Artificial Intelligence in Geosciences最新文献

{"title":"Generating high-resolution climate data in the Andes using artificial intelligence: A lightweight alternative to the WRF model","authors":"Christian Carhuancho ,&nbsp;Edwin Villanueva ,&nbsp;Christian Yarleque ,&nbsp;Romel Erick Principe ,&nbsp;Marcia Castromonte","doi":"10.1016/j.aiig.2025.100143","DOIUrl":"10.1016/j.aiig.2025.100143","url":null,"abstract":"<div><div>In weather forecasting, generating atmospheric variables for regions with complex topography, such as the Andean regions with peaks reaching 6500 m above sea level, poses significant challenges. Traditional regional climate models often struggle to accurately represent the atmospheric behavior in such areas. Furthermore, the capability to produce high spatio-temporal resolution data (less than 27 km and hourly) is limited to a few institutions globally due to the substantial computational resources required. This study presents the results of atmospheric data generated using a new type of artificial intelligence (AI) models, aimed to reduce the computational cost of generating downscaled climate data using climate regional models like the Weather Research and Forecasting (WRF) model over the Andes. The WRF model was selected for this comparison due to its frequent use in simulating atmospheric variables in the Andes.</div><div>Our results demonstrate a higher downscaling performance for the four target weather variables studied (temperature, relative humidity, zonal and meridional wind) over coastal, mountain, and jungle regions. Moreover, this AI model offers several advantages, including lower computational costs compared to dynamic models like WRF and continuous improvement potential with additional training data.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100143"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144653503","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":"Opportunities, epistemological assessment and potential risks of machine learning applications in volcano science","authors":"Mónica Ágreda-López,&nbsp;Maurizio Petrelli","doi":"10.1016/j.aiig.2025.100153","DOIUrl":"10.1016/j.aiig.2025.100153","url":null,"abstract":"<div><div>This manuscript explores the opportunities and epistemological risks of using machine learning in the Earth sciences with a focus on igneous petrology and volcanology. It begins by highlighting the benefits of machine learning, particularly in automating tasks, enhancing modelling strategies, and accelerating knowledge discovery. However, the integration of machine learning into scientific research also introduces significant challenges. Key concerns include understanding what machine learning models learn, ensuring transparency, reproducibility, and improving model interpretability. These issues become especially critical in high-risk contexts such as volcanic hazard assessment, risk mitigation, and crisis management, where the reliance on machine learning outcomes can have profound consequences for human lives. The manuscript also introduces additional ethical considerations, such as the risk of over-reliance on machine learning models and the broader implications of geopolitical development plans, laws and regulations in the EU, China, and the US.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100153"},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145009932","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":"Interpretable machine learning models for evaluating strength of ternary geopolymers","authors":"Junfei Zhang ,&nbsp;Huisheng Cheng ,&nbsp;Ninghui Sun ,&nbsp;Zehui Huo ,&nbsp;Junlin Chen","doi":"10.1016/j.aiig.2025.100128","DOIUrl":"10.1016/j.aiig.2025.100128","url":null,"abstract":"<div><div>Ternary geopolymers incorporating multiple solid wastes such as steel slag (SS), fly ash (FA), and granulated blast furnace slag (GBFS) are considered environmentally friendly and exhibit enhanced performance. However, the mechanisms governing strength development and the design of optimal mixtures are not fully understood due to the complexity of their components. This study presents the development of four machine learning models—Artificial Neural Network (ANN), Support Vector Regression (SVR), Extremely Randomized Tree (ERT), and Gradient Boosting Regression (GBR)—for predicting the unconfined compressive strength (UCS) of ternary geopolymers. The models were trained using a dataset comprising 120 mixtures derived from laboratory tests. Shapley Additive Explanations analysis was employed to interpret the machine learning models and elucidate the influence of different components on the properties of ternary geopolymers. The results indicate that ANN exhibits the highest predictive accuracy for UCS (R = 0.949). Furthermore, the UCS of ternary geopolymers is most sensitive to the content of GBFS. This study provides valuable insights for optimizing the mix proportions in ternary blended geopolymer mixtures.