Lithological Classification Research Articles

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.

OutcropHyBNet: Hybrid Backbone Networks with Data Augmentation for Accurate Stratum Semantic Segmentation of Monocular Outcrop Images in Carbon Capture and Storage Applications.

The rapid advancement of climate change and global warming have widespread impacts on society, including ecosystems, water security, food production, health, and infrastructure. To achieve significant global emission reductions, approximately 74% is expected to come from cutting carbon dioxide (CO2) emissions in energy supply and demand. Carbon Capture and Storage (CCS) has attained global recognition as a preeminent approach for the mitigation of atmospheric carbon dioxide levels, primarily by means of capturing and storing CO2 emissions originating from fossil fuel systems. Currently, geological models for storage location determination in CCS rely on limited sampling data from borehole surveys, which poses accuracy challenges. To tackle this challenge, our research project focuses on analyzing exposed rock formations, known as outcrops, with the goal of identifying the most effective backbone networks for classifying various strata types in outcrop images. We leverage deep learning-based outcrop semantic segmentation techniques using hybrid backbone networks, named OutcropHyBNet, to achieve accurate and efficient lithological classification, while considering texture features and without compromising computational efficiency. We conducted accuracy comparisons using publicly available benchmark datasets, as well as an original dataset expanded through random sampling of 13 outcrop images obtained using a stationary camera, installed on the ground. Additionally, we evaluated the efficacy of data augmentation through image synthesis using Only Adversarial Supervision for Semantic Image Synthesis (OASIS). Evaluation experiments on two public benchmark datasets revealed insights into the classification characteristics of different classes. The results demonstrate the superiority of Convolutional Neural Networks (CNNs), specifically DeepLabv3, and Vision Transformers (ViTs), particularly SegFormer, under specific conditions. These findings contribute to advancing accurate lithological classification in geological studies using deep learning methodologies. In the evaluation experiments conducted on ground-level images obtained using a stationary camera and aerial images captured using a drone, we successfully demonstrated the superior performance of SegFormer across all categories.

Lithological classification and analysis based on random forest and multiple features: a case study in the Qulong copper deposit, China

Lithological classification and analysis based on random forest and multiple features: a case study in the Qulong copper deposit, China

The British Geological Survey Rock Classification Scheme, its representation as linked data, and a comparison with some other lithology vocabularies

Controlled vocabularies are critical to constructing FAIR (findable, accessible, interoperable, re-useable) data. One of the most widely required, yet complex, vocabularies in earth science is for rock and sediment type, or ‘lithology’. Since 1999 the British Geological Survey has used its own Rock Classification Scheme in many of its workflows and products including the national digital geological map. This scheme pre-dates others that have been published, and is deeply embedded in BGS’ processes. By publishing this classification scheme now as a Simple Knowledge Organisation System (SKOS) machine-readable informal ontology, we make it available for ourselves and third parties to use in modern semantic applications, and we open the future possibility of using the tools SKOS provides to align our scheme with other published schemes. These include the IUGS-CGI Simple Lithology Scheme, the European Commission INSPIRE Lithology Code List, the Queensland Geological Survey Lithotype Scheme, the USGS Lithologic Classification of Geologic Map Units, and Mindat.org. The BGS lithology classification was initially based on four narrative reports that can be downloaded from the BGS website, although it has been added to subsequently. The classification is almost entirely mono-hierarchical in nature and includes 3454 currently valid concepts in a classification 11 levels deep. It includes igneous rocks and sediments, metamorphic rocks, sediments and sedimentary rocks, and superficial deposits including anthropogenic deposits. The SKOS informal ontology built on it is stored in a triplestore and the triples are updated nightly by extracting from a relational database where the ontology is maintained. Bulk downloads and version history are available on github. The RCS concepts themselves are used in other BGS linked data, namely the Lexicon of Named Rock Units and the linked data representation of the 1:625 000 scale geological map of the UK. Comparing the RCS with the other published lithology schemes, all are broadly similar but show characteristics that reveal the interests and requirements of the groups that developed them, in terms of their level of detail both overall and in constituent parts. It should be possible to align the RCS with the other classifications, and future work will focus on automated mechanisms to do this, and possibly on constructing a formal ontology for the RCS.

