Artificial Intelligence in Geosciences最新文献

{"title":"Machine-learning seismic damage assessment model for building structures","authors":"Fatma Zohra Belhadj ,&nbsp;Ahmed Fouad Belhadj ,&nbsp;Mohamed Chabaat","doi":"10.1016/j.aiig.2025.100155","DOIUrl":"10.1016/j.aiig.2025.100155","url":null,"abstract":"<div><div>Buildings in seismic-prone regions are highly vulnerable to structural damage, necessitating meticulous Seismic Damage Assessment (SDA) for accurate design and mitigation strategies. The intricate nature of Seismic Damage Assessment (SDA) poses challenges, particularly when employing Finite Element Analysis (FE) for individual structures, as simulation techniques are time-intensive due to the inherent complexity of the models. Computational methods combining Soil-Structure Interaction (SSI) for earthquake damage assessment further compound the challenge, requiring substantial computational efforts to construct a comprehensive database for area-based prediction models. This study introduces such challenges via a novel Artificial Neural Network (ANN) approaches-based model as an alternative for prompt building Seismic Damage Assessment evaluation. The proposed ANN model leverages three key inputs—seismic, building, and soil parameters—incorporating a multi-step analysis process to generate seismic responses with soil-structure interaction. The findings underscore the remarkable accuracy of the SDA-Net model, positioning it as an effective predictive tool and rapid decision support system for structures affected by SSI impacts. This innovative approach not only serves as a proactive pre-disaster management tool for assessing potential damage but also emerges as a practical asset for ensuring the safety and durability of structures in the face of natural disasters. The study's contribution lies in its potential application as a valuable tool in structural engineering, aligning with the objectives and scope of the Research Journal of The Institution of Structural Engineers.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100155"},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145157171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deciphering influential features in the seismic catalog for large earthquake occurrence from a machine learning perspective","authors":"Jinsu Jang ,&nbsp;Byung-Dal So ,&nbsp;David A. Yuen ,&nbsp;Sung-Joon Chang","doi":"10.1016/j.aiig.2025.100161","DOIUrl":"10.1016/j.aiig.2025.100161","url":null,"abstract":"<div><div>The spatiotemporal distribution and magnitude of seismicity collected over decades are crucial for understanding the stress interactions underlying large earthquakes. In this study, machine learning (ML) explainers identify and rank the features that distinguish Large Earthquake Occurrence (LEO) from non-LEO spatiotemporal windows. Seventy-eight statistics related to time, latitude, longitude, depth, and magnitude were extracted from the earthquake catalog (Global Centroid Moment Tensor) to produce 202,706 spatiotemporally discretized windows. ML explainers trained on these windows revealed the maximum magnitude (<em>M</em>_<em>max</em>) as the most influential feature. Classification performance improved when the maximum inter-event time, the average inter-event time, and the minimum ratio of focal depth to magnitude were jointly trained with <em>M</em>_<em>max</em>. The top five features showed weak-to-moderate correlations, providing complementary information to the ML explainers. Our explainable ML framework can be extended to different earthquake catalogs, including those with focal mechanisms and small-magnitude events.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100161"},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145465151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Digital core reconstruction of tight carbonate rocks based on SliceGAN","authors":"Ying Zhou ,&nbsp;Taiping Zhao ,&nbsp;Wenjing Zhang ,&nbsp;Feiqi Teng ,&nbsp;Xin Nie","doi":"10.1016/j.aiig.2025.100116","DOIUrl":"10.1016/j.aiig.2025.100116","url":null,"abstract":"<div><div>The pore structures of the Majiagou Formation in the Ordos Basin are complex, featuring micro- and nano-scale intra-crystalline and inter-crystalline pores that significantly impact hydrocarbon storage and flow. Precisely characterizing the rock internal structures is crucial for reservoir exploration and development. However, it is difficult to accurately characterize the pore structure of rock using traditional imaging methods to meet the simulation requirements. In this context, this study focuses on high-resolution 3D digital core reconstruction using the SliceGAN model. Specifically, the Modular Automated Processing System (MAPS) image and Quantitative Evaluation of Minerals by Scanning Electron Microscopy (QEMSCAN) image were combined to divide MAPS into three categories: pore, dolomite, and calcite. Then, through the SliceGAN algorithm, the 3D digital core was reconstructed. To evaluate the reconstruction, the auto-correlation function, two-point probability function, porosity, mineral content, and specific surface area were employed. The results show that the SliceGAN can effectively capture the micro-features in the core, and the internal structure of the generated core was consistent with that of the original core. This study provided a new sight for reconstructing cores with complex pore structures and strong heterogeneity and innovatively supports tight carbonate reservoir characterization and evaluation.