Pub Date : 2025-09-01Epub Date: 2025-06-26DOI: 10.1016/j.acags.2025.100262
Olanrewaju Muili, Hassan A. Babaie
This study examined the feasibility and accuracy of applying machine learning for sinkhole classification and prediction and using the results in automated sinkhole susceptibility mapping for west central Florida. A two-stage processing pipeline was developed. In the first stage, we assessed the predictive power of five exemplary machine learning algorithms: random forest (RF), logistic regression (LR), k-nearest neighbor (KNN), support vector machine (SVM), and multilayer perceptron (MLP), and select the best-performing model. The top-performed model was then chosen to develop a sinkhole susceptibility map (SSM) in the second step of the process. Nine feature layers were derived from the collected geospatial data and utilized as conditional variables. Several statistical metrics and receiver operating characteristic curves were utilized to evaluate the accuracy of the models. The results showed that the RF model, with a ROC of 0.984, had the highest prediction capability in the research area.
We generated a susceptibility map using the RF model, and the study area was classified into high susceptibility (H) and low susceptibility (L) areas. Confusion Matrix (CM) and Matthews Correlation Coefficient (MCC) were used to confirm the results of the sinkhole susceptibility map's classification. We present a model that predicts sinkhole distribution in the study area, and the output of our model is consistent with the sinkhole hazard map that the Florida Division of Emergency Management had previously created. This work can assist the government, community, and land managers in creating plans for mitigating hazards and land degradation.
{"title":"Sinkhole susceptibility analysis using machine learning for west central Florida","authors":"Olanrewaju Muili, Hassan A. Babaie","doi":"10.1016/j.acags.2025.100262","DOIUrl":"10.1016/j.acags.2025.100262","url":null,"abstract":"<div><div>This study examined the feasibility and accuracy of applying machine learning for sinkhole classification and prediction and using the results in automated sinkhole susceptibility mapping for west central Florida. A two-stage processing pipeline was developed. In the first stage, we assessed the predictive power of five exemplary machine learning algorithms: random forest (RF), logistic regression (LR), k-nearest neighbor (KNN), support vector machine (SVM), and multilayer perceptron (MLP), and select the best-performing model. The top-performed model was then chosen to develop a sinkhole susceptibility map (SSM) in the second step of the process. Nine feature layers were derived from the collected geospatial data and utilized as conditional variables. Several statistical metrics and receiver operating characteristic curves were utilized to evaluate the accuracy of the models. The results showed that the RF model, with a ROC of 0.984, had the highest prediction capability in the research area.</div><div>We generated a susceptibility map using the RF model, and the study area was classified into high susceptibility (H) and low susceptibility (L) areas. Confusion Matrix (CM) and Matthews Correlation Coefficient (MCC) were used to confirm the results of the sinkhole susceptibility map's classification. We present a model that predicts sinkhole distribution in the study area, and the output of our model is consistent with the sinkhole hazard map that the Florida Division of Emergency Management had previously created. This work can assist the government, community, and land managers in creating plans for mitigating hazards and land degradation.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"27 ","pages":"Article 100262"},"PeriodicalIF":2.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144514348","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}
Pub Date : 2025-09-01Epub Date: 2025-08-09DOI: 10.1016/j.acags.2025.100280
Lennart Siemann, Ramiro Relanez
The presented study investigates the prediction of buried paleo-channels for probabilistic ground modeling of offshore windfarm development areas using geostatistical methods. These channels, common in glaciogenic regions like the North Sea, can pose significant geohazards affecting turbine foundation stability. Conventional 2D seismic data interpretation provides the best estimate of the position but lacks probabilistic assessment, specifically at unexplored locations. Multiple-point statistics (MPS) and sequential indicator simulation (SIS) are applied to quantify the probability of channel features from seismic data, away from seismic lines. MPS utilizes training images to capture complex spatial structures, while SIS relies on variogram models for modeling spatial variability. Results demonstrate that denser seismic line spacing (150 m) yields higher accuracy compared to wider spacings (300 m and 600 m), underscoring the importance of data density in offshore subsurface site characterization. Additionally, the findings indicate that MPS provides lower errors, making it preferable for precise channel location prediction. The selected training image did not have a major impact on the outcome on the tested data. Conversely, SIS offers broader coverage of potential channel locations, which may be advantageous for further de-risking. This research contributes to more informed ground modeling by incorporating probabilistic approaches. Therefore, it supports in offshore wind farm site development by enhancing knowledge of the subsurface at an early stage of wind farm development to aid decisions in windfarm and further site investigation planning.