Estimation of 3D Permeability from Pore Network Models Constructed Using 2D Thin-Section Images in Sandstone Reservoirs

Using thin-section images to estimate core permeability is an economical and less time-consuming method for reservoir evaluation, which is a goal that many petroleum developers aspire to achieve. Although three-dimensional (3D) pore volumes have been successfully applied to train permeability models, it is very expensive to carry out. In this regard, deriving permeability from two-dimensional (2D) images presents a novel approach in which data are fitted directly on the basis of pore-throat characteristics extracted from more cost-effective thin sections. This work proposes a Fluid–MLP workflow for estimating 3D permeability models. We employed DIA technology combined with artificial lithology and pore classification to calculate up to 110 characteristic parameters of the pore-throat structure on the basis of 2D rock cast thin sections. The MLP network was adopted to train the permeability prediction model, utilizing these 110 parameters as input. However, the accuracy of the conventional MLP network only reached 90%. We propose data preprocessing using fluid flow simulations to improve the training accuracy of the MLP network. The fluid flow simulations involve generating a pore network model based on the 2D pore size distribution, followed by employing the lattice Boltzmann method to estimate permeability. Subsequently, six key structural parameters, including permeability calculated by LBM, pore type, lithology, two-dimensional porosity, average pore–throat ratio, and average throat diameter, were fed into the MLP network for training to form a new Fluid–MLP workflow. Comparing the results predicted using this new Fluid–MLP workflow with those of the original MLP network, we found that the Fluid–MLP network exhibited superior predictive performance.

Spatial lithological heterogeneity of the deep-sea sediments and its controlling factors in the northern West Caroline Basin, tropical West Pacific

Uncovering the spatial distribution of deep-sea sediment lithologies is crucial for the research on earth system science and the exploration of critical mineral resources. The conventional global deep-sea sediment lithology distribution maps showed that the lithologies were relatively uniform in the global major ocean basins. Furthermore, it was deemed that the deep-sea sediment lithologies were related to the productivity of surface seawater. However, later studies have illustrated that the distribution of deep-sea sediment lithologies exhibited greater variability and heterogeneity than conventional maps and that water depth played a more important role in controlling deep-sea sediment lithologies than productivity. In addition, few studies have focused on the relationship between the heterogeneous deep-sea sediment lithologies and the diverse seafloor topography in the West Pacific. In this study, we provide a high-resolution spatial distribution map of deep-sea sediment lithologies by systematic descriptions of 112 surface samples in the northern West Caroline Basin, tropical West Pacific, with a large range of water depth and a diverse seafloor topography to verify the previous prediction of sediment lithology distribution. Subsequently, based on the results of the determinations of carbonate and biogenic silica contents, the sediment redox-potential tests, and the calculations of multiple variables, we carried out quantitative studies and correlation analyses for these variables to reveal the relative contribution of different factors to the lithological heterogeneity in the northern West Caroline Basin. Our results show that the actual deep-sea sediments have greater heterogeneity in terms of lithological classes and distribution patterns than the earlier predicted lithology maps. Furthermore, our analyses reveal that water depth and seafloor topography are the more important controlling factors on the deep-sea sediment lithology to some extent than productivity and that water depth and topography may exert different effects on the different sediment components. For the calcareous component, water depth is the main controlling factor due to the increased solubility of carbonate with water depth. Carbonate materials can dilute other components in the waters above the carbonate compensation depth, which is around 4500 m below the sea surface in the study area. Meanwhile, the siliceous component may be enriched in the unique negative seafloor topography of the trench and trough with the specific lateral transport mechanism and the redox environment. These findings imply a more complicated actual deep-sea sediment lithology distribution than previously thought given that various water depths and diverse topography in the global oceans, which are significant for understanding deep-sea sedimentary processes and improving the models for predicting global sediment lithology in the deep sea.