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 1","pages":"Article 100116"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143864930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An intelligent recognition method of deep shale gas reservoir laminaset based on laminaset clustering and R-L-M algorithm","authors":"Yu Zeng ,&nbsp;Fuqiang Lai ,&nbsp;Haijie Zhang ,&nbsp;Yi Jiang ,&nbsp;Junwei Pu ,&nbsp;Tongtong Luo ,&nbsp;Xiaoxia Zhao","doi":"10.1016/j.aiig.2025.100113","DOIUrl":"10.1016/j.aiig.2025.100113","url":null,"abstract":"<div><div>Lamina structures, as typical sedimentary features in shale formations, determine both the quality of shale reservoirs and fracturing effects. In this study, through electric imaging logging, based on core scanning photos, thin sections, and other data from the Wufeng-Longmaxi Formation shale reservoirs in the western Sichuan Block, the characteristics and classification scheme of deep shale gas reservoir laminaset were clarified. In addition, with core scale electrical images, the electrical imaging logging response characteristics of different types of laminaset were identified. Based on electrical imaging logging images, a laminaset clustering algorithm was designed to segment the laminaset and then Levenberg-Marquardt (L-M) algorithm was improved by introducing a random forest to obtain the R-L-M algorithm, which was used to extract key parameters of laminaset such as attitude, type, density, and thickness. The average accuracy, recall rate, and F1 score of laminaset recognition results of this algorithm were 14.82 % higher than those of a well-known international commercial software (T). This method was used to evaluate the Longmaxi Formation shale gas reservoir in the western Sichuan Block. The development density of clay-siliceous (organic-lean) laminaset from the Longyi 1–4 small layer to the lower Wufeng Formation firstly decreased and then increased and the minimum value was found in Longyi 1-1 small layer. In contrast, the development density of siliceous-clay laminaset (organic-rich) first increased and then gradually decreased and the maximum value was found in Longyi 1-1 small layer. The clay-siliceous laminaset (organic matters-contained) and the calcareous-clay laminaset (organic matters-contained) showed a stable developmental trend.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 1","pages":"Article 100113"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143828417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Loosening rocks detection at Draa Sfar deep underground mine in Morocco using infrared thermal imaging and image segmentation models","authors":"Kaoutar Clero ,&nbsp;Said Ed-Diny ,&nbsp;Mohammed Achalhi ,&nbsp;Mouhamed Cherkaoui ,&nbsp;Imad El Harraki ,&nbsp;Sanaa El Fkihi ,&nbsp;Intissar Benzakour ,&nbsp;Tarik Soror ,&nbsp;Said Rziki ,&nbsp;Hamd Ait Abdelali ,&nbsp;Hicham Tagemouati ,&nbsp;François Bourzeix","doi":"10.1016/j.aiig.2025.100106","DOIUrl":"10.1016/j.aiig.2025.100106","url":null,"abstract":"<div><div>Rockfalls are among the frequent hazards in underground mines worldwide, requiring effective methods for detecting unstable rock blocks to ensure miners' and equipment's safety. This study proposes a novel approach for identifying potential rockfall zones using infrared thermal imaging and image segmentation techniques. Infrared images of rock blocks were captured at the Draa Sfar deep underground mine in Morocco using the FLUKE TI401 PRO thermal camera. Two segmentation methods were applied to locate the potential unstable areas: the classical thresholding and the K-means clustering model. The results show that while thresholding allows a binary distinction between stable and unstable areas, K-means clustering is more accurate, especially when using multiple clusters to show different risk levels. The close match between the clustering masks of unstable blocks and their corresponding visible light images further validated this. The findings confirm that thermal image segmentation can serve as an alternative method for predicting rockfalls and monitoring geotechnical issues in underground mines. Underground operators worldwide can apply this approach to monitor rock mass stability. However, further research is recommended to enhance these results, particularly through deep learning-based segmentation and object detection models.