Mine hydrogeological model construction system and method

Abstract

The embodiment of the invention discloses a mine hydrogeological model construction system and method, and the system comprises a construction module which is used for constructing a geological database according to collected data; wherein the data comprises hydrogeological data, drilling data and exploration data; the division module is used for performing stratigraphic division on the current geologic body according to a preset division rule to obtain a corresponding stratigraphic sequence; wherein each stratum is associated with corresponding elevation and thickness data; the processing module is used for constructing a model by adopting a hybrid modeling mode according to the data in the geological database and the stratum sequence; the method has the beneficial effects that association of fine division between multiple data and corresponding stratums is established, so that the underground geological form can be better reflected, and the accuracy of geological judgment is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of geological modeling, and particularly relates to a system and method for constructing a mine hydrogeological model. Background Art

[0002] A hydrogeological model systematically summarizes the basic characteristics of a groundwater system by integrating on-site and experimental data. By constructing a hydrogeological model, the movement law of groundwater in a mine area can be simulated and predicted, providing a scientific basis for mine water control work, which is of great significance for the prediction and prevention of hydrogeological disasters.

[0003] Currently, most construction methods are based on single data or local areas for model construction; although there are also solutions using multi-data applications, there is a lack of fine division between corresponding strata, thus affecting the accuracy of geological judgment. Summary of the Invention

[0004] Aiming at the technical defects mentioned in the background art, the purpose of the embodiments of the present invention is to provide a system and method for constructing a mine hydrogeological model.

[0005] To achieve the above object, in a first aspect, the embodiments of the present invention provide a system for constructing a mine hydrogeological model, the system comprising:

[0006] A construction module, configured to construct a geological database according to the collected data; wherein, the data includes hydrogeological data, borehole data, and exploration data;

[0007] A division module, configured to divide the current geological body into strata according to a preset division rule to obtain a corresponding stratum sequence; wherein, each stratum is associated with corresponding elevation and thickness data;

[0008] A processing module, configured to perform model construction according to the data in the geological database and the stratum sequence by using a hybrid modeling method.

[0009] As a preferred implementation manner of the present application, the processing module is further configured to:

[0010] Zone the geological body based on the permeability coefficient, and the permeability coefficient in each zone is determined according to the permeability coefficient data and pumping test in the zone; thereby establishing a more complete hydrogeological model;

[0011] Wherein, the following calculation formula is adopted:

[0012] s=(Q / 4πT)*W(u);

[0013] u = r 2 / 4at;

[0014] s is the drawdown, in m; Q is the water yield of the pumping well, in m 3 / d; T is the transmissivity, in ㎡ / d; W(u) is the Theis well function; u is the independent variable of the Theis well function; r is the borehole diameter, in m; a is the pressure conductivity coefficient, in ㎡ / d; t is the time, in min;

[0015] Then, by plotting the measured drawdown-time curve, translating the vertical and horizontal coordinates to fit it with the standard curve, selecting any matching point, and reading the corresponding coordinate values, the parameters can be determined.

[0016] As a preferred implementation mode of the present application, the mine hydrogeological model construction system further includes an optimization module, and the optimization module is used for:

[0017] According to the borehole data, use the corresponding point data to correct the horizons;

[0018] Then, combined with geostatistical interpolation, automatically adjust the formation cross-piercing to form a formation-coordinated model.

[0019] As a preferred implementation mode of the present application, the processing module is further used for:

[0020] Predict the water inflow of the working face using the trained prediction model; wherein, the prediction model is trained based on the combined long short-term memory network and gated recurrent unit to improve the generalization ability and accuracy;

[0021] The prediction model includes an input layer, a hidden layer, an output layer, a network training layer, and a prediction layer; wherein, the hidden layer is a network constructed by LSTM-GRU units;

[0022] The gated recurrent unit calculates zt and rt based on the input state information xt at the current moment and the hidden layer information hi-1 stored at the previous moment; uses the reset gate to determine the amount of new information in hi-1 for the storage node; calculates the hidden layer output at the current moment through the update gate.

