Saliba, A.; Tout, K.; Zaki, C.; Claramunt, C. Bridging Human Expertise with Machine Learning and GIS for Mine Type Prediction and Classification. ISPRS Int. J. Geo-Inf.2024, 13, 259.
Saliba, A.; Tout, K.; Zaki, C.; Claramunt, C. Bridging Human Expertise with Machine Learning and GIS for Mine Type Prediction and Classification. ISPRS Int. J. Geo-Inf. 2024, 13, 259.
Saliba, A.; Tout, K.; Zaki, C.; Claramunt, C. Bridging Human Expertise with Machine Learning and GIS for Mine Type Prediction and Classification. ISPRS Int. J. Geo-Inf.2024, 13, 259.
Saliba, A.; Tout, K.; Zaki, C.; Claramunt, C. Bridging Human Expertise with Machine Learning and GIS for Mine Type Prediction and Classification. ISPRS Int. J. Geo-Inf. 2024, 13, 259.
Abstract
This paper introduces an intelligent model that combines military expertise with the latest ad-vancements in machine learning (ML) and Geographic Information Systems (GIS) to support humanitarian demining decision-making processes. The model is based on direct input and val-idation from field decision-makers for their practical applicability and effectiveness. With a survey polling the inputs of demining experts, 95% of the responses came with an affirmation of the potential of the model to reduce threats and increase operational efficiency. It includes mili-tary-specific factors that factor in the proximity to strategic locations as well as environmental variables like vegetation cover and terrain resolution. With Gradient Boosting algorithms such as XGBoost and LightGBM, the accuracy rate is almost 97%. Such precision levels further enhance threat assessment, better allocation of resources, and around a 30% reduction in the cost and time of conducting demining operations, signifying a strong synergy of human expertise with algo-rithmic precision for maximal safety and effectiveness in demining
Keywords
Decision-making; Human expertise; Machine-learning; GIS; Mine Type classification.
Subject
Computer Science and Mathematics, Data Structures, Algorithms and Complexity
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.