Computers & Geosciences最新文献

{"title":"Deep learning contribution to the automatic picking of surface-wave dispersion for the characterization of railway earthworks","authors":"J. Cárdenas ,&nbsp;A. Burzawa ,&nbsp;N. Radic ,&nbsp;L. Bodet ,&nbsp;R. Vidal ,&nbsp;K. Diop ,&nbsp;M. Dangeard ,&nbsp;A. Dhemaied","doi":"10.1016/j.cageo.2025.105883","DOIUrl":"10.1016/j.cageo.2025.105883","url":null,"abstract":"<div><div>Railway Trackbed (RT), which collectively describes the subgrade structures that support rail tracks, is of great importance to the effective maintenance and rehabilitation of the rail network. Therefore, a comprehensive understanding of the mechanical condition of Railway Earthwork (RE) is necessary. The development of non-destructive and efficient methods for the characterization of REs is a priority. Previous studies have investigated the potential of surface waves for the characterization of RE. Preliminary results indicate that this approach is effective, particularly when using high yield acquisition setup such as landstreamer. However, these instruments generate an amount of data that necessitates optimized and automated processing. The potential of Deep Learning (DL) to automate the processing of surface wave data is being explored. In this study, the primary objective is to identify the energy maxima and propagation modes in dispersion images. A supervised convolutional neural network (CNN), designated as ‘U-Net’, was selected to perform segmentation tasks. This model, called ‘U2-pick’, integrates two U-net architectures: one for maxima identification and another for propagation mode identification. The training dataset was constructed using synthetic data that is representative of a French High-Speed-Line (HSL) RE structure. The preliminary outcomes on the synthetic datasets are encouraging, demonstrating accurate identification of energy maxima and mode classification. However, the predictions made on field datasets revealed that while the energy peaks were identified with a high degree of accuracy, the mode assignment proved to be less satisfactory, especially in the case of higher modes. Finally, a comparison of the accuracy and picking time was performed using more standard tools like maxima search, semi-automatic, and Machine Learning (ML) tools.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"198 ","pages":"Article 105883"},"PeriodicalIF":4.2,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143395140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An improved general method for measuring pore size distribution with digital images of porous media","authors":"Shuaibing Song,&nbsp;Tong Zhang,&nbsp;Qingyi Tu","doi":"10.1016/j.cageo.2025.105893","DOIUrl":"10.1016/j.cageo.2025.105893","url":null,"abstract":"<div><div>As one of the most fundamental and vital parameters for characterizing the pore structure characteristics of porous media materials, the accurate and efficient quantitative measurement of pore size distribution (PSD) has a wide and strong demand in various research fields. In this paper, by analogy with the pore size measurement principle of mercury intrusion porosimetry (MIP), an improved general method for measuring the PSD of porous media from their digital images is developed by using a cluster of predefined digital circular or spherical pores with different radius dimensions to pack the pore space step by step in an overlapping manner. To verify the validity and accuracy of the proposed method, a set of artificially generated pore structures with known PSD is used as the benchmark test dataset, and the results show that the PSD measured by the proposed method is consistent with the theoretical benchmark value. In addition, the pore structures of real porous media materials with large dimensions are selected as the test dataset as well, and the computational efficiency of the proposed method is comprehensively evaluated by comparing that of the existing advanced PSD measurement methods, the results of which show that the proposed method takes the least amount of time to complete the PSD measurement. In terms of accuracy and efficiency, the proposed method has good performance, indicating that it can be promoted as a general method for the PSD measurement of various porous media materials.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"197 ","pages":"Article 105893"},"PeriodicalIF":4.2,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143387527","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":"Data space inversion for efficient predictions and uncertainty quantification for geothermal models","authors":"Alex de Beer ,&nbsp;Andrew Power ,&nbsp;Daniel Wong ,&nbsp;Ken Dekkers ,&nbsp;Michael Gravatt ,&nbsp;Elvar K. Bjarkason ,&nbsp;John P. O’Sullivan ,&nbsp;Michael J. O’Sullivan ,&nbsp;Oliver J. Maclaren ,&nbsp;Ruanui Nicholson","doi":"10.1016/j.cageo.2025.105882","DOIUrl":"10.1016/j.cageo.2025.105882","url":null,"abstract":"<div><div>The ability to make accurate predictions with quantified uncertainty provides a crucial foundation for the successful management of a geothermal reservoir. Conventional approaches for making predictions using geothermal reservoir models involve estimating unknown model parameters using field data, then propagating the uncertainty in these estimates through to the predictive quantities of interest. However, the unknown parameters are not always of direct