Lithology Identification Method Research Articles

Hybrid Lithology Identification Method Based on Isometric Feature Mapping Manifold Learning and Particle Swarm Optimization-Optimized LightGBM

Hybrid Lithology Identification Method Based on Isometric Feature Mapping Manifold Learning and Particle Swarm Optimization-Optimized LightGBM

A Real‐time Lithological Identification Method based on SMOTE‐Tomek and ICSA Optimization

AbstractIn petroleum engineering, real‐time lithology identification is very important for reservoir evaluation, drilling decisions and petroleum geological exploration. A lithology identification method while drilling based on machine learning and mud logging data is studied in this paper. This method can effectively utilize downhole parameters collected in realtime during drilling, to identify lithology in real‐time and provide a reference for optimization of drilling parameters. Given the imbalance of lithology samples, the synthetic minority over‐sampling technique (SMOTE) and Tomek link were used to balance the sample number of five lithologies. Meanwhile, this paper introduces Tent map, random opposition‐based learning and dynamic perceived probability to the original crow search algorithm (CSA), and establishes an improved crow search algorithm (ICSA). In this paper, ICSA is used to optimize the hyperparameter combination of random forest (RF), extremely random trees (ET), extreme gradient boosting (XGB), and light gradient boosting machine (LGBM) models. In addition, this study combines the recognition advantages of the four models. The accuracy of lithology identification by the weighted average probability model reaches 0.877. The study of this paper realizes high‐precision real‐time lithology identification method, which can provide lithology reference for the drilling process.

A novel hybrid CNN–SVM method for lithology identification in shale reservoirs based on logging measurements

Shale oil and gas reservoirs are lithologically complex and heterogeneous and accurate identification of lithology is necessary for the correct identification of lithofacies. There is also a poor mapping relation between logging response and lithology, making reliable lithological identification difficult. We propose a hybrid CNN-SVM model for lithological identification of the shale reservoir in the southern Songliao Basin of Northeast China. As training data, seven conventional logging curves are used, including spontaneous potential (SP) and deep and shallow lateral resistivity (RD, RS) logs. The CNN automatically extracts feature information from well log data and lithology, while the SVM overcomes the problem of limited sample size. Using the receiver operator characteristic (ROC) curves and the area under the curve (AUC) values, we assess the effect of lithological classification. The accuracy of lithological identification for test well H2 is 91.95%, and the AUC of the hybrid model is 0.94, 0.98, and 0.99 in mudstone, shale, and sandstone, respectively. The hybrid model outperforms CNN and SVM in terms of the identification of three types of lithologies and is more stable in terms of AUC value and ROC curve shape. The lithological identification accuracy for test well H3 is 89.49%, which demonstrates that the method has much capacity for generalization and may be extensively utilized in the study area. Finally, from the perspective of model interpretability, SHapley Additive exPlanations (SHAP) is developed to increase transparency and further confirm the reliability of the hybrid model.

Intelligent Classification of Volcanic Rocks Based on Honey Badger Optimization Algorithm Enhanced Extreme Gradient Boosting Tree Model: A Case Study of Hongche Fault Zone in Junggar Basin

Lithology identification is the fundamental work of oil and gas reservoir exploration and reservoir evaluation. The lithology of volcanic reservoirs is complex and changeable, the longitudinal lithology changes a great deal, and the log response characteristics are similar. The traditional lithology identification methods face difficulties. Therefore, it is necessary to use machine learning methods to deeply explore the corresponding relationship between the conventional log curve and lithology in order to establish a lithology identification model. In order to accurately identify the dominant lithology of volcanic rock, this paper takes the Carboniferous intermediate basic volcanic reservoir in the Hongche fault zone as the research object. Firstly, the Synthetic Minority Over-Sampling Technique–Edited Nearest Neighbours (SMOTEENN) algorithm is used to solve the problem of the uneven data-scale distribution of different dominant lithologies in the data set. Then, based on the extreme gradient boosting tree model (XGBoost), the honey badger optimization algorithm (HBA) is used to optimize the hyperparameters, and the HBA-XGBoost intelligent model is established to carry out volcanic rock lithology identification research. In order to verify the applicability and efficiency of the proposed model in volcanic reservoir lithology identification, the prediction results of six commonly used machine learning models, XGBoost, K-nearest neighbor (KNN), gradient boosting decision tree model (GBDT), adaptive boosting model (AdaBoost), support vector machine (SVM) and convolutional neural network (CNN), are compared and analyzed. The results show that the HBA-XGBoost model proposed in this paper has higher accuracy, precision, recall rate and F1-score than other models, and can be used as an effective means for the lithology identification of volcanic reservoirs.

