Medium-deep layer underground hot water resource exploration method and device based on multi-source data fusion

Abstract

The invention provides a medium-deep layer underground hot water resource exploration method and device based on multi-source data fusion, and belongs to the technical field of underground hot water resource exploration, and the method comprises the following steps: S1, collecting multi-source data of a target area, including geological data, geophysical data, geochemical data and remote sensing data; s2, preprocessing the multi-source data, wherein the preprocessing comprises wavelet packet transformation frequency division decomposition, principal component analysis noise reduction and normalization processing; according to the method, through systematic fusion and dynamic optimization of multi-source data, the problems of data noise, conflict and uncertainty are effectively solved, and the precision and reliability of medium-deep layer underground hot water resource exploration are improved; by means of the built three-dimensional coupling model and an improved heat conduction equation solving method, heat storage characteristics in the complex geology-thermodynamics environment are accurately described, full-process efficient operation is achieved in combination with an automatic hardware device, and an integrated solution is provided for scientific development of underground hot water resources.

Description

Technical Field

[0001] The present invention relates to the technical field of exploration of deep geothermal water resources, and specifically relates to a method and device for exploring deep geothermal water resources based on multi-source data fusion. Background Art

[0002] As an important clean energy source, the exploration of deep geothermal water resources requires comprehensive consideration of multi-dimensional data such as geology, geophysics, geochemistry, and remote sensing. Traditional exploration methods have problems such as low data fusion efficiency, fixed weight allocation, insufficient handling of conflicting evidence, and poor model adaptability, making it difficult to accurately depict the distribution of heat reservoirs under complex geological conditions. In view of the above problems, the present invention proposes an exploration method and device based on multi-source data fusion, which improves the accuracy and reliability of resource exploration through advanced data processing, fusion modeling, and dynamic optimization technologies.

[0003] Therefore, a method and device for exploring deep geothermal water resources based on multi-source data fusion are proposed. Summary of the Invention

[0004] The present invention aims to solve the problems raised in the background art, and provides a method and device for exploring deep geothermal water resources based on multi-source data fusion.

[0005] The specific technical solutions are as follows:

[0006] A method for exploring deep geothermal water resources based on multi-source data fusion, comprising the following steps:

[0007] Step S1: Collect multi-source data of the target area, including geological data, geophysical data, geochemical data, and remote sensing data;

[0008] Step S2: Perform preprocessing on the multi-source data, including wavelet packet transform frequency division decomposition, principal component analysis noise reduction, and normalization processing;

[0009] Step S3: Construct a Bayesian network model to represent the probabilistic dependence relationship between data sources, and combine fuzzy inference and information entropy weight allocation to achieve multi-level data fusion;

[0010] Step S4: Generate a comprehensive anomaly map with confidence ratings and delineate potential resource areas, and combine drilling verification and machine learning to dynamically optimize model parameters.

[0011] In the above method for exploring deep geothermal water resources based on multi-source data fusion, in step S1:

[0012] The geological data includes formation lithology, fault structure, and hydrogeological parameters;

[0013] The geophysical data includes resistivity data, gravity data, and seismic shear wave velocity structure data;

[0014] The geochemical data includes groundwater chemical components and isotope compositions;

[0015] The remote sensing data includes thermal infrared radiation images and multispectral vegetation index data.

[0016] The above-mentioned exploration method for medium and deep geothermal water resources based on multi-source data fusion, wherein the preprocessing described in step S2 includes:

[0017] Step S2a: Decompose the original data into frequency bands using the dual-tree complex wavelet transform, and filter out high-frequency noise and low-frequency drift;

[0018] Step S2b: Perform principal component analysis on the data of each frequency band, and extract the principal components with a contribution rate ≥ 85% to reconstruct the data;

[0019] Step S2c: Normalize the multi-source data based on the improved Z-score method to eliminate the dimension difference.

[0020] The above-mentioned exploration method for medium and deep geothermal water resources based on multi-source data fusion, wherein in step S3:

[0021] The fuzzy inference uses a Gaussian membership function to quantify the feature mapping;

[0022] The information entropy weight is dynamically adjusted by calculating the uncertainty of each data source, and the weight distribution formula is:

[0023] Wherein,

[0024] Where:

[0025] H i : The information entropy of the i-th data source, representing the data uncertainty;

[0026] λ: Fusion sensitivity coefficient (value range 0.5 - 2.0), controlling the concentration degree of weight distribution;

[0027] σ 2 : The noise variance of the data source, calculated by the preprocessing module;

[0028] ∈: Smoothing constant (default 1e-5), preventing the denominator from being zero.

