A prospecting prediction method based on AE-LightGBM model

Abstract

The present invention discloses a mineral prospecting prediction method based on the AE‑LightGBM model, which relates to the technical field of mineral prospecting prediction. Step S1: Acquire data of a study area including mineral points, non-mineral points and unknown mineral points to construct an original data set; Step S2: Train an autoencoder based on unlabeled data to obtain an encoded labeled data set; Step S3: Use a Bayesian optimization algorithm on the encoded labeled data set to determine the optimal hyperparameter combination of the LightGBM model, and train an optimal LightGBM prediction model based on this; Step S4: Use the optimal LightGBM prediction model to perform mineral prospecting prediction and evaluation on the study area. The present invention adopts the above-mentioned mineral prospecting prediction method based on the AE‑LightGBM model, which can make full use of the rich information of unlabeled data, and at the same time, combined with the guidance of labeled data, significantly improve the accuracy, generalization ability and stability of the model, which is of great significance in the field of mineral prospecting prediction.

Description

Technical Field

[0001] The present invention relates to the technical field of prospecting prediction, and in particular to a prospecting prediction method based on an AE-LightGBM model. Background Art

[0002] Mineral resources are a crucial foundation for national economic development and are of great significance to modern industry and social progress. With the continuous development and depletion of mineral resources, the difficulty of prospecting and prediction is increasing. With the development of information technology, many machine learning techniques are gradually being applied to prospecting and prediction, improving the efficiency and accuracy of prospecting.

[0003] Mineral prospecting and prediction tasks often involve a large amount of unlabeled data and a small amount of labeled data. Using only a small amount of labeled data for supervised learning can't fully capture the underlying patterns and regularities in the data, potentially resulting in poor model generalization. In contrast, combining the strengths of unsupervised and supervised learning can more effectively utilize all data. Unsupervised learning can extract useful feature representations from large amounts of unlabeled data, automatically discovering structures and patterns within the data, while supervised learning can make accurate predictions using a small amount of labeled data. This approach can fully leverage the rich information in unlabeled data while combining it with guidance from labeled data to significantly improve the model's accuracy, generalization, and stability. Summary of the Invention

[0004] The purpose of the present invention is to provide a prospecting prediction method based on the AE-LightGBM model to solve the problems raised in the above background technology, make full use of the rich information of unlabeled data, and combine with the guidance of labeled data to significantly improve the accuracy, generalization ability and stability of the model.

[0005] To achieve the above object, the present invention provides a prospecting prediction method based on the AE-LightGBM model, comprising the following steps:

[0006] Step S1: Acquire the research area data including mineral points, non-mineral points and unknown mineral points, and perform preprocessing operations to construct the original data set;

[0007] Step S2: train an autoencoder based on unlabeled data, compress the original dataset into a low-dimensional latent space through the encoder, and then restore the data through the decoder, automatically learn the most representative feature patterns in the data, and use the trained encoder to encode all mining points to obtain the encoded labeled dataset;

[0008] Step S3: On the encoded labeled dataset, use the Bayesian optimization algorithm to determine the optimal hyperparameter combination of the LightGBM model, and use it to train the optimal LightGBM prediction model;

[0009] Step S4: Use the optimal LightGBM prediction model to predict and evaluate the mineral exploration in the study area.

[0010] Preferably, in step S1, the data attributes of the study area data are obtained by extracting and interpolating the borehole data, specifically including:

[0011] Spatial attributes: coordinates; geological attributes: strata, lithology, and faults; geochemical attributes: grade, elements; geophysical attributes: polarizability, resistivity, and magnetic susceptibility;

[0012] Each data corresponds to a spatial coordinate of the study area, where the number of mineral points in the study area is at least 100 groups and the number of unknown mineral points is at least 10,000.

[0013] Preferably, the preprocessing operation in step S1 includes integrating attributes, labels and spatial coordinate information of the data; performing scaling processing on the attribute values; and removing duplicate samples.

[0014] Preferably, the labeled data set in step S2 is represented as [X L :Y L :I L ], the unlabeled dataset is represented as [X U :I U ], where X is the attribute matrix, Y is the label matrix, and I is the spatial coordinate matrix.

[0015] Preferably, in step S2, the autoencoder is composed of an encoder and a decoder, the decoder is composed of a multi-layer fully connected neural network, the encoder is composed of an embedding layer and a multi-layer fully connected neural network, and the embedding layer can map categorical variables into numerical vectors;

[0016] The fully connected network structures of the encoder and decoder are symmetrical. The number of neurons in each layer of the encoder gradually decreases, compressing the high-dimensional input data into a low-dimensional potential representation. The decoder increases the number of neurons layer by layer through a symmetrical structure, gradually restoring the low-dimensional representation to the original data dimension.