Multi-scale data joint inversion of minerals and porosity in altered igneous reservoirs—A case study in the South China Sea

There are abundant igneous gas reservoirs in the South China Sea with significant value of research, and lithology classification, mineral analysis and porosity inversion are important links in reservoir evaluation. However, affected by the diverse lithology, complicated mineral and widespread alteration, conventional logging lithology classification and mineral inversion become considerably difficult. At the same time, owing to the limitation of the wireline log response equation, the quantity and accuracy of minerals can hardly meet the exploration requirements of igneous formations. To overcome those issues, this study takes the South China Sea as an example, and combines multi-scale data such as micro rock slices, petrophysical experiments, wireline log and element cutting log to establish a set of joint inversion methods for minerals and porosity of altered igneous rocks. Specifically, we define the lithology and mineral characteristics through core slices and mineral data, and establish an igneous multi-mineral volumetric model. Then we determine element cutting log correction method based on core element data, and combine wireline log and corrected element cutting log to perform the lithology classification and joint inversion of minerals and porosity. However, it is always difficult to determine the elemental eigenvalues of different minerals in inversion. This paper uses multiple linear regression methods to solve this problem. Finally, an integrated inversion technique for altered igneous formations was developed. The results show that the corrected element cutting log are in good agreement with the core element data, and the mineral and porosity results obtained from the joint inversion based on the wireline log and corrected element cutting log are also in good agreement with the core data from X-ray diffraction. The results demonstrate that the inversion technique is applicable and this study provides a new direction for the mineral inversion research of altered igneous formations.

GF-2 Data for Lithological Classification Using Texture Features and PCA/ICA Methods in Jixi, Heilongjiang, China

Lithological classification is a pivotal aspect in the field of geology, and traditional field surveys are inefficient and challenging in certain areas. Remote sensing technology offers advantages such as high efficiency and wide coverage, providing a solution to the aforementioned issues. The aim of this study is to apply remote sensing technology for lithological classification and attempt to enhance the accuracy of classification. Taking a study area in Jixi, Heilongjiang Province, China, as an example, lithological classification is conducted using high-resolution satellite remote sensing data from GF-2 and texture data based on gray-level co-occurrence matrix (GLCM). By comparing the accuracy of lithological classification using different methods, the support vector machine (SVM) method with the highest overall accuracy is selected for further investigation. Subsequently, this study compares the effects of combining GF-2 data with different texture data, and the results indicate that combining textures can effectively improve the accuracy of lithological classification. In particular, the combination of GF-2 and the Dissimilarity index performs the best among single-texture combinations, with an overall accuracy improvement of 7.8630% (increasing from 74.6681% to 82.5311%) compared to using only GF-2 data. In the multi-texture combination dataset, the Mean index is crucial for enhancing classification accuracy. Selecting appropriate textures for combination can effectively improve classification accuracy, but it is important to note that excessive overlaying of textures may lead to a decrease in accuracy. Furthermore, this study employs principal component analysis (PCA) and independent component analysis (ICA) to process the GF-2 data and combines the resulting PCA and ICA datasets with different texture data for lithological classification. The results demonstrate that combining PCA and ICA with texture data further enhances classification accuracy. In conclusion, this study demonstrates the application of remote sensing technology in lithological classification, with a focus on exploring the application value of different combinations of multispectral data, texture data, PCA data, and ICA data. These findings provide valuable insights for future research in this field.

Machine Learning-Based Real-Time Prediction of Formation Lithology and Tops Using Drilling Parameters with a Web App Integration

The accurate prediction of underground formation lithology class and tops is a critical challenge in the oil industry. This paper presents a machine-learning (ML) approach to predict lithology from drilling data, offering real-time litho-facies identification. The ML model, applied via the web app “GeoVision”, achieves remarkable performance during its training phase with a mean accuracy of 95% and a precision of 98%. The model successfully predicts claystone, marl, and sandstone classes with high precision scores. Testing on new data yields an overall accuracy of 95%, providing valuable insights and setting a benchmark for future efforts. To address the limitations of current methodologies, such as time lags and lack of real-time data, we utilize drilling data as a unique endeavor to predict lithology. Our approach integrates nine drilling parameters, going beyond the narrow focus on the rate of penetration (ROP) often seen in previous research. The model was trained and evaluated using the open Volve field dataset, and careful data preprocessing was performed to reduce features, balance the sample distribution, and ensure an unbiased dataset. The innovative methodology demonstrates exceptional performance and offers substantial advantages for real-time geosteering. The accessibility of our models is enhanced through the user-friendly web app “GeoVision”, enabling effective utilization by drilling engineers and marking a significant advancement in the field.