[0029] The above-mentioned exploration method for medium and deep geothermal water resources based on multi-source data fusion, wherein the multi-level data fusion described in step SZ includes:

[0030] Step S3a: Infer the probability relationship between data sources based on the Bayesian network;

[0031] Step S3b: Use Dempster-Shafer evidence theory to solve the problem of conflict evidence fusion;

[0032] Step S3c: Dynamically adjust the fusion weight coefficient through the particle swarm optimization algorithm;

[0033] The conflict evidence fusion adopts a modified Dempster combination rule:

[0034]

[0035] Where:

[0036] ψ(B,C) = exp(-β·|conf(B,C)|): Conflict attenuation factor, where β is the attenuation coefficient;

[0037] conf(B,C): Conflict degree between evidence B and C;

[0038] K: Conflict amount in the traditional Dempster rule;

[0039] δ: Conflict compensation term (δ = 0.1K).

[0040] The above-mentioned exploration method for medium-deep geothermal water resources based on multi-source data fusion, wherein the dynamically optimized model parameters in step S4 include:

[0041] Step S4a: Obtain underground core and water sample data through drilling and sampling;

[0042] Step S4b: Use the support vector machine algorithm to compare the fusion result with the actual data and calculate the error rate;

[0043] Step S4c: If the error rate exceeds the threshold, reversely adjust the Bayesian network parameters and the fuzzy membership function.

[0044] The above-mentioned exploration method for medium-deep geothermal water resources based on multi-source data fusion, wherein step S4 further includes:

[0045] Construct a three-dimensional geological-thermodynamic coupling model based on the fusion result, and the model includes:

[0046] Three-dimensional grid model of formation lithology;

[0047] Three-dimensional distribution model of fault structures;

[0048] Dynamic distribution field of rock thermal conductivity.

[0049] The above-mentioned exploration method for medium-deep geothermal water resources based on multi-source data fusion, wherein the three-dimensional geological-thermodynamic coupling model solves the non-Darcy flow heat conduction equation by the finite volume method, and combines Monte Carlo simulation to evaluate the uncertainty of resource quantity prediction. The solution of the non-Darcy flow heat conduction equation adopts the following modified form:

[0050]

[0051] Parameter description:

[0052] is the non-linear flow coefficient, φ is the porosity, μ is the fluid viscosity, and k is the permeability;

[0053] γ: temperature attenuation coefficient;

[0054] P: fluid pressure field.

[0055] The present invention also provides an exploration device for medium-deep geothermal water resources based on multi-source data fusion, which is used to execute the above-mentioned exploration method for medium-deep geothermal water resources based on multi-source data fusion, and includes:

[0056] A data acquisition module, which integrates a high-precision gravimeter, a distributed optical fiber temperature measurement system, and an unmanned aerial vehicle (UAV)-borne multi-spectral thermal infrared imager;

[0057] A data preprocessing module, which is configured with a wavelet packet transform unit accelerated by FPGA and a GPU parallel principal component analysis unit;

[0058] A data fusion module, which includes a Bayesian network modeling unit, an evidence theory inference engine, and a dynamic weight optimization unit;

[0059] A verification and correction module, which realizes closed-loop optimization through a drilling equipment control unit and a machine learning algorithm.

[0060] For the above-mentioned exploration device for medium-deep geothermal water resources based on multi-source data fusion, wherein the data acquisition module further includes:

[0061] An underground three-component microseismic monitoring array, which is used to obtain seismic wave data with a depth ≥ 3 km;

[0062] An automatic on-line analyzer for fluid chemical components, which can detect the chemical components and isotope content of groundwater in real time.

[0063] The present invention has the following beneficial effects:

[0064] Through the systematic integration and dynamic optimization of multi-source data, the present invention breaks through the limitations of single-data exploration, effectively addresses data noise, conflicts, and uncertainty issues, and improves the accuracy and reliability of medium-deep geothermal water resource exploration; the constructed three-dimensional coupling model and the improved method for solving the heat conduction equation accurately depict the characteristics of the geothermal reservoir under complex geological-thermodynamic environments, and combined with automated hardware devices, achieve efficient operation throughout the process, providing an integrated solution for the scientific development of geothermal water resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a flowchart of the method for exploring medium-deep geothermal water resources based on multi-source data fusion provided by an embodiment of the present invention;

[0066] Figure 2 It is an architecture diagram of the device for exploring medium-deep geothermal water resources based on multi-source data fusion provided by an embodiment of the present invention;

[0067] Figure 3 It is a comparison curve graph of information entropy in the method for exploring medium-deep geothermal water resources based on multi-source data fusion provided by an embodiment of the present invention;

[0068] Figure 4 It is a comparison curve graph of noise levels in the method for exploring medium-deep geothermal water resources based on multi-source data fusion provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0069] The technical solution of the present invention will be further described below in conjunction with the drawings and through specific embodiments.

