different machine learning-based artificial intelligence models. Obviously, groundwater migration information as dynamic data has a greater correlation with time, making its data analysis more difficult.

[0003] For example, Chinese invention patent publication CN104808258A proposes a method for determining the migration path of karst groundwater using sugar as a tracer. Specifically, this method includes the placement and design of delivery wells and monitoring wells, tracer pretreatment, tracer placement, determination of water flow direction, determination of groundwater flow velocity, determination of tracer dosage, placement of tracer in the delivery well, sampling and testing of the tracer in the monitoring well, and analysis of the groundwater migration path based on the results. This application utilizes sugar as a tracer in the detection of karst groundwater flow velocity and direction, offering advantages such as being non-toxic, non-polluting, having a low natural background value, being undisturbed, chemically stable, not altering the groundwater migration direction, easy to detect, highly sensitive, and low-cost. It also does not pollute the environment or pose a health hazard to operators.

[0004] For example, Chinese invention patent publication CN121121957A proposes a method and system for early warning of roof water transport patterns based on clustering algorithms. The method includes: collecting monitoring data and performing data preprocessing; analyzing the correlation and potential relationships between various monitoring data points to determine the number of clusters K; and using methods such as the elbow rule and silhouette coefficient to determine the optimal number of clusters K; applying... The algorithm performs clustering and conducts in-depth analysis of the clustering results; the results are then used for water hazard risk early warning. This application reveals the inherent laws and characteristics of groundwater migration, providing technical support for roof water migration and water hazard early warning decisions, effectively preventing water inrush accidents and ensuring the safety of underground workers.

[0005] However, none of the aforementioned existing technologies involve the effective prediction of groundwater migration information in a given geographical area over future time. This makes it difficult to obtain groundwater migration information for three-dimensional geological structure modeling, or the accuracy of the obtained groundwater migration information is insufficient. Consequently, it is difficult to model the three-dimensional geological structure of the given geographical area over future time, or the obtained three-dimensional geological structure model deviates significantly from the actual geological structure. This makes it impossible to lay out key reference data in advance for future groundwater resource extraction and future underground exploration. Summary of the Invention

[0006] To address technical challenges in this field, this invention provides a method for constructing a three-dimensional geological structure model that couples geological structure with groundwater migration. This method enables the design of machine learning-based intelligent analysis models for transfer information with different customized structures for different geographical regions. Based on selectively chosen multi-source data, it effectively analyzes groundwater migration information within a given geographical region in the current time segment, which is considered a future time segment. Furthermore, by combining various geographical structure parameters corresponding to the given geographical region, it reliably models the intelligent analysis model of transfer information for the given geographical region in future time segments. This facilitates the targeted formulation of groundwater resource extraction strategies and underground exploration strategies for future time segments.

[0007] According to the present invention, a method for constructing a three-dimensional geological structure model that couples geological structure with groundwater migration is provided, the method comprising: Acquire stratigraphic lithology data, porosity, permeability, fault distribution data, aquifer thickness and burial depth within a specified geographic area to serve as various geographic structural parameters corresponding to the specified geographic area; Collect groundwater transfer information for each past time segment before the current time segment for a set geographical area. The groundwater transfer information for each time segment for the set geographical area includes the groundwater level, flow direction indicator, flow velocity, recharge, discharge and hydraulic gradient of the set geographical area within the time segment. The Hofit neural network is subjected to multiple learning processes to obtain an intelligent analysis model of transfer information corresponding to a set geographical area. The number of learning processes performed by the Hofit neural network shows the same numerical trend as the geographical area occupied by the set geographical area. The intelligent analysis model using the transfer information corresponding to the set geographical area analyzes the groundwater transfer information of the set geographical area in the current time segment based on the length of time segment occupied on the time axis, the geographical area occupied by the set geographical area, the various geographical structure parameters corresponding to the set geographical area, and the groundwater transfer information corresponding to each past time segment before the current time segment. Based on the groundwater transfer information corresponding to the current time segment of the set geographical region and the various geographical structure parameters corresponding to the set geographical region, a three-dimensional geological structure model of the set geographical region within the current time interval is constructed.

