Ore prospecting method for predicting migration of ore-forming fluid based on AI model

Abstract

The invention discloses a prospecting method for predicting migration of metallogenic fluid based on an AI model, and relates to the technical field of mineral resource exploration. The method comprises the following steps: acquiring geological data and fluid data of target mineralization; performing correlation analysis based on the geological data and the fluid data, and extracting correlation features; performing AI model construction and training according to the geological data, the fluid data and the associated data, determining the trained model as an ore-forming fluid migration prediction model, and determining a migration path and a mineral precipitation position of the ore-forming fluid by using the ore-forming fluid migration prediction model; and constructing a three-dimensional model according to the geological data, the migration path of the metallogenic fluid and the mineral precipitation position, and visually displaying the migration process of the metallogenic fluid based on the three-dimensional model. According to the method, the prediction accuracy of the migration of the metallogenic fluid can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of mineral resource exploration, and in particular to a prospecting method for predicting the migration of ore-forming fluids based on an AI model. Background Art

[0002] In current prospecting practice, the traditional methods for predicting the migration of ore-forming fluids and determining the location of mineral deposits mainly rely on the empirical judgment of geologists, geological statistical analysis and simple mathematical models. However, these methods have many limitations.

[0003] First, the acquisition and processing of geological data often rely on manual operations, which is not only time-consuming and labor-intensive, but also prone to human errors. Especially when faced with massive, multi-dimensional geological data, the processing efficiency and accuracy of traditional methods are seriously challenged.

[0004] Secondly, in the correlation analysis of geological data and fluid data, traditional methods can only perform simple statistical analysis, and it is difficult to deeply explore the intrinsic connections and potential laws between the data, which leads to an insufficient understanding of the migration mechanism of mineralizing fluids, and the accuracy and reliability of the prediction results are greatly reduced.

[0005] Therefore, there is an urgent need for a prospecting method based on AI models to predict the migration of ore-forming fluids, which can overcome the shortcomings of existing technologies and provide strong support for the exploration and development of mineral resources. Summary of the invention

[0006] The purpose of the present invention is to provide a prospecting method for predicting the migration of ore-forming fluids based on an AI model, which can improve the prediction accuracy of the migration of ore-forming fluids.

[0007] To achieve the above object, the present invention provides the following solutions:

[0008] A prospecting method for predicting the migration of ore-forming fluids based on an AI model, comprising:

[0009] Obtaining geological data and fluid data of target mineralization; the geological data includes geological, geophysical, geochemical and remote sensing data; the fluid data includes temperature, pressure and fluid composition;

[0010] Performing correlation analysis based on the geological data and the fluid data, and extracting correlation features;

[0011] constructing and training an AI model according to the geological data, the fluid data and the associated data, determining the trained model as a mineralizing fluid migration prediction model, and using the mineralizing fluid migration prediction model to determine the migration path of the mineralizing fluid and the location of mineral precipitation;

[0012] A three-dimensional model is constructed based on the geological data, the migration path of the ore-forming fluid and the location of mineral precipitation, and a visual display of the migration process of the ore-forming fluid based on the three-dimensional model is performed.

[0013] Optionally, before constructing and training the AI ​​model, it also includes: preprocessing the geological data and the fluid data; the preprocessing adopts a numerical resampling algorithm or an outlier dynamic screening algorithm.

[0014] Optionally, the processing process of the numerical resampling algorithm is:

[0015] First, the validity and rationality of the geological data and the fluid data are judged: a range threshold of validity and rationality is set, and when the geological data and the fluid data meet the range threshold, the next step is entered;

[0016] Then, the geological data and the fluid data are respectively tested for continuity within a set time length: when there are missing points in the geological data and the fluid data, they are supplemented by quadratic Lagrange interpolation to obtain resampled data;

[0017] Finally, a window function method is used to construct an FIR digital filter, and the FIR digital filter is used to filter the resampled data to obtain valid data.

