Ali Moradi Afrapoli
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Ali Moradi Afrapoli has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
- Arman Hazrathosseini
Department of Mining and Metallurgical Engineering, Amirkabir University of Technology, Tehran, Iran
4 shared publications H. Askari-Nasab
4 shared publicationsHooman Askari-Nasab
4 shared publications- Hooman Askari-Nasab
University of Alberta
3 shared publications - Iman Masoumi
DSE—Section of Mathematics and Statistics University of Salento Italy
3 shared publications Mohammad Tabesh
3 shared publications
Latest Publications
- Open Access
- 27 September 2026
- Published by MDPI AG in Geohazards
- Vol. 7 (4) , 116
A Prototype Geo-Digital Twin Framework for Scenario-Based Landslide Susceptibility Assessment Using Machine Learning
Landslides are among the most destructive natural hazards in mountainous and environmentally sensitive regions, causing significant damage to infrastructure, ecosystems, and human life. This study proposes a framework as a prototype Geo Digital Twin for landslide susceptibility assessment and scenario analysis in Eastern Kentucky, USA. A Random Forest model was developed using topographic, hydrological, geological, and environmental conditioning factors, including aspect, elevation, lithology, distance to streams, and NDVI. The model achieved strong predictive performance, with an accuracy of 0.87, an F1 score of 0.85, and a ROC–AUC of 0.94. The trained model was integrated into a service-oriented prototype Geo Digital Twin platform implemented with Django and Mapbox, enabling interactive spatial visualization and scenario simulation. In particular, vegetation change scenarios were evaluated by modifying NDVI values to examine their influence on landslide susceptibility. To improve the interpretation of these scenario outcomes, a fuzzy inference system was introduced by combining changes in predicted susceptibility (ΔP) with NDVI values into a Fuzzy Impact Index (FII). The fuzzy analysis indicates that vegetation reduction can substantially alter slope responses depending on baseline environmental conditions. The results demonstrate that the proposed framework not only provides accurate susceptibility mapping but also facilitates explainable scenario analysis to support geospatial decision-making regarding landslides.
- 27 September 2026
- Published by MDPI AG in Geohazards
- Vol. 7 (4) , 116
Open AccessA Prototype Geo-Digital Twin Framework for Scenario-Based Landslide Susceptibility Assessment Using Machine Learning
Landslides are among the most destructive natural hazards in mountainous and environmentally sensitive regions, causing significant damage to infrastructure, ecosystems, and human life. This study proposes a framework as a prototype Geo Digital Twin for landslide susceptibility assessment and scenario analysis in Eastern Kentucky, USA. A Random Forest model was developed using topographic, hydrological, geological, and environmental conditioning factors, including aspect, elevation, lithology, distance to streams, and NDVI. The model achieved strong predictive performance, with an accuracy of 0.87, an F1 score of 0.85, and a ROC–AUC of 0.94. The trained model was integrated into a service-oriented prototype Geo Digital Twin platform implemented with Django and Mapbox, enabling interactive spatial visualization and scenario simulation. In particular, vegetation change scenarios were evaluated by modifying NDVI values to examine their influence on landslide susceptibility. To improve the interpretation of these scenario outcomes, a fuzzy inference system was introduced by combining changes in predicted susceptibility (ΔP) with NDVI values into a Fuzzy Impact Index (FII). The fuzzy analysis indicates that vegetation reduction can substantially alter slope responses depending on baseline environmental conditions. The results demonstrate that the proposed framework not only provides accurate susceptibility mapping but also facilitates explainable scenario analysis to support geospatial decision-making regarding landslides.
- Open Access
Managing Open Pit to Underground Transition: A Systematic Review of Environmental and Operational Risks for Integrated Mine Planning
The transition from open pit to underground mining is becoming increasingly important as near-surface ore is depleted and mines seek to extend operating life. Yet its environmental and operational effects are often discussed separately. This systematic review examines the risks reported during the transition stage and develops an integrated framework for mine planning. Following a PRISMA-guided approach, peer-reviewed literature published between 2010 and 2026 was screened, and 69 records were included in the final review, comprising 66 primary studies and three directly relevant review articles. The evidence shows that the transition redistributes rather than simply reduces environmental pressure. Water management, ground stability, underground air quality, ventilation, and energy demand may become more important as underground development advances, while some surface impacts may decline as open pit activity decreases. The review therefore treats the active overlap period as a distinct planning stage and brings the main environmental and operational risks into one transition-planning framework.