[0008] Compared with the prior art, the present invention has at least the following five outstanding substantive features: Substantial Feature 1: By using dynamic data of a set geographical region within the current time segment (which is considered a future time segment) and static data corresponding to the set geographical region, a three-dimensional geological structure model of the set geographical region within the future time segment is constructed. The dynamic data consists of groundwater transfer information corresponding to the future time segment, while the static data consists of various geographical structure parameters. Crucially, an artificial intelligence model is used to perform intelligent analysis of the dynamic data, thereby providing key reference data in advance for groundwater resource extraction and underground exploration in the future time segment. Substantial Feature Two: To perform intelligent analysis of groundwater transfer information in a given geographical area at the current time segment, a machine learning-based intelligent analysis model for transfer information with a customized structure for the given geographical area is introduced. The intelligent analysis model for the transfer information of the given geographical area is a Hoffert neural network that has undergone multiple learning processes, and the number of learning processes of the Hoffert neural network shows the same numerical trend as the geographical area occupied by the given geographical area. Different intelligent analysis models for transfer information with customized structures for different geographical areas are provided to ensure the effectiveness and stability of the intelligent analysis results. The third essential feature is that in each learning process performed on the Hofit Neural Network, the known groundwater transfer information corresponding to a certain geographical region at a certain time segment is used as the single output of the Hofit Neural Network. The time length of the time segment on the time axis, the geographical area occupied by the geographical region, the various geographical structural parameters corresponding to the geographical region, and the groundwater transfer information corresponding to each past time segment before the specific time segment are used as the item-by-item input of the Hofit Neural Network to complete the learning process, thereby ensuring the learning effect of each machine learning process. Substantial Feature Four: To perform intelligent analysis of groundwater transfer information corresponding to the current time segment of a set geographical area, various basic data were specifically selected, including the length of time the time segment occupies on the time axis, the geographical area occupied by the set geographical area, the various geographical structure parameters corresponding to the set geographical area, and the groundwater transfer information corresponding to each of the previous time segments of the set geographical area before the current time segment. The multi-source selection of the above basic data further ensures the effectiveness and stability of the intelligent analysis results. Substantive Feature Five: Specifically, the various geographical structural parameters corresponding to the set geographical region are the stratigraphic lithology data, porosity, permeability, fault distribution data, aquifer thickness and burial depth within the set geographical region. The groundwater transfer information corresponding to each time segment of the set geographical region is the groundwater level, flow direction indicator, flow velocity, recharge, discharge and hydraulic gradient within the set geographical region in the time segment. The current time segment starts at the current moment. The current time segment and all previous time segments before the current time segment form a complete time interval on the time axis. The time length occupied by each time segment on the time axis is equal. The number of previous time segments before the selected current time segment is positively correlated with the average aquifer thickness of the surrounding geographical regions. Thus, a customized data structure is designed for the various basic data used for intelligent analysis. Attached Figure Description

[0009] The embodiments of the present invention will now be described with reference to the accompanying drawings, wherein: Figure 1 This is a schematic diagram of the working scenario of the method for constructing a three-dimensional geological structure model that couples geological structure and groundwater migration according to the present invention.

[0010] Figure 2 This is a flowchart illustrating the steps of a three-dimensional geological structure model construction method that couples geological structure with groundwater migration, as shown in Embodiment 1 of the present invention.

[0011] Figure 3 The flowchart illustrates the steps of a method for constructing a three-dimensional geological structure model that couples geological structure with groundwater migration, as shown in Embodiment 2 of the present invention.

[0012] Figure 4 The flowchart illustrates the steps of a method for constructing a three-dimensional geological structure model that couples geological structure with groundwater migration, as shown in Embodiment 3 of the present invention.

[0013] Figure 5 The flowchart illustrates the steps of a method for constructing a three-dimensional geological structure model that couples geological structure with groundwater migration, as shown in Embodiment 4 of the present invention.

[0014] Figure 6 This is a flowchart illustrating the steps of a method for constructing a three-dimensional geological structure model that couples geological structure with groundwater migration, as shown in Embodiment 5 of the present invention. Detailed Implementation

[0015] like Figure 1 The diagram illustrates a working scenario of the method for constructing a three-dimensional geological structure model that couples geological structure with groundwater migration, as presented in this invention. The machine learning method proposed in this invention relates to the field of computer-aided design.