[0018] Optionally, the processing process of the outlier dynamic screening algorithm is:

[0019] The geological data and the fluid data are placed in different buffers for temporary storage according to the set cache time. For the buffers that have completed temporary storage, the data in the set buffers are popped out in sequence, and dynamic anomaly detection is performed with the set range thresholds of validity and rationality to screen out abnormal values ​​and obtain valid data.

[0020] Optionally, the order of popping is first in, last out.

[0021] Optionally, the construction and training process of the ore-forming fluid migration prediction model includes:

[0022] A pre-trained network for building an AI model based on an attention mechanism and a generative adversarial network; the pre-trained network includes an input layer, a hidden layer, and an output layer connected in sequence; the hidden layer includes a convolutional layer, a recurrent layer, and a fully connected layer connected in sequence;

[0023] The pre-trained network is trained using the geological data, the fluid data and the associated data, and Dropout or L2 regularization is used to prevent network overfitting. When the trained network meets the set iteration conditions or accuracy, the trained network is determined to be the ore-forming fluid migration prediction model.

[0024] Optionally, the loss function used in the training is RMSE loss and MAE loss.

[0025] Optionally, the method further includes: building a data monitoring interface for visually displaying the migration process of the ore-forming fluid, and using a data visualization tool to dynamically display it on the data monitoring interface.

[0026] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0027] The present invention discloses a prospecting method for predicting the migration of ore-forming fluids based on an AI model, the method comprising obtaining geological data and fluid data of target mineralization; performing correlation analysis based on the geological data and the fluid data, and extracting correlation features; constructing and training an AI model according to the geological data, the fluid data, and the correlation data, determining the trained model as an ore-forming fluid migration prediction model, and using the ore-forming fluid migration prediction model to determine the migration path of the ore-forming fluid and the mineral precipitation position; constructing a three-dimensional model according to the geological data, the migration path of the ore-forming fluid, and the mineral precipitation position, and visually displaying the ore-forming fluid migration process based on the three-dimensional model. The present invention can improve the prediction accuracy of ore-forming fluid migration. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0029] Figure 1 The present invention is a flow chart of the prospecting method for predicting the migration of ore-forming fluids based on the AI ​​model. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] The purpose of the present invention is to provide a prospecting method for predicting the migration of ore-forming fluids based on an AI model, which can improve the prediction accuracy of the migration of ore-forming fluids.

[0032] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0033] like Figure 1 As shown, the present invention provides a prospecting method for predicting the migration of ore-forming fluids based on an AI model, comprising:

[0034] A prospecting method for predicting the migration of ore-forming fluids based on an AI model, comprising:

[0035] Step 100: Acquire geological data and fluid data of target mineralization; the geological data include geological, geophysical, geochemical and remote sensing data; the fluid data include temperature, pressure and fluid composition.

[0036] Step 200: Perform correlation analysis based on the geological data and the fluid data, and extract correlation features.

[0037] Step 300: Construct and train an AI model based on the geological data, the fluid data and the associated data, determine the trained model as a mineralizing fluid migration prediction model, and use the mineralizing fluid migration prediction model to determine the migration path of the mineralizing fluid and the location of mineral precipitation.

[0038] Step 400: construct a three-dimensional model based on the geological data, the migration path of the ore-forming fluid and the location of mineral precipitation, and visualize the migration process of the ore-forming fluid based on the three-dimensional model.

[0039] Before the AI ​​model is constructed and trained in step 300, the method further includes: preprocessing the geological data and the fluid data; the preprocessing adopts a numerical resampling algorithm or an outlier dynamic screening algorithm.

[0040] As a specific implementation, the processing process of the numerical resampling algorithm is:

[0041] First, the validity and rationality of the geological data and the fluid data are judged: a range threshold of validity and rationality is set, and when the geological data and the fluid data meet the range threshold, the next step is entered; then, the continuity of the geological data and the fluid data is detected within a set time length: when there are missing points in the geological data and the fluid data, quadratic Lagrange interpolation is used to supplement them to obtain resampled data; finally, a window function method is used to construct an FIR digital filter, and the FIR digital filter is used to filter the resampled data to obtain valid data.