[0023] As a specific implementation mode of the present application, when the prediction model is trained, production factors are also used as prediction variables;

[0024] Meanwhile, the following correlation judgments are also made, specifically including:

[0025] Let Y = {y1, y2,..., yn} be random variables, and X = {x1, x2,..., xn} be independent variables. There is a correlation between them, which can be expressed as

[0026] y = b0 + b1x1 + b2x2 + … + bnxn + ε; where b0, b1, b2, …, bn are theoretical regression coefficients, representing the linear influence on y, and ε is a random error, representing the influence of factors other than the n independent variables x on y and the non-linear influence of the independent variables on y;

[0027] Then, use the coefficient of determination R 2 to quantitatively identify the correlation degree between X and Y, 0 ≤ R 2 ≤ 1, the larger R 2 is, the greater the correlation between X and Y;

[0028]

[0029] Among them, y i is the measured value, y a is the average value of y, and y s i is the predicted value of y i .

[0030] In a second aspect, an embodiment of the present invention further provides a method for constructing a mine hydrogeological model, which is applied to a mine hydrogeological model construction system described in the first aspect. The method includes:

[0031] Construct a geological database according to the collected data; where the data includes hydrogeological data, borehole data, and exploration data;

[0032] According to a preset division rule, divide the current geological body into strata to obtain the corresponding stratigraphic sequence; where each stratum is associated with corresponding elevation and thickness data;

[0033] According to the data in the geological database and the stratigraphic sequence, and using a hybrid modeling method, perform model construction.

[0034] The technical solution provided by the embodiment of the present invention first constructs a geological database according to the collected data; then divides the current geological body into strata according to a preset division rule to obtain the corresponding stratigraphic sequence; and then performs model construction according to the data in the geological database and the stratigraphic sequence, and using a hybrid modeling method; thereby establishing a fine-grained association between multiple data and the corresponding strata, facilitating a better reflection of the underground geological morphology, and further improving the accuracy of geological judgment. Brief Description of the Drawings

[0035] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art.

[0036] Figure 1It is a principle block diagram of a system for constructing a mine hydrogeological model provided by an embodiment of the present invention;

[0037] Figure 2 It is a flowchart of a method for constructing a mine hydrogeological model provided by an embodiment of the present invention. Detailed implementation manners

[0038] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0039] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so as to implement the embodiments of the present application described herein.

[0040] It should be understood that when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0041] Throughout the specification, the reference to "one embodiment", "embodiment", "one example" or "example" means that the specific features, structures or characteristics described in connection with the embodiment or example are included in at least one embodiment of the present invention. Therefore, the phrases "in one embodiment", "in an embodiment", "one example" or "example" appearing throughout the specification do not necessarily all refer to the same embodiment or example. In addition, the specific features, structures or characteristics can be combined in any appropriate combination and / or sub-combination in one or more embodiments or examples.

[0042] It should be noted that, unless otherwise specified, the technical terms in this embodiment have the ordinary meanings understood by those in the technical field to which they belong.

[0043] Please refer to Figure 1 , a system for constructing a mine hydrogeological model provided by an embodiment of the present invention, the system includes:

[0044] A construction module, configured to construct a geological database according to the collected data; wherein, the data includes hydrogeological data, borehole data and exploration data;

[0045] A partitioning module, configured to perform stratigraphic partitioning on the current geological body according to a preset partitioning rule to obtain a corresponding stratigraphic sequence; wherein, each stratum is associated with corresponding elevation and thickness data;

[0046] A processing module, configured to perform model construction by using a hybrid modeling method according to the data in the geological database and the stratigraphic sequence.