{"title":"Assessing paleo channel probability for offshore wind farm ground modeling - comparison of multiple-point statistics and sequential indicator simulation","authors":"Lennart Siemann, Ramiro Relanez","doi":"10.1016/j.acags.2025.100280","DOIUrl":"10.1016/j.acags.2025.100280","url":null,"abstract":"<div><div>The presented study investigates the prediction of buried paleo-channels for probabilistic ground modeling of offshore windfarm development areas using geostatistical methods. These channels, common in glaciogenic regions like the North Sea, can pose significant geohazards affecting turbine foundation stability. Conventional 2D seismic data interpretation provides the best estimate of the position but lacks probabilistic assessment, specifically at unexplored locations. Multiple-point statistics (MPS) and sequential indicator simulation (SIS) are applied to quantify the probability of channel features from seismic data, away from seismic lines. MPS utilizes training images to capture complex spatial structures, while SIS relies on variogram models for modeling spatial variability. Results demonstrate that denser seismic line spacing (150 m) yields higher accuracy compared to wider spacings (300 m and 600 m), underscoring the importance of data density in offshore subsurface site characterization. Additionally, the findings indicate that MPS provides lower errors, making it preferable for precise channel location prediction. The selected training image did not have a major impact on the outcome on the tested data. Conversely, SIS offers broader coverage of potential channel locations, which may be advantageous for further de-risking. This research contributes to more informed ground modeling by incorporating probabilistic approaches. Therefore, it supports in offshore wind farm site development by enhancing knowledge of the subsurface at an early stage of wind farm development to aid decisions in windfarm and further site investigation planning.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"27 ","pages":"Article 100280"},"PeriodicalIF":3.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144827361","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}
Pub Date : 2025-09-01Epub Date: 2025-09-03DOI: 10.1016/j.acags.2025.100284
Tingchang Yin , Teng Man , Pei Zhang , Sergio Andres Galindo-Torres
Fracture networks in the subsurface can serve as the primary pathway for fluid flow, allowing for solute transport. This process is critical to various real-world applications, including resource extraction and contaminant migration in fractured rocks. We develop an open-source code called cuDFNsys to simulate flow and transport in discrete fracture networks (DFNs). Our code uses the mixed hybrid finite element method to solve the hydraulic head and velocity fields in DFNs, and the particle tracking method to simulate the movement of solute plumes. The GPU parallelization accelerates the generation of DFNs, identification of intersections between fractures, determination of elementary matrices, and motion of particles. We use several benchmarks to verify the accuracy of flow and transport simulation in cuDFNsys. Dispersion in a DFN is used to demonstrate examples of particle tracking. Performance analyses demonstrate that our code is well-suited for Monte Carlo iterations of DFN simulations, enabling physicists and geoscientists to study critical phenomena and phase transitions in fracture networks using percolation theory.