A novel integrated strategy of easy pruning, parameter searching, and re-parameterization for lightweight intelligent lithology identification

Lithology identification is a necessary task for activities of reservoir evaluation and underground engineering construction. Recently, the intelligent lithology identification method based on deep learning of image has attracted more and more attention with its excellent performance. However, the existing models are not developed specifically for lithology identification, and there is still room for improving accuracy and a large number of redundant calculations during inference. Therefore, it is necessary to develop a lightweight model specifically for lithologic identification. In order to realize accurate, rapid and effective lithology identification, we propose a novel integrated strategy of easy pruning, parameter searching, and reparameterization for lightweight intelligent lithology identification. Firstly, a model dedicated to lithology classification and easy to pruning is constructed by using the multi-branch structure; secondly, a pruning parameter search method based on differential evolution of expressivity is proposed; and finally, the model is further compressed using reparameterization. We validate the entire method using 160 lithologies. P3DNet has an accuracy of 97.69% on 160 lithologies. The pruning method based on differential evolution of expressivity can realize the optimal pruning under the condition of predetermined accuracy. The P3DNet with 134,380 parameters can achieve an accuracy of 97.50% on 160 lithologies, and it takes only 3.84 ms for the NVIDIA GeForce GTX 2080 Ti GPU to infer an image with a resolution of 224×224×3. The pruned P3DNet is 39.54% faster than MobileNet v3 and 50.65% faster than ShuffleNet V2. Our method can significantly reduce the requirements of the image-based identification method on device memory, computing power, etc., and greatly expand the application scenarios of the intelligent identification method. Relevant research can provide strong support for rapid and intelligent identification of lithology in site survey and construction.

A real-time intelligent lithology identification method based on a dynamic felling strategy weighted random forest algorithm

Real-time intelligent lithology identification while drilling is vital to realizing downhole closed-loop drilling. The complex and changeable geological environment in the drilling makes lithology identification face many challenges. This paper studies the problems of difficult feature information extraction, low precision of thin-layer identification and limited applicability of the model in intelligent lithologic identification. The author tries to improve the comprehensive performance of the lithology identification model from three aspects: data feature extraction, class balance, and model design. A new real-time intelligent lithology identification model of dynamic felling strategy weighted random forest algorithm (DFW-RF) is proposed. According to the feature selection results, gamma ray and 2 MHz phase resistivity are the logging while drilling (LWD) parameters that significantly influence lithology identification. The comprehensive performance of the DFW-RF lithology identification model has been verified in the application of 3 wells in different areas. By comparing the prediction results of five typical lithology identification algorithms, the DFW-RF model has a higher lithology identification accuracy rate and F1 score. This model improves the identification accuracy of thin-layer lithology and is effective and feasible in different geological environments. The DFW-RF model plays a truly efficient role in the real-time intelligent identification of lithologic information in closed-loop drilling and has greater applicability, which is worthy of being widely used in logging interpretation.

Multi-scale spatiotemporal feature lithology identification method based on split-frequency weighted reconstruction

The accurate identification of lithology in thin and deep layers is a crucial task in logging. However, traditional logging lithology identification methods are often inefficient for thin and deep layers and sometimes require human intervention, which greatly reduces the efficiency of oil and gas production. Therefore, this study proposes a multi-scale spatiotemporal feature lithology identification method under split-frequency weighted reconstruction. First, split-frequency weighted reconstruction of the logging curves is performed by Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) to improve their thin layer resolution. Subsequently, a feature fusion model of multi-scale convolutional neural networks and bidirectional gated recurrent neural networks (MCNN-BIGRU) is constructed to learn the spatiotemporal features of the logging curves. Finally, during feature propagation, the attention mechanism assigns weights to historical features to mitigate the accumulation of error information, thereby improving the lithology recognition effect. To verify the model's performance, we constructed a lithology dataset with five wells and conducted an experiment to show that the reconstructed logging curves have significantly higher vertical resolution than the original curves. Furthermore, the MCNN-BIGRU-AT model developed in this study exhibited a better lithology identification effect than the single-structure model, with a highest accuracy of 96.69%. In summary, the proposed method is a novel and efficient method for lithology identification.