[0047] In this embodiment, the data also includes geology, groundwater, seismic data, sedimentary facies, sand bodies, etc. of the corresponding mining area, which will not be elaborated here;

[0048] The partitioning rule is based on stratigraphic architecture, stratigraphic age, sedimentary facies, subfacies, microfacies and other sedimentary formations, folds, faults, joints, bedding and other geological structures for fine partitioning, making full use of and integrating relevant parameters such as stratigraphic lithology, structure, sedimentary facies, etc., and re-performing high-resolution sequence stratigraphy and sedimentary facies partitioning on the geological body.

[0049] In application, when performing model construction, combining data such as the numbers corresponding to the stratigraphic sequence, the elevation of the bottom plate of each stratum and the thickness of the stratum, and combining the compiled geological section and the isopach map of the coal seam roof and floor, a three-dimensional model is constructed by using a hybrid modeling method of TIN (Triangulated Irregular Network) and ARTP (Apparent Rectangular Triangular Prism); thus making up for the technical limitations of only constructing several coal seams or strata in the past.

[0050] It should be noted that by applying the base-level cycle correlation in high-resolution sequence stratigraphy, the correctness of sand body connection is ensured to the greatest extent; relying on multiple stratigraphic partitioning and fine well-to-well correlation, the strata and sand bodies are re-partitioned and connected; thus obtaining the corresponding group.

[0051] Further, in application, in order to more finely reflect the hydrogeological characteristics, on the basis of the above technical solution, the processing module is further configured to:

[0052] Partition the geological body based on the permeability coefficient, and the permeability coefficient in each area is determined according to the permeability coefficient data and pumping test in the area; and then a more complete hydrogeological model is established;

[0053] Among them, the following calculation formula is used:

[0054] s=(Q / 4πT)*W(u);

[0055] u = r 2 / 4at;

[0056] s is the drawdown, m; Q is the discharge of the pumping well, m 3 / d; T is the transmissivity, ㎡ / d; W(u) is the Theis well function; u is the independent variable of the Theis well function; r is the borehole diameter, m; a is the hydraulic diffusivity, ㎡ / d; t is the time, min;

[0057] Then, by plotting the measured drawdown-time curve, translating the horizontal and vertical coordinates to fit it with the standard curve, selecting any matching point, and reading the corresponding coordinate values, the parameters can be determined.

[0058] In this embodiment, to improve the accuracy, the permeability coefficient data of different regions cannot be directly borrowed even if they are in the same stratum; among them, the permeability coefficient data includes the pore structure, porosity, and saturation of rocks or soils, as well as the texture of rocks or soils, etc.

[0059] Furthermore, during implementation, to achieve optimization and correction, the described mine hydrogeological model construction system further includes an optimization module, and the optimization module is used for:

[0060] According to the borehole data, use the corresponding point data to correct the horizons;

[0061] Then, combined with geostatistical interpolation, automatically adjust the formation cross-bedding to form a formation-coordinated model.

[0062] During application, based on the corrected formation framework, adjust the position of the formation based on geostatistical interpolation, and automatically adjust the formation cross-bedding to form a formation-coordinated model; among them, the methods of geostatistical interpolation can adopt Kriging, inverse distance weighted interpolation method, etc.

[0063] For the above solution, first construct a geological database according to the collected data; then, according to the preset division rules, divide the current geological body into formations to obtain the corresponding formation sequence; then, according to the data in the geological database and the formation sequence, and adopt a hybrid modeling method to construct the model; thus establish a fine division association between multiple data and the corresponding formations, which is convenient to better reflect the underground geological morphology, and then improve the accuracy of geological judgment.

[0064] Furthermore, on the basis of the above technical solution, the processing module is further used for:

[0065] Predict the water inflow of the working face using the trained prediction model; among them, the prediction model is trained based on the combined long short-term memory network and gated recurrent unit to improve the generalization ability and accuracy;

[0066] The prediction model includes an input layer, a hidden layer, an output layer, a network training layer, and a prediction layer; among them, the hidden layer is a network constructed by LSTM-GRU units;

[0067] The gated recurrent unit calculates zt and rt based on the input state information xt at the current moment and the hidden layer information hi-1 stored at the previous moment; uses a reset gate to determine the amount of new information in the storage node in hi-1; and calculates the hidden layer output at the current moment through an update gate.