{"title":"GPU-accelerated simulation of steady-state flow and particle transport in discrete fracture networks","authors":"Tingchang Yin , Teng Man , Pei Zhang , Sergio Andres Galindo-Torres","doi":"10.1016/j.acags.2025.100284","DOIUrl":"10.1016/j.acags.2025.100284","url":null,"abstract":"<div><div>Fracture networks in the subsurface can serve as the primary pathway for fluid flow, allowing for solute transport. This process is critical to various real-world applications, including resource extraction and contaminant migration in fractured rocks. We develop an open-source code called <em>cuDFNsys</em> to simulate flow and transport in discrete fracture networks (DFNs). Our code uses the mixed hybrid finite element method to solve the hydraulic head and velocity fields in DFNs, and the particle tracking method to simulate the movement of solute plumes. The GPU parallelization accelerates the generation of DFNs, identification of intersections between fractures, determination of elementary matrices, and motion of particles. We use several benchmarks to verify the accuracy of flow and transport simulation in <em>cuDFNsys</em>. Dispersion in a DFN is used to demonstrate examples of particle tracking. Performance analyses demonstrate that our code is well-suited for Monte Carlo iterations of DFN simulations, enabling physicists and geoscientists to study critical phenomena and phase transitions in fracture networks using percolation theory.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"27 ","pages":"Article 100284"},"PeriodicalIF":3.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144988473","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}
Pub Date : 2025-09-01Epub Date: 2025-06-18DOI: 10.1016/j.acags.2025.100259
Weilin Chen, Jiyin Zhang, Wenjia Li, Xiang Que, Chenhao Li, Xiaogang Ma
The integration of machine learning (ML) and deep learning (DL) in geoscience has demonstrated great promise for mineral prediction. However, existing approaches are predominantly data-driven and often overlook expert geological knowledge, limiting their interpretability, accuracy, and practical applicability. This study introduces a new method that combines Large Language Models (LLMs), knowledge graphs (KGs), and Neuro-Symbolic AI (NSAI) models to predict mineralization systems in diverse copper deposits, significantly increasing the precision in prediction results. We utilize LLMs to generate KGs from geological literature, extracting symbolic rules that encode domain-specific insights about copper mineralization. These rules, derived dynamically from expert knowledge, are integrated into ML models as guidance during the training and prediction phases. By fusing symbolic reasoning with ML's computational power, our approach overcomes the limitations of black-box models, offering both improved accuracy and transparency in mineral prediction. To validate this method, we apply it to a comprehensive geochemical dataset of global copper deposits. The results show that rule-guided ML models achieve notable performance improvements, outperforming traditional ML methods in accuracy, precision, and robustness. Interpretability is further enhanced by using tools such as SHAP values, which explain the influence of individual geochemical features within the rule-based framework. This combination not only identifies critical geochemical elements like Cu, Fe, and S but also provides coherent, domain-aligned explanations for the predicted mineralization patterns. Our findings demonstrate the transformative potential of combining LLMs, KGs, and ML models for mineral prediction. This hybrid approach enables geoscientists to leverage both computational and expert knowledge, achieving a deeper understanding of mineralization systems.
{"title":"Integrating neuro-symbolic AI and knowledge graph for enhanced geochemical prediction in copper deposits","authors":"Weilin Chen, Jiyin Zhang, Wenjia Li, Xiang Que, Chenhao Li, Xiaogang Ma","doi":"10.1016/j.acags.2025.100259","DOIUrl":"10.1016/j.acags.2025.100259","url":null,"abstract":"<div><div>The integration of machine learning (ML) and deep learning (DL) in geoscience has demonstrated great promise for mineral prediction. However, existing approaches are predominantly data-driven and often overlook expert geological knowledge, limiting their interpretability, accuracy, and practical applicability. This study introduces a new method that combines Large Language Models (LLMs), knowledge graphs (KGs), and Neuro-Symbolic AI (NSAI) models to predict mineralization systems in diverse copper deposits, significantly increasing the precision in prediction results. We utilize LLMs to generate KGs from geological literature, extracting symbolic rules that encode domain-specific insights about copper mineralization. These rules, derived dynamically from expert knowledge, are integrated into ML models as guidance during the training and prediction phases. By fusing symbolic reasoning with ML's computational power, our approach overcomes the limitations of black-box models, offering both improved accuracy and transparency in mineral prediction. To validate this method, we apply it to a comprehensive geochemical dataset of global copper deposits. The results show that rule-guided ML models achieve notable performance improvements, outperforming traditional ML methods in accuracy, precision, and robustness. Interpretability is further enhanced by using tools such as SHAP values, which explain the influence of individual geochemical features within the rule-based framework. This combination not only identifies critical geochemical elements like Cu, Fe, and S but also provides coherent, domain-aligned explanations for the predicted mineralization patterns. Our findings demonstrate the transformative potential of combining LLMs, KGs, and ML models for mineral prediction. This hybrid approach enables geoscientists to leverage both computational and expert knowledge, achieving a deeper understanding of mineralization systems.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"27 ","pages":"Article 100259"},"PeriodicalIF":2.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144331437","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}