interest; instead, the predictions are of primary importance. Data space inversion (DSI) is an alternative methodology that allows for the efficient estimation of predictive quantities of interest, with quantified uncertainty, that avoids the need to estimate model parameters entirely. In this paper, we illustrate the applicability of DSI to geothermal reservoir modelling. We first review the processes of model calibration, prediction and uncertainty quantification from a Bayesian perspective, and introduce data space inversion as a simple, efficient technique for approximating the posterior predictive distribution. We then introduce a modification of the typical DSI algorithm that allows us to sample directly and efficiently from the DSI approximation to the posterior predictive distribution, and apply the algorithm to two model problems in geothermal reservoir modelling. We evaluate the accuracy and efficiency of our DSI algorithm relative to other common methods for uncertainty quantification and study how the number of reservoir model simulations affects the resulting approximation to the posterior predictive distribution. Our results demonstrate that data space inversion is a robust and efficient technique for making predictions with quantified uncertainty using geothermal reservoir models, providing a useful alternative to more conventional approaches.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"197 ","pages":"Article 105882"},"PeriodicalIF":4.2,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143377638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GPR-FWI-Py: Open-source Python software for multi-scale regularized full waveform inversion in Ground Penetrating Radar using random excitation sources","authors":"Xiangyu Wang ,&nbsp;Hai Liu ,&nbsp;Xu Meng ,&nbsp;Hesong Hu","doi":"10.1016/j.cageo.2025.105870","DOIUrl":"10.1016/j.cageo.2025.105870","url":null,"abstract":"<div><div>Full Waveform Inversion (FWI) of Ground Penetrating Radar (GPR) is crucial for enhancing subsurface imaging, yet its applications often confronts computational and usability challenges. This paper introduces GPR-FWI-Py, a comprehensive 2D GPR FWI code package that addresses these challenges through a multi-scale strategy, a random excitation source strategy, and Total Variation (TV) regularization. Optimized for high-performance computing, the software is developed in pure Python, ensuring both high efficiency and accessibility. Key features include user-friendly design and readability, which empower users to easily adapt and maintain the software to meet specific project needs. Performance evaluations on layered and Over-Thrust models confirm that our strategies significantly improve FWI results. The modular architecture of GPR-FWI-Py not only simplifies the integration of the FWI algorithm into GPR imaging but also enhances adaptability by supporting the introduction of additional functionalities.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"197 ","pages":"Article 105870"},"PeriodicalIF":4.2,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143377635","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 deep learning-based parametric inversion for forecasting water-filled bodies position using electromagnetic method","authors":"Lu Gan ,&nbsp;Rongjiang Tang ,&nbsp;Hao Li ,&nbsp;Fusheng Li ,&nbsp;Yunbo Rao","doi":"10.1016/j.cageo.2025.105881","DOIUrl":"10.1016/j.cageo.2025.105881","url":null,"abstract":"<div><div>The transient electromagnetic method (TEM) is extensively employed for identifying regions with low resistivity ahead of tunnel construction. Nevertheless, performing a 2D or 3D inversion of geo-electric models across the entire subsurface is impractical due to the limited space within the underground tunnel and the non-uniqueness associated with TEM inversion. We design a tunnel electromagnetic joint scan observation system and present a deep learning-based parametric inversion for improved tunnel electromagnetic imaging, designed specifically for tunnel prediction of water-filled structures. It utilizes a configuration wherein transmitters scan along the surface while receivers are positioned within the tunnel, employing time-domain and frequency-domain transmitters and a multi-component receiver. The DL model for the first time provides parametric imaging of two different view, forming a self-checking mechanism, which can help constrain the predictions and reduce the non-uniqueness of the inversion. Trained by synthetic data, our system shows impressive adaptability to predict the 3D spatial position of water-filled anomalies and strong robustness under different tunnel environments including metal inference and undulating terrain conditions.