Artificial Intelligence in Geosciences最新文献

{"title":"Identification of major minerals in igneous rock microscopic images from thin sections through deep neural network analysis","authors":"Kouadio Krah ,&nbsp;Sié Ouattara ,&nbsp;Gbele Ouattara ,&nbsp;Marc Euphrem Allialy ,&nbsp;Alain Clement","doi":"10.1016/j.aiig.2025.100157","DOIUrl":"10.1016/j.aiig.2025.100157","url":null,"abstract":"<div><div>Several socio-environmental needs (medicine, industry, engineering, orogenesis, genesis, etc.) require minerals to be more precisly defined and characterised. The identification of minerals plays a crucial role for researchers and is becoming an essential aspect of geological analysis. However, traditional methods relied heavily on expert knowledge and specialised equipment, making them labour-intensive, costly and time-consuming. This dependence is often labour-intensive, not to mention costly and time-consuming. To address this issue, some researchers have opted for machine learning algorithms to quickly identify a single mineral in a microscopic image of rocks. However this approch does not correspond to patterns of mineral distribution, where minerals are typically found in associations. These associations make it difficult to accurately identify minerals using conventional machine learning algorithms. This paper introduces a deep neural learning model based on multi-label classification, utilizing the problem adaptation method to analyse microscopic images of rock thin sections. The model is based on the ResNet50 architecture, which is designed to analyse minerals and generates the probability of a mineral presence in an image. This method provides a solution to the dependence between associated minerals. Experiments on many test images showed a model confidence, achieving average precision, recall and F1_score 97.15 %, 96.25 % and 96.69 %, respectively. Visualisation of the class activation mapping using the Grad-CAM algorithm indicates that our model is likely to locate the identified minerals effectively. In this way, the importance of each pixel with the class of interest can be assessed using heat maps. The <strong>recorded</strong> results, in terms of both performance and pixel_level evaluation, demonstrate the promising potential of the model used. It can therefore be considered for multi-labels image classification, particulary for images representing rock minerals. This approach serves as a valuable support tool for geological studies.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100157"},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219427","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":"Improved estimation of two-phase capillary pressure with nuclear magnetic resonance measurements via machine learning","authors":"Oriyomi Raheem ,&nbsp;Misael M. Morales ,&nbsp;Wen Pan ,&nbsp;Carlos Torres-Verdín","doi":"10.1016/j.aiig.2025.100144","DOIUrl":"10.1016/j.aiig.2025.100144","url":null,"abstract":"&lt;div&gt;&lt;div&gt;Capillary pressure plays a crucial role in determining the spatial distribution of oil and gas, particularly in medium-to-low permeability reservoirs, where it is closely linked to the rock's pore structure and wettability. In these environments, pore structure is the primary factor influencing capillary pressure, with different pore types affecting fluid transport through varying degrees of hydrocarbon saturation. One of the main challenges in characterizing pore structure is how to use data from core plugs to establish a relationship with microscopic pore and throat properties, enabling more accurate predictions of capillary pressure. While special core analysis laboratory experiments are effective, they are time-consuming and expensive. In contrast, nuclear magnetic resonance (NMR) measurements, which provide information on pore body size distribution, are faster and can be leveraged to estimate capillary pressure using machine learning algorithms. Recently, artificial intelligence methods have also been applied to capillary pressure prediction (Qi et al., 2024).&lt;/div&gt;&lt;div&gt;Currently, no readily applicable predictive model exists for estimating an entire capillary pressure curve directly from standard petrophysical logs and core data. Although porescale imaging and network modeling techniques can compute capillary pressure from micro-CT rock images (Øren and Bakke, 2003; Valvatne and Blunt, 2004), these approaches are time-consuming, limited to small sample volumes, and not yet practical for routine reservoir evaluation. In this study, we introduce rock classification techniques and implement a data-driven machine learning (ML) method to estimate saturation-dependent capillary pressure from core petrophysical properties. The new model integrates cumulative NMR