A class-rebalancing self-training semisupervised learning for imbalanced data lithology identification

Lithologic identification plays a crucial role in petroleum geologic exploration, and machine learning (ML) has become increasingly prevalent in intelligent lithology identification in recent years. However, identifying lithologies presents challenges due to a lack of lithologic labels and an imbalanced distribution of lithologies. To address this issue and obtain satisfactory lithologic identification results, this study investigates a class-rebalancing self-training (CReST) lithology identification framework. This framework uses logging data and limited lithologic labels as input and achieves promising lithology classification through the CReST approach. Four ML algorithms with high overall performance are selected from 25 common algorithms to establish CReST models, such as bagging classifier, extra trees classifier, random forest classifier, and support vector classifier. The classification results of the models are compared and analyzed under three conditions. The experimental findings indicate that (1) under label scarcity, the effect of category recognition varies greatly with different sample numbers; (2) under self-training (ST), overall performance is improved, but the difference in performance caused by category imbalance also increases; and (3) under CReST framework, the model effectively resolves the identification problems caused by a lack of labels and an imbalanced category distribution. Specifically, the precision of identifying categories with fewer samples is improved by more than 20%.

A site amplification model for Switzerland based on site-condition indicators and incorporating local response as measured at seismic stations

AbstractThe spatial estimation of the soil response is one of the key ingredients for the modelling of earthquake risk. We present a ground motion amplification model for Switzerland, developed as part of a national-scale earthquake risk model. The amplification model is based on local estimates of soil response derived for about 240 instrumented sites in Switzerland using regional seismicity data by means of empirical spectral modelling techniques. These local measures are then correlated to continuous layers of topographic and geological soil condition indicators (multi-scale topographic slopes, a lithological classification of the soil, a national geological model of bedrock depth) and finally mapped at the national scale resorting to regression kriging as geostatistical interpolation technique. The obtained model includes amplification maps for PGV (peak ground velocity), PSA (pseudo-spectral acceleration) at periods of 1.0, 0.6 and 0.3 s; the modelled amplification represents the linear soil response, relative to a reference rock profile with VS30 (time-averaged shear-wave velocity in the uppermost 30 m of soil column) = 1105 m/s. Each of these amplification maps is accompanied by two layers quantifying its site-to-site and single-site, within event variabilities, respectively (epistemic and aleatory uncertainties). The PGV, PSA(1.0 s) and PSA(0.3 s) maps are additionally translated to macroseismic intensity aggravation layers. The national-scale amplification model is validated by comparing it with empirical measurements of soil response at stations not included in the calibration dataset, with existing city-scale amplification models and with macroseismic intensity observations from historical earthquakes. The model is also included in the Swiss ShakeMap workflow.

Lithology classification of igneous rocks using C-band and L-band dual-polarization SAR data

Abstract Distinguishing different kinds of igneous rocks is difficult because of their subtle differences. Synthetic aperture radar (SAR) is sensitive to rock surface morphology, which can help a lot in classification. Dual-pol SAR data have the advantages of low cost, but few articles are using only dual-pol SAR data for igneous rock classification. In this study, we explored the performance of dual-pol SAR data in distinguishing granitoid, tuff, and syenite porphyry. Backscatter coefficients, polarization decomposition parameters, and texture features from gray-level co-occurrence matrix extracted by Sentinel-1 or PALSAR were classified using several machine learning algorithms. The results are as follows. First, the texture information has greater potential for igneous rock classification, but the polarization decomposition parameters contribute less. Second, after comparing machine learning algorithms, AdaBoost algorithm has the highest overall accuracy for either C-band or L-band SAR data. C-band SAR data provide better classification results than L-band. Finally, tuff is the easiest igneous rock to be successfully classified, and L-band dual-pol SAR data have advantages in the discrimination of syenite porphyry. This study outlines the effectiveness of dual-pol SAR data for igneous rock classification, which will help to select SAR data of appropriate wavelengths for specific types of lithology discrimination.