[0016] The specific technical process of this invention is as follows: Technical Process A: To perform intelligent analysis of groundwater transfer information for a defined geographical area in the current time segment, a machine learning-based intelligent analysis model for transfer information, with a customized structure for the defined geographical area, is introduced, such as... Figure 1 As shown; Specifically, the customized structural design of the intelligent analysis model for transfer information corresponding to a geographical region is mainly reflected in the following aspects: Aspect 1: The intelligent analysis model for the transfer information corresponding to the geographical region is set as the Hofit neural network after multiple learning processes; Aspect 2: The number of learning processes performed by the selected Hofit neural network shows the same numerical trend as the geographical area occupied by the set geographical region, thus allowing for customized intelligent analysis models for different transfer information with different structural designs for different geographical regions. Thirdly, in each learning process performed on the Hofit Neural Network, the known groundwater transfer information corresponding to a certain geographical region at a certain time segment is used as the single output of the Hofit Neural Network. The time length of the time segment on the time axis, the geographical area occupied by the geographical region, the various geographical structural parameters corresponding to the geographical region, and the groundwater transfer information corresponding to each past time segment before the certain time segment are used as the input of the Hofit Neural Network to complete the learning process, thereby ensuring the learning effect of each machine learning process. In this way, the effectiveness and stability of the intelligent analysis results are ensured through the customized structural designs mentioned above. Technical Process B: To perform intelligent analysis of groundwater transfer information for a defined geographical area in the current time segment, various basic data were selected in a targeted manner; Specifically, such as Figure 1 As shown, the basic data includes the length of time a time segment occupies on the time axis, the geographical area occupied by the set geographical region, the various geographical structure parameters corresponding to the set geographical region, and the groundwater transfer information corresponding to each past time segment before the current time segment for the set geographical region. More specifically, the various geographical structural parameters corresponding to the geographical region are defined as the stratigraphic lithology data, porosity, permeability, fault distribution data, aquifer thickness and burial depth within the geographical region. The groundwater transfer information corresponding to each time segment of the geographical region is defined as the groundwater level, flow direction, flow velocity, recharge, discharge and hydraulic gradient within the time segment. The current time segment starts at the current moment, and the current time segment and all previous time segments before the current time segment form a complete time interval on the time axis. Each time segment occupies an equal time length on the time axis, and the number of previous time segments before the selected current time segment is positively correlated with the average aquifer thickness of the surrounding geographical regions. This allows for the design of a customized data structure for the various basic data used for intelligent analysis. In this way, by selecting multiple sources of the above-mentioned basic data, the effectiveness and stability of the intelligent analysis results are further guaranteed; Technical Process C: Utilizing Technical Process A, a machine learning-based intelligent analysis model for groundwater transfer information is designed with a customized structure for the specified geographic area. Based on Technical Process B, various basic data are specifically selected to complete the intelligent analysis of groundwater transfer information for the specified geographic area in the current time segment. For example... Figure 1 As shown; Specifically, since the current time segment starts at the current moment, it is a type of future time segment. In this way, the intelligent analysis of the dynamic data of the future time segment of the set geographical area is completed, thereby providing key information for the construction of the three-dimensional geological structure model of the future time segment of the set geographical area. Technical Process D: Using the groundwater transfer information of the designated geographical area obtained from the intelligent analysis in Technical Process C, corresponding to the current time segment, and combining it with various geographical structural parameters of the designated geographical area, a three-dimensional geological structure model of the designated geographical area in future time segments is constructed, such as... Figure 1 As shown; Specifically, the groundwater transfer information of the set geographical area obtained by intelligent analysis in the current time segment is the dynamic data of the set geographical area in the future time segment. Combined with the various geographical structure parameters that are static data of the set geographical area, the three-dimensional geological structure model of the set geographical area in the future time segment is constructed. Therefore, through the coordinated operation of the above-mentioned technical processes, this invention uses dynamic data of a set geographical region in the current time segment (which is a future time segment) and static data corresponding to the set geographical region to complete the construction of a three-dimensional geological structure model of the set geographical region in the future time segment. The dynamic data is the groundwater transfer information corresponding to the future time segment, and the static data is various geographical structure parameters. Crucially, an artificial intelligence model is used to complete the intelligent analysis of the dynamic data, thereby laying out key reference data in advance for the exploitation of groundwater resources and underground exploration in the future time segment.

[0017] The key points of this invention are: intelligent analysis of dynamic data of future time segments of a geographical region, intelligent analysis models of different transfer information with customized structural designs for different geographical regions, targeted design of each learning process of the Hofit neural network, and multi-source selection of various basic data for intelligent analysis.

[0018] The following will describe in detail the method for constructing a three-dimensional geological structure model that couples geological structure and groundwater migration according to the present invention through examples. Example

[0019] Figure 2 This is a flowchart illustrating the steps of a three-dimensional geological structure model construction method that couples geological structure with groundwater migration, as shown in Embodiment 1 of the present invention.