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 1","pages":"Article 100106"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143143632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fast 2D forward modeling of electromagnetic propagation well logs using finite element method and data-driven deep learning","authors":"A.M. Petrov,&nbsp;A.R. Leonenko,&nbsp;K.N. Danilovskiy,&nbsp;O.V. Nechaev","doi":"10.1016/j.aiig.2025.100112","DOIUrl":"10.1016/j.aiig.2025.100112","url":null,"abstract":"<div><div>We propose a novel workflow for fast forward modeling of well logs in axially symmetric 2D models of the near-wellbore environment. The approach integrates the finite element method with deep residual neural networks to achieve exceptional computational efficiency and accuracy. The workflow is demonstrated through the modeling of wireline electromagnetic propagation resistivity logs, where the measured responses exhibit a highly nonlinear relationship with formation properties. The motivation for this research is the need for advanced modeling algorithms that are fast enough for use in modern quantitative interpretation tools, where thousands of simulations may be required in iterative inversion processes. The proposed algorithm achieves a remarkable enhancement in performance, being up to 3000 times faster than the finite element method alone when utilizing a GPU. While still ensuring high accuracy, this makes it well-suited for practical applications when reliable payzone assessment is needed in complex environmental scenarios. Furthermore, the algorithm's efficiency positions it as a promising tool for stochastic Bayesian inversion, facilitating reliable uncertainty quantification in subsurface property estimation.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 1","pages":"Article 100112"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143776649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A staged deep learning approach to spatial refinement in 3D temporal atmospheric transport","authors":"M. Giselle Fernández-Godino ,&nbsp;Wai Tong Chung ,&nbsp;Akshay A. Gowardhan ,&nbsp;Matthias Ihme ,&nbsp;Qingkai Kong ,&nbsp;Donald D. Lucas ,&nbsp;Stephen C. Myers","doi":"10.1016/j.aiig.2025.100120","DOIUrl":"10.1016/j.aiig.2025.100120","url":null,"abstract":"<div><div>High-resolution spatiotemporal simulations effectively capture the complexities of atmospheric plume dispersion in complex terrain. However, their high computational cost makes them impractical for applications requiring rapid responses or iterative processes, such as optimization, uncertainty quantification, or inverse modeling. To address this challenge, this work introduces the Dual-Stage Temporal Three-dimensional UNet Super-resolution (DST3D-UNet-SR) model, a highly efficient deep learning model for plume dispersion predictions. DST3D-UNet-SR is composed of two sequential modules: the temporal module (TM), which predicts the transient evolution of a plume in complex terrain from low-resolution temporal data, and the spatial refinement module (SRM), which subsequently enhances the spatial resolution of the TM predictions. We train DST3D-UNet-SR using a comprehensive dataset derived from high-resolution large eddy simulations (LES) of plume transport. We propose the DST3D-UNet-SR model to significantly accelerate LES of three-dimensional (3D) plume dispersion by three orders of magnitude. Additionally, the model demonstrates the ability to dynamically adapt to evolving conditions through the incorporation of new observational data, substantially improving prediction accuracy in high-concentration regions near the source.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 1","pages":"Article 100120"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144185115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Variogram modelling optimisation using genetic algorithm and machine learning linear regression: application for Sequential Gaussian Simulations mapping","authors":"André William Boroh ,&nbsp;Alpha Baster Kenfack Fokem ,&nbsp;Martin Luther Mfenjou ,&nbsp;Firmin Dimitry Hamat ,&nbsp;Fritz Mbounja Besseme","doi":"10.1016/j.aiig.2025.100124","DOIUrl":"10.1016/j.aiig.2025.100124","url":null,"abstract":"<div><div>The objective of this study is to develop an advanced approach to variogram modelling by integrating genetic algorithms (GA) with machine learning-based linear regression, aiming to improve the accuracy and efficiency of geostatistical analysis, particularly in mineral exploration. The study combines GA and machine learning to optimise variogram parameters, including range, sill, and nugget, by minimising the root mean square error (RMSE) and maximising the coefficient of determination (R²). The experimental variograms were computed and modelled using theoretical models, followed by optimisation via evolutionary algorithms. The method was applied to gravity data from the Ngoura-Batouri-Kette mining district in Eastern Cameroon, covering 141 data points. Sequential Gaussian Simulations (SGS) were employed for predictive mapping to validate simulated results against true values. Key findings show variograms with ranges between 24.71 km and 49.77 km, optimised RMSE and R² values of 11.21 mGal² and 0.969, respectively, after 42 generations of GA optimisation. Predictive mapping using SGS demonstrated that simulated values closely matched true values, with the simulated mean at 21.75 mGal compared to the true mean of 25.16 mGal, and variances of 465.70 mGal² and 555.28 mGal², respectively. The results confirmed spatial variability and anisotropies in the N170-N210 directions, consistent with prior studies. This work presents a novel integration of GA and machine learning for variogram modelling, offering an automated, efficient approach to parameter estimation. The methodology significantly enhances predictive geostatistical models, contributing to the advancement of mineral exploration and improving the precision and speed of decision-making in the petroleum and mining industries.