Handling imbalanced data in supervised machine learning for lithological mapping using remote sensing and airborne geophysical data

Abstract With balanced training sample (TS) data, learning algorithms offer good results in lithology classification. Meanwhile, unprecedented lithological mapping in remote places is predicted to be difficult, resulting in limited and unbalanced samples. To address this issue, we can use a variety of techniques, including ensemble learning (such as random forest [RF]), over/undersampling, class weight tuning, and hybrid approaches. This work investigates and analyses many strategies for dealing with imbalanced data in lithological classification based on RF algorithms with limited drill log samples using remote sensing and airborne geophysical data. The research was carried out at Komopa, Paniai District, Papua Province, Indonesia. The class weight tuning, oversampling, and balance class weight procedures were used, with TSs ranging from 25 to 500. The oversampling approach outperformed the class weight tuning and balance class weight procedures in general, with the following metric values: 0.70–0.80 (testing accuracy), 0.43–0.56 (F1 score), and 0.32–0.59 (Kappa score). The visual comparison also revealed that the oversampling strategy gave the most reliable classifications: if the imbalance ratio is proportionate to the coverage area in each lithology class, the classifier capability is optimal.

Lithological Classification by Hyperspectral Images Based on a Two-Layer XGBoost Model, Combined with a Greedy Algorithm

Lithology classification is important in mineral resource exploration, engineering geological exploration, and disaster monitoring. Traditional laboratory methods for the qualitative analysis of rocks are limited by sampling conditions and analytical techniques, resulting in high costs, low efficiency, and the inability to quickly obtain large-scale geological information. Hyperspectral remote sensing technology can classify and identify lithology using the spectral characteristics of rock, and is characterized by fast detection, large coverage area, and environmental friendliness, which provide the application potential for lithological mapping at a large regional scale. In this study, ZY1-02D hyperspectral images were used as data sources to construct a new two-layer extreme gradient boosting (XGBoost) lithology classification model based on the XGBoost decision tree and an improved greedy search algorithm. A total of 153 spectral bands of the preprocessed hyperspectral images were input into the first layer of the XGBoost model. Based on the tree traversal structural characteristics of the leaf nodes in the XGBoost model, three built-in XGBoost importance indexes were split and combined. The improved greedy search algorithm was used to extract the spectral band variables, which were imported into the second layer of the XGBoost model, and the bat algorithm was used to optimize the modeling parameters of XGBoost. The extraction model of rock classification information was constructed, and the classification map of regional surface rock types was drawn. Field verification was performed for the two-layer XGBoost rock classification model, and its accuracy and reliability were evaluated based on four indexes, namely, accuracy, precision, recall, and F1 score. The results showed that the two-layer XGBoost model had a good lithological classification effect, robustness, and adaptability to small sample datasets. Compared with the traditional machine learning model, the two-layer XGBoost model shows superior performance. The accuracy, precision, recall, and F1 score of the verification set were 0.8343, 0.8406, 0.8350, and 0.8157, respectively. The variable extraction ability of the constructed two-layer XGBoost model was significantly improved. Compared with traditional feature selection methods, the GREED-GFC method, when applied to the two-layer XGBoost model, contributes to more stable rock classification performance and higher lithology prediction accuracy, and the smallest number of extracted features. The lithological distribution information identified by the model was in good agreement with the lithology information verified in the field.

Hydraulic conductivity estimation and lithological classification of an esker aquifer system using surface electrical resistivity surveys and a neural network