[0068] During application, the LSTM layer accepts the input, performs normalization processing, and then sends it to the gated recurrent unit for processing, that is, the GRU layer.

[0069] Subsequently, to prevent overfitting, after passing through the Dropout layer, it is sequentially connected to the fully connected layer and the output layer to form the corresponding network structure.

[0070] Implementing combined prediction through multiple models can effectively combine the advantages of each model, improve the robustness, generalization performance, and training speed of the model.

[0071] In this embodiment, when the prediction model is trained, production factors are also used as prediction variables; among them, the production factors include mining area, raw coal output, excavation length, mining height, etc.; thus, it is more in line with the actual application and improves the practicality on the basis of existing dimensions such as mine geology, hydrogeology, hydro-meteorology, and topography.

[0072] Furthermore, the following correlation judgments are also made, specifically including:

[0073] Let Y = {y1, y2,..., yn} be a random variable, and X = {x1, x2,..., xn} be an independent variable. There is a correlation between them, which can be expressed as

[0074] y = b0 + b1x1 + b2x2 +... + bn xn + ε; where b0, b1, b2,..., bn are theoretical regression coefficients, representing the linear influence on y, and ε is a random error, representing the influence of factors other than the n independent variables x on y and the non-linear influence of the independent variables on y.

[0075] Then, using the coefficient of determination R 2 to quantitatively identify the degree of correlation between X and Y, 0 ≤ R 2 ≤ 1, the larger R 2 is, the greater the correlation between X and Y.

[0076]

[0077] Among them, y i is the measured value, y a is the average value of y, and y s i is the predicted value of y i .

[0078] Refer to Figure 2, Based on the same inventive concept, an embodiment of the present invention further provides a method for constructing a mine hydrogeological model, which is applied to a mine hydrogeological model construction system described above. The method includes:

[0079] S101, constructing a geological database according to the collected data; wherein, the data includes hydrogeological data, borehole data, and exploration data;

[0080] S102, dividing the current geological body into strata according to the preset division rules to obtain the corresponding stratigraphic sequence; wherein, each stratum is associated with the corresponding elevation and thickness data;

[0081] S103, performing model construction according to the data in the geological database and the stratigraphic sequence, and adopting a hybrid modeling method.

[0082] Further, the method further includes:

[0083] Dividing the geological body based on the permeability coefficient, and the permeability coefficient in each area is determined according to the permeability coefficient data and pumping test in the area; thereby establishing a more complete hydrogeological model;

[0084] The following calculation formula is adopted:

[0085] s = (Q / 4πT) * W(u);

[0086] u = r 2 / 4at;

[0087] s is the drawdown, m; Q is the water yield of the pumping well, m 3 / d; T is the transmissivity, ㎡ / d; W(u) is the Theis well function; u is the independent variable of the Theis well function; r is the borehole diameter, m; a is the storage coefficient, ㎡ / d; t is the time, min;

[0088] Then, by plotting the measured drawdown-time curve, translating the horizontal and vertical coordinates to fit it with the standard curve, selecting any matching point, and reading the corresponding coordinate values, the parameters can be determined.

[0089] In this embodiment, to improve the accuracy of modeling, the method further includes:

[0090] According to the borehole data, using the corresponding point data to correct the horizons;

[0091] Then, combining geostatistical interpolation to automatically adjust the formation cross-strata to form a formation-coordinated model.

[0092] The method further includes:

[0093] The water inflow of the working face is predicted using the trained prediction model; wherein, the prediction model is trained based on the combined long short-term memory network and gated recurrent unit to improve the generalization ability and accuracy;

[0094] The prediction model includes an input layer, a hidden layer, an output layer, a network training layer, and a prediction layer; wherein, the hidden layer is a network constructed by LSTM-GRU units;

[0095] The gated recurrent unit calculates zt and rt based on the input state information xt at the current moment and the hidden layer information hi-1 stored at the previous moment; uses a reset gate to determine the amount of new information in hi-1 for the storage node; and calculates the hidden layer output at the current moment through an update gate.