Pub Date : 2025-09-01Epub Date: 2025-07-17DOI: 10.1016/j.acags.2025.100264
Muhammad Khan , Andy Anderson Bery , Yasir Bashir , Sya'rawi Muhammad Husni Sharoni , Syed Sadaqat Ali
Interpreting seismic faults is crucial for prospect generation, reservoir modeling, and CO2 storage assessment. However, identifying faults in complex tectonic regimes remains challenging, particularly in regions that have experienced multiple phases of tectonic activity. Despite advancements in structural seismic attributes and machine learning, interpreters often still rely on manual methods to analyze intricate fault systems, such as those found in the Poseidon study area located in the Browse basin, Northwestern Australia, where the fault network is shaped by both extensional and compressional tectonic events. This paper introduces a hybrid approach that combines machine learning with seismic structural attributes to extract complex fault networks from 3D seismic data. The method begins by using pre-trained models to generate a fault probability cube, which is then refined through re-training with manually labeled data to incorporate local structural knowledge. To address false negatives, the model is further retrained using an ant-tracking volume generated from the fault probability cube of the manually trained model as automatically labeled data. The fault probability cube is regenerated from the automatically labeled trained model and further enhanced by post-processing techniques, such as ant-tracking, to improve fault connectivity and streamline the automated fault identification process. This hybrid approach effectively detects and extracts both major and minor discontinuities from 3D seismic data with high accuracy, significantly reducing the time and effort required for interpretation compared to traditional techniques.
{"title":"Automated fault network extraction in complex tectonic regimes: A hybrid machine learning and structural attributes approach","authors":"Muhammad Khan , Andy Anderson Bery , Yasir Bashir , Sya'rawi Muhammad Husni Sharoni , Syed Sadaqat Ali","doi":"10.1016/j.acags.2025.100264","DOIUrl":"10.1016/j.acags.2025.100264","url":null,"abstract":"<div><div>Interpreting seismic faults is crucial for prospect generation, reservoir modeling, and CO<sub>2</sub> storage assessment. However, identifying faults in complex tectonic regimes remains challenging, particularly in regions that have experienced multiple phases of tectonic activity. Despite advancements in structural seismic attributes and machine learning, interpreters often still rely on manual methods to analyze intricate fault systems, such as those found in the Poseidon study area located in the Browse basin, Northwestern Australia, where the fault network is shaped by both extensional and compressional tectonic events. This paper introduces a hybrid approach that combines machine learning with seismic structural attributes to extract complex fault networks from 3D seismic data. The method begins by using pre-trained models to generate a fault probability cube, which is then refined through re-training with manually labeled data to incorporate local structural knowledge. To address false negatives, the model is further retrained using an ant-tracking volume generated from the fault probability cube of the manually trained model as automatically labeled data. The fault probability cube is regenerated from the automatically labeled trained model and further enhanced by post-processing techniques, such as ant-tracking, to improve fault connectivity and streamline the automated fault identification process. This hybrid approach effectively detects and extracts both major and minor discontinuities from 3D seismic data with high accuracy, significantly reducing the time and effort required for interpretation compared to traditional techniques.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"27 ","pages":"Article 100264"},"PeriodicalIF":2.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144711698","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}
Pub Date : 2025-09-01Epub Date: 2025-07-26DOI: 10.1016/j.acags.2025.100271
Waleed M. AlGharbi , Rebecca E. Bell , Cédric M. John
Seismic stratigraphy entails a regional scanning (reconnaissance) of seismic data to identify and annotate seismic reflection terminations. To identify these terminations in modern 3D seismic datasets, interpreters have to examine thousands of inlines and crosslines, which is a time-consuming process. Furthermore, accurate identification of these features relies heavily on human visual observation along with individual expertise.