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 1","pages":"Article 100124"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144168286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic description of rock thin sections: A web application","authors":"Stalyn Paucar,&nbsp;Christian Mejia-Escobar,&nbsp;Victor Collaguazo","doi":"10.1016/j.aiig.2025.100118","DOIUrl":"10.1016/j.aiig.2025.100118","url":null,"abstract":"<div><div>The identification and characterization of rock types is a core activity in geology and related fields, including mining, petroleum, environmental science, industry, and construction. Traditionally, this task is performed by human specialists who analyze and describe the type, composition, texture, shape, and other properties of rock samples, whether collected in-situ or prepared in a laboratory. However, the process is subjective, dependent on the specialist’s experience, and time-consuming. This study proposes an artificial intelligence-based approach that combines computer vision and natural language processing to generate both textual and verbal descriptions from images of rock thin sections. A dataset of images and corresponding textual descriptions is used to train a hybrid deep learning model. Features extracted from the images using EfficientNetB7 are processed by a Transformer network to generate textual descriptions, which are then converted into verbal responses using a speech synthesis service. The experimental results show an accuracy of 0.892 and a BLEU score of 0.71. This model offers potential utility for research, professional, and academic applications and has been deployed as a web application for public use.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 1","pages":"Article 100118"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144212094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Innovative cone resistance and sleeve friction prediction from geophysics based on a coupled geo-statistical and machine learning process","authors":"A. Bolève,&nbsp;R. Eddies,&nbsp;M. Staring,&nbsp;Y. Benboudiaf,&nbsp;H. Pournaki,&nbsp;M. Nepveaux","doi":"10.1016/j.aiig.2025.100110","DOIUrl":"10.1016/j.aiig.2025.100110","url":null,"abstract":"<div><div>Geotechnical parameters derived from an intrusive cone penetration test (CPT) are used to asses mechanical properties to inform the design phase of infrastructure projects. However, local, in situ 1D measurements can fail to capture 3D subsurface variations, which could mean less than optimal design decisions for foundation engineering. By coupling the localised measurements from CPTs with more global 3D measurements derived from geophysical methods, a higher fidelity 3D overview of the subsurface can be obtained. Machine Learning (ML) may offer an effective means to capture all types of geophysical information associated with CPT data at a site scale to build a 2D or 3D ground model. In this paper, we present an ML approach to build a 3D ground model of cone resistance and sleeve friction by combining several CPT measurements with Multichannel Analysis of Surface Waves (MASW) and Electrical Resistivity Tomography (ERT) data on a land site characterisation project in the United Arab Emirates (UAE). To avoid a potential overfitting problem inherent to the use of machine learning and a lack of data at certain locations, we explore the possibility of using a prior Geo-Statistical (GS) approach that attempts to constrain the overfitting process by “artificially” increasing the amount of input data. A sensitivity study is also performed on input features used to train the ML algorithm to better define the optimal combination of input features for the prediction. Our results showed that ERT data were not useful in capturing 3D variations of geotechnical properties compared to V_s due to the geographical location of the site (200 m east from the Oman Gulf) and the possible effect of saline water intrusion. Additionally, we demonstrate that the use of a prior GS phase could be a promising and interesting means to make the prediction of ground properties more robust, especially for this specific case study described in this paper. Looking ahead, better representation of the subsurface can lead to a number of benefits for stakeholders involved in developing assets. Better ground/geotechnical models mean better site calibration of design methods and fewer design assumptions for reliability-based design, creating an opportunity for value engineering in the form of lighter construction without compromising safety, shorter construction timelines, and reduced resource requirements.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 1","pages":"Article 100110"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143526930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}