[0096] During training, production factors are also used as prediction variables; at the same time, the following correlation judgments are also made, specifically including:

[0097] Let Y = {y1, y2,..., yn} be a random variable, and X = {x1, x2,..., xn} be an independent variable. There is a correlation between them, which can be expressed as y = b0 + b1x1 + b2x2 +... + bn xn + ε; where b0, b1, b2,..., bn are theoretical regression coefficients, representing the linear influence on y, and ε is a random error, representing the influence of factors other than the n independent variables x on y and the non-linear influence of the independent variables on y.

[0098] Then, use the coefficient of determination R 2 to quantitatively identify the degree of correlation between X and Y, 0 ≤ R 2 ≤ 1, the larger R 2 is, the greater the correlation between X and Y;

[0099]

[0100] where y i is the measured value, y a is the average value of y, and y s i is the predicted value of y i ;

[0101] It should be noted that for a more specific description of the working process of the method embodiment, please refer to the foregoing system embodiment part and will not be elaborated here.

[0102] For the entire solution, first construct a geological database based on the collected data; then, according to the preset division rules, divide the current geological body to obtain the corresponding stratigraphic sequence; then, based on the data in the geological database and the stratigraphic sequence, and using a hybrid modeling method, construct a model; thereby establishing a fine division correlation between multiple data and the corresponding strata, facilitating a better reflection of the underground geological morphology, and further improving the accuracy of geological judgment.

[0103] In several embodiments provided in the present application, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system embodiments described above are merely illustrative. For example, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0104] In addition, in each embodiment of the present invention, the functional modules can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part. When each module is used, it will only collect and store user information with the full authorization of the user and in compliance with relevant laws and regulations, and protect the security and privacy of user data. Unauthorized access is strictly prohibited; the processing of data will be carried out within the scope stipulated by law and will not exceed the purpose and scope authorized by the user; at the same time, the user has the right to access, correct, delete, restrict processing, refuse, etc. regarding their personal data; and strictly abide by the applicable laws and regulations and conduct compliance reviews.

[0105] When the above-mentioned functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The above is only the preferred embodiment of the present invention and is not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0106] As described above, the above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or replacements, and these modifications or replacements should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A mine hydrogeological model construction system, characterized in that: The system comprises: A construction module, used to construct a geological database based on the collected data; wherein the data includes hydrogeological data, drilling data and exploration data; The division module is used to divide the current geological body into strata according to the preset division rules to obtain the corresponding stratigraphic sequence; wherein each stratum is associated with corresponding elevation and thickness data; The processing module is used to construct a model based on the data in the geological database and the stratigraphic sequence by adopting a hybrid modeling method.

2. A mine hydrogeological model construction system according to claim 1, characterized in that: The processing module is further used for: The geological body is divided into zones based on the permeability coefficient. The permeability coefficient of each zone is determined based on the permeability coefficient data and pumping test in the zone; thus, a more complete hydrogeological model is established; The following calculation formula is used: s=(Q / 4πT)*W(u); u=r 2 / 4at; s is the water level drop, m; Q is the water output of the pumping well, m 3 / d; T is the water conductivity, ㎡ / d; W(u) is the Theis well function; u is the independent variable of the Theis well function; r is the pore size, m; a is the pressure conductivity, ㎡ / d; t is the time, min; Then, the measured drawdown-time curve is plotted, the vertical and horizontal coordinates are translated to fit it with the standard curve, and any matching point is selected and the corresponding coordinate value is read to determine the parameters.

3. A mine hydrogeological model construction system as claimed in claim 1 or 2, characterized in that: It also includes an optimization module, wherein the optimization module is used to: According to the drilling data, the corresponding point data is used to correct the horizon; Combined with geostatistical interpolation, the stratigraphic penetration is automatically adjusted to form a stratigraphically coordinated model.