A growing number of studies have shown promising results applying machine learning techniques to identify geological features from seismic data such as salt bodies and faults. However, the identification of seismic reflection terminations has not received the same level of interest and remains a manual process. One of the barriers to utilizing machine learning techniques in seismic interpretation is the lack of “labelled” data. In this study, we evaluate the ability of deep learning Convolutional Neural Networks (CNN) trained on synthetic seismic images to identify seismic reflection terminations.
A dataset comprising 160 000 synthetic seismic images that represent conformable and four types of seismic reflection terminations (truncation, toplap, onlap, and downlap) were created using geometric geological modelling and 1D convolution seismic modelling. The dataset was then split into two classes (“Contains Termination” and “No Termination”). A new CNN model architecture named “Seismic Reflection Terminations Attribute (SRT-Ai)” was trained on 80 % of the synthetic seismic dataset. SRT-Ai predicted the test set (remaining 20 %) with an accuracy and precision of 99.9 %. To test its generalization, SRT-Ai was also evaluated on real seismic images, achieving 91 % accuracy and 96 % precision against published interpretations used as reference labels. Qualitative analysis of predictions along seismic sections shows a strong correspondence between the model predictions and manual regional interpretations.
SRT-Ai is proposed as a screening tool that will assist seismic interpreters with the identification of major seismic terminations, minimise seismic interpretation uncertainties, reduce the time taken for seismic reconnaissance, and limit the reliance on human visual observation at the early stage of seismic interpretation process.
{"title":"SRT-Ai: Identifying seismic reflection terminations using deep learning","authors":"Waleed M. AlGharbi , Rebecca E. Bell , Cédric M. John","doi":"10.1016/j.acags.2025.100271","DOIUrl":"10.1016/j.acags.2025.100271","url":null,"abstract":"<div><div>Seismic stratigraphy entails a regional scanning (reconnaissance) of seismic data to identify and annotate seismic reflection terminations. To identify these terminations in modern 3D seismic datasets, interpreters have to examine thousands of inlines and crosslines, which is a time-consuming process. Furthermore, accurate identification of these features relies heavily on human visual observation along with individual expertise.</div><div>A growing number of studies have shown promising results applying machine learning techniques to identify geological features from seismic data such as salt bodies and faults. However, the identification of seismic reflection terminations has not received the same level of interest and remains a manual process. One of the barriers to utilizing machine learning techniques in seismic interpretation is the lack of “labelled” data. In this study, we evaluate the ability of deep learning Convolutional Neural Networks (CNN) trained on synthetic seismic images to identify seismic reflection terminations.</div><div>A dataset comprising 160 000 synthetic seismic images that represent conformable and four types of seismic reflection terminations (truncation, toplap, onlap, and downlap) were created using geometric geological modelling and 1D convolution seismic modelling. The dataset was then split into two classes (“Contains Termination” and “No Termination”). A new CNN model architecture named “Seismic Reflection Terminations Attribute (SRT-Ai)” was trained on 80 % of the synthetic seismic dataset. SRT-Ai predicted the test set (remaining 20 %) with an accuracy and precision of 99.9 %. To test its generalization, SRT-Ai was also evaluated on real seismic images, achieving 91 % accuracy and 96 % precision against published interpretations used as reference labels. Qualitative analysis of predictions along seismic sections shows a strong correspondence between the model predictions and manual regional interpretations.</div><div>SRT-Ai is proposed as a screening tool that will assist seismic interpreters with the identification of major seismic terminations, minimise seismic interpretation uncertainties, reduce the time taken for seismic reconnaissance, and limit the reliance on human visual observation at the early stage of seismic interpretation process.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"27 ","pages":"Article 100271"},"PeriodicalIF":3.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144721214","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}
Pub Date : 2025-09-01Epub Date: 2025-07-02DOI: 10.1016/j.acags.2025.100258
Timur Merembayev, Yerlan Amanbek
In this paper, a fracture network model is proposed to enhance the understanding of subsurface fracture characterization. The model combines geostatistical methods such as sequential indicators and Gaussian simulations. The model uses data from natural faults in Kazakhstan to predict the segment, azimuth, and length of fractures in unknown areas. The model is validated by comparing the simulated fracture networks with the original fracture data and by hiding some regions within the fracture network. The results show that the geostatistical methods perform better than the machine learning algorithm for azimuth prediction, while the machine learning algorithm performs better for length prediction. In addition, the validation of the fracture network model is conducted by comparing the production curve profiles in the tracer test setting. They are in good agreement.