[0070] Among them, the drawings are only for illustrative purposes, showing only schematic diagrams rather than physical diagrams, and should not be construed as limitations on this patent; for better illustration of the embodiments of the present invention, some components in the drawings will be omitted, enlarged, or reduced, which do not represent the dimensions of actual products; for those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted.

[0071] In the drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components; in the description of the present invention, it should be understood that if terms such as "upper", "lower", "left", "right", "inner", "outer", etc. are used to indicate the orientation or positional relationship, it is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, so the terms describing the positional relationship in the drawings are only for illustrative purposes and should not be construed as limitations on this patent. For those of ordinary skill in the art, the specific meanings of the above terms can be understood according to specific circumstances.

[0072] In the description of the present invention, unless otherwise clearly specified and limited, if terms such as "connection" are used to indicate the connection relationship between components, such terms should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or integrated; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components or the interaction relationship between two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0073] The method for exploring medium-deep geothermal water resources based on multi-source data fusion provided in this embodiment is as Figures 1-4 shown, where: Figure 3 is the information entropy comparison curve graph in the method for exploring medium-deep geothermal water resources based on multi-source data fusion provided in this embodiment. This graph shows the changes in information entropy of different data sources before and after preprocessing, helping to understand the influence of the preprocessing steps on the amount of data information; Figure 4 is the noise level comparison curve graph in the method for exploring medium-deep geothermal water resources based on multi-source data fusion provided in this embodiment. This graph shows the changes in noise variance of different data sources before and after preprocessing, helping to evaluate the noise suppression effect of the preprocessing steps; It includes the following steps:

[0074] Step S1: Collect multi-source data of the target area, including geological data, geophysical data, geochemical data, and remote sensing data;

[0075] Step S2: Preprocess the multi-source data, including wavelet packet transform frequency division decomposition, principal component analysis noise reduction, and normalization processing;

[0076] Step S3: Construct a Bayesian network model to characterize the probability dependence relationship between data sources, and combine fuzzy reasoning and information entropy weight assignment (based on the dynamic weight adjustment formula) to achieve multi-level data fusion;

[0077] Step S4: Generate a comprehensive anomaly map with confidence ratings and delineate potential resource areas, and combine drilling verification and machine learning to dynamically optimize model parameters.

[0078] This method for exploring medium-deep geothermal water resources based on multi-source data fusion can, through the fusion processing of multi-source data, integrate the advantages of different types of data, comprehensively characterize the potential characteristics of geothermal water resources in the target area, and improve the systematicness of the exploration process and the accuracy of resource identification; Dynamically optimizing model parameters can make the method adapt to different exploration scenarios and enhance the self-adaptability and reliability of the overall process.

[0079] Among them, in step S1:

[0080] The geological data includes formation lithology, fault structure, and hydrogeological parameters;

[0081] Geophysical data includes resistivity data (accuracy ≤ 0.1 Ω·m), gravity data (resolution ≤ 0.1 mGal), and seismic shear wave velocity structure data;

[0082] Geochemical data includes chemical components and isotope composition of groundwater;

[0083] Remote sensing data includes thermal infrared radiation images (spatial resolution ≤ 1 m) and multispectral vegetation index data.

[0084] This scheme clarifies the specific content and accuracy requirements of various types of data, ensures that the collected data covers multi-dimensional information such as geology, physical properties, chemical properties, and remote sensing, provides comprehensive and high-precision basic data support for subsequent fusion analysis, and avoids exploration deviations caused by data missing or insufficient accuracy.

[0085] Among them, the preprocessing in step S2 includes:

[0086] Step S2a: Perform sub-band decomposition on the original data using the dual-tree complex wavelet transform to filter out high-frequency noise and low-frequency drift;

[0087] Step S2b: Perform principal component analysis on the data of each frequency band, and extract the principal component reconstruction data with a contribution rate ≥ 85%;

[0088] Step S2c: Normalize the multi-source data based on the improved Z-score method to eliminate the dimensional difference.

[0089] In this scheme, the preprocessing process uses wavelet packet transform for frequency band noise reduction, principal component analysis for dimensionality reduction, and normalization processing, effectively removing noise interference in the data, reducing data redundancy, and unifying the dimension, improving the quality and compatibility of multi-source data, and laying a high-quality data foundation for subsequent fusion modeling.

[0090] Among them, in step S3:

[0091] Fuzzy inference uses a Gaussian membership function to quantify the feature mapping;

[0092] The information entropy weight is dynamically adjusted by calculating the uncertainty of each data source, and the weight distribution formula is:

[0093] Among them,

[0094] Among them:

[0095] H i : The information entropy of the i-th data source, representing the data uncertainty;

[0096] λ: The fusion sensitivity coefficient (value range 0.5 - 2.0), controlling the concentration degree of weight distribution;

[0097] σ 2 : The noise variance of the data source, calculated by the preprocessing module;

[0098] ∈: The smoothing constant (default 1e-5), which prevents the denominator from being zero.