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100128"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144523230","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":"Advancements in Sinkhole Remediation: Field data-driven Sinkhole grout volume prediction model via machine learning-based regression Analysis","authors":"Bubryur Kim ,&nbsp;Yuvaraj Natarajan ,&nbsp;K.R. Sri Preethaa ,&nbsp;V. Danushkumar ,&nbsp;Ryan Shamet ,&nbsp;Jiannan Chen ,&nbsp;Rui Xie ,&nbsp;Timothy Copeland ,&nbsp;Boo Hyun Nam ,&nbsp;Jinwoo An","doi":"10.1016/j.aiig.2025.100159","DOIUrl":"10.1016/j.aiig.2025.100159","url":null,"abstract":"<div><div>Sinkhole formation poses a significant geohazard in karst regions, where unpredictable subsurface erosion often necessitates costly grouting for stabilization. Accurate estimation of grout volume remains a persistent challenge due to spatial variability, site-specific conditions, and the limitations of traditional empirical methods. This study introduces a novel machine learning-based regression model for grout volume prediction that integrates cone penetration test (CPT)-derived Sinkhole Resistance Ratio (SRR) values, spatial correlations between CPT and grouting points (GPs), and field-recorded grout volumes from six sinkhole sites in Florida. Three data transformation methods, the Proximal Allocation Method (PAM), the Equitable Distribution Method (EDM), and the Threshold-based Equitable Distribution Method (TEDM), were applied to distribute grout influence across CPTs, with TEDM demonstrating superior predictive performance. Synthetic data augmentation using spline methodology further improved model robustness. A high-degree polynomial regression model, optimized with ridge regularization, achieved high accuracy (R² = 0.95; PEV = 0.94) and significantly outperformed existing linear and logarithmic models. Results confirm that lower SRR values correlate with higher grout demand, and the proposed model reliably captures these nonlinear relationships. This research advances sinkhole remediation practice by providing a data-driven, accurate, and generalizable framework for grout volume estimation, enabling more efficient resource allocation and improved project outcomes.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100159"},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145320144","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":"Quantification of greenhouse gas emissions from livestock using remote sensing & artificial intelligence","authors":"Evet Naturinda ,&nbsp;Fortunate Kemigyisha ,&nbsp;Anthony Gidudu ,&nbsp;Isa Kabenge ,&nbsp;Emmanuel Omia ,&nbsp;Jackline Aboth","doi":"10.1016/j.aiig.2025.100147","DOIUrl":"10.1016/j.aiig.2025.100147","url":null,"abstract":"<div><div>Greenhouse gases (GHGs) from agriculture in Africa are among the world's fastest-growing emissions, with the livestock sector as the primary contributor. However, the methods for quantifying these emissions rely on manual and outdated data collection and processing approaches. Therefore, there is a need to develop more accurate and efficient methods of quantifying GHGs from livestock. This research developed a remote sensing and Artificial Intelligence (AI) based approach to quantify GHG emissions from cattle in the Kisombwa Ranching Scheme in Mubende District, central Uganda.</div><div>We trained a deep learning algorithm, You Only Look Once (YOLO) v4, to detect cattle from the Unmanned Aerial Vehicle (UAV) images of the study area and applied the Simple Online Real-time Tracker (SORT) algorithm for automated counting. Methane (CH₄₎ and Nitrous Oxide (N₂O) emissions from manure management and enteric fermentation were estimated using the number of cattle and the Tier 1 guidelines from the Intergovernmental Panel on Climate Change (IPCC). The total estimated emissions were 321,121.34 kg carbon dioxide equivalent (CO₂eq) per year, with CH₄ at 282,282.96 kg CO₂eq per year (88 %) and N₂O at 38,838.38 kg CO₂eq per year (12 %). Enteric fermentation contributed the highest emissions, about 99 % of the total CH₄ emissions and 87 % of the total GHGs.</div><div>The proposed remote sensing and AI-driven method achieved an average F1 score of 88.9 %, average precision of 97 %, and average recall of 82.9 % on the testing set of images. Therefore, these research findings demonstrate that remote sensing and AI are a more potent and efficient approach to upscale quantifying and reporting animal population and livestock GHG emissions for sustainable agriculture and climate change mitigation.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100147"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144702139","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":"Machine learning assisted estimation of total solids content of drilling fluids","authors":"B.T. Gunel ,&nbsp;Y.D. Pak ,&nbsp;A.