{"title":"Rock-type classification: A (critical) machine-learning perspective","authors":"","doi":"10.1016/j.cageo.2024.105730","DOIUrl":"10.1016/j.cageo.2024.105730","url":null,"abstract":"<div><div>We investigate machine-learning techniques for rock-type classification. A throughout literature review (considering the machine-learning technique, number of classes, rock types, and image types) presents a diversity of datasets employed and a wide range of classification results as well as multiple problem formulations. Throughout the discussion of the literature, we highlight some common machine-learning pitfalls and criticize the decisions taken by some authors on the problem formulation. We present an experimental contribution by evaluating the classification of seven types of rocks found in carbonate reservoirs along with state-of-the-art Convolutional Neural Networks (CNNs) architectures available through a well-known open-source library. For this experimentation, we detail the preparation of the dataset of drill core plugs (DCPs), the experimental setup itself, and the obtained results considering the normalized accuracy and the traditional accuracy as metrics. We performed the manual background segmentation of the employed dataset of DCPs; so the results reported are not influenced by the background of the images. We evaluate top-1, top-2, and top-3 performance for the problem. We apply fusion of multiple CNNs for richer classification decisions. We also contribute by presenting the manual classification — human labeling by looking at the image on the computer screen — of the same seven-class dataset, performed by six non-geologist volunteers. Finally, we present a conclusion for the results obtained with our experiments and share valuable advice for researchers applying machine learning to rock classification.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":null,"pages":null},"PeriodicalIF":4.2,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142552516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A hybrid inversion algorithm to obtain the resistivity of the uninvaded zone based on the array induction log","authors":"","doi":"10.1016/j.cageo.2024.105766","DOIUrl":"10.1016/j.cageo.2024.105766","url":null,"abstract":"<div><div>This study investigates the impact of the drilling mud invasion on the borehole-measured resistivity. The primary objective is to retrieve the true resistivity of the formation, which helps in identifying different fluids in the reservoir. To achieve this goal, We proposed a hybrid inversion approach integrating the Levenberg-Marquardt and Markov Chain Monte Carlo algorithms with a five-parameter formation resistivity model. Synthetic and real-world data are utilized to assess the method's robustness and reliability. The simulated result indicated that the method is reliable when the data noise level is less than 5%.</div><div>The method applied to real-world data revealed that the resistivity profile on the water zone showed a slight increase in the inverted resistivity from measured resistivity. Meanwhile, in the oil zone, the calculated resistivity revealed a high deviation from the measured resistivity, indicating the effects of mud invasion. The introduced methods are only applicable when the invasions of mud occur within the range of the logging tool's depth of investigation. Moreover, the method may give no reliable result when the invasion exceeds the tool's investigation depth. It indicates its limitation.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":null,"pages":null},"PeriodicalIF":4.2,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593369","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Improving the training performance of generative adversarial networks with limited data: Application to the generation of geological models","authors":"","doi":"10.1016/j.cageo.2024.105747","DOIUrl":"10.1016/j.cageo.2024.105747","url":null,"abstract":"<div><div>In the past years, there is a growing interest in the applications of Generative Adversarial Networks (GANs) to generate geological models. Although GANs have proven to be an effective tool to learn and reproduce the complex data patterns present in some geological models, some challenges still remain open. Among others, a well-noticed problem is the need for a large number of samples to ensure high-quality training, which can be prohibitively expensive in some cases. As an attempt to offer a (possibly partial) solution to the aforementioned challenge, in this study, we investigate the feasibility and effectiveness of a zero-centered discriminator regularization technique for improving the performance of a GAN. Additionally, we evaluate an adaptive data augmentation technique to overcome the potential issue of limited training data, for the purpose of generating geologically feasible realizations of hydrocarbon reservoir models. Our findings demonstrate that a combination of the two techniques lead to notable performance improvements of a GAN. Particularly, it is observed that using the adaptive data augmentation technique in a GAN can yield similar results to those obtained by the GAN with a much larger dataset.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":null,"pages":null},"PeriodicalIF":4.2,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142552530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A reverse tracing of the water flow path algorithm for slope length extraction based on triangulated irregular network","authors":"","doi":"10.1016/j.cageo.2024.105737","DOIUrl":"10.1016/j.cageo.2024.105737","url":null,"abstract":"<div><div>Terrain factor is an important factor affecting soil erosion, in which slope length is an important indicator of terrain factor. In this paper, we model the regional topographic relief with triangulated irregular network TIN, use the slope aspect of the TIN triangular surface to determine the flow direction, and propose an algorithm (RT-WFP) for extracting the slope length by tracing the water flow trajectory in reverse direction. The slope cutoff point rule is set in the algorithm to improve the accuracy of the slope length extraction results. We calculated the slope length of the experimental area of the small watershed of Golden Hook-shaped collapsing hill in Bailu Township, Ganxian District, and the rationality of the algorithm proposed in this paper is verified through the comparison and analysis with the traditional slope length extraction algorithm. The experimental results show that, compared with the traditional D8 algorithm, the water flow path extracted by this algorithm in the experimental area more closely matches the water flow path based on contour mapping, and the slope length extracted by this algorithm has a lower sensitivity to the resolution of the data, and the percentage of cells with a slope length value of no more than 300 m (the limit standard of the RUSLE model) at a resolution of 30 m reaches 94.19%.