[0017] The autoencoder adopts a batch regularization strategy, uses the Adam optimizer to adjust the learning rate, and uses PReLU() as the activation function. The formula is as follows:

[0018]

[0019] Among them, α is the automatically learned parameter, and x is the input value;

[0020] The training data of the autoencoder is X in the unlabeled data U , the loss function is the mean square error MSE, the formula is as follows:

[0021]

[0022] Among them, n is the number of samples of data, x i is the i-th sample of the input, is the i-th sample reconstructed by the autoencoder.

[0023] Preferably, in step S2, the trained encoder is used to encode the data attributes of all data samples, and the input X L and X U , the output is the encoded attribute X' L and X' U , construct the encoded labeled dataset [X' L :Y L ], randomly divided into training set and test set.

[0024] Preferably, in step S3, the optimal hyperparameter combination of the LightGBM model is determined by a Bayesian optimization algorithm, and the objective function is set to the average F1 score of the k-fold cross validation on the training set, and the formula is as follows:

[0025]

[0026] Among them, k is the number of cross-validation folds, F1 (i) is the F1 score of the i-th fold.

[0027] Preferably, the LightGBM hyperparameters optimized by Bayesian optimization in step S3 include: number of iterations, learning rate, upper limit of leaf of decision tree, upper limit of depth of decision tree, category of gradient boosting, minimum number of samples on leaf, minimum split gain, regularization coefficient and feature sampling ratio;

[0028] The optimization number is no less than 100 times to obtain the best hyperparameter combination.

[0029] Preferably, in step S3, the hyperparameters of the LightGBM model are set according to the optimal hyperparameter combination, and training is performed on the training set. The loss function is set to cross-entropy, and the formula is as follows:

[0030]

[0031] Where n is the number of samples, y i is the true label of the i-th sample, p i is the probability that the model predicts a positive sample;

[0032] The best LightGBM model is obtained and preliminarily tested on the test set.

[0033] Preferably, the specific steps of step S4 are as follows:

[0034] Step S41: The attributes X' of all the encoded samples in the study area are L and X' U , as input;

[0035] Step S42: Use the optimal LightGBM model to perform prospecting prediction and obtain the mineralization probability of the entire study area;

[0036] Step S43: combining the predicted probability with the corresponding spatial coordinates to obtain the spatial distribution of the mineralization probability of the study area;

[0037] Step S44: perform result evaluation.

[0038] Therefore, the present invention adopts the above-mentioned prospecting prediction method based on the AE-LightGBM model, which can make full use of the rich information of unlabeled data and, combined with the guidance of labeled data, significantly improve the accuracy, generalization ability and stability of the model, which is of great significance in the field of prospecting prediction.

[0039] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a structural schematic diagram of an embodiment of a prospecting prediction method based on the AE-LightGBM model of the present invention;

[0041] Figure 2 A schematic diagram of a neural network architecture of an automatic encoder for a mineral prospecting prediction method based on the AE-LightGBM model of the present invention;

[0042] Figure 3 The figure is a ROC curve diagram of a comparative model of a prospecting prediction method based on the AE-LightGBM model of the present invention;

[0043] Figure 4 This is a ROC curve diagram of a model trained by a prospecting prediction method based on the AE-LightGBM model of the present invention. DETAILED DESCRIPTION

[0044] The technical solution of the present invention is further described below with reference to the accompanying drawings and embodiments.

[0045] Unless otherwise defined, the technical or scientific terms used in the present invention shall have the usual meanings understood by persons of ordinary skill in the field to which the present invention belongs. The words "first", "second" and similar terms used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Words such as "include" or "comprise" mean that the elements or objects preceding the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Words such as "connect" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0046] Example

[0047] See also Figure 1-4 The present invention provides a prospecting prediction method based on the AE-LightGBM model. In this embodiment, a manganese ore test park is used as the research area, and prospecting prediction is performed based on the collected geophysical and chemical data and other multi-source data.

[0048] like Figure 1 FIG. 1 is a flow chart of a prospecting prediction method based on the AE-LightGBM model of the present invention, which specifically includes the following steps:

[0049] Step S1 collects data from the study area, including 647 mineral points, 723 non-mineral points, and nearly 3.5 million unknown mineral points. The data attributes include spatial attributes (coordinates), geological attributes (strata, faults, folds), geochemical attributes (grades of 13 elements such as Mn, Cr, and Ni), and labels. Strata and labels are categorical variables, and the remaining attributes are numerical variables.