Correction to: Automatic lithology identification method based on efficient deep convolutional network

Correction to: Automatic lithology identification method based on efficient deep convolutional network

Automatic lithology identification method based on efficient deep convolutional network

Automatic lithology identification method based on efficient deep convolutional network

An automatic identification method of imbalanced lithology based on Deep Forest and K-means SMOTE

Accurate identification of lithology is an important basis for oil and gas exploration and reservoir geological evaluation. Logging parameters often have a complex nonlinear relationship with lithology. With the development of artificial intelligence technology, a variety of data mining algorithms have been applied to lithology identification with logging data. However, due to the constraints of practical conditions, the number of labeled lithology samples is small and the imbalance between classes is obvious, which usually affect the results of lithology identification. In this paper, we proposed a hybrid unbalanced lithology identification method based on Deep Forest and K-means SMOTE to solve the above mentioned problems. Deep Forest is the first deep model of a non-differential form base learner which can perform layer-by-layer processing and feature enhancement. Compared with traditional shallow model, ensemble model and deep neural networks, it has the best performance with the accuracy of 96.17%. K-means SMOTE oversampling is able to filter subclusters and balance the dataset by oversampling only within safe regions, reducing interference from noise points and boundary ambiguity. We achieved further performance improvements in minority lithology classification via K-means SMOTE oversampling with the accuracy of 97.17%. The comprehensive evaluation results showed that the method proposed in this paper has a good effect on the identification of unbalanced lithology, and has a practical application prospect.

Channel attention-based static-dynamic graph convolutional network for lithology identification with scarce labels

Accurately identifying the complicated lithology distribution of unconventional reservoirs has become an urgent need for oil and gas exploitation. However, the expensive and rare lithology labels limit the precision of current machine learning-based lithology identification methods. Meanwhile, those methods neglect the associated information implicit in adjacent logging samples and underutilize the abundant unlabeled data. In this paper, a channel attention-based static-dynamic graph convolutional network for lithology identification is proposed to solve the problem of scarce labels. To utilize the unlabeled logging data adequately, logging graphs are modeled based on geographic distance and feature similarity to characterize associated information as well as logging features. On the basis, the dynamic similarity graph is introduced to magnify distinctions and reduce connections between samples with different lithologies, improving the quality of logging graphs. Aiming at enhancing the model performance of eliminating redundant and noisy information in logging graphs, the channel attention mechanism is taken into account to realize the fusion and complementation between different associated information. Verification experiments are conducted by utilizing the logging datasets from a shale formation. Results show that the proposed approach has general applicability and achieves high identification accuracy for various strata. Moreover, the proposed approach reduces the cost of drilling coring for lithology identification immensely and can serve as a reference for applying graph theory to solve future reservoir-related issues in petroleum exploitation.

Reservoir Lithology Identification Based on Multicore Ensemble Learning and Multiclassification Algorithm Based on Noise Detection Function.

Reservoir lithology identification is an important part of well logging interpretation. The accuracy of identification affects the subsequent exploration and development work, such as reservoir division and reserve prediction. Correct reservoir lithology identification has important geological significance. In this paper, the wavelet threshold method will be used to preliminarily reduce the noise of the curve, and then the MKBoost-MC model will be used to identify the reservoir lithology. It is found that the prediction accuracy of MKBoost-MC is higher than that of the traditional SVM algorithm, and though the operation of MKBoost-MC takes a long time, the speed of MKBoost-MC reservoir lithology identification is much higher than that of manual processing. The accuracy of MKBoost-MC for reservoir lithology recognition can reach the application standard. For the unbalanced distribution of lithology types, the MKBoost-MC algorithm can be effectively suppressed. Finally, the MKBoost-MC reservoir lithology identification method has good applicability and practicality to the lithology identification problem.