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"197 ","pages":"Article 105881"},"PeriodicalIF":4.2,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143377636","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 veins recognition method for slope rock mass geological images in complex background noise","authors":"Niu Wen-jing ,&nbsp;Chen Yuan-xin ,&nbsp;He Ben-guo ,&nbsp;Chen Guang-mu ,&nbsp;Qiu Zhen-hua ,&nbsp;Fan Wen-yu","doi":"10.1016/j.cageo.2025.105885","DOIUrl":"10.1016/j.cageo.2025.105885","url":null,"abstract":"<div><div>The veins formed by magma intrusion often exist in the rock mass of slopes in the form of weak structural planes, thereby triggering landslide engineering disasters. Therefore, accurately identifying veins information from complex slope geological images is crucial. In light of this, this paper tackles the challenges encountered by traditional edge detection and deep learning algorithms in effectively detecting veins amidst complex background noise. These challenges include poor detection performance, low-quality manually annotated data, and the significant workload associated with manual annotation. To address these issues, we propose a vein intelligent recognition algorithm that combines OpenCV, AnyLabeling, and Mask R-CNN. By employing OpenCV, this study utilizes denoising and cropping techniques on the original images characterized by complex background noise. By preprocessing the raw dataset, it removes image noise and optimizes feature details within the images, thereby enhancing the quality of the dataset; Utilizing AnyLabeling for objective and automated annotation of veins information, this process eliminates the subjectivity associated with manual annotations, resulting in the creation of a high-quality library of veins image recognition samples; Building upon this foundation, we develop a Mask R-CNN model for veins contour segmentation. This model accurately and efficiently identifies veins information in complex geological images with background noise. Its successful application has been rigorously validated on a specific open-pit mine slope. The results indicate that this method successfully addresses the challenge of accurately identifying veins contours under complex background noise; The preprocessing technique, which combines OpenCV and AnyLabeling, demonstrates a significant enhancement in both the accuracy and efficiency of dataset annotation. This improvement contributes to heightened precision in the recognition results. Effectively discerned intricate veins details within the specific open-pit mine slope, resulting in an impressive 93.6% increase in MIoU value. This notable enhancement substantially improves the precision of slope stability calculation outcomes. The research findings are of significant importance for the analysis of veins-type geological hazards.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"197 ","pages":"Article 105885"},"PeriodicalIF":4.2,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143377637","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":"Analysis of earthquake detection using deep learning: Evaluating reliability and uncertainty in prediction methods","authors":"Sebastián Gamboa-Chacón ,&nbsp;Esteban Meneses ,&nbsp;Esteban J. Chaves","doi":"10.1016/j.cageo.2025.105877","DOIUrl":"10.1016/j.cageo.2025.105877","url":null,"abstract":"<div><div>This study evaluates the performance and reliability of earthquake detection using the EQTransformer, a novel deep learning program that is widely used in seismological observatories and research for enhancing earthquake catalogs. We test the EQTransformer capabilities and uncertainties using seismic data from the Volcanological and Seismological Observatory of Costa Rica and compare two detection options: the simplified method (MseedPredictor) and the complex method (Predictor), the latter incorporating Monte Carlo Dropout, to assess their reproducibility and uncertainty in identifying seismic events. Our analysis focuses on 24 h-duration data that began on February 18, 2023, following a magnitude 5.5 mainshock. Notably, we observed that sequential experiments with identical data and parametrization yield different detections and a varying number of events as a function of time. The results demonstrate that the complex method, which leverages iterative dropout, consistently yields more reproducible and reliable detections than the simplified method, which shows greater variability and is more prone to false positives. This study highlights the critical importance of method selection in deep learning models for seismic event detection, emphasizing the need for rigorous evaluation of detection algorithms to ensure accurate and consistent earthquake catalogs and interpretations. Our findings provide valuable insights for the application of AI tools in seismology, particularly in enhancing the precision and reliability of seismic monitoring efforts.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"197 ","pages":"Article 105877"},"PeriodicalIF":4.2,"publicationDate":"2025-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143347037","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":"Knowledge-driven stochastic modeling of geological geometry features conditioned on drillholes and outcrop contacts","authors":"Xiaolong Wei ,&nbsp;Zhen Yin ,&nbsp;Wilson Bonner ,&nbsp;Jef Caers","doi":"10.1016/j.cageo.2024.105779","DOIUrl":"10.1016/j.cageo.2024.105779","url":null,"abstract":"<div><div>Geometry features in geosciences are crucial for understanding both near-surface and deeper Earth’s interior structures. Geometry features have traditionally been delineated through diverse data sources such as surface mapping, geophysics, and core samples. However, the quantitative integration of geological knowledge and insights with the geoscientific data remains insufficiently addressed in the model construction. We have formulated a novel framework that employs stochastic level set simulation to model subsurface geometric features. The uniqueness of our framework involves geological