data and densely resampled core measurements as training data, with prediction errors quantified throughout the process. To approach the common condition of sparsely sampled training data, we transformed the prediction problem into an overdetermined one by applying composite fitting to both capillary pressure and pore throat size distribution, and Gaussian cumulative distribution fitting to the NMR &lt;span&gt;&lt;math&gt;&lt;mrow&gt;&lt;msub&gt;&lt;mi&gt;T&lt;/mi&gt;&lt;mn&gt;2&lt;/mn&gt;&lt;/msub&gt;&lt;/mrow&gt;&lt;/math&gt;&lt;/span&gt; measurements, generating evenly sampled data points. Using these preprocessed input features, we performed classification based on the natural logarithm of the permeability-to-porosity ratio &lt;span&gt;&lt;math&gt;&lt;mrow&gt;&lt;mo&gt;(&lt;/mo&gt;&lt;mrow&gt;&lt;mi&gt;ln&lt;/mi&gt;&lt;mrow&gt;&lt;mo&gt;(&lt;/mo&gt;&lt;mrow&gt;&lt;mi&gt;k&lt;/mi&gt;&lt;mo&gt;/&lt;/mo&gt;&lt;mi&gt;ϕ&lt;/mi&gt;&lt;/mrow&gt;&lt;mo&gt;)&lt;/mo&gt;&lt;/mrow&gt;&lt;/mrow&gt;&lt;mo&gt;)&lt;/mo&gt;&lt;/mrow&gt;&lt;/math&gt;&lt;/span&gt; to cluster distinct rock types. For each rock class, we applied regression techniques—such as random forest (RF), k-nearest neighbors (k-NN), extreme gradient boosting (XGB), and artificial neural networks (ANN)—to estimate the logarithm of capillary pressure. The methods were tested on blind core samples, and performance comparisons among different estimation methods ","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100144"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144633212","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":"Quantifying uncertainty in foraminifera classification: How deep learning methods compare to human experts","authors":"Iver Martinsen ,&nbsp;Steffen Aagaard Sørensen ,&nbsp;Samuel Ortega ,&nbsp;Fred Godtliebsen ,&nbsp;Miguel Tejedor ,&nbsp;Eirik Myrvoll-Nilsen","doi":"10.1016/j.aiig.2025.100145","DOIUrl":"10.1016/j.aiig.2025.100145","url":null,"abstract":"<div><div>Foraminifera are shell-bearing microorganisms that are commonly found in marine deposits on the seabed. They are important indicators in many analyses, are used in climate change research, monitoring marine environments, evolutionary studies, and are also frequently used in the oil and gas industry. Although some research has focused on automating the classification of foraminifera images, few have addressed the uncertainty in these classifications. Although foraminifera classification is not a safety-critical task, estimating uncertainty is crucial to avoid misclassifications that could overlook rare and ecologically significant species that are informative indicators of the environment in which they lived. Uncertainty estimation in deep learning has gained significant attention and many methods have been developed. However, evaluating the performance of these methods in practical settings remains a challenge. To create a benchmark for uncertainty estimation in the classification of foraminifera, we administered a multiple choice questionnaire containing classification tasks to four senior geologists. By analyzing their responses, we generated human-derived uncertainty estimates for a test set of 260 images of foraminifera and sediment grains. These uncertainty estimates served as a baseline for comparison when training neural networks in classification. We then trained multiple deep neural networks using a range of uncertainty quantification methods to classify and state the uncertainty about the classifications. The results of the deep learning uncertainty quantification methods were then analyzed and compared with the human benchmark, to see how the methods performed individually and how the methods aligned with humans. Our results show that human-level performance can be achieved with deep learning and that test-time data augmentation and ensembling can help improve both uncertainty estimation and classification performance. Our results also show that human uncertainty estimates are helpful indicators for detecting classification errors and that deep learning-based uncertainty estimates can improve calibration and classification accuracy.