[0099] This scheme dynamically adjusts the weights based on information entropy and noise level, can adaptively allocate fusion weights according to the uncertainty of data, enables low-noise and high-certainty data to dominate in the fusion, avoids the limitations of traditional fixed-weight methods, and improves the anti-interference ability of the fusion result to data fluctuations.

[0100] Example:

[0101] In the data fusion stage, the weights are dynamically adjusted according to the information entropy and noise level of each data source.

[0102] For example:

[0103] The geophysical data has a low noise variance (σ 2 = 0.02), and the information entropy H i = 0.3, so the weight is higher;

[0104] The remote sensing data has a high noise variance σ 2 = 0.15), and the information entropy H i = 0.8, so the weight is lower.

[0105] Technical effects:

[0106] By combining the exponential function with the noise variance, higher weights are preferentially given to low-noise and high-certainty data;

[0107] The weight allocation is adaptively adjusted, avoiding the solidification problem of traditional weighted averaging, and improving the robustness of the fusion result.

[0108] Working principle process:

[0109] 1. The preprocessing module calculates the σ of each data source 2 ;

[0110] 2. The information entropy module calculates H i ;

[0111] 3. Dynamically generate the weight w i , and input it into the fusion model.

[0112] Among them, the multi-level data fusion in step S3 includes:

[0113] Step S3a: Infer the probability relationship between data sources based on the Bayesian network;

[0114] Step S3b: Use the Dempster-Shafer evidence theory to solve the problem of conflict evidence fusion;

[0115] Step S3c: Dynamically adjust the fusion weight coefficient through the particle swarm optimization algorithm;

[0116] For conflict evidence fusion, a modified Dempster combination rule is adopted:

[0117]

[0118] Where:

[0119] ψ(B,C) = exp(-β·|conf(B,C)|): conflict attenuation factor, where β is the attenuation coefficient (ranging from 1 to 3);

[0120] conf(B,C): conflict degree between evidence B and C, calculated by the fuzzy inference engine;

[0121] K: conflict amount in the traditional Dempster rule;

[0122] δ: conflict compensation term (δ = 0.1K), to prevent the denominator from being too small.

[0123] This solution, with multi-level data fusion combining probability inference of Bayesian networks, improved conflict handling of evidence theory, and dynamic weight adjustment by particle swarm optimization, can effectively handle conflicts and uncertainties among multi-source data, alleviate the sensitivity problem of traditional fusion methods to highly conflicting evidence, and improve the stability and credibility of fusion results in complex data scenarios.

[0124] Example:

[0125] When the resistivity data (evidence B) conflicts with the seismic data (evidence C) (conf(B,C) = 0.6), the weight of the conflicting evidence is reduced by the attenuation factor ψ. For example:

[0126] When β = 2, ψ = exp(-2×0.6) ≈ 0.30, significantly suppressing the influence of conflicting evidence.

[0127] Technical effects:

[0128] Introduce an exponential conflict attenuation factor to alleviate the sensitivity problem of the traditional Dempster rule to highly conflicting evidence;

[0129] The conflict compensation term δ avoids numerical instability in extreme conflict scenarios and improves the reliability of fusion.

[0130] Working principle process:

[0131] The fuzzy inference engine calculates the conflict degree conf(B,C) between evidences;

[0132] Adjust the weight of the evidence combination according to ψ(B, C);

[0133] Output the corrected fusion result m(A).

[0134] Among them, the dynamic optimization model parameters in step S4 include:

[0135] Step S4a: Obtain underground core and water sample data through drilling and sampling;

[0136] Step S4b: Use the support vector machine (SVM) algorithm to compare the fusion result with the actual data and calculate the error rate;

[0137] Step S4c: If the error rate exceeds the threshold, reversely adjust the Bayesian network parameters and the fuzzy membership function.

[0138] This solution uses drilling data and machine learning algorithms to dynamically optimize the model parameters, corrects the theoretical model through the feedback of actual exploration data, forms a closed loop of "exploration - verification - optimization", ensures that the fusion model matches the actual geological conditions, and continuously improves the accuracy of resource exploration.

[0139] Among them, step S4 also includes:

[0140] Construct a three-dimensional geological-thermodynamic coupling model based on the fusion result. The model includes:

[0141] Three-dimensional grid model of formation lithology (resolution ≤ 50m);

[0142] Three-dimensional distribution model of fault structures;

[0143] Dynamic distribution field of rock thermal conductivity.

[0144] This solution constructs a three-dimensional geological-thermodynamic coupling model, realizes the spatial distribution modeling of formation lithology, fault structures and thermal conductivity, intuitively presents the occurrence environment of underground hot water resources, and provides a quantitative analysis basis for resource potential assessment in three-dimensional space dimensions.