{"title":"Natural fracture network model using Gaussian simulation and machine learning algorithms","authors":"Timur Merembayev, Yerlan Amanbek","doi":"10.1016/j.acags.2025.100258","DOIUrl":"10.1016/j.acags.2025.100258","url":null,"abstract":"<div><div>In this paper, a fracture network model is proposed to enhance the understanding of subsurface fracture characterization. The model combines geostatistical methods such as sequential indicators and Gaussian simulations. The model uses data from natural faults in Kazakhstan to predict the segment, azimuth, and length of fractures in unknown areas. The model is validated by comparing the simulated fracture networks with the original fracture data and by hiding some regions within the fracture network. The results show that the geostatistical methods perform better than the machine learning algorithm for azimuth prediction, while the machine learning algorithm performs better for length prediction. In addition, the validation of the fracture network model is conducted by comparing the production curve profiles in the tracer test setting. They are in good agreement.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"27 ","pages":"Article 100258"},"PeriodicalIF":2.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144563203","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}
Pub Date : 2025-09-01Epub Date: 2025-08-08DOI: 10.1016/j.acags.2025.100274
Margaret A. Goldman , Graham W. Lederer , Joshua M. Rosera , Garth E. Graham , Asitang Mishra , Alice Yepremyan
The U.S. Geological Survey (USGS), Defense Advanced Projects Research Agency (DARPA), Jet Propulsion Laboratory (JPL), and MITRE ran a 12-week machine learning competition aimed at accelerating development of AI tools for critical mineral assessments. The Artificial Intelligence for Critical Mineral Assessment Competition solicited innovative solutions for two challenges: 1) automated georeferencing of historical geologic and topographic maps, and 2) automated feature extraction from historical maps. Competitors used a new dataset of historical map images to train, validate, and evaluate their models. Automated georeferencing pipelines attained a median root-mean square error of 1.1 km. Prompt-based extraction (i.e., with user input) of polygons, polylines, and points from geologic maps yielded median F1 scores of 0.77, 0.56, 0.35, respectively. Geologic maps pose numerous challenges for AI workflows because they vary significantly. However, despite its short duration, the competition yielded promising results that have since spurred further innovation in this area and led to the development of new AI tools to semi-automate key, time-consuming parts of the assessment workflow.