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100145"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144694746","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":"Quantifying uncertainty of mineral prediction using a novel Bayesian deep learning framework","authors":"Yue Liu","doi":"10.1016/j.aiig.2025.100164","DOIUrl":"10.1016/j.aiig.2025.100164","url":null,"abstract":"<div><div>Mineral resource exploration increasingly demands not only accurate prospectivity maps but also reliable measures of confidence to guide high-stakes decisions. In this study, a novel Bayesian deep learning (BDL) framework was introduced, which embeds probabilistic inference within a deep neural network to jointly predict mineralization potential and quantify uncertainty. Two posterior approximation strategies, Metropolis–Hastings (MH) sampling and variational inference (VI), are implemented to estimate model weights as distributions rather than as fixed values, enabling decomposition of predictive uncertainty into aleatoric and epistemic components. When applied to eleven ore-controlling features in the Nanling tungsten polymetallic region (China), both MH-based and VI-based BDL models demonstrate strong classification performance while revealing contrasting spatial patterns and uncertainty patterns. Correlation studies across probability bands confirm that MH sampling captures a broader spread of uncertainty at the cost of greater computational demand, while VI delivers greater efficiency but risks underestimating uncertainty. The results highlight trade-offs between accuracy, interpretability, and computational load, demonstrating that MH-based BDL offers more robust uncertainty assessments, whereas VI-based BDL places greater emphasis on efficiency. By providing spatially explicit probability and uncertainty maps, this framework advances risk-aware mineral exploration, enabling practitioners to target areas of high potential with low uncertainty and to identify regions warranting additional data acquisition.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100164"},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145519710","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":"On the application of machine learning algorithms in predicting the permeability of oil reservoirs","authors":"Andrey V. Soromotin ,&nbsp;Dmitriy A. Martyushev ,&nbsp;João Luiz Junho Pereira","doi":"10.1016/j.aiig.2025.100126","DOIUrl":"10.1016/j.aiig.2025.100126","url":null,"abstract":"<div><div>Permeability is one of the main oil reservoir characteristics. It affects potential oil production, well-completion technologies, the choice of enhanced oil recovery methods, and more. The methods used to determine and predict reservoir permeability have serious shortcomings. This article aims to refine and adapt machine learning techniques using historical data from hydrocarbon field development to evaluate and predict parameters such as the skin factor and permeability of the remote reservoir zone. The article analyzes data from 4045 wells tests in oil fields in the Perm Krai (Russia). An evaluation of the performance of different Machine Learning (ML) algorithms in the prediction of the well permeability is performed. Three different real datasets are used to train more than 20 machine learning regressors, whose hyperparameters are optimized using Bayesian Optimization (BO). The resulting models demonstrate significantly better predictive performance compared to traditional methods and the best ML model found is one that never was applied before to this problem. The permeability prediction model is characterized by a high R² adjusted value of 0.799. A promising approach is the integration of machine learning methods and the use of pressure recovery curves to estimate permeability in real-time. The work is unique for its approach to predicting pressure recovery curves during well operation without stopping wells, providing primary data for interpretation. These innovations are exclusive and can improve the accuracy of permeability forecasts. It also reduces well downtime associated with traditional well-testing procedures. The proposed methods pave the way for more efficient and cost-effective reservoir development, ultimately supporting better decision-making and resource optimization in oil production.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100126"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144330611","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":"Comparison of the performance of gradient boost, linear regression, decision tree, and voting algorithms to separate geochemical anomalies areas in the fractal environment","authors":"Mirmahdi Seyedrahimi-Niaraq ,&nbsp;Hossein Mahdiyanfar ,&nbsp;Mohammad hossein Olyaee","doi":"10.1016/j.aiig.2025.100156","DOIUrl":"10.1016/j.aiig.2025.100156","url":null,"abstract":"<div><div>In this investigation, the Gradient Boosting (GB), Linear Regression (LR), Decision Tree (DT), and Voting algorithms were applied to predict the distribution pattern of Au geochemical data. Trace and indicator elements, including Mo, Cu, Pb, Zn, Ag, Ni, Co, Mn, Fe, and As, were used with these machine learning algorithms (MLAs) to predict Au concentration values in the Doostbigloo porphyry Cu-Au-Mo mineralization area. The performance of the models was evaluated using the Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) metrics. The