[0145] Among them, the three-dimensional geological-thermodynamic coupling model also includes a spatial distribution model of fracture networks, a spatial distribution model of terrestrial heat flow, a thermodynamic model and a fluid flow model, enabling the following technological improvements on the original basis for the three-dimensional geological-thermodynamic coupling model:

[0146] 1. Fracture network modeling:

[0147] Accurately depict the spatial distribution characteristics of underground fractures, reveal the key channels and reservoir space distributions of hot water migration, and provide a structural basis for the analysis of resource occurrence laws.

[0148] 2. Analysis of terrestrial heat flow distribution:

[0149] Quantify the geothermal anomaly characteristics of the region, and combine with the dynamic field of thermal conductivity to locate the heat flow enrichment area, enhancing the spatial directivity of resource potential assessment.

[0150] 3. Thermodynamic behavior simulation:

[0151] Couple the temperature field with the thermal physical properties of rocks to simulate the heat transfer process and thermal equilibrium state of the heat reservoir, and evaluate the long-term stability and sustainable development potential of the reservoir.

[0152] 4. Fluid flow dynamic prediction:

[0153] Based on the non-Darcy flow equation and the fracture network model, simulate the pressure distribution, flow path and dynamic response after exploitation of the geothermal water underground, and optimize the design of the development plan.

[0154] Overall technical effect

[0155] The new sub-model realizes the full-dimensional analysis of the occurrence environment of geothermal water resources through multi-physics field coupling, including geological structure, thermodynamic characteristics and fluid dynamic behavior. Its technical effects are as follows:

[0156] Refined modeling: Expand from a single geological structure to multi-field coupling of heat-flow-force, enhancing the characterization ability of complex reservoirs;

[0157] Dynamic prediction ability: Combine the fluid flow model with the thermodynamic simulation to support the visual prediction and risk assessment of the resource exploitation process;

[0158] Upgrade of decision-making support: Through the integration of terrestrial heat flow and fracture network data, provide a scientific basis for target area optimization, well location deployment and development strategy formulation.

[0159] Summary: The supplementary scheme significantly enhances the comprehensive analysis and prediction ability of the three-dimensional coupling model through the combination of multi-dimensional modeling and dynamic simulation, providing more comprehensive technical support for the precise exploration and efficient development of geothermal water resources.

[0160] Among them, the three-dimensional geological-thermodynamic coupling model solves the non-Darcy flow heat conduction equation by the finite volume method, and combines the Monte Carlo simulation to evaluate the uncertainty of resource quantity prediction. The solution of the non-Darcy flow heat conduction equation adopts the following modified form:

[0161]

[0162] Parameter description:

[0163] The non-linear flow coefficient, φ is the porosity, μ is the fluid viscosity, and k is the permeability;

[0164] γ: Temperature decay coefficient (with a value range of 0.01 - 0.1), representing the influence of high temperature on flow resistance;

[0165] P: Fluid pressure field, obtained through hydrodynamic simulation.

[0166] This solution improves the solution method of the non - Darcy flow heat conduction equation, introduces a temperature - dependent energy dissipation term, accurately depicts the coupling relationship between underground fluid flow and heat conduction in a high - temperature environment, combines Monte Carlo simulation to evaluate and predict uncertainty, and improves the scientificity and accuracy of resource quantity calculation under complex geothermal reservoir conditions.

[0167] Example:

[0168] In a high - temperature reservoir (T > 150 °C), the e -γT term significantly reduces the flow energy loss. For example:

[0169] When γ = 0.05 and T = 200 °C, e -0.05×200 ≈ 0.0067, reflecting the inhibitory effect of high temperature on flow.

[0170] Technical effects:

[0171] By introducing a temperature - dependent exponential term, more accurately depict the energy dissipation of non - Darcy flow in a high - temperature environment;

[0172] Combined with the porosity - permeability dynamic correlation model, improve the inversion accuracy of resource quantity.

[0173] Working principle process:

[0174] 1. The hydrodynamic module calculates the pressure field P;

[0175] 2. The thermodynamics module inputs the temperature field T;

[0176] 3. Simultaneously solve the equations and output the three - dimensional geothermal reservoir distribution.