[0020] like Figure 2 As shown, the method for constructing a three-dimensional geological structure model that couples geological structure with groundwater migration includes the following specific steps: Step S201: Obtain stratigraphic lithology data, porosity, permeability, fault distribution data, aquifer thickness and burial depth within the set geographical area as various geographical structural parameters corresponding to the set geographical area. For example, multiple different parameter acquisition devices can be selected to collect stratigraphic lithology data, porosity, permeability, fault distribution data, aquifer thickness and burial depth within a specified geographical area; Obviously, the various geographical structural parameters corresponding to the set geographical region are the static data corresponding to the set geographical region. In order to obtain the three-dimensional geological structure model of the set geographical region in future time segments, it is also necessary to obtain the dynamic data corresponding to the set geographical region, that is, the groundwater transfer information corresponding to the set geographical region in future time segments. The present invention is used to solve the technical problem that the dynamic data is difficult to effectively analyze. Specifically, the technical problem of the present invention is that the lack of effective groundwater transfer information in the future time leads to the deviation in the modeling of the three-dimensional geological structure model in the future time. Step S202: Collect groundwater transfer information for each past time segment before the current time segment for the set geographical area. The groundwater transfer information for the set geographical area in each time segment includes the groundwater level, flow direction, flow velocity, recharge, discharge and hydraulic gradient of the set geographical area in the time segment. Specifically, each time segment occupies an equal amount of time on the timeline. For example, if the current time is 5:00 PM, the current time segment is from 5:00 PM to 5:10 PM. Therefore, the current time segment is a type of future time segment. As a further example, the previous time segments preceding the current time segment can be 4:50 PM to 5:00 PM, 4:40 PM to 4:50 PM, 4:30 PM to 4:40 PM, 4:20 PM to 4:30 PM, 4:10 PM to 4:20 PM, 4:00 PM to 4:10 PM, 3:50 PM to 4:00 PM, 3:40 PM to 3:50 PM, 3:30 PM to 3:40 PM, 3:20 PM to 3:30 PM, 3:10 PM to 3:20 PM, and 3:00 PM to 3:10 PM, for a total of 12 time segments. Step S203: Perform multiple learning processes on the Hofit neural network to obtain an intelligent analysis model of transfer information corresponding to the set geographical area. The number of learning processes performed by the Hofit neural network shows the same numerical change trend as the geographical area occupied by the set geographical area. For example, the number of learning processes performed by the Hofit neural network shows the same numerical trend as the geographical area occupied by the set geographical region, including: when the geographical area occupied by the set geographical region is 1 square kilometer, the selected Hofit neural network performs 200 learning processes; when the geographical area occupied by the set geographical region is 2 square kilometers, the selected Hofit neural network performs 400 learning processes; when the geographical area occupied by the set geographical region is 3 square kilometers, the selected Hofit neural network performs 600 learning processes; when the geographical area occupied by the set geographical region is 4 square kilometers, the selected Hofit neural network performs 800 learning processes, and so on. Step S204: Using the intelligent analysis model of the transfer information corresponding to the set geographical area, based on the time length of the time segment on the time axis, the geographical area occupied by the set geographical area, the various geographical structure parameters corresponding to the set geographical area, and the groundwater transfer information corresponding to each past time segment before the current time segment, the intelligent analysis model of the groundwater transfer information corresponding to the set geographical area in the current time segment is used. In this way, intelligent analysis of dynamic data of a set geographical area in the current time segment that belongs to a future time segment is completed, providing key data for the subsequent construction of a three-dimensional geological structure model of the set geographical area in the current time interval; Step S205: Construct a three-dimensional geological structure model of the set geographical region within the current time interval based on the groundwater transfer information corresponding to the set geographical region in the current time segment and the various geographical structure parameters corresponding to the set geographical region; In this way, the constructed three-dimensional geological structure model of the specified geographical area within the current time interval contains both dynamic and static data, thus completing the full data analysis of the three-dimensional geological structure model; The current time segment starts at the current moment. The current time segment and all previous time segments before the current time segment form a complete time interval on the time axis, and each time segment occupies an equal time length on the time axis. Among them, the collection of groundwater transfer information corresponding to each past time segment before the current time segment for the selected geographical area includes: the number of each past time segment before the selected current time segment is positively correlated with the average aquifer thickness of each geographical area surrounding the selected geographical area; For example, a positive correlation between the number of previous time segments before the selected current time segment and the average aquifer thickness of the surrounding geographic regions includes: the average aquifer thickness of the surrounding geographic regions is 5 meters, the number of previous time segments before the selected current time segment is 6, the average aquifer thickness of the surrounding geographic regions is 10 meters, the number of previous time segments before the selected current time segment is 12, the average aquifer thickness of the surrounding geographic regions is 15 meters, the number of previous time segments before the selected current time segment is 18, the average aquifer thickness of the surrounding geographic regions is 20 meters, the number of previous time segments before the selected current time segment is 24, and so on. Among them, the intelligent analysis model for the transfer information corresponding to the geographical region is set as the Hofit neural network after multiple learning processes; In each learning process performed on the Hofit Neural Network, the known groundwater transfer information corresponding to a certain geographical region in a certain time segment is used as the single output of the Hofit Neural Network, and the time length occupied by the time segment on the time axis, the geographical area occupied by the geographical region, the various geographical structural parameters corresponding to the geographical region, and the groundwater transfer information corresponding to each past time segment before the certain time segment are used as the item-by-item input of the Hofit Neural Network to complete this learning process. Among them, the number of learning processes performed by the Hofit neural network and the geographical area occupied by the set geographical region show the same numerical change trend, including: using a first numerical change curve to represent the numerical change trend of the geographical area occupied by the set geographical region, and using a second numerical change curve to represent the numerical change trend of the number of learning processes performed by the Hofit neural network. Specifically, programmable logic devices can be used to simulate and test the first and second numerical change curves respectively; Furthermore, the fact that the number of learning processes performed by the Hofit neural network shows the same numerical change trend as the geographical area occupied by the set geographical region also includes: the curvature values ​​at uniform intervals on the first numerical change curve are the same as the curvature values ​​at uniform intervals on the second numerical change curve, and the number of uniform intervals on the first numerical change curve is equal to the number of uniform intervals on the second numerical change curve. Example

[0021] Figure 3 The flowchart illustrates the steps of a method for constructing a three-dimensional geological structure model that couples geological structure with groundwater migration, as shown in Embodiment 2 of the present invention.

[0022] like Figure 3 As shown, with Figure 2 Unlike the previous embodiment, in the method for constructing a three-dimensional geological structure model that couples geological structure and groundwater transport, after constructing a three-dimensional geological structure model of a set geographical region within the current time interval based on the groundwater transfer information corresponding to the set geographical region in the current time segment and the various geographical structure parameters corresponding to the set geographical region, i.e. after step S205, the method further includes: Step S206: Receive the three-dimensional geological structure model of the set geographical area within the current time interval, and perform on-site display of the three-dimensional geological structure model of the set geographical area within the current time interval; The process of receiving a three-dimensional geological structure model of a set geographical area within the current time interval and displaying the three-dimensional geological structure model of the set geographical area within the current time interval includes: using a field display device installed in the ground control room to receive a three-dimensional geological structure model of a set geographical area within the current time interval and display the three-dimensional geological structure model of the set geographical area within the current time interval. For example, a field display device set up in a ground control room is used to receive a three-dimensional geological structure model of a set geographical area within the current time interval, and to perform field display on the three-dimensional geological structure model of the set geographical area within the current time interval. The field display device can be an LED display array or a liquid crystal display screen. Example

[0023] Figure 4 The flowchart illustrates the steps of a method for constructing a three-dimensional geological structure model that couples geological structure with groundwater migration, as shown in Embodiment 3 of the present invention.