Open AccessManaging Open Pit to Underground Transition: A Systematic Review of Environmental and Operational Risks for Integrated Mine Planning
The transition from open pit to underground mining is becoming increasingly important as near-surface ore is depleted and mines seek to extend operating life. Yet its environmental and operational effects are often discussed separately. This systematic review examines the risks reported during the transition stage and develops an integrated framework for mine planning. Following a PRISMA-guided approach, peer-reviewed literature published between 2010 and 2026 was screened, and 69 records were included in the final review, comprising 66 primary studies and three directly relevant review articles. The evidence shows that the transition redistributes rather than simply reduces environmental pressure. Water management, ground stability, underground air quality, ventilation, and energy demand may become more important as underground development advances, while some surface impacts may decline as open pit activity decreases. The review therefore treats the active overlap period as a distinct planning stage and brings the main environmental and operational risks into one transition-planning framework.
- Open Access
- 27 July 2026
- Published by MDPI AG in Preprints.org
Managing Open Pit to Underground Transition: A Review of Environmental, and Operational Risks for Integrated Mine Planning
The transition from open pit to underground mining is becoming increasingly important as near-surface ore is depleted and operations seek to extend mine life. However, its environmental effects are still often discussed in separate technical areas rather than as one connected planning problem. This review examines the environmental impacts reported during the transition stage and proposes an integrated framework to support mine planning. Following a PRISMA-guided approach, peer-reviewed studies published between 2010 and 2026 were screened, and 68 studies were included in the final review. The findings show that the transition does not simply reduce environmental impacts; instead, it redistributes them across water, ground stability, air quality, energy use, land disturbance, and nearby communities. The main reported concerns include groundwater rebound and inflow, slope instability and subsidence, underground dust exposure, and higher ventilation-related energy demand, while some surface impacts, such as land clearing, dust, and blasting noise, may decline as open pit activity decreases. Overall, the transition should be treated as a distinct planning stage, and the proposed framework helps mine planners address these impacts together rather than separately.
- 27 July 2026
- Published by MDPI AG in Preprints.org
Open AccessManaging Open Pit to Underground Transition: A Review of Environmental, and Operational Risks for Integrated Mine Planning
The transition from open pit to underground mining is becoming increasingly important as near-surface ore is depleted and operations seek to extend mine life. However, its environmental effects are still often discussed in separate technical areas rather than as one connected planning problem. This review examines the environmental impacts reported during the transition stage and proposes an integrated framework to support mine planning. Following a PRISMA-guided approach, peer-reviewed studies published between 2010 and 2026 were screened, and 68 studies were included in the final review. The findings show that the transition does not simply reduce environmental impacts; instead, it redistributes them across water, ground stability, air quality, energy use, land disturbance, and nearby communities. The main reported concerns include groundwater rebound and inflow, slope instability and subsidence, underground dust exposure, and higher ventilation-related energy demand, while some surface impacts, such as land clearing, dust, and blasting noise, may decline as open pit activity decreases. Overall, the transition should be treated as a distinct planning stage, and the proposed framework helps mine planners address these impacts together rather than separately.
- 13 March 2026
- Published by Taylor & Francis in International Journal of Modelling and Simulation
- p. 1-19
GHG-considerate operational excellence in surface mines: an integrated stochastic discrete-continuous simulation-based optimization framework
1. Mining operations, crucial to global economic activities, heavily rely on fleets of trucks and shovels for material handling, constituting a significant portion of operational costs. The main ma...
- 13 March 2026
- Published by Taylor & Francis in International Journal of Modelling and Simulation
- p. 1-19
GHG-considerate operational excellence in surface mines: an integrated stochastic discrete-continuous simulation-based optimization framework
1. Mining operations, crucial to global economic activities, heavily rely on fleets of trucks and shovels for material handling, constituting a significant portion of operational costs. The main ma...