[0177] This embodiment also provides a deep - medium underground hot water resource exploration device based on multi - source data fusion, used to execute the above - mentioned deep - medium underground hot water resource exploration method based on multi - source data fusion, including: a data acquisition module, a data pre - processing module, a data fusion module, and a verification and correction module. The data acquisition module is connected to the data pre - processing module, the data fusion module is connected to the data pre - processing module, and the verification and correction module is connected to the data fusion module, where:

[0178] The data acquisition module integrates a high - precision gravimeter (resolution ≤ 0.1 mGal), a distributed optical fiber temperature measurement system (temperature measurement accuracy ± 0.1 °C), and an unmanned aerial vehicle - borne multi - spectral thermal infrared imager;

[0179] The data preprocessing module configures a wavelet packet transform unit accelerated by FPGA and a parallel principal component analysis unit of GPU;

[0180] The data fusion module includes a Bayesian network modeling unit, an evidence theory inference engine, and a dynamic weight optimization unit;

[0181] The verification and correction module realizes closed-loop optimization through a drilling equipment control unit and a machine learning algorithm.

[0182] Through integrating high-precision acquisition equipment, FPGA / GPU acceleration processing units, and a multi-module collaborative architecture, this exploration device realizes the full-process automation and high efficiency from data acquisition, preprocessing to fusion verification, reduces the cost of manual intervention, and improves the efficiency and real-time performance of exploration operations.

[0183] Among them, the data acquisition module also includes: a downhole three-component microseismic monitoring array and an automatic on-line analyzer for fluid chemical components, where:

[0184] The downhole three-component microseismic monitoring array is used to obtain seismic wave data with a depth ≥ 3 km;

[0185] The automatic on-line analyzer for fluid chemical components real-time detects the chemical components and isotope content of groundwater.

[0186] The data acquisition module adds a downhole microseismic monitoring array and an on-line chemical analyzer, which can obtain deep seismic wave data and real-time fluid composition information, expand the depth and real-time performance of data acquisition, and provide richer original data for the analysis of deep geothermal reservoir structures and the study of hydrochemical characteristics.

[0187] Among them, the data acquisition module also includes: a borehole fracture imaging system and a distributed optical fiber water-richness monitor, where:

[0188] The borehole fracture imaging system obtains three-dimensional spatial distribution data of the fracture width, density, and orientation of the borehole wall through downhole high-definition cameras and laser scanning technology;

[0189] Technical parameters: imaging resolution ≤ 1 mm, detection depth ≥ 3 km, supporting real-time transmission of the three-dimensional model of the fracture network.

[0190] Technical effect: directly reveals the geometric shape and connectivity of deep geothermal reservoir fractures, and provides high-precision measured data for the construction of fracture network models.

[0191] The distributed optical fiber water-richness monitor uses fiber optic sensing technology to arrange distributed temperature-strain sensors along the borehole, real-time monitors the changes in formation temperature gradient, pore water pressure, and permeability, and inversely calculates the distribution of water-richness;

[0192] Technical parameters: Spatial resolution ≤ 0.5 m, temperature measurement accuracy ±0.1 °C, strain sensitivity ≤ 1 με.

[0193] Technical effects: Dynamically capture the characteristics of groundwater activities and the spatial distribution of water-rich areas, and evaluate the recharge capacity of the thermal reservoir in combination with chemical component data.

[0194] In summary:

[0195] Fracture imaging system: Break through the indirect speculation of fractures by traditional geophysical methods, directly obtain the three-dimensional spatial distribution of the fracture network through in-situ imaging, and the modeling accuracy is improved by ≥40%;

[0196] Support the refined identification of deep (≥3 km) fractures, and avoid reservoir evaluation deviation caused by data loss.

[0197] Fiber optic water-rich monitor: Realize the real-time dynamic monitoring of water-rich parameters, combine temperature and strain data to accurately locate high-permeability areas;

[0198] Link with chemical analyzers to reveal the spatio-temporal evolution laws of hot water migration paths and chemical components, and provide data support for the sustainable development of resources.

[0199] The new solution fills the gap in the direct measurement of fracture networks and water richness by traditional exploration technologies, forms a "structure-physical property-fluid" trinity data acquisition system, and significantly enhances the comprehensive analysis ability of medium-deep thermal reservoir systems.

[0200] The working process of the medium-deep geothermal water resource exploration device based on multi-source data fusion is as follows:

[0201] 1. Data acquisition stage:

[0202] Gravity and geothermal data: High-precision gravimeters and distributed fiber optic temperature measurement systems simultaneously collect underground density field and temperature field data;

[0203] Remote sensing data: Unmanned aerial vehicle (UAV)-borne thermal infrared imager obtains surface thermal anomalies and vegetation index distributions;

[0204] Deep data: Downhole microseismic monitoring arrays transmit seismic wave data at depths ≥3 km in real time, and automatic fluid analyzers online detect the chemical components of groundwater.

[0205] 2. Pretreatment stage:

[0206] Noise reduction processing: The wavelet packet transform unit accelerated by FPGA performs frequency division decomposition on the original data to filter out high-frequency noise and low-frequency drift;

[0207] Feature extraction: The GPU parallel principal component analysis unit extracts the principal components with a contribution rate ≥85% and reconstructs the standardized data;

[0208] Normalization: The improved Z-score method eliminates the dimensional difference and outputs data in a unified format to the storage system.