Cross-Well Lithology Identification Based on Wavelet Transform and Adversarial Learning

For geological analysis tasks such as reservoir characterization and petroleum exploration, lithology identification is a crucial and foundational task. The logging lithology identification tasks at this stage generally build a lithology identification model, assuming that the logging data share an independent and identical distribution. This assumption, however, does not hold among various wells due to the variations in depositional conditions, logging apparatus, etc. In addition, the current lithology identification model does not fully integrate the geological knowledge, meaning that the model is not geologically reliable and easy to interpret. Therefore, we propose a cross-domain lithology identification method that incorporates geological information and domain adaptation. This method consists of designing a named UAFN structure to better extract the semantic (depth) features of logging curves, introducing geological information via wavelet transform to improve the model’s interpretability, and using dynamic adversarial domain adaptation to solve the data-drift issue cross-wells. The experimental results show that, by combining the geological information in wavelet coefficients with semantic information, more lithological features can be extracted in the logging curve. Moreover, the model performance is further improved by dynamic domain adaptation and wavelet transform. The addition of wavelet transform improved the model performance by an average of 6.25%, indicating the value of the stratigraphic information contained in the wavelet coefficients for lithology prediction.

Reservoir Lithology Identification Based on Improved Adversarial Learning

Reservoir lithology identification is critical to reservoir characterization, reserves calculation, and geological modeling. The deep learning lithology identification method is a data-driven algorithm for establishing the relationship between lithology-sensitive properties and litho-types from a large amount of observed data. The lithology label is inadequate for high drilling and core recovery costs. Consequently, we propose a reservoir lithology identification method based on improved adversarial learning to relieve the overfitting problem and the multi-solution problem caused by inadequate labeled data and massive learnable parameters in training. Firstly, a probabilistic lithology classification neural network (PLCNN) is constructed to predict lithology from density, P-velocity, and S-velocity. In addition, we design an improved adversarial learning (IAL) lithology identification workflow to train the PLCNN with limited labeled data and large-scale unlabeled data. In the workflow, a lightweight discrimination network is established to ensure that the prediction result of the PLCNN is consistent with the data distribution characteristics of real underground lithology. Finally, the proposed method is successfully applied to the Book cliffs model. Compared with the conventional supervised learning workflow, the misclassification of sand and sandy shale can be relieved efficiently with the IAL workflow, and the classification accuracy can be improved to 92.71%.

Lithology identification using principal component analysis and particle swarm optimization fuzzy decision tree

Lithology identification using geophysical log information is vital for log interpretation and reservoir evaluation. As a result of the highly similar features for log curves that characterize complex lithology, there is significant information redundancy regarding the process of lithology identification. In addition, as a result of the highly nonlinear characteristics of log curves, the mapping relationship with lithology has certain ambiguities and uncertainties, which affect the lithology prediction results. Combining principal component analysis (PCA) and the fuzzy decision tree (FDT) model, we propose a new intelligent lithology identification method that is capable of effectively solving these problems well. However, because of the inaccuracy for empirically set parameters, an adaptive fuzzy decision tree algorithm based on particle swarm optimization (PSO-FDT) was proposed after analyzing the main features of the fuzzy decision tree and using an improved particle swarm optimization (PSO) algorithm to determine the relevant parameters. Compared with the FDT algorithm which determines parameter values empirically, the performance of the PSO-FDT has been significantly improved. Finally, the proposed PSO-FDT model was verified using test data. Experiments confirm that the proposed model is more effective than other lithology identification models. The identification accuracy for all lithologies was equal to or greater than that of the other methods. In addition, the overall accuracy was improved by at least 9.71%.

Intelligent identification of logging cuttings based on deep learning

In oil and gas exploration, rock sample identification is a basic and important work. At present, the methods of rock sample identification mainly include gravity and magnetism, well logging, earthquake, remote sensing, electromagnetism, geochemistry, hand sample, and thin section analysis. Most of these methods for lithology identification are based on manual identification methods, which require a certain professional background and rich identification experience. Based on the deep learning method, this paper constructs the intelligent recognition model of cuttings lithology in logging work, which can realize the automatic recognition of rock images. The pre-training model is VGG16, and the parameters in the pre-training model are frozen and fine-tuned by the method of transfer learning, and finally the rock image identification based on vgg16 is realized. The accuracy of the trained model was 98% in the training set and 86% in the validation set. The experimental results show that the deep learning model based on transfer learning and vgg16 proposed in this paper has strong applicability to cuttings data and can distinguish rock types well. The intelligent lithology identification method proposed in this paper has good generalization performance and can be used for rapid intelligent identification of rock lithology in geology, well logging, power fault inspection, water conservancy and other projects.