[0042] As a specific implementation, the processing process of the outlier dynamic screening algorithm is as follows:

[0043] According to the set cache time, the geological data and the fluid data are put into different buffers for temporary storage. For the buffers that have completed temporary storage, the data in the set buffers are popped out in sequence, and dynamic anomaly detection is performed with the set range threshold of validity and rationality to filter out abnormal values ​​and obtain valid data. The order of the popping is first in, last out.

[0044] The model needs to be trained before prediction is made, so a process of constructing and training the ore-forming fluid migration prediction model is provided, which specifically includes:

[0045] A pre-trained network of an AI model is constructed based on an attention mechanism and a generative adversarial network; the pre-trained network includes an input layer, a hidden layer, and an output layer connected in sequence; the hidden layer includes a convolutional layer, a loop layer, and a fully connected layer connected in sequence; the pre-trained network is trained using the geological data, the fluid data, and the associated data, and Dropout or L2 regularization is used to prevent the network from overfitting. When the trained network meets the set iteration conditions or accuracy, the trained network is determined to be the ore-forming fluid migration prediction model. The loss functions used in the training are RMSE loss and MAE loss.

[0046] As a specific implementation, the visual display of step 400 also includes: building a data monitoring interface for visually displaying the mineralizing fluid migration process, and using a data visualization tool to dynamically display it on the data monitoring interface.

[0047] Based on the above technical solution, the following embodiments are provided.

[0048] Step 1: Data Collection

[0049] Geological Data Collection: Collect geological, geophysical, geochemical and remote sensing data of the target area.

[0050] Fluid Data Collection: Collect fluid temperature, pressure, and composition data in the target area.

[0051] Step 2: Data Preprocessing

[0052] Numerical resampling:

[0053] Determine the validity and rationality of the data and set the threshold range.

[0054] The data were checked for continuity and the missing data were supplemented using quadratic Lagrange interpolation.

[0055] Construct a FIR digital filter to filter the resampled data to obtain valid data.

[0056] Dynamic outlier removal:

[0057] Put the data into the buffer for temporary storage and pop it from the stack in a first-in, last-out order.

[0058] Dynamically detect outliers and filter them out to obtain valid data.

[0059] Step 3: Association analysis and feature extraction

[0060] Correlation analysis: Correlation analysis is performed based on preprocessed geological data and fluid data.

[0061] Feature extraction: Extract features related to the migration of ore-forming fluids.

[0062] Step 4: AI model construction and training

[0063] Pre-trained network construction: A pre-trained network is constructed based on the attention mechanism and the generative adversarial network, including input layer, hidden layer and output layer. The hidden layer includes convolutional layer, recurrent layer and fully connected layer.

[0064] Model training:

[0065] The pre-trained network is trained using geological data, fluid data, and associated data.

[0066] Use Dropout or L2 regularization to prevent overfitting.

[0067] RMSE loss and MAE loss are used as the loss functions for training.

[0068] When the network meets the set iteration conditions or accuracy, it is determined to be a prediction model for ore-forming fluid migration.

[0069] Step 5: Prediction of ore-forming fluid migration path and mineral precipitation location

[0070] Application of prediction model: Use the trained ore-forming fluid migration prediction model to determine the migration path of ore-forming fluids and the location of mineral precipitation.

[0071] Step 6: 3D model construction and visualization

[0072] Three-dimensional model construction: Three-dimensional model construction is carried out based on geological data, ore-forming fluid migration paths and mineral precipitation locations.

[0073] Visual display: Use data visualization tools to dynamically display the migration process of ore-forming fluids on the data monitoring interface.

[0074] Optional step: Building the data monitoring interface

[0075] Interface construction: Build a data monitoring interface to display dynamic data of the ore-forming fluid migration process.