[0024] like Figure 4 As shown, with Figure 2 Unlike the previous embodiment, in the method for constructing a three-dimensional geological structure model that couples geological structure and groundwater transport, after constructing a three-dimensional geological structure model of a set geographical region within the current time interval based on the groundwater transfer information corresponding to the set geographical region in the current time segment and the various geographical structure parameters corresponding to the set geographical region, i.e. after step S205, the method further includes: Step S207: Wirelessly transmit the three-dimensional geological structure model of the set geographical area within the current time interval to the remote groundwater management server; The process of wirelessly transmitting a three-dimensional geological structure model of a set geographical area within the current time interval to a remote groundwater management server includes: wirelessly transmitting a three-dimensional geological structure model of a set geographical area within the current time interval to a remote groundwater management server via a two-way wireless communication link. For example, wirelessly transmitting a three-dimensional geological structure model of a set geographical area within the current time interval to a remote groundwater management server via a two-way wireless communication link includes: the wireless communication link being based on a frequency division duplex communication mechanism or a time division duplex communication mechanism. Example

[0025] Figure 5 The flowchart illustrates the steps of a method for constructing a three-dimensional geological structure model that couples geological structure with groundwater migration, as shown in Embodiment 4 of the present invention.

[0026] like Figure 5 As shown, with Figure 2Unlike the previous embodiment, in the method for constructing a three-dimensional geological structure model that couples geological structure and groundwater migration, before acquiring stratigraphic lithology data, porosity, permeability, fault distribution data, aquifer thickness and burial depth within a set geographical area as various geographical structure parameters corresponding to the set geographical area, i.e., before step S201, the method further includes: Step S208: Divide each geographic region to obtain the set geographic region and other geographic regions surrounding the set geographic region; The process of dividing geographical regions to obtain a set geographical region and other geographical regions surrounding the set geographical region includes: dividing geographical regions using a user setting mode to obtain a set geographical region and other geographical regions surrounding the set geographical region. Specifically, for the designated geographical region and other geographical regions surrounding the designated geographical region, different geographical regions have different geographical region identifiers. Specifically, for a given geographic region and other geographic regions surrounding the given geographic region, different geographic regions have different geographic region identifiers, including: different geographic region identifiers are different binary values. Example

[0027] Figure 6 This is a flowchart illustrating the steps of a method for constructing a three-dimensional geological structure model that couples geological structure with groundwater migration, as shown in Embodiment 5 of the present invention.

[0028] like Figure 6 As shown, with Figure 2 Unlike the previous embodiment, in the method for constructing a three-dimensional geological structure model that couples geological structure and groundwater migration, after performing multiple learning processes on the Hoffer neural network to obtain an intelligent analysis model of transfer information corresponding to a set geographical area, and after the number of learning processes performed by the Hoffer neural network shows the same numerical trend as the geographical area occupied by the set geographical area, i.e., after step S203, the method further includes: Step S209: Receive the intelligent analysis model of transfer information corresponding to the set geographical area, and store the intelligent analysis model of transfer information corresponding to the set geographical area; The process of receiving and storing the intelligent analysis model of transfer information corresponding to a set geographical area includes: storing the model of the intelligent analysis model of transfer information corresponding to the set geographical area by storing the various model parameters of the intelligent analysis model of transfer information corresponding to the set geographical area. Specifically, the model storage of the intelligent analysis model for the transfer information corresponding to the set geographical area is completed by storing the various model parameters of the model for the set geographical area. This includes storing each model parameter in a different physical address.

[0029] Next, the various method embodiments of the present invention will be described in detail.

[0030] In the method for constructing a three-dimensional geological structure model that couples geological structure and groundwater migration according to various embodiments of the present invention: The data obtained include stratigraphic lithology, porosity, permeability, fault distribution, aquifer thickness and burial depth within a specified geographic area. These data are used as various geographic structural parameters corresponding to the specified geographic area. The stratigraphic lithology data within the specified geographic area includes the stratigraphic lithology type identifier, mineral content and rock layer thickness. Specifically, the stratigraphic lithology data within a geographic region is defined as the stratigraphic lithology type identifier, mineral content, and stratum thickness within the geographic region. The specific values ​​of the stratigraphic lithology data within the geographic region are binary data formed by sequentially concatenating the three binary values ​​corresponding to the stratigraphic lithology type identifier, mineral content, and stratum thickness within the geographic region. Among them, obtaining stratigraphic lithology data, porosity, permeability, fault distribution data, aquifer thickness and burial depth within a set geographical area as various geographical structural parameters corresponding to the set geographical area also includes: stratigraphic lithology types include pure mudstone, pure sandstone and semi-mudstone / sandstone. Among them, obtaining stratigraphic lithology data, porosity, permeability, fault distribution data, aquifer thickness and burial depth within a set geographical area as various geographical structural parameters corresponding to the set geographical area also includes: the aquifer thickness and burial depth within the set geographical area are the aquifer thickness and aquifer burial depth within the set geographical area.