Ö. Herekeli ,&nbsp;S. Gül ,&nbsp;B. Kulga ,&nbsp;E. Artun","doi":"10.1016/j.aiig.2025.100138","DOIUrl":"10.1016/j.aiig.2025.100138","url":null,"abstract":"&lt;div&gt;&lt;div&gt;Characterization and optimization of physical and chemical properties of drilling fluids are critical for the efficiency and success of drilling operations. In particular, maintaining the optimal levels of solids content is essential for achieving the most effective fluid performance. Proper management of solids content also reduces the risk of tool failures. Traditional solids content analysis methods, such as retort analysis, require substantial human intervention and time, which can lead to inaccuracies, time-management issues, and increased operational risks. In contrast to human-intensive methods, machine learning may offer a viable alternative for solids content estimation due to its pattern-recognition capability. In this study, a large set of laboratory reports of drilling-fluid analyses from 130 oil wells around the world were compiled to construct a comprehensive data set. The relationships among various rheological parameters were analyzed using statistical methods and machine learning algorithms. Several machine learning algorithms of diverse classes, namely linear (linear regression, ridge regression, and ElasticNet regression), kernel-based (support vector machine) and ensemble tree-based (gradient boosting, XGBoost, and random forests) algorithms, were trained and tuned to estimate solids content from other readily available drilling fluid properties. Input variables were kept consistent across all models for interpretation and comparison purposes. In the final stage, different evaluation metrics were employed to evaluate and compare the performance of different classes of machine learning models. Among all algorithms tested, random forests algorithm was found to be the best predictive model resulting in consistently high accuracy. Further optimization of the random forests model resulted in a mean absolute percentage error (MAPE) of 3.9% and 9.6% and R&lt;span&gt;&lt;math&gt;&lt;msup&gt;&lt;mrow&gt;&lt;/mrow&gt;&lt;mrow&gt;&lt;mn&gt;2&lt;/mn&gt;&lt;/mrow&gt;&lt;/msup&gt;&lt;/math&gt;&lt;/span&gt; of 0.99 and 0.93 for the training and testing sets, respectively. Analysis of residuals, their histograms and Q-Q normality plots showed Gaussian distributions with residuals that are scattered around a mean of zero within error ranges of &lt;span&gt;&lt;math&gt;&lt;mo&gt;±&lt;/mo&gt;&lt;/math&gt;&lt;/span&gt;1% and &lt;span&gt;&lt;math&gt;&lt;mo&gt;±&lt;/mo&gt;&lt;/math&gt;&lt;/span&gt;4%, for training and testing, respectively. The selected model was further validated by applying the rheological measurements from mud samples taken from an offshore well from the Gulf of Mexico. The model was able to estimate total solids content in those four mud samples with an average absolute error of 1.08% of total solids content. The model was then used to develop a web-based graphical-user-interface (GUI) application, which can be practically used at the rig site by engineers to optimize drilling fluid programs. The proposed model can complement automation workflows that are designed to measure fundamental rheological properties in real time during drilling operations. While a st","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100138"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144581266","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":"Geophysical data denoising using dictionary learning method with Ramanujan sums for oil and minerals exploration","authors":"Lakshmi Kuruguntla ,&nbsp;Mamatha Bandaru ,&nbsp;Dokku Tejaswi ,&nbsp;Anup Kumar Mandpura ,&nbsp;Sravan Kumar Sikhakoli ,&nbsp;Vineela Chandra Dodda","doi":"10.1016/j.aiig.2025.100168","DOIUrl":"10.1016/j.aiig.2025.100168","url":null,"abstract":"<div><div>Denoising is an important preprocessing step in seismic exploration that improves the signal-to-noise ratio (SNR) and helps identify oil and minerals. Dictionary learning (DL) is a promising method for noise attenuation. The DL extracts sparse features from noisy seismic data using over-complete dictionaries and performs denoising based on a threshold. However, the choice of threshold in DL greatly impacts the denoising results and the improvement in output SNR. Ramanujan’s sum(s) (RS) is a signal processing tool that exhibits derivative behavior and finds applications in edge detection and noise estimation of signals. Hence, we propose a novel DL method with threshold estimation based on RS to improve the output SNR. In this work, we estimate the noise variance of seismic data based on RS and use it as a threshold value for the DL method to perform denoising. We analyze the results of the proposed work on synthetically generated and field data sets. We perform simulations on noisy seismic data across a wide range of SNR values and tabulate the denoised results using the performance metrics SNR and mean squared error. The results indicate that the proposed method provides superior SNR and reduced mean squared error compared to MAD, SURE-based, and adaptive soft-thresholding techniques.