[0050] The various attributes were concatenated and integrated, and numerical attributes other than coordinates were discretized and scaled to obtain the original dataset. This dataset was then divided into unlabeled and labeled datasets based on labels. The unlabeled dataset was deduplicated, resulting in 137,018 samples. The labeled dataset was deduplicated and balanced, resulting in 1,036 samples. Table 1 shows a portion of the preprocessed data.

[0051] Table 1 Partial data sheet

[0052]

[0053]

[0054] Step S02: Use the unlabeled data after deduplication (excluding coordinates and labels) as training data for the autoencoder, where Figure 2 Schematic diagram of the neural network architecture of the autoencoder.

[0055] The autoencoder uses a batch normalization strategy, with the batch size (batch_size) set to 64; the number of epochs of the dataset is set to 100; the Adam optimizer is used to adjust the learning rate, with an initial learning rate of 0.001; and PReLU() is used as the activation function, with the following formula:

[0056]

[0057] Among them, α is a parameter that can be automatically learned, and x is the input value;

[0058] The loss function of the autoencoder is the mean square error (MSE), which is formulated as follows:

[0059]

[0060] Where n is the number of samples of data, x i is the i-th sample of the input, is the i-th sample reconstructed by the autoencoder.

[0061] All data are encoded using the trained encoder module, and some of the encoded data are shown in Table 2. The encoded labeled dataset is randomly divided into a training set (75%) and a test set (25%).

[0062] Table 2 Partial data table after encoding

[0063] X Y Feature 0 Feature 1 Feature 2 Feature 3 label 887133 3120000 -4.6451054 5.75887 -7.9776893 4.170929 1 887457 3121000 -4.425543 5.350671 -7.3455424 4.205764 1 883972 3097994 -2.613967 4.137289 -6.745719 6.0801363 0 865162 3127244 -2.9887774 6.879778 -4.2890563 1.8771343 0 867112 3090974 -7.2686644 7.262398 -7.3756323 7.7210927 -1 858022 3140174 -0.54217523 2.9779255 -3.3129318 5.168526 -1

[0064] Step S03: Determine the optimal hyperparameter combination of the LightGBM model using the Bayesian optimization algorithm; the objective function is set to the average F1 score of the 5-fold cross-validation on the training set, and the formula is as follows:

[0065]

[0066] Among them, F1 (i) is the F1 score of the i-th fold.

[0067] The hyperparameters for optimization include the number of iterations, learning rate, upper limit of the leaf size of the decision tree, upper limit of the depth of the decision tree, minimum number of samples on a leaf, minimum split gain, regularization coefficient, and feature sampling ratio. The range of the parameters is shown in Table 3. The number of iterations is set to 100. The optimal hyperparameter combination is shown in Table 4.

[0068] Table 3 Parameter adjustment range table (k is the step size)

[0069] Hyperparameters Search Scope n_estimators [150,400],k＝50 learning_rate [0.01,0.1],k＝0.01 num_leaves [20,150],k＝1 max_depth [5,15],k＝1 min_data_in_leaf [1,50],k＝1 min_gain_to_split [0,1] reg_alpha [0,1] reg_lambda [0,1] feature_fraction [0.6,1] bagging_fraction [0.6,1]

[0070] Table 4 Optimal parameters

[0071]

[0072]

[0073] The hyperparameters of the LightGBM model are set according to the optimal hyperparameter combination, and training is performed on the training set; the loss function is set to cross-entropy, and the formula is as follows:

[0074]

[0075] Where n is the number of samples, y i is the true label of the i-th sample, p i is the probability that the model predicts a positive sample, and the best LightGBM model is obtained.

[0076] The comparison model is introduced. Compared with the model trained by the present invention, the autoencoder is not used to learn in unlabeled data. The rest of the technical route is the same as the present invention. The comparison model and the model trained by the present invention are tested on the test set, and their ROC curves are obtained respectively, as shown in Figure 2. Figure 3 、 4 shown.

[0077] In step S4, the comparison model and the model trained by the present invention are used to predict all samples, respectively, to obtain the metallogenic probability of the entire study area. This prediction is then combined with the corresponding spatial coordinates to obtain the spatial distribution of the metallogenic probability of the study area. The average metallogenic probability of the comparison model in the test area (a known mineral area somewhere in the study area) is 0.22, while the average metallogenic probability of the model trained by the present invention is 0.57.

[0078] Therefore, the present invention adopts the above-mentioned prospecting prediction method based on the AE-LightGBM model, which can make full use of the rich information of unlabeled data and, combined with the guidance of labeled data, significantly improve the accuracy, generalization ability and stability of the model, which is of great significance in the field of prospecting prediction.