- Open Access
ASTER Remote Sensing Satellite Imagery for Regional Mineral Mapping in the McMurdo Dry Valleys, South Victoria Land, Antarctica
The McMurdo Dry Valleys (DVs) of South Victoria Land, Antarctica, constitute the largest ice-free region on the continent and one of Earth’s most Mars-analog environments. Their hyper-arid polar desert conditions offer a unique setting for investigating surface weathering and mineralogical processes under extreme climates. This study presents the first regional-scale mapping of alteration and crystalline weathering minerals across the McMurdo DVs. It uses Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) multispectral data; visible and near-infrared (VNIR) and shortwave infrared (SWIR) bands were analyzed through a Spectral Hourglass Workflow, endmember extraction, and spectral unmixing with Matched Filtering (MF) and Constrained Energy Minimization (CEM). Inter-algorithm consistency analysis between MF and CEM yielded 78.83% overall agreement with a Kappa coefficient of 0.75, indicating strong methodological consistency in mineral discrimination using ASTER VNIR+SWIR data. It should be noted that this agreement reflects internal algorithmic robustness rather than independent geological validation. Geological reliability is instead supported by documented field observations, lithological map comparisons, and spectral correspondence with the USGS spectral library. Validation employed documented field observations, lithological maps, and the USGS spectral library. Results reveal distinct spatial distributions of hematite-limonite/goethite, jarosite, kaolinite/smectite-illite-pyrophyllite-alunite, muscovite, hydrous silica/sericite/jarosite/hematite, epidote/chlorite, and calcite, closely associated with lithological units and unconsolidated deposits in Taylor, Wright, Victoria, and McKelvey Valleys. An inter-algorithm consistency check achieved 78.83% overall accuracy with a Kappa coefficient of 0.75, underscoring the robustness of ASTER VNIR+SWIR data for Antarctic mineral discrimination despite localized spectral mixing. Beyond refining the geological understanding of the McMurdo DVs, these results establish ASTER as an effective tool for regional mineralogical mapping in inaccessible polar terrains. The findings further strengthen the role of the Dry Valleys as a terrestrial analog for Mars, where similar mineralogical assemblages and spectral ambiguities have been observed, thereby contributing to both Antarctic geoscience and planetary exploration frameworks.
Open AccessASTER Remote Sensing Satellite Imagery for Regional Mineral Mapping in the McMurdo Dry Valleys, South Victoria Land, Antarctica
The McMurdo Dry Valleys (DVs) of South Victoria Land, Antarctica, constitute the largest ice-free region on the continent and one of Earth’s most Mars-analog environments. Their hyper-arid polar desert conditions offer a unique setting for investigating surface weathering and mineralogical processes under extreme climates. This study presents the first regional-scale mapping of alteration and crystalline weathering minerals across the McMurdo DVs. It uses Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) multispectral data; visible and near-infrared (VNIR) and shortwave infrared (SWIR) bands were analyzed through a Spectral Hourglass Workflow, endmember extraction, and spectral unmixing with Matched Filtering (MF) and Constrained Energy Minimization (CEM). Inter-algorithm consistency analysis between MF and CEM yielded 78.83% overall agreement with a Kappa coefficient of 0.75, indicating strong methodological consistency in mineral discrimination using ASTER VNIR+SWIR data. It should be noted that this agreement reflects internal algorithmic robustness rather than independent geological validation. Geological reliability is instead supported by documented field observations, lithological map comparisons, and spectral correspondence with the USGS spectral library. Validation employed documented field observations, lithological maps, and the USGS spectral library. Results reveal distinct spatial distributions of hematite-limonite/goethite, jarosite, kaolinite/smectite-illite-pyrophyllite-alunite, muscovite, hydrous silica/sericite/jarosite/hematite, epidote/chlorite, and calcite, closely associated with lithological units and unconsolidated deposits in Taylor, Wright, Victoria, and McKelvey Valleys. An inter-algorithm consistency check achieved 78.83% overall accuracy with a Kappa coefficient of 0.75, underscoring the robustness of ASTER VNIR+SWIR data for Antarctic mineral discrimination despite localized spectral mixing. Beyond refining the geological understanding of the McMurdo DVs, these results establish ASTER as an effective tool for regional mineralogical mapping in inaccessible polar terrains. The findings further strengthen the role of the Dry Valleys as a terrestrial analog for Mars, where similar mineralogical assemblages and spectral ambiguities have been observed, thereby contributing to both Antarctic geoscience and planetary exploration frameworks.
- Open Access
- 30 September 2025
- Published by Glowny Instytut Gornictwa (Central Mining Institute) in Journal of Sustainable Mining
- Vol. 24 (4) , 538-550
Towards sustainable mining: GHG considerate open pit long-term planning using adaptive large neighborhood search algorithm
Mine planning involves the systematic design and coordination of mineral extraction from the earth’s crust, integrating exploration, production, and various engineering considerations. With increasing emphasis on environmental responsibility, the mining industry is under pressure to incorporate environmental considerations into mine planning. This paper addresses the precedence-constrained production scheduling problem (PCPSP) within the context of green long-term mining planning, aiming to optimize extraction processes while restricting carbon emission. Given the NP-hard nature of the PCPSP, this study introduces an adaptive large neighborhood search (ALNS) algorithm tailored specifically for long-term mine planning. A range of computational experiments have been carried out, including parameter tuning for the ALNS algorithm, comparisons against an exact solver, and analysis of our destroy-repair operators to determine their key elements. The efficacy of developed ALNS, evaluated using various benchmarks, reveals optimality gaps around 0.08. These results highlight the effectiveness of the proposed approach in addressing the PCPSP within mine planning and production scheduling, providing insights into improving mining operations while considering environmental concerns.