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100168"},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145519714","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":"Constructing regional mineral prospecting knowledge graph from GIS maps","authors":"Jiawen Liu ,&nbsp;Yuxin Ye ,&nbsp;Ziheng Li ,&nbsp;Zhezhe Xing ,&nbsp;Shuisheng Ye","doi":"10.1016/j.aiig.2025.100169","DOIUrl":"10.1016/j.aiig.2025.100169","url":null,"abstract":"<div><div>Geographic Information System (GIS) layers contain both spatial precision and domain knowledge, making them valuable for mineral prospectivity analysis. This study proposes a task-oriented methodology to construct a mineral prospecting knowledge graph directly from GIS maps. The framework integrates ontology construction, spatiotemporal semantic embedding, and triple confidence evaluation. Ontologies are built from GIS layers through terminology extraction and alignment with existing standards, while spatial and temporal semantics are encoded using GeoSPARQL and the Geological Time Ontology. Graph Convolutional Networks (GCN) combined with the TransE embedding model are then applied to assess triple plausibility. A case study in the Eastern Tianshan region of Xinjiang verifies the effectiveness of the proposed method through semantic evaluation and graph-theoretic analysis. Guided by GIS, ontology construction significantly enhances the semantic fidelity and structural robustness of the prospecting knowledge graph, providing relatively reliable support for subsequent reasoning and predictive studies.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100169"},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145579224","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":"Machine learning assisted enhancement of petrophysical property dataset of fractured Variscan granites of the Cornubian Batholith, SW UK","authors":"A. Turan ,&nbsp;E. Artun ,&nbsp;I. Sass","doi":"10.1016/j.aiig.2025.100151","DOIUrl":"10.1016/j.aiig.2025.100151","url":null,"abstract":"<div><div>Outcrop analogue studies play an important role in advancing our comprehension of reservoir architectures, offering insights into hidden reservoir rocks prior to drilling, in a cost-effective manner. These studies contribute to the delineation of the three-dimensional geometry of geological structures, the characterization of petro- and thermo-physical properties, and the structural geological aspects of reservoir rocks. Nevertheless, several challenges, including inaccessible sampling sites, limited resources, and the dimensional constraints of different laboratories hinder the acquisition of comprehensive datasets. In this study, we employ machine learning techniques to estimate missing data in a petrophysical dataset of fractured Variscan granites from the Cornubian Batholith in Southwest UK. The utilization of mean, k-nearest neighbors, and random forest imputation methods addresses the challenge of missing data, thereby revealing the effectiveness of random forest imputation in providing realistic estimations. Subsequently, supervised classification models are trained to classify samples according to their pluton origins, with promising accuracy achieved by models trained with imputed values. Variable importance ranking of the models showed that the choice of imputation method influences the inferred importance of specific petrophysical properties. While porosity (POR) and grain density (GD) were among important variables, variables with high missingness ratio were not among the top variables. This study demonstrates the value of machine learning in enhancing petrophysical datasets, while emphasizing the importance of careful method selection and model validation for reliable results. The findings contribute to a more informed decision-making process in geothermal exploration and reservoir characterization efforts, thereby demonstrating the potential of machine learning in advancing subsurface characterization techniques.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100151"},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145009931","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":"Understanding hydrological responses through LULC analysis and predictive modelling (MLPNN-MC Model): A study of Bandu Sub-watershed (India) over three decades","authors":"Sudipto Halder ,&nbsp;Somnath Mandal ,&nbsp;Zarkheen Mukhtar ,&nbsp;Debdas Ray ,&nbsp;Gupinath Bhandari ,&nbsp;Suman Paul","doi":"10.1016/j.aiig.2025.100152","DOIUrl":"10.1016/j.aiig.2025.100152","url":null,"abstract":"","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100152"},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887019","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}