{"title":"Extracting data from maps: Lessons learned from the artificial intelligence for critical mineral assessment competition","authors":"Margaret A. Goldman , Graham W. Lederer , Joshua M. Rosera , Garth E. Graham , Asitang Mishra , Alice Yepremyan","doi":"10.1016/j.acags.2025.100274","DOIUrl":"10.1016/j.acags.2025.100274","url":null,"abstract":"<div><div>The U.S. Geological Survey (USGS), Defense Advanced Projects Research Agency (DARPA), Jet Propulsion Laboratory (JPL), and MITRE ran a 12-week machine learning competition aimed at accelerating development of AI tools for critical mineral assessments. The Artificial Intelligence for Critical Mineral Assessment Competition solicited innovative solutions for two challenges: 1) automated georeferencing of historical geologic and topographic maps, and 2) automated feature extraction from historical maps. Competitors used a new dataset of historical map images to train, validate, and evaluate their models. Automated georeferencing pipelines attained a median root-mean square error of 1.1 km. Prompt-based extraction (i.e., with user input) of polygons, polylines, and points from geologic maps yielded median F1 scores of 0.77, 0.56, 0.35, respectively. Geologic maps pose numerous challenges for AI workflows because they vary significantly. However, despite its short duration, the competition yielded promising results that have since spurred further innovation in this area and led to the development of new AI tools to semi-automate key, time-consuming parts of the assessment workflow.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"27 ","pages":"Article 100274"},"PeriodicalIF":3.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144852248","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}
Pub Date : 2025-09-01Epub Date: 2025-08-07DOI: 10.1016/j.acags.2025.100275
Yong-Feng Li , Huan Li , Jing Xiao , Weidong Ren , Mohammed Abdalla Elsharif Ibrahim
During construction, drilling parameters are manually adjusted by the operator, which can affect the blasting effect due to inappropriate initial parameters. To address this issue, an automatic optimal drilling method based on image partitioning of the heading face is proposed: i) Obtain images of the heading face using a suitable vehicle camera, and calculate pixel coordinates on the virtual heading face through rock drilling cart positioning and virtual heading face positioning; ii) Apply the region growth algorithm to extract the image region of the heading face, segment the image into several super-pixel units using the linear iterative clustering algorithm, followed by combining super-pixels based on the gray difference criterion. The resulting super-pixel blocks serve as the training sample set for the rock-partition method based on super-pixels and support vector machine (SVM); iii) Establish a database of drilling parameters. The results demonstrate that, compared to the region growth algorithm, the classification method based on super-pixels and SVM has higher accuracy. The algorithm has high accuracy of partition effect and good real-time performance, providing a reliable basis for optimizing the opening parameters.
{"title":"On-board camera-based automatic zoning method for heading face by using computerized rock drilling cart","authors":"Yong-Feng Li , Huan Li , Jing Xiao , Weidong Ren , Mohammed Abdalla Elsharif Ibrahim","doi":"10.1016/j.acags.2025.100275","DOIUrl":"10.1016/j.acags.2025.100275","url":null,"abstract":"<div><div>During construction, drilling parameters are manually adjusted by the operator, which can affect the blasting effect due to inappropriate initial parameters. To address this issue, an automatic optimal drilling method based on image partitioning of the heading face is proposed: i) Obtain images of the heading face using a suitable vehicle camera, and calculate pixel coordinates on the virtual heading face through rock drilling cart positioning and virtual heading face positioning; ii) Apply the region growth algorithm to extract the image region of the heading face, segment the image into several super-pixel units using the linear iterative clustering algorithm, followed by combining super-pixels based on the gray difference criterion. The resulting super-pixel blocks serve as the training sample set for the rock-partition method based on super-pixels and support vector machine (SVM); iii) Establish a database of drilling parameters. The results demonstrate that, compared to the region growth algorithm, the classification method based on super-pixels and SVM has higher accuracy. The algorithm has high accuracy of partition effect and good real-time performance, providing a reliable basis for optimizing the opening parameters.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"27 ","pages":"Article 100275"},"PeriodicalIF":3.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144827362","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}
Pub Date : 2025-09-01Epub Date: 2025-08-13DOI: 10.1016/j.acags.2025.100278
Yuyang Song , Lina Hao , Weile Li