proposed ensemble Voting algorithm outperformed the other models, yielding more accurate predictions according to both metrics. The predicted data from the GB, LR, DT, and Voting MLAs were modeled using the Concentration-Area fractal method, and Au geochemical anomalies were mapped. To compare and validate the results, factors such as the location of the mineral deposits, their surface extent, and mineralization trend were considered. The results indicate that integrating hybrid MLAs with fractal modeling significantly improves geochemical prospectivity mapping. Among the four models, three (DT, GB, Voting) accurately identified both mineral deposits. The LR model, however, only identified Deposit I (central), and its mineralization trend diverged from the field data. The GB and Voting models produced similar results, with their final maps derived from fractal modeling showing the same anomalous areas. The anomaly boundaries identified by these two models are consistent with the two known reserves in the region. The results and plots related to prediction indicators and error rates for these two models also show high similarity, with lower error rates than the other models. Notably, the Voting model demonstrated superior performance in accurately delineating mineral deposit locations and identifying realistic mineralization trends while minimizing false anomalies.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100156"},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219420","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":"Cellular automata models for simulation and prediction of urban land use change: Development and prospects","authors":"Baoling Gui,&nbsp;Anshuman Bhardwaj,&nbsp;Lydia Sam","doi":"10.1016/j.aiig.2025.100142","DOIUrl":"10.1016/j.aiig.2025.100142","url":null,"abstract":"<div><div>Rapid urbanization and land-use changes are placing immense pressure on resources, infrastructure, and environmental sustainability. To address these, accurate urban simulation models are essential for sustainable development and governance. Among them, Cellular Automata (CA) models have become key tools for predicting urban expansion, optimizing land-use planning, and supporting data-driven decision-making. This review provides a comprehensive examination of the development of urban cellular automata (UCA) models, presenting a new framework to enhance individual UCA sub-modules within the context of emerging technologies, sustainable environments, and public governance. By addressing gaps in prior UCA modelling reviews—particularly in the integration and optimization of UCA sub-module technologies—this framework is designed to simplify UCA model understanding and development. We systematically review pioneering case studies, deconstruct current UCA operational processes, and explore modern technologies, such as big data and artificial intelligence, to optimize these sub-modules further. We discuss current limitations within UCA models and propose future pathways, emphasizing the necessity of comprehensive analyses for effective UCA simulations. Proposed solutions include strengthening our understanding of urban growth mechanisms, examining spatial positioning and temporal evolution dynamics, and enhancing urban geographic simulations with deep learning techniques to support sustainable transitions in public governance. These improvements offer data-driven decision support for environmental management, advancing policies that foster sustainable urban development.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100142"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144518220","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":"Unveiling climate-driven water surface dynamics in the largest tropical lake in Borneo: A machine learning approach using multi-source satellite imagery","authors":"Mohamad Rifai ,&nbsp;Harintaka","doi":"10.1016/j.aiig.2025.100166","DOIUrl":"10.1016/j.aiig.2025.100166","url":null,"abstract":"<div><div>Tropical lakes such as Lake Sentarum in Kalimantan, Indonesia, represent ecologically rich ecosystems with high biodiversity and constitute the largest lake on the island of Kalimantan. This lake serves as a sensitive indicator of climate change; however, its monitoring is often hindered by persistent cloud cover. This study evaluates the effectiveness of a Gradient Tree Boosting machine learning model integrated with multisource satellite data, including optical imagery, Sentinel-1 SAR, Sentinel-2, and high resolution NICFI data, in accurately mapping surface water dynamics. The Gradient Tree Boosting model was trained and validated using water and non water samples collected from annual imagery spanning 2019 to 2024, achieving validation accuracies ranging from 80 percent to 97 percent. Results demonstrate that Gradient Tree Boosting successfully integrates the strengths of each sensor, producing consistent annual water maps despite extreme hydrological fluctuations caused by El Niño and La Niña events. These findings highlight the model's potential application in water resource management, particularly in providing accurate baseline data to support adaptation planning for droughts and floods in climate vulnerable regions.