- 30 September 2025
- Published by Glowny Instytut Gornictwa (Central Mining Institute) in Journal of Sustainable Mining
- Vol. 24 (4) , 538-550
Open AccessTowards sustainable mining: GHG considerate open pit long-term planning using adaptive large neighborhood search algorithm
Mine planning involves the systematic design and coordination of mineral extraction from the earth’s crust, integrating exploration, production, and various engineering considerations. With increasing emphasis on environmental responsibility, the mining industry is under pressure to incorporate environmental considerations into mine planning. This paper addresses the precedence-constrained production scheduling problem (PCPSP) within the context of green long-term mining planning, aiming to optimize extraction processes while restricting carbon emission. Given the NP-hard nature of the PCPSP, this study introduces an adaptive large neighborhood search (ALNS) algorithm tailored specifically for long-term mine planning. A range of computational experiments have been carried out, including parameter tuning for the ALNS algorithm, comparisons against an exact solver, and analysis of our destroy-repair operators to determine their key elements. The efficacy of developed ALNS, evaluated using various benchmarks, reveals optimality gaps around 0.08. These results highlight the effectiveness of the proposed approach in addressing the PCPSP within mine planning and production scheduling, providing insights into improving mining operations while considering environmental concerns.
- 12 December 2024
- Published by SAGE Publications in Mining Technology: Transactions of the Institutions of Mining and Metallurgy
- Vol. 134 (1) , 3-14
An intelligent rule-based decision-making system for preliminary truck dispatching within open-pit mines
Preliminary truck dispatching involves directing trucks to appropriate destinations before addressing specific optimization objectives such as maximizing ore production or minimizing waiting times. While rule-based systems are commonly used for preliminary dispatching, they lack adaptability to unforeseen scenarios. This study presents an intelligent rule-based system that integrates reinforcement learning to generate labeled data and supervised learning to train a deep neural network on the collected data. A modified Q-learning algorithm, RapidQ, was introduced to expedite the data collection process. The system was implemented in a simulated open-pit mine case study, which incorporated a broader range of dispatching features that are underexplored but essential compared to previous studies. The simulation was designed to handle uncertainties such as weather conditions, blasting needs, truck and shovel failures, and maintenance schedules. When evaluated against a conventional rule-based system, the proposed intelligent dispatching system achieved 10 times fewer incorrect dispatches, 4% fuel savings, a 10% reduction in queuing time, and a 14% increase in ore production. The developed system can be positioned as a potential upper-stage solution in future multi-stage intelligent dispatching systems, complemented by specific dispatching algorithms at the lower stage.
- 12 December 2024
- Published by SAGE Publications in Mining Technology: Transactions of the Institutions of Mining and Metallurgy
- Vol. 134 (1) , 3-14
An intelligent rule-based decision-making system for preliminary truck dispatching within open-pit mines
Preliminary truck dispatching involves directing trucks to appropriate destinations before addressing specific optimization objectives such as maximizing ore production or minimizing waiting times. While rule-based systems are commonly used for preliminary dispatching, they lack adaptability to unforeseen scenarios. This study presents an intelligent rule-based system that integrates reinforcement learning to generate labeled data and supervised learning to train a deep neural network on the collected data. A modified Q-learning algorithm, RapidQ, was introduced to expedite the data collection process. The system was implemented in a simulated open-pit mine case study, which incorporated a broader range of dispatching features that are underexplored but essential compared to previous studies. The simulation was designed to handle uncertainties such as weather conditions, blasting needs, truck and shovel failures, and maintenance schedules. When evaluated against a conventional rule-based system, the proposed intelligent dispatching system achieved 10 times fewer incorrect dispatches, 4% fuel savings, a 10% reduction in queuing time, and a 14% increase in ore production. The developed system can be positioned as a potential upper-stage solution in future multi-stage intelligent dispatching systems, complemented by specific dispatching algorithms at the lower stage.