4. A mine hydrogeological model construction system as claimed in claim 3, characterized in that: The processing module is further used for: The water inflow of the working face is predicted using a trained prediction model; wherein the prediction model is trained based on a combined long short-term memory network and a gated recurrent unit to improve generalization ability and accuracy; The prediction model includes an input layer, a hidden layer, an output layer, a network training layer and a prediction layer; wherein the hidden layer is a network constructed with LSTM-GRU units; The gated recurrent unit calculates zt and rt based on the input state information xt at the current moment and the hidden layer information hi-1 stored at the previous moment; uses the reset gate to determine the amount of new information stored in the node hi-1; and calculates the hidden layer output at the current moment through the update gate.

5. A mine hydrogeological model construction system as claimed in claim 4, characterized in that: When training the prediction model, the production factors are also used as prediction variables. At the same time, the following correlation judgments are also performed, including: Let Y = {y1, y2, ..., yn} be a random variable and X = {x1, x2, ..., xn} be an independent variable. There is a correlation between them, which can be expressed as y = b0+b1x1+b2x2+...++bnxn+ε; Where b0, b1, b2, …, bn are theoretical regression coefficients, representing the linear impact on y, and ε is the random error, representing the impact of factors other than the n independent variables x on y and the nonlinear impact of the independent variables on y; Reuse determination coefficient R 2 Quantitatively determine the correlation between X and Y, 0≤R 2 ≤1, R 2 The larger it is, the greater the correlation between X and Y; Among them, y i is the measured value, y a is the mean value of y, s i for y i The predicted value of .

6. A method for constructing a mine hydrogeological model, characterized in that: The method applied to a mine hydrogeological model construction system according to claim 1 comprises: Constructing a geological database based on the collected data; wherein the data includes hydrogeological data, drilling data and exploration data; According to the preset division rules, the current geological body is divided into strata to obtain the corresponding stratigraphic sequence; wherein each stratum is associated with corresponding elevation and thickness data; The model is constructed based on the data in the geological database and the stratigraphic sequence and by adopting a hybrid modeling approach.

7. A method for constructing a mine hydrogeological model according to claim 6, characterized in that: The method further comprises: The geological body is divided into zones based on the permeability coefficient. The permeability coefficient of each zone is determined based on the permeability coefficient data and pumping test in the zone; thus, a more complete hydrogeological model is established; The following calculation formula is used: s=(Q / 4πT)*W(u); u=r 2 / 4at; s is the water level drop, m; Q is the water output of the pumping well, m 3 / d; T is the water conductivity, ㎡ / d; W(u) is the Theis well function; u is the independent variable of the Theis well function; r is the pore size, m; a is the pressure conductivity, ㎡ / d; t is the time, min; Then, the measured drawdown-time curve is plotted, the vertical and horizontal coordinates are translated to fit it with the standard curve, and any matching point is selected and the corresponding coordinate value is read to determine the parameters.

8. A method for constructing a mine hydrogeological model according to claim 7, characterized in that: The method further comprises: According to the drilling data, the corresponding point data is used to correct the horizon; Combined with geostatistical interpolation, the stratigraphic penetration is automatically adjusted to form a stratigraphically coordinated model.

9. A method for constructing a mine hydrogeological model according to claim 8, characterized in that: The method further comprises: The water inflow of the working face is predicted using a trained prediction model; wherein the prediction model is trained based on a combined long short-term memory network and a gated recurrent unit to improve generalization ability and accuracy; the prediction model includes an input layer, a hidden layer, an output layer, a network training layer and a prediction layer; wherein the hidden layer is a network constructed using LSTM-GRU units; The gated recurrent unit calculates zt and rt based on the input state information xt at the current moment and the hidden layer information hi-1 stored at the previous moment; uses the reset gate to determine the amount of new information stored in the node hi-1; and calculates the hidden layer output at the current moment through the update gate.

Images