[0031] In the method for constructing a three-dimensional geological structure model that couples geological structure and groundwater migration according to various embodiments of the present invention: The groundwater transfer information corresponding to each time segment of a set geographical area includes the groundwater level, flow direction indicator, flow velocity, recharge, discharge and hydraulic gradient of the set geographical area within the time segment. The hydraulic gradient of the set geographical area within the time segment is the difference in water level between the start and end positions of the groundwater channel in the set geographical area within the time segment divided by the length of the groundwater channel in the set geographical area within the time segment. Specifically, the length calculation formula can be used to calculate the specific value of the difference between the water level at the beginning and end of the groundwater channel in the set geographical area within the time segment, divided by the length of the groundwater channel in the set geographical area within the time segment. The groundwater transfer information corresponding to each time segment of the set geographical area includes the groundwater level, flow direction, flow velocity, recharge, discharge and hydraulic gradient of the set geographical area within the time segment. It also includes the groundwater level of the set geographical area within the time segment as the average of the water level difference between the start and end positions of the groundwater channel within the time segment of the set geographical area. The groundwater transfer information corresponding to each time segment of the set geographical area includes the groundwater level, flow direction, flow velocity, recharge, discharge and hydraulic gradient of the set geographical area within the time segment. It also includes the recharge of the set geographical area within the time segment as the inflow of groundwater into the set geographical area within the time segment. The groundwater transfer information corresponding to each time segment of the set geographical area includes the groundwater level, flow direction, flow velocity, recharge, discharge and hydraulic gradient of the set geographical area within the time segment. It also includes the discharge of the set geographical area within the time segment as the outflow of groundwater from the set geographical area within the time segment.

[0032] And in the method for constructing a three-dimensional geological structure model that couples geological structure with groundwater migration according to various method embodiments of the present invention: The intelligent analysis model for the transfer information corresponding to the set geographical area uses the time length of the time segment on the time axis, the geographical area occupied by the set geographical area, the various geographical structural parameters corresponding to the set geographical area, and the groundwater transfer information corresponding to each of the previous time segments before the current time segment to intelligently analyze the groundwater transfer information corresponding to the set geographical area in the current time segment. This includes: synchronously inputting the time length of the time segment on the time axis, the geographical area occupied by the set geographical area, the various geographical structural parameters corresponding to the set geographical area, and the groundwater transfer information corresponding to each of the previous time segments before the current time segment into the intelligent analysis model for the transfer information corresponding to the set geographical area. Specifically, a PLC chip can be selected to synchronize the input of various geographical structure parameters corresponding to the set geographical area and the groundwater transfer information corresponding to each past time segment before the current time segment to the intelligent analysis model of the transfer information corresponding to the set geographical area. The intelligent analysis of groundwater transfer information in the current time segment using the intelligent analysis model of transfer information corresponding to the set geographical area includes: running the intelligent analysis model of transfer information corresponding to the set geographical area to obtain the groundwater transfer information of the set geographical area in the current time segment output by the intelligent analysis model of transfer information corresponding to the set geographical area. This analysis is based on the time length of the time segment on the time axis, the geographical area occupied by the set geographical area, the various geographical structure parameters corresponding to the set geographical area, and the groundwater transfer information of the set geographical area in the current time segment. Furthermore, the groundwater transfer information corresponding to the current time segment of the set geographical region, the time length of the time segment on the time axis, the geographical area occupied by the set geographical region, the various geographical structure parameters corresponding to the set geographical region, and the groundwater transfer information corresponding to each past time segment of the set geographical region before the current time segment are all represented by binary values.

[0033] In addition, the following technical content can be cited to further highlight the essential features of the present invention: The positive correlation between the number of previous time segments before the selected current time segment and the average aquifer thickness of the surrounding geographical regions includes: using an information transformation function to represent the information transformation relationship between the number of previous time segments before the selected current time segment and the average aquifer thickness of the surrounding geographical regions. The information transformation relationship, which uses an information transformation function to represent the positive correlation between the number of previous time segments before the selected current time segment and the average aquifer thickness of the surrounding geographical regions, includes: in the information transformation function, the average aquifer thickness of the surrounding geographical regions is the input information of the information transformation function, and the number of previous time segments before the selected current time segment is the output information of the information transformation function. For example, the MATLAB toolbox can be used to simulate and test the information processing process that uses an information transformation function to represent the positive correlation between the number of previous time segments before the selected current time segment and the average aquifer thickness of the surrounding geographic regions.

[0034] It should be understood that the embodiments disclosed herein are illustrative and non-limiting. The scope of the invention is defined by the appended claims rather than by the foregoing description, and all equivalent concepts and variations within that meaning are intended to be included in the claims.