[0209] 3. Data Fusion Stage:

[0210] Hierarchical Fusion:

[0211] Data Layer: The Bayesian network modeling unit infers the probabilistic dependence relationship of multi-source data;

[0212] Feature Layer: The fuzzy inference engine maps multi-source features to the same fuzzy space, and the dynamic weight optimization unit assigns information entropy weights;

[0213] Decision Layer: The evidence theory inference engine processes conflicting evidence and outputs a comprehensive anomaly map with confidence ratings.

[0214] 4. Verification and Correction Stage:

[0215] Drilling Verification: The target area is delineated according to the anomaly map, and the drilling equipment control unit drives the drill rig to take samples to obtain core and water sample data;

[0216] Machine Learning Optimization: The support vector machine (SVM) compares the fusion results with the drilling data and reversely adjusts the parameters of the Bayesian network and the fuzzy membership function;

[0217] Dynamic Iteration: The corrected parameters are fed back to the fusion module, and the loop optimization is performed until the error rate meets the standard.

[0218] 5. Result Output:

[0219] 3D Modeling: Based on the fusion results, a geological-thermodynamic coupling model is constructed to visualize the thermal reservoir distribution and resource quantity prediction;

[0220] Decision Support: Output a recommendation for the drilling target area and an evaluation report on the recoverable amount of the thermal reservoir to guide actual exploration and development.

[0221] Through modular design and intelligent feedback mechanism, the full-chain automation of multi-source data from acquisition to decision-making is realized. The expansion of the data acquisition module enhances the monitoring ability of deep geology and fluid dynamics; the heterogeneous computing architecture of the preprocessing and fusion module improves the processing efficiency; the closed-loop optimization mechanism of the verification and correction module significantly improves the exploration accuracy and reliability. The overall solution shows high adaptability and engineering practicability under complex geological conditions.

[0222] In summary, the medium-deep geothermal water resource exploration method and device based on multi-source data fusion provided in this embodiment have the following advantages:

[0223] Through the systematic integration and dynamic optimization of multi-source data, the present invention breaks through the limitations of single-data exploration, effectively handles data noise, conflicts, and uncertainty problems, and improves the accuracy and reliability of deep and medium-depth underground hot water resource exploration; the constructed three-dimensional coupling model and the improved solution method for the heat conduction equation accurately characterize the heat reservoir characteristics under complex geological-thermodynamic environments, and combined with automated hardware devices, realize efficient operation throughout the process, providing an integrated solution for the scientific development of underground hot water resources.

[0224] Overall work process

[0225] 1. Data collection: Use high-precision equipment to obtain geological, geophysical, geochemical, and remote sensing data of the target area, covering various types of information such as formation lithology, resistivity, groundwater chemical components, and thermal infrared images.

[0226] 2. Pretreatment: Improve data quality and unify the dimension through dual-tree complex wavelet transform frequency division noise reduction, principal component analysis to extract high-contribution features, and improved Z-score normalization.

[0227] 3. Multi-level fusion: Construct a Bayesian network to represent the probability dependence relationship of data, combine fuzzy inference and dynamic weight allocation (based on information entropy and noise level), and use the improved evidence theory to process conflicting evidence to achieve hierarchical fusion of multi-source data.

[0228] 4. Verification and optimization: Generate a comprehensive anomaly map with confidence ratings to delineate potential areas, obtain actual data through drilling and sampling, use support vector machines to compare the fusion results, and reverse-adjust the model parameters; construct a three-dimensional geological-thermodynamic coupling model, solve the improved non-Darcy flow heat conduction equation, evaluate the uncertainty of resource quantity prediction, and form a closed-loop optimization.

[0229] The above are only preferred embodiments of the present invention, and do not limit the implementation manners and protection scope of the present invention. For those skilled in the art, it should be realized that any equivalent replacement and obvious changes made by using the description and illustrations of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for exploring medium-deep geothermal water resources based on multi-source data fusion, characterized in that, The following steps are involved: Step S1: Collect multi-source data of the target area, including geological data, geophysical data, geochemical data and remote sensing data; Step S2: pre-processing the multi-source data, including wavelet packet transform frequency decomposition, principal component analysis noise reduction and normalization processing; Step S3: Construct a Bayesian network model to characterize the probabilistic dependency relationship between data sources, and combine fuzzy reasoning with information entropy weight distribution to achieve multi-level data fusion; Step S4: Generate a comprehensive anomaly map with confidence ratings and delineate potential resource areas, combining drilling verification with machine learning to dynamically optimize model parameters.