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100166"},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145623402","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":"AI-based approaches for wetland mapping and classification: A review of current practices and future perspectives","authors":"Kai Cheng ,&nbsp;Cong Zhang ,&nbsp;Yaocheng Fan ,&nbsp;Hongli Diao ,&nbsp;Shibin Xia","doi":"10.1016/j.aiig.2025.100165","DOIUrl":"10.1016/j.aiig.2025.100165","url":null,"abstract":"<div><div>Wetlands are critical ecosystems that provide essential ecological, hydrological, and socio-economic services, such as water purification, climate regulation, and biodiversity conservation. However, effective wetland management faces significant challenges, particularly in the analysis and classification of complex wetland environments. Traditional methods of wetland monitoring often suffer from limitations in spatial coverage, temporal resolution, and data processing efficiency. Recent advancements in artificial intelligence (AI), particularly machine learning and deep learning techniques, have been increasingly integrated with remote sensing technologies, offering a powerful solution to these challenges. AI has demonstrated significant potential in automating large-scale remote sensing data analysis, enabling the extraction of detailed spatial information, and enhancing the accuracy and efficiency of wetland mapping and classification. Bibliometric analysis indicates a growing body of research, with notable contributions from China and the United States, though regional disparities and a lack of diverse datasets remain key issues. Despite the success of AI in wetland monitoring, challenges persist in addressing environmental heterogeneity, mixed pixels, and data quality. This review synthesizes the current state of AI-based approaches in wetland mapping and classification, identifies trends and gaps, and outlines future research directions, emphasizing the need for interdisciplinary collaboration and integration of multi-source data to advance AI applications in wetland conservation.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100165"},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145465152","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":"Intelligent identification of fractures and holes in ultrasonic logging images based on the improved YOLOv8 model","authors":"Jingyi Han ,&nbsp;Xiumei Zhang ,&nbsp;Yujuan Qi ,&nbsp;Lin Liu","doi":"10.1016/j.aiig.2025.100167","DOIUrl":"10.1016/j.aiig.2025.100167","url":null,"abstract":"<div><div>Aiming to address the demand for intelligent recognition of geological features in whole-wellbore ultrasonic images, this paper integrates the YOLOv8 model with the Convolution Block Attention Module (CBAM). It proposes an intelligent method for detecting fractures and holes, as well as segmenting whole-wellbore images. Firstly, we develop a dataset sample of effective reservoir sections by integrating logging data and conducting data augmentation on fracture and hole samples in ultrasonic logging images. A standardized process procedure for the generation of new samples and model training has been proposed effectively. Subsequently, the improved YOLOv8 model undergoes a process of training and validation. The results indicate that the model achieves average accuracies of 0.910 and 0.884 in target detection and image segmentation tasks, respectively. These findings demonstrate a notable performance improvement compared to the original model. Furthermore, a sliding window strategy is proposed to tackle the challenges of high computational demands and insufficient accuracy in the intelligent processing of full-well ultrasonic images. To manage overlapping regions within the sliding window, we employ the Non-Maximum Suppression (NMS) principle for effective processing. Finally, the model has been tested on actual logging images and demonstrates an enhanced capability to identify irregular fractures and holes, which significantly improves the efficiency of geological feature recognition in the whole-well section ultrasonic logging images.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100167"},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145519713","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}