[0076] Dynamic display: Use data visualization tools to dynamically display the migration process of ore-forming fluids on the interface.

[0077] Implementation Effect

[0078] By implementing the above methods, the geological exploration team can more accurately predict the migration path of ore-forming fluids and the location of mineral precipitation, improving the efficiency and success rate of mineral resource exploration. In addition, the construction and visualization of the 3D model provides the team with intuitive geological information, which helps to better understand the mineralization process and formulate exploration strategies.

[0079] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0080] This article uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only used to help understand the core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A prospecting method for predicting the migration of ore-forming fluids based on an AI model, characterized in that: include: Obtaining geological data and fluid data of target mineralization; the geological data includes geological, geophysical, geochemical and remote sensing data; the fluid data includes temperature, pressure and fluid composition; Performing correlation analysis based on the geological data and the fluid data, and extracting correlation features; constructing and training an AI model according to the geological data, the fluid data and the associated data, determining the trained model as a mineralizing fluid migration prediction model, and using the mineralizing fluid migration prediction model to determine the migration path of the mineralizing fluid and the location of mineral precipitation; A three-dimensional model is constructed based on the geological data, the migration path of the ore-forming fluid and the location of mineral precipitation, and a visual display of the migration process of the ore-forming fluid based on the three-dimensional model is performed.

2. The ore prospecting method for predicting the migration of ore-forming fluids based on an AI model according to claim 1, characterized in that: Before AI model construction and training, it also includes: preprocessing the geological data and the fluid data; the preprocessing adopts a numerical resampling algorithm or an outlier dynamic screening algorithm.

3. The ore prospecting method for predicting the migration of ore-forming fluids based on an AI model according to claim 2, characterized in that: The processing process of the numerical resampling algorithm is: First, the validity and rationality of the geological data and the fluid data are judged: a range threshold of validity and rationality is set, and when the geological data and the fluid data meet the range threshold, the next step is entered; Then, the geological data and the fluid data are respectively tested for continuity within a set time length: when there are missing points in the geological data and the fluid data, they are supplemented by quadratic Lagrange interpolation to obtain resampled data; Finally, a window function method is used to construct an FIR digital filter, and the FIR digital filter is used to filter the resampled data to obtain valid data.

4. The ore prospecting method for predicting the migration of ore-forming fluids based on an AI model according to claim 2, characterized in that: The processing process of the outlier dynamic screening algorithm is as follows: The geological data and the fluid data are placed in different buffers for temporary storage according to the set cache time. For the buffers that have completed temporary storage, the data in the set buffers are popped out in sequence, and dynamic anomaly detection is performed with the set range thresholds of validity and rationality to screen out abnormal values ​​and obtain valid data.

5. The ore prospecting method for predicting the migration of ore-forming fluids based on an AI model according to claim 4, characterized in that: The order of popping is first in, last out.

6. The ore prospecting method for predicting the migration of ore-forming fluids based on an AI model according to claim 1, characterized in that: The construction and training process of the ore-forming fluid migration prediction model includes: A pre-trained network for building an AI model based on an attention mechanism and a generative adversarial network; the pre-trained network includes an input layer, a hidden layer, and an output layer connected in sequence; the hidden layer includes a convolutional layer, a recurrent layer, and a fully connected layer connected in sequence; The pre-trained network is trained using the geological data, the fluid data and the associated data, and Dropout or L2 regularization is used to prevent network overfitting. When the trained network meets the set iteration conditions or accuracy, the trained network is determined to be the ore-forming fluid migration prediction model.

7. The ore prospecting method for predicting the migration of ore-forming fluids based on an AI model according to claim 6, characterized in that: The loss functions used in the training are RMSE loss and MAE loss.

8. The ore prospecting method for predicting the migration of ore-forming fluids based on an AI model according to claim 1, characterized in that: Also includes: A data monitoring interface is constructed to visualize the migration process of the ore-forming fluid, and a data visualization tool is used to dynamically display the data monitoring interface.

Images