Natural hazards such as landslides pose significant geological threats that can severely endanger the safety and property of residents in affected areas. Therefore, the prompt detection and accurate localisation of landslides are crucial. With the advancement of remote sensing technology and computational methods, artificial intelligence (AI)-based landslide detection techniques have emerged as effective solutions. Compared to traditional methods, these AI-driven approaches offer enhanced efficiency, accuracy and reliability, improving the speed and precision of landslide detection. They also provide valuable data for disaster prevention, mitigation and the assessment of landslide susceptibility and hazard levels. This study focuses on the western Sichuan region and constructs a historical landslide dataset using Google Earth imagery, which includes 4280 landslide samples (3424 for training and 856 for validation). To augment the dataset, 11 data augmentation techniques were applied, including copy–paste, random horizontal flipping, mosaic, random rotation, random hue, saturation and value transformation, affine transformation, random Gaussian noise, random scaling, random brightness and contrast adjustment, mixup and random cropping. These methods improve the diversity of landslide data, helping deep learning models capture more comprehensive global and local information during optimisation. This research utilises the YOLOv10-n object detection framework, enhanced with RepBlock from EfficientRep, FusedMBConv and MBConv techniques derived from EfficientNetV2, CSCGhostblockv2 from GhostNetv2, CReToNeXt from Damo-YOLO and CSCFocalNeXt. These innovations explore the impact of different backbone architectures on model performance. Additionally, the model incorporates four distinct attention mechanisms—convolutional block attention module (CBAM), global attention mechanism(GAM), sim attention module(SimAM) and selective kernel(SK) attention—to assess their influence on detection accuracy. The detection heads are optimised by substituting with three alternatives—DynamicHead, adaptive spatial feature fusion and real-time detection transformer—to enhance feature integration and investigate their effect on model performance. The results indicate that combining EfficientNetV2 with CBAM and v10Detect yields the highest performance. When applied to the historical landslide dataset from the western Sichuan region, the YOLO-EfficientNetV2 model achieves an average precision of 0.861 and an F1 score of 0.82, with a model size of 5.54 M. This model demonstrates superior capability in accurately identifying landslide locations, addressing the common challenge of balancing detection precision and speed in traditional object detection models, while also reducing parameter size and increasing detection speed.
{"title":"Landslide detection using deep learning on remotely sensed images","authors":"Yuyang Song , Lina Hao , Weile Li","doi":"10.1016/j.acags.2025.100278","DOIUrl":"10.1016/j.acags.2025.100278","url":null,"abstract":"<div><div>Natural hazards such as landslides pose significant geological threats that can severely endanger the safety and property of residents in affected areas. Therefore, the prompt detection and accurate localisation of landslides are crucial. With the advancement of remote sensing technology and computational methods, artificial intelligence (AI)-based landslide detection techniques have emerged as effective solutions. Compared to traditional methods, these AI-driven approaches offer enhanced efficiency, accuracy and reliability, improving the speed and precision of landslide detection. They also provide valuable data for disaster prevention, mitigation and the assessment of landslide susceptibility and hazard levels. This study focuses on the western Sichuan region and constructs a historical landslide dataset using Google Earth imagery, which includes 4280 landslide samples (3424 for training and 856 for validation). To augment the dataset, 11 data augmentation techniques were applied, including copy–paste, random horizontal flipping, mosaic, random rotation, random hue, saturation and value transformation, affine transformation, random Gaussian noise, random scaling, random brightness and contrast adjustment, mixup and random cropping. These methods improve the diversity of landslide data, helping deep learning models capture more comprehensive global and local information during optimisation. This research utilises the YOLOv10-n object detection framework, enhanced with RepBlock from EfficientRep, FusedMBConv and MBConv techniques derived from EfficientNetV2, CSCGhostblockv2 from GhostNetv2, CReToNeXt from Damo-YOLO and CSCFocalNeXt. These innovations explore the impact of different backbone architectures on model performance. Additionally, the model incorporates four distinct attention mechanisms—convolutional block attention module (CBAM), global attention mechanism(GAM), sim attention module(SimAM) and selective kernel(SK) attention—to assess their influence on detection accuracy. The detection heads are optimised by substituting with three alternatives—DynamicHead, adaptive spatial feature fusion and real-time detection transformer—to enhance feature integration and investigate their effect on model performance. The results indicate that combining EfficientNetV2 with CBAM and v10Detect yields the highest performance. When applied to the historical landslide dataset from the western Sichuan region, the YOLO-EfficientNetV2 model achieves an average precision of 0.861 and an F<sub>1</sub> score of 0.82, with a model size of 5.54 M. This model demonstrates superior capability in accurately identifying landslide locations, addressing the common challenge of balancing detection precision and speed in traditional object detection models, while also reducing parameter size and increasing detection speed.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"27 ","pages":"Article 100278"},"PeriodicalIF":3.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144917695","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号