knowledge, represented by two-dimensional (2D) geological diagrams, in the numerical modeling using Procrustes analysis. We account for the geological diagrams’ variability and uncertainty through transformations such as rotation, scaling, and translation. By using the designed loss functions, the resulting models align with the established geological knowledge and are also conditioned on the lithology from drillhole and surface observations (i.e., outcrop contacts). We apply the methodology to a field study of a Cu-Ni-PGE (copper-nickel-platinum group element) prospect hosted in a mafic intrusion, the Crystal Lake Gabbro (CLG), in northwest Ontario. Our study focuses on a single segment of the y-shaped CLG. The numerical outcomes of this application demonstrate that the incorporation of expert knowledge, drillholes, and surface data yields models with reliable geological geometry features, particularly the distribution of bottom boundary for intrusion models which is highly associated with economic mineralization.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"196 ","pages":"Article 105779"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143093168","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":"Quantitative lithology prediction from seismic data using deep learning","authors":"Wenliang Nie ,&nbsp;Jiayi Gu ,&nbsp;Bo Li ,&nbsp;Xiaotao Wen ,&nbsp;Xiangfei Nie","doi":"10.1016/j.cageo.2024.105821","DOIUrl":"10.1016/j.cageo.2024.105821","url":null,"abstract":"<div><div>Lithology prediction is essential for understanding subsurface structures and properties. Deep learning (DL) methods, which can capture the nonlinear relationship between lithology and seismic data, have gained significant attention as an effective tool in lithology prediction. However, these methods still face many challenges such as limited well-log data, class imbalances, and the need for robust predictive models. To address these issues, we propose an adaptive boosting-convolutional neural network (AdaBoost-CNN) framework integrated with improved inverse spectral decomposition (ISD) based on non-convex L_1-2 regularization. The ISD method generates high-resolution time-frequency (T-F) spectral maps from seismic data, which serve as inputs for the CNN. Furthermore, we introduce an enhanced sample weight adjustment strategy and a \"CNN transfer\" mechanism within the AdaBoost framework to address class imbalance and enhance training efficiency. The performance of AdaBoost–CNN was validated through field cases, and a comprehensive evaluation of the model parameters was conducted to understand their impact on performance. Field experiments demonstrated that the proposed method enhanced both the training efficiency and generalization ability of the models. Additionally, it effectively predicted lithology from seismic data and quantified lithology probabilities, thereby providing insights into the distribution of subsurface lithology.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"196 ","pages":"Article 105821"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143093171","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 generalization through self-supervised learning using generative pre-training transformer for natural gas segmentation","authors":"Luiz Fernando Trindade Santos ,&nbsp;Marcelo Gattass ,&nbsp;Carlos Rodriguez ,&nbsp;Jan Hurtado ,&nbsp;Frederico Miranda ,&nbsp;Diogo Michelon ,&nbsp;Roberto Ribeiro","doi":"10.1016/j.cageo.2024.105809","DOIUrl":"10.1016/j.cageo.2024.105809","url":null,"abstract":"<div><div>Seismic reflection is an essential geophysical method for subsurface mapping in the oil and gas industry, used to deduce the position and extension of potential gas accumulations through the processing and interpretation of data. However, interpreting seismic reflection data presents inherent ambiguity, as similar signatures may arise from geological scenarios with distinct physical properties. Furthermore, seismic interpretation is costly and labor-intensive, complicating the generation of extensive labeled datasets useful for conventional AI-assisted solutions. The emergence of self-supervised learning techniques has gained significant attention in the AI community, enabling the pre-training of deep neural networks without annotated data. This paper proposes a two-stage method for segmenting natural gas regions in seismic reflection images by using a generative pre-training transformer model for feature extraction and a recurrent neural network for per-seismic trace analysis. In the first stage, we pre-train the feature extractor in a self-supervised fashion under a seismic image reconstruction task. In the second stage, using the pre-trained feature extractor, we train the recurrent neural network for the segmentation of natural gas accumulations in 1D seismic image traces. We conducted quantitative and qualitative experiments on a private dataset to demonstrate how our self-supervised learning methodology helps achieve better gains in model generalization. The increase, which can reach up to 20%, in the F1-Score metric corroborates the latter. Thus, an improvement in generalization corresponds to an increase in success rates in drilling new wells.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"196 ","pages":"Article 105809"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143093174","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}