2. The exploration method for medium-deep geothermal water resources based on multi-source data fusion according to claim 1, wherein In step S1: The geological data include stratum lithology, fracture structure and hydrogeological parameters; The geophysical data include resistivity data, gravity data and seismic shear wave velocity structure data; The geochemical data include groundwater chemical composition and isotopic composition; The remote sensing data includes thermal infrared radiation images and multispectral vegetation index data.

3. The exploration method of medium-deep geothermal water resources based on multi-source data fusion according to claim 1, characterized in that The pre-processing in step S2 includes: Step S2a: Decompose the original data into frequency bands using dual-tree complex wavelet transform to filter out high-frequency noise and low-frequency drift; Step S2b: Perform principal component analysis on the data of each frequency band, extract the principal components with a contribution rate ≥ 85% and reconstruct the data; Step S2c: Normalize the multi-source data based on the improved Z-score method to eliminate dimensional differences.

4. The exploration method for medium-deep geothermal water resources based on multi-source data fusion according to claim 1, wherein, In step S3: The fuzzy reasoning uses a Gaussian membership function to quantify the feature map; The information entropy weight is dynamically adjusted by calculating the uncertainty of each data source, and the weight distribution formula is: Among them, in: H i : Information entropy of the i-th data source, representing data uncertainty; λ: Fusion sensitivity coefficient (range: 0.5 to 2.0), which controls the degree of concentration of weight distribution; σ 2 : The noise variance of the data source, calculated by the preprocessing module; ∈: Smoothing constant (default 1e-5), prevents the denominator from being zero.

5. The exploration method for medium-deep geothermal water resources based on multi-source data fusion according to claim 1, characterized in that The multi-level data fusion in step S3 includes: Step S3a: inferring the probabilistic relationship between data sources based on the Bayesian network; Step S3b: Use Dempster-Shafer evidence theory to solve the problem of fusion of conflicting evidence; Step S3c: Dynamically adjust the fusion weight coefficient through the particle swarm optimization algorithm; The conflict evidence fusion adopts the modified Dempster combination rule: in: ψ(B,C)=exp(-β·|conf(B,C)|): conflict attenuation factor, where β is the attenuation coefficient; conf(B,C): the degree of conflict between evidence B and C; K: the amount of conflict in the traditional Dempster rule; δ: conflict compensation term (δ=0.1K).

6. The exploration method for medium-deep geothermal water resources based on multi-source data fusion according to claim 1, characterized in that, The dynamic optimization model parameters in step S4 include: Step S4a: Obtaining underground core and water sample data through drilling sampling; Step S4b: using the support vector machine algorithm to compare the fusion result with the actual data and calculate the error rate; Step S4c: If the error rate exceeds the threshold, reversely adjust the Bayesian network parameters and the fuzzy membership function.

7. The exploration method for medium-deep geothermal water resources based on multi-source data fusion according to claim 1, characterized in that, Step S4 further includes: A three-dimensional geological-thermodynamic coupling model is constructed based on the fusion results. The three-dimensional geological-thermodynamic coupling model includes: Three-dimensional grid model of stratum lithology; Three-dimensional distribution model of fault structure; Dynamic distribution field of rock thermal conductivity.

8. The exploration method of medium-deep geothermal water resources based on multi-source data fusion according to claim 7, characterized in that The three-dimensional geological-thermodynamic coupling model solves the non-Darcy flow heat conduction equation by the finite volume method and combines Monte Carlo simulation to evaluate the uncertainty of resource quantity prediction. The solution of the non-Darcy flow heat conduction equation adopts the following modified form: Parameter description: The non - linear flow coefficient, φ is the porosity, μ is the fluid viscosity, and k is the permeability; γ: Temperature attenuation coefficient; P: Fluid pressure field.

9. An exploration device for medium-deep geothermal water resources based on multi-source data fusion, characterized in that, To implement the exploration method for medium-deep geothermal water resources based on multi-source data fusion according to any one of claims 1-8, including: Data acquisition module, integrating a high-precision gravimeter, a distributed optical fiber temperature measurement system, and an airborne multi-spectral thermal infrared imager; Data preprocessing module, configured with a wavelet packet transform unit accelerated by FPGA and a GPU parallel principal component analysis unit; Data fusion module, including a Bayesian network modeling unit, an evidence theory inference engine, and a dynamic weight optimization unit; Verification and correction module, realizing closed-loop optimization through a drilling equipment control unit and a machine learning algorithm.

10. The exploration device for medium-deep geothermal water resources based on multi-source data fusion according to claim 9, characterized in that, The data acquisition module further includes: Downhole three-component microseismic monitoring array, used to obtain seismic wave data with a depth ≥ 3 km; Automatic on-line analyzer for fluid chemical components, which can detect the chemical components and isotope content of groundwater in real time.

Images