Empirical and theoretical relationships between hydraulic conductivity, lithology, and electrical resistivity provide a basis for the use of electrical resistivity for aquifer characterization in unconsolidated sediments. This study demonstrates a meaningful field-scale correlation between vertically distributed hydraulic conductivity obtained from packer-based borehole hydraulic tests, and electrical resistivity obtained from surface-based geophysical surveys over the Vars-Winchester esker aquifer system, Ontario, Canada. Electrical resistivity alone has order-of-magnitude predictive capacity for hydraulic conductivity, but is insufficient to reliably discriminate between aquifer and aquitard lithology. An alternative methodology is developed that takes advantage of the observed correlation between hydraulic conductivity and elevation, and the separability of lithology in terms of elevation. Electrical resistivity and elevation are combined as predictor variables for hydraulic conductivity using both multiple linear regression and nonlinear neural network regression, and for neural network classification of lithology. Neural network regression results in prediction accuracy for log-transformed hydraulic conductivity of 0.38–0.52 with clear definition of vertical and lateral heterogeneity. Classification accuracy for lithology is 83–84% with high probability of discrimination between the unconsolidated aquifer and aquitard sediments, and lower probability identification of the bedrock surface due to fewer samples at depth and limited penetration depth of the resistivity survey.

A semi-supervised coarse-to-fine approach with bayesian optimization for lithology identification

Lithology identification is critical in the interpretation of well-logging data for petroleum exploration and development. However, the limited availability of labeled well-logging data for machine learning model training can lead to compromised accuracy in lithology classification models. Here, we propose a semi-supervised lithology identification model to overcome this challenge. Our framework consists of Bayesian optimization for tuning ensemble algorithms, including random forest, gradient boosting decision tree, extremely randomized trees, and adaptive boosting, to establish a high-quality baseline model for semi-supervised learning. We also employ a self-training strategy to increase the number of labeled samples in the training set and use the predicted label with the highest confidence as a pseudo-label to reduce the accumulation of deviation caused by incorrect pseudo-labels. Our semi-supervised coarse-to-fine framework improves rock classification accuracy, particularly for sandstone. Testing our model on well-logging data from two real regions, we found that the ExtraRF-based semi-supervised model in the HGF area performs the best, with a maximum classification accuracy of 91.6%, which is 5% higher than the original coarse-to-fine model without using Bayesian optimization and pseudo-labeling techniques.

A New Method for the Identification of Lunar Cryptomaria and Their Analysis in the Schiller‐Schickard Region

AbstractCryptomaria play critical roles in elucidating the early thermal history of the Moon. In contrast with traditional dark halo impact crater (DHC) identification methods, this study focused on exposed rock (0.5%–29.54% rock abundance) surfaces as windows for cryptomare identification. We classified the lithology of these rock surfaces to find those that match mare basalt using major element oxide products based on data from the Diviner instrument aboard the Lunar Reconnaissance Orbiter (LRO) and by Lunar Prospector thorium products, in accordance with laboratory lithological classification criteria. Then, by combining the locations of 0.5%–29.54% rock abundance values with the lithologies, we created a map of exposed basaltic rock surfaces and 14 cryptomare candidate regions with dozens of closely spaced basaltic rock pixels were identified across the Moon. Among 14 candidate regions, 11 cryptomaria were consistent with results in literature (Whitten & Head, 2015a; https://doi.org/10.1016/J.ICARUS.2014.09.031) based on DHCs, and 3 cryptomaria were newly identified. In the Schiller‐Schickard region, we refined the boundaries of 18 individual cryptomare units using our rock analysis combined with LRO color shaded relief maps. A detailed analysis of the distribution, composition, area, depth, thickness, and volume and the morphological features of these 18 identified cryptomare units indicates that the basalt materials covered by the Orientale basin or other impact crater ejecta display variable thicknesses and discontinuous layers. These identified cryptomare units and their morphological features provide information on regional stratigraphy as well as on the thermal evolution of the Moon.

Landslide Susceptibility Zoning in Yunnan Province Based on SBAS-InSAR Technology and a Random Forest Model