[0079] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the same. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solutions of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A prospecting prediction method based on the AE-LightGBM model, characterized in that: The following steps are involved: Step S1: Acquire the research area data including mineral points, non-mineral points and unknown mineral points, and perform preprocessing operations to construct the original data set; Step S2: train an autoencoder based on unlabeled data, compress the original dataset into a low-dimensional latent space through the encoder, and then restore the data through the decoder, automatically learn the most representative feature patterns in the data, and use the trained encoder to encode all mining points to obtain the encoded labeled dataset; Step S3: On the encoded labeled dataset, use the Bayesian optimization algorithm to determine the optimal hyperparameter combination of the LightGBM model, and use it to train the optimal LightGBM prediction model; Step S4: Use the best LightGBM prediction model to predict and evaluate the mineral exploration in the study area; The labeled dataset in step S2 is represented as , the unlabeled dataset is represented as ,in, is the attribute matrix, is the label matrix, is the spatial coordinate matrix; In step S2, the autoencoder is composed of an encoder and a decoder, the decoder is composed of a multi-layer fully connected neural network, the encoder is composed of an embedding layer and a multi-layer fully connected neural network, and the embedding layer maps the categorical variable to a numerical vector; The fully connected network structures of the encoder and decoder are symmetrical. The number of neurons in each layer of the encoder gradually decreases, compressing the high-dimensional input data into a low-dimensional potential representation. The decoder increases the number of neurons layer by layer through a symmetrical structure, gradually restoring the low-dimensional representation to the original data dimension. The autoencoder adopts a batch regularization strategy, uses the Adam optimizer to adjust the learning rate, and uses PReLU() as the activation function. The formula is as follows: ； in, are the parameters for automatic learning, is the input value; The training data of the autoencoder is the unlabeled data , the loss function is the mean square error , the formula is as follows: ； in, is the number of data samples, For the input samples, The first samples.

2. The prospecting prediction method based on the AE-LightGBM model according to claim 1 is characterized in that: In step S1, the data attributes of the study area data are obtained by extracting and interpolating the borehole data, specifically including: Spatial attributes: coordinates; geological attributes: strata, lithology, and faults; geochemical attributes: grade, elements; geophysical attributes: polarizability, resistivity, and magnetic susceptibility; Each data corresponds to a spatial coordinate of the study area, where the number of mineral points in the study area is at least 100 groups and the number of unknown mineral points is at least 10,000.

3. The mineral prospecting prediction method based on the AE-LightGBM model according to claim 2, characterized in that: The preprocessing operation in step S1 includes integrating the attributes, labels and spatial coordinate information of the data; scaling the attribute values; and removing duplicate samples.

4. The mineral prospecting prediction method based on the AE-LightGBM model according to claim 3, characterized in that: In step S2, the trained encoder is used to encode the data attributes of all data samples, and the input and , the output is the encoded attribute and , construct the encoded labeled dataset , randomly divided into training set and test set.

5. The mineral prospecting prediction method based on the AE-LightGBM model according to claim 4, characterized in that: In step S3, the optimal hyperparameter combination of the LightGBM model is determined by the Bayesian optimization algorithm, and the objective function is set to the average F1 score of the k-fold cross validation on the training set, and the formula is as follows: ； in, is the number of cross-validation folds, For the The F1 score of the fold.

6. The prospecting prediction method based on the AE-LightGBM model according to claim 5 is characterized in that: The LightGBM hyperparameters optimized by Bayesian optimization in step S3 include: number of iterations, learning rate, upper limit of leaf of decision tree, upper limit of depth of decision tree, category of gradient boosting, minimum number of samples on leaf, minimum split gain, regularization coefficient and feature sampling ratio; The optimization number is no less than 100 times to obtain the best hyperparameter combination.

7. The mineral prospecting prediction method based on the AE-LightGBM model according to claim 6, characterized in that: In step S3, the hyperparameters of the LightGBM model are set according to the optimal hyperparameter combination, and training is performed on the training set. The loss function is set to cross-entropy, and the formula is as follows: ； Where n is the number of samples, is the true label of the i-th sample, is the probability that the model predicts a positive sample; The best LightGBM model is obtained and preliminarily tested on the test set.

8. The mineral prospecting prediction method based on the AE-LightGBM model according to claim 7, characterized in that: The specific steps of step S4 are as follows: Step S41: Attributes of all the encoded samples in the study area and , as input; Step S42: Use the optimal LightGBM model to perform prospecting prediction and obtain the mineralization probability of the entire study area; Step S43: combining the predicted probability with the corresponding spatial coordinates to obtain the spatial distribution of the mineralization probability of the study area; Step S44: perform result evaluation.

Images