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":null,"pages":null},"PeriodicalIF":4.2,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142552515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Application of polynomial type elastic outer boundary conditions in fractal composite reservoir seepage model","authors":"","doi":"10.1016/j.cageo.2024.105764","DOIUrl":"10.1016/j.cageo.2024.105764","url":null,"abstract":"<div><div>In this paper, the elastic function in the explanation of elastic outer boundary condition is regarded as polynomial functions of space variable <span><math><mrow><mi>r</mi></mrow></math></span> and time variable <span><math><mrow><mi>t</mi></mrow></math></span>, and this is incorporated into the analysis of fractal composite reservoirs. The Laplace space solution the fractal composite reservoir models, which have polynomial elastic outer boundary conditions, is achieved through a modified method of similarity construction and the Gaver-Stehfest numerical inversion technique is used to derive the semi-analytical solutions for the models in actual space. Next, the polynomial elastic function is turned into a first-order function about time variable. Curves of pressure in non-dimensional well bottom under different quadratic pressure gradient terms and primary control factors are drawn by using MATLAB software and their impact on non-dimensional well bottom are analyzed. It is proved that the three impractical outer boundary conditions are only a particular case of the polynomial elastic outer boundary conditions. The research in this paper expands the discussion scope of elastic outer boundary conditions, and has strong reference significance.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":null,"pages":null},"PeriodicalIF":4.2,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142586652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"SwinInver: 3D data-driven seismic impedance inversion based on Swin Transformer and adversarial training","authors":"","doi":"10.1016/j.cageo.2024.105743","DOIUrl":"10.1016/j.cageo.2024.105743","url":null,"abstract":"<div><div>As deep learning becomes increasingly prevalent in seismic impedance inversion, 3D data-driven approaches have garnered substantial interest. However, two critical challenges persist. First, existing methodologies predominantly rely on Convolutional Neural Networks (CNNs), which, due to the inherent locality of convolutional operations, are inadequate in capturing the global context of seismic data. This limitation notably hinders their performance in inverting complex subsurface structures, such as salt bodies. Second, the current inversion frameworks are prone to overfitting, particularly when trained on limited seismic datasets. To address these challenges, we propose SwinInver, a novel backbone network that integrates the Swin Transformer as its fundamental unit, coupled with a high-resolution network design to facilitate comprehensive global modeling of intricate subsurface structures. Furthermore, we incorporate adversarial training to enhance the inversion process and effectively mitigate overfitting. Experimental evaluations demonstrate that SwinInver significantly surpasses conventional CNN-based approaches in both synthetic and field data scenarios, providing a more accurate and reliable framework for seismic impedance inversion.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":null,"pages":null},"PeriodicalIF":4.2,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142578525","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Intelligent fault prediction with wavelet-SVM fusion in coal mine","authors":"","doi":"10.1016/j.cageo.2024.105744","DOIUrl":"10.1016/j.cageo.2024.105744","url":null,"abstract":"<div><div>Fault prediction in coal mining is crucial for safety, and recent technological advancements are steering this field towards supervised intelligent interpretation, moving beyond traditional human-machine interaction. Currently, support vector machine (SVM) predictions often rely on seismic attribute data; however, the poor quality of some fault data characteristics hampers their predictive capability. To localize the fault based on original seismic data and improve SVM prediction we propose the W-SVM algorithm, which integrates wavelet transform and SVM. Through wavelet transform, we localize fault features in seismic data, which are then used for SVM prediction. Validation using real data confirms the feasibility of the W-SVM approach. The W-SVM model successfully identifies 34 known faults. Beyond achieving high prediction accuracy, the model exhibits improved stability and generalization. The difference among the evaluation metrics for training, validation, and testing is within 5%. Moreover, this study localizes the response of faults through wavelet transform, simplifies the dataset preparation process, improves computational efficiency, and increases overall applicability. This advancement further promotes the development of intelligent identification of faults in coal mines.