Yunnan Province, China, has complex topography and geomorphology, many ravines and valleys, and frequent landslide geological disasters and is of great significance in the assessment of regional landslide geological disasters in Yunnan Province for disaster prevention and mitigation. In this study, Yunnan Province was selected as the research area, and the average annual deformation rate of radar line-of-sight in Yunnan Province over four years from 2018 to 2021 was obtained with SBAS-InSAR technology, which was used as one of the index factors for the susceptibility evaluation of Yunnan Province. The deformation rate reflects the slow movement of the land surface. In addition, elevation, slope, aspect, lithological classification, geological structure, rainfall, distance from roads, distance from rivers, topographic undulation, and NDVI were selected as evaluation index factors and combined with the annual mean deformation rate. A random forest model was used to evaluate and accurately analyze landslide geological disasters in Yunnan Province. The results showed that as an important index factor, the annual mean deformation rate of Yunnan Province can be added to the random forest model to improve the prediction accuracy. The area with high susceptibility accounted for 10% of the entire province, and the number of landslides in the region accounted for 68% of the province. Additionally, the results for prone zoning were highly correlated with the landslide distribution. The accuracy of the random forest model prediction was 0.80, and the AUC value was 0.87, indicating that the random forest model was a highly accurate and reliable evaluation method for studying landslide geological disasters. It is very suitable for the evaluation of landslide susceptibility in Yunnan Province.

Lithology identification based on interpretability integration learning

An interpretability model for intelligent lithology identification is proposed, which utilizes Ensemble Learning Stacking, Permutation Importance (PI), and Local Interpretable Model-agnostic Explanations (LIME) techniques. The aim of this method is to provide more accurate geological information and scientific support for oil and gas resource exploration. Two logging datasets from the public domain were used as experiments, and support vector machine (SVM), random forest (RF), and naive Bayes (NB) were employed as base learners, while SVM was utilized as the meta learner for lithology classification via stacking algorithm. The accuracy of the model was verified using evaluation metrics such as Area Under Curve (AUC), precision, recall, and F1-score. The PI and LIME techniques were employed to explain the lithology identification model. The results indicate that the stacking algorithm produced the best indexes and highest prediction accuracy. With respect to overall interpretation, PHIND, GR, and RT were found to have the most significant influence on lithology identification in a natural gas protection area in the United States, while DEN, CAL, and PEF were observed to be the most influential variables for lithology identification in the Daqing Oilfield in China. From the perspective of a single sample, the LIME algorithm can provide a quantitative prediction probability and degree of influence of the characteristic variables.

Analysis of alternative strategies applied to Naïve-Bayes classifier into the recognition of electrofacies: Application in well-log data at Recôncavo Basin, North-East Brazil

This paper is concerned with the applicability of different strategies to improve the definition of prior probabilities and/or likelihoods of naïve Bayes (NB) classifiers. Standard NB method computes likelihoods and priors by means of normal distributions and evaluation of the entire training data-set, respectively. NB is one of the most prolific classification methods in data mining and machine learning. Despite decent efficiency facing good training data, NB classifiers present the intriguing assumption of conditional independence between the attributes. Several algorithms have been proposed to improve the effectiveness of NB classifiers by inserting discriminant approaches into its generative structure. From a reliability perspective, the standard NB approach might not explore the real capabilities of NB classifiers facing the lithologic classification problem. To cover such distrust, a novel approach considering four particular strategies are suggested and compared to the standard NB classification outcomes. At first, a kernel density estimation (KDE) is considered to ameliorate the likelihood models. We also apply the NB classifier in parts by separating the training data-set in individual wells in a committee architecture framework. A tuning strategy is also considered for automatic estimation of prior probabilities in an optimization-scheme. Another novel alternative, named as CRC, adapted to the standard NB classifier consists in defining priors based on depth zones from regional stratigraphic information in which to apply NB classifier. We prepare an extensive statistical investigation, based on precision, recall, classification errors, fscores and confusion matrices to bespeak the most relevant NB strategy for classification of electrofacies. Despite the decent classification outcomes for all above-mentioned strategies, CRC can be considered, by a narrow margin, the most prolific method to be applied as an improvement of the standard NB to classify rock units. Tests are performed on a validation well (i.e., 7-MP-50D-BA) of Massapê Field, in Recôncavo Basin, northeast Brazil to highlight the classification particularities provided by the improved strategy. A significant improvement in the classification of sandstones (i.e., from 68 % to 83 % accuracy) is observed, according to the confusion matrix analysis. Additionally, a minimal decreasing is observed into the classification of shales and slurries (i.e., from 92% to 90% and to 63% to 56%, respectively), which is acceptable according to the fscores and errors. This aspect reinforces the relevance of using the NB classifier jointly with previous geologic information to optimize the lithologic classification.