Lithology identification method based on integrated K-means clustering and meta-object representation

Lithology identification method based on integrated K-means clustering and meta-object representation

Deep learning of rock microscopic images for intelligent lithology identification: Neural network comparison and selection

An intelligent lithology identification method is proposed based on deep learning of the rock microscopic images. Based on the characteristics of rock images in the dataset, we used Xception, MobileNet_v2, Inception_ResNet_v2, Inception_v3, Densenet121, ResNet101_v2, and ResNet-101 to develop microscopic image classification models, and then the network structures of seven different convolutional neural networks (CNNs) were compared. It shows that the multi-layer representation of rock features can be represented through convolution structures, thus better feature robustness can be achieved. For the loss function, cross-entropy is used to back propagate the weight parameters layer by layer, and the accuracy of the network is improved by frequent iterative training. We expanded a self-built dataset by using transfer learning and data augmentation. Next, accuracy (acc) and frames per second (fps) were used as the evaluation indexes to assess the accuracy and speed of model identification. The results show that the Xception-based model has the optimum performance, with an accuracy of 97.66% in the training dataset and 98.65% in the testing dataset. Furthermore, the fps of the model is 50.76, and the model is feasible to deploy under different hardware conditions and meets the requirements of rapid lithology identification. This proposed method is proved to be robust and versatile in generalization performance, and it is suitable for both geologists and engineers to identify lithology quickly.

Identification of Rock Properties of Rock Wall Cut by Roadheader Based on PSO-VMD-LSSVM

The problem of low digging efficiency and mining imbalance due to outdated digging technology and low degree of equipment intelligence has long existed in coal mine roadway excavation work. Lithology identification is the key to the intelligence of roadheading equipment. Accurate lithology identification significantly affects the automatic control of roadheader cutting conditions. Completing the identification of lithology in the process of rock wall cutting by a roadheader involved the following steps: building a tunneling experiment platform, making four rock specimens with different lithologies, completing the tunneling simulation experiments on four lithologies, obtaining current sensor data of four lithologies cutting, and finally proposing an intelligent lithology identification method of PSO-VMD-LSSVM. The research results show that the particle swarm algorithm (PSO) optimized the variational modal decomposition (VMD) with minimum envelope information entropy as the fitness function can realize the adaptive decomposition of the current signal of truncated motors. The signal reconstruction can increase the signal-to-noise ratio of the current signal by selecting the eigenmodal components according to the energy density and correlation coefficient criterion. The multi-scale fuzzy entropy is used as the eigenvector of the reconstructed current signal as the fuzzy entropy of different lithology cut-off motor currents has better differentiation at different scales. The least-squares support vector machine (LSSVM) is used to classify the feature vectors processed by custom decomposition parameter VMD and gives a recognition rate of 87.5%. The recognition rate increases to 97.5% for the feature vectors processed by PSO-VMD. The particle swarm algorithm optimizes the noise reduction via VMD to effectively improve the lithology recognition rate. The research results can provide a methodological reference for rock property recognition during rock cutting by a roadheading machine.

A framework of active learning and semi-supervised learning for lithology identification based on improved naive Bayes

Lithology identification is the basis of energy exploration and reservoir evaluation, intelligent and accurate identification of underground lithology is a key issue. The establishment of a machine learning lithology identification model using logging data is a hot research direction in recent years. However, the logging data has a high degree of non-linearity and multi-response characteristics, and there are insufficient numbers of labeled samples in the training data set. These will eventually affect the modeling accuracy and may cause over-fitting. Therefore, a framework of active learning and semi-supervised learning for lithology identification based on improved naive Bayes (ALSLINB) is proposed. The contributions are fourfold: (i) The Gaussian mixture model (GMM) based on the EM algorithm is used to estimate the probability density of the log data, which fits the probability distribution of the nonlinear multi-response log data. (ii) A framework combining active learning (AL) and semi-supervised learning is proposed for the expansion of labeled samples in the training data set. (iii) The application of pseudo-labeling detection technology can effectively improve the authenticity of pseudo-label samples. (iv) Different from the general deterministic lithology identification method, the result of the ALSLINB algorithm corresponds to the probability score, which provides an auxiliary basis for the prediction result. Finally, the ALSLINB algorithm is applied to two different data sets for a large number of experiments and compared with the related baseline methods to verify its effectiveness and generalization ability. The result proves that the ALSLINB algorithm can complete the lithology recognition task well and has high accuracy and robustness, which provides a new direction for intelligent lithology identification.