Claims

1. A method for constructing a three-dimensional geological structure model that couples geological structure with groundwater migration, characterized in that, The method includes: Obtain stratigraphic lithology data, porosity, permeability, fault distribution data, aquifer thickness and burial depth within a specified geographic area to serve as various geographic structural parameters corresponding to the specified geographic area. Collect groundwater transfer information for each past time segment before the current time segment for a set geographical area. The groundwater transfer information for each time segment for the set geographical area includes the groundwater level, flow direction indicator, flow velocity, recharge, discharge and hydraulic gradient of the set geographical area within the time segment. The Hofit neural network is subjected to multiple learning processes to obtain an intelligent analysis model of transfer information corresponding to a set geographical area. The number of learning processes performed by the Hofit neural network shows the same numerical trend as the geographical area occupied by the set geographical area. The intelligent analysis model using the transfer information corresponding to the set geographical area analyzes the groundwater transfer information of the set geographical area in the current time segment based on the length of time segment occupied on the time axis, the geographical area occupied by the set geographical area, the various geographical structure parameters corresponding to the set geographical area, and the groundwater transfer information corresponding to each past time segment before the current time segment. Based on the groundwater transfer information corresponding to the current time segment of the set geographical region and the various geographical structure parameters corresponding to the set geographical region, a three-dimensional geological structure model of the set geographical region within the current time interval is constructed.

2. The method for constructing a three-dimensional geological structure model coupling geological structure and groundwater migration as described in claim 1, characterized in that: The current time segment starts at the current moment. The current time segment and all previous time segments before the current time segment form a complete time interval on the time axis, and each time segment occupies an equal amount of time on the time axis. Among them, the collection of groundwater transfer information corresponding to each past time segment before the current time segment for the selected geographical area includes: the number of each past time segment before the selected current time segment is positively correlated with the average aquifer thickness of each geographical area surrounding the selected geographical area; Among them, the intelligent analysis model for the transfer information corresponding to the geographical region is set as the Hofit neural network after multiple learning processes; In each learning process performed on the Hofit Neural Network, the known groundwater transfer information corresponding to a certain geographical region at a certain time segment is used as the single output of the Hofit Neural Network. The time length of the time segment on the time axis, the geographical area occupied by the geographical region, the various geographical structural parameters corresponding to the geographical region, and the groundwater transfer information corresponding to each past time segment before the certain time segment are used as the item-by-item input of the Hofit Neural Network to complete this learning process.

3. The method for constructing a three-dimensional geological structure model coupling geological structure and groundwater migration as described in claim 2, characterized in that: The number of learning processes performed by the Hofit neural network shows the same numerical trend as the geographical area occupied by the set geographical region, including: using a first numerical change curve to represent the numerical change trend of the geographical area occupied by the set geographical region, and using a second numerical change curve to represent the numerical change trend of the number of learning processes performed by the Hofit neural network. Among them, the numerical change trend of the number of learning processes of the Hofit neural network and the geographical area occupied by the set geographical region also includes: the curvature values ​​at uniform intervals on the first numerical change curve are the same as the curvature values ​​at uniform intervals on the second numerical change curve, and the number of uniform intervals on the first numerical change curve is equal to the number of uniform intervals on the second numerical change curve.

4. The method for constructing a three-dimensional geological structure model coupling geological structure and groundwater migration as described in claim 3, characterized in that, After constructing a three-dimensional geological structure model of the designated geographical area within the current time interval based on the groundwater transfer information corresponding to the designated geographical area in the current time segment and various geographical structure parameters corresponding to the designated geographical area, the method further includes: Receive a 3D geological structure model of a specified geographic area within the current time interval, and perform on-site display of the 3D geological structure model of the specified geographic area within the current time interval; The process of receiving a three-dimensional geological structure model of a set geographical area within the current time interval and displaying the three-dimensional geological structure model of the set geographical area within the current time interval includes: using a field display device installed in a ground control room to receive the three-dimensional geological structure model of the set geographical area within the current time interval and display the three-dimensional geological structure model of the set geographical area within the current time interval.

5. The method for constructing a three-dimensional geological structure model coupling geological structure and groundwater migration as described in claim 3, characterized in that, After constructing a three-dimensional geological structure model of the designated geographical area within the current time interval based on the groundwater transfer information corresponding to the designated geographical area in the current time segment and various geographical structure parameters corresponding to the designated geographical area, the method further includes: The three-dimensional geological structure model of the set geographical area within the current time interval is wirelessly transmitted to a remote groundwater management server. The process of wirelessly transmitting a three-dimensional geological structure model of a set geographical area within the current time interval to a remote groundwater management server includes: wirelessly transmitting the three-dimensional geological structure model of a set geographical area within the current time interval to a remote groundwater management server via a two-way wireless communication link.

6. The method for constructing a three-dimensional geological structure model coupling geological structure and groundwater migration as described in claim 3, characterized in that, Before acquiring stratigraphic lithology data, porosity, permeability, fault distribution data, aquifer thickness, and burial depth within a designated geographical area to serve as various geographical structural parameters corresponding to that area, the method further includes: Divide the geographic regions into a set geographic region and other geographic regions surrounding the set geographic region. The process of dividing geographical regions to obtain a set geographical region and other geographical regions surrounding the set geographical region includes: dividing geographical regions using a user setting mode to obtain a set geographical region and other geographical regions surrounding the set geographical region. Specifically, different geographical regions have different geographical region identifiers for the designated geographical region and other geographical regions surrounding the designated geographical region.