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":null,"pages":null},"PeriodicalIF":4.2,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142560840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A novel algorithm for identifying arrival times of P and S Waves in seismic borehole surveys","authors":"","doi":"10.1016/j.cageo.2024.105746","DOIUrl":"10.1016/j.cageo.2024.105746","url":null,"abstract":"<div><div>The arrival times of P and S waves, originating from earthquakes, diverse seismic tests, and events, are crucial geotechnical parameters. Derived from the inversion of these travel times, V<sub>P</sub> (P-wave velocity) and V<sub>S</sub> (S-wave velocity) are pivotal in geotechnical engineering, correlating directly with dynamic soil properties and enabling calculations of Poisson's Ratio (<strong>ν</strong>), Young's modulus (E), Shear modulus (μ), and Bulk modulus (B). Both V<sub>P</sub> and V<sub>S</sub> are crucial for evaluating soil behaviour under various conditions, aiding in modelling soil for settlement, wave propagation, seismic wave interaction, liquefaction potential analysis, seismic response analysis, and many more. The selection of arrival times for seismic tests, including Crosshole, Downhole, and Uphole tests, is done manually, which is time-consuming and potentially erroneous. To address this issue, various algorithms have been developed to automate the picking process. Some of these algorithms use wavelet transforms and Bayesian information criteria, while others use machine learning techniques such as artificial neural networks. These methods vary in terms of their accuracy, yet each one possesses inherent limitations when it comes to processing data with different levels of signal-to-noise ratio. The advancement of automated algorithms for determining arrival times is an ongoing and dynamic field of research. Apart from the existing research focused on determining the arrival time of P waves, there is a dearth of studies investigating the detection of S wave arrival times. To fill this gap, this study proposes new approaches for detecting both P and S wave arrival time(s). One approach entails the utilization of an iterative optimization algorithm to accurately fit a curve to the leading edge of the P waveform. The arrival time is determined by calculating a fraction relative to the highest point obtained from the fitted peak. The second approach entails identifying the exact moment of the S wave's arrival by determining the points of intersection between the oppositely polarized S waveforms. These methods provide a promising approach for automatically detecting both P and S wave arrival time(s), which has the potential to improve the precision and efficiency in picking up arrival time(s).</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":null,"pages":null},"PeriodicalIF":4.2,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142554641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Adaptive constraint-guided surrogate enhanced evolutionary algorithm for horizontal well placement optimization in oil reservoir","authors":"","doi":"10.1016/j.cageo.2024.105740","DOIUrl":"10.1016/j.cageo.2024.105740","url":null,"abstract":"<div><div>In the face of escalating global energy demands, this study introduces an Adaptive Constraint-Guided Surrogate Enhanced Evolutionary Algorithm (ACG-EBS) for optimizing horizontal well placements in oil reservoirs. Addressing the complex challenge of maximizing oil production, the ACG-EBS integrates geological, engineering, and economic considerations into a novel optimization framework. This algorithm stands out for its adept navigation through a complex and discrete decision space of horizontal well placements, an area where traditional methods often encounter challenges. Key innovations include the Adaptive Constraint Initialization Mechanism (ACIM) and the Evolutionary Constraint-Tailored Candidate Refinement strategy (ECTCR), which collectively elevate the feasibility of candidate solutions. An enhanced balance strategy harmonizes comprehensive and niche surrogate models, optimizing the balance between exploration and exploitation. Through testing on both two-dimensional and three-dimensional reservoir models, the ACG-EBS has proven highly effective in identifying optimal well placements that align with field deployment realities and maximize economic returns. This contribution significantly supports the ongoing evolution of oilfield development optimization, showcasing the algorithm's potential to enhance oil production and economic outcomes.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":null,"pages":null},"PeriodicalIF":4.2,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142571583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Constructing three-dimension digital rock with porosity information constraint: A double-network-cycled style-based deep-learning approach","authors":"","doi":"10.1016/j.cageo.2024.105741","DOIUrl":"10.1016/j.cageo.2024.105741","url":null,"abstract":"<div><div>Understanding reservoir properties from geophysical responses necessitates the construction of accurate petrophysical templates based on adequate petrophysical data. However, engineering coring is often limited by complex subsurface conditions and high costs. Artificial intelligence (AI) techniques offer an efficient and economical way to synthesize digital samples. Nevertheless, traditional deep learning approaches may suffer from mode collapse, particularly when generating samples with complex structures from a limited number of training samples. To address this challenge, we propose novel Generative Adversarial Networks (GANs) to controllably generate 3D digital rock samples according to porosity distribution. By employing a style-transfer generator, multi-scale information of 3D digital rock is integrated into the generation process, effectively reducing the risk of mode collapse. Embedding the generator into a double-network-cycled framework further enhances the controllability of conditional information in the generated samples. Our analysis shows that the minimum error between the generated samples and the desired samples in terms of porosity is only 0.07%. A clear contrast is observed in morphological parameters, and differences in pore structure lead to significant variations in mechanical and hydraulic properties between original samples and synthetic samples with similar porosity. This indicates that the property contrast is likely caused by differences in pore structures rather than porosity. These findings will assist in future studies on the effect of pore structure on petrophysical properties and improve the utility of rock physics templates in geophysical inversion.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":null,"pages":null},"PeriodicalIF":4.2,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}