7. The method for constructing a three-dimensional geological structure model coupling geological structure and groundwater migration as described in claim 3, characterized in that, After performing multiple learning processes on the Hofit neural network to obtain an intelligent analysis model of transfer information corresponding to a set geographical region, and after the number of learning processes performed on the Hofit neural network shows the same numerical trend as the geographical area occupied by the set geographical region, the method further includes: Receives and stores the intelligent analysis model of transfer information corresponding to the set geographical area; The process of receiving and storing the intelligent analysis model of transfer information corresponding to a set geographical region includes: storing the model of the intelligent analysis model of transfer information corresponding to the set geographical region by storing the various model parameters of the intelligent analysis model of transfer information corresponding to the set geographical region.

8. The method for constructing a three-dimensional geological structure model coupling geological structure and groundwater migration as described in any one of claims 3-7, characterized in that: The data obtained include stratigraphic lithology, porosity, permeability, fault distribution, aquifer thickness and burial depth within a specified geographic area. These data are used as various geographic structural parameters corresponding to the specified geographic area. The stratigraphic lithology data within the specified geographic area includes the stratigraphic lithology type identifier, mineral content and rock layer thickness. Among them, obtaining stratigraphic lithology data, porosity, permeability, fault distribution data, aquifer thickness and burial depth within a set geographical area as various geographical structural parameters corresponding to the set geographical area also includes: stratigraphic lithology types include pure mudstone, pure sandstone and semi-mudstone / sandstone. Among them, obtaining stratigraphic lithology data, porosity, permeability, fault distribution data, aquifer thickness and burial depth within a set geographical area as various geographical structural parameters corresponding to the set geographical area also includes: the aquifer thickness and burial depth within the set geographical area are the aquifer thickness and aquifer burial depth within the set geographical area.

9. The method for constructing a three-dimensional geological structure model coupling geological structure and groundwater migration as described in any one of claims 3-7, characterized in that: The groundwater transfer information corresponding to each time segment of a set geographical area includes the groundwater level, flow direction indicator, flow velocity, recharge, discharge and hydraulic gradient of the set geographical area within the time segment. The hydraulic gradient of the set geographical area within the time segment is the difference in water level between the start and end positions of the groundwater channel in the set geographical area within the time segment divided by the length of the groundwater channel in the set geographical area within the time segment. The groundwater transfer information corresponding to each time segment of the set geographical area includes the groundwater level, flow direction, flow velocity, recharge, discharge and hydraulic gradient of the set geographical area within the time segment. It also includes the groundwater level of the set geographical area within the time segment as the average of the water level difference between the start and end positions of the groundwater channel within the time segment of the set geographical area. The groundwater transfer information corresponding to each time segment of the set geographical area includes the groundwater level, flow direction, flow velocity, recharge, discharge and hydraulic gradient of the set geographical area within the time segment. It also includes the recharge of the set geographical area within the time segment as the inflow of groundwater into the set geographical area within the time segment. The groundwater transfer information corresponding to each time segment of the set geographical area includes the groundwater level, flow direction, flow velocity, recharge, discharge and hydraulic gradient of the set geographical area within the time segment. It also includes the discharge of the set geographical area within the time segment as the outflow of groundwater from the set geographical area within the time segment.

10. The method for constructing a three-dimensional geological structure model coupling geological structure and groundwater migration as described in any one of claims 3-7, characterized in that: The intelligent analysis model for the transfer information corresponding to the set geographical area uses the time length of the time segment on the time axis, the geographical area occupied by the set geographical area, the various geographical structural parameters corresponding to the set geographical area, and the groundwater transfer information corresponding to each of the previous time segments before the current time segment to intelligently analyze the groundwater transfer information corresponding to the set geographical area in the current time segment. This includes: synchronously inputting the time length of the time segment on the time axis, the geographical area occupied by the set geographical area, the various geographical structural parameters corresponding to the set geographical area, and the groundwater transfer information corresponding to each of the previous time segments before the current time segment into the intelligent analysis model for the transfer information corresponding to the set geographical area. The intelligent analysis of groundwater transfer information in the current time segment using the intelligent analysis model of transfer information corresponding to the set geographical area includes: running the intelligent analysis model of transfer information corresponding to the set geographical area to obtain the groundwater transfer information of the set geographical area in the current time segment output by the intelligent analysis model of transfer information corresponding to the set geographical area. This analysis is based on the time length of the time segment on the time axis, the geographical area occupied by the set geographical area, the various geographical structure parameters corresponding to the set geographical area, and the groundwater transfer information of the set geographical area in the current time segment. The groundwater transfer information corresponding to the current time segment of the set geographical region, the time length of the time segment on the time axis, the geographical area occupied by the set geographical region, the various geographical structure parameters corresponding to the set geographical region, and the groundwater transfer information corresponding to each past time segment of the set geographical region before the current time segment are all represented by binary values.

Images