A location-based model using GIS with machine learning, and a human-based approach for demining a post-war region - Journal of Location Based Services

Aug 5, 2026

Upload by Eliana

Locating and removing landmines and other explosive remnants of war (ERW) remains dangerous and time-intensive, requiring coordinated multilevel on-site surveys. This paper presents a landmine location-based prediction model that integrates military experience with machine-learning methods and spatiotemporal data, adding military-based features to support context modelling and training. Beyond predicting likely location areas, it ranks affected regions by clearance priority and difficulty to reduce survey time and operational risk. Experiments using SVM, Random Forest, and XGBoost address imbalanced data and target strong performance and accuracy.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages24

Reading Time1 h 0 min

AccessFree to download

Introduction

Humanitarian demining context and objectives

Challenges: safety, detection, clearance

Lebanon’s landmine threat and responsible organizations

Proposed location-based prediction approach

Area selection and military-based features

Model training and handling imbalanced data

Experimental results

Machine learning models and performance

Science Arts & Métiers (SAM) is an open access repository that collects the work of Arts et Métiers Institute of Technology researchers and makes it freely available over the web where possible. This is an author-deposited version published in: [https://sam.ensam.eu](https://sam.ensam.eu)[ ](https://sam.ensam.eu)Handle ID: .[http://hdl.handle.net/10985/25189](http://hdl.handle.net/10985/25189) To cite this version : Adib SALIBA, Kifah TOUT, Chamseddine ZAKI, Christophe CLARAMUNT-A location-based model using GIS with machine learning, and a human-based approach for demining a post-war region-Journal of Location Based Services p.1-23-2024 | Any correspondence concerning this service should be sent to the repository [Administrator :](Administrator : scienceouverte@ensam.eu)[ ](Administrator : scienceouverte@ensam.eu)[scienceouverte@ensam.eu](Administrator : scienceouverte@ensam.eu) | | | --- | --- | A location-based model using GIS with machine learning, and a human-based approach for demining a post-war region Adib Salibaa,b, Kifah Touta, Chamseddine Zakic and Christophe Claramuntb,d aFaculty of Sciences, Lebanese University, Beirut, Lebanon; bNaval Academy Research Institute, Lanvéoc, France; cCollege of Engineering and Technology, American University of the Middle East, Kuwait; dOkinawa Institute of Science and Technology, Japan ABSTRACT Locating and removing landmines and other ERW (Explosive Remnants of War) is dangerous, hazardous, and time-con-suming. It requires implementing multilevel on-site surveys: general non-technical surveys to mark the areas affected and technical surveys to determine the perimeter of related mine-fields. This paper introduces a landmine locationbased pre-diction model, combining military experience with machine-learning techniques and spatiotemporal data, by introducing a new approach for area selection and adding military-based features for context modelling and model training. Besides predicting landmine’s location areas, this model classifies the affected regions by priority and difficulty of clearance, in such a way as to minimise the long time needed by surveys and reduce the danger related to that task, thus providing the clearance organisations with a good resource allocation for their operations. We applied several machine learning tech-niques that combine Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGBOOST), tak-ing into consideration the imbalanced data problem and tweaking for the best performance and accuracy. The experi-mental results show that the model has the potential to provide reliable predictions and valuable services for demin-ing operations on the field. KEYWORDS Location-based model; machine-learning; demining 1. Introduction Landmines are explosive devices that are designed to be placed on or in the ground to disable or kill enemy forces or civilians. They are often used in war or conflict situations, and they can remain active and dangerous long after the conflict has ended, posing a significant threat to civilians, and hindering the recovery and development of affected areas. In total, there have been 2374 reported casualties of mines or other explosive remnants of war in Lebanon, of which 631 people were killed (from 1971 until the beginning of CONTACT Christophe Claramunt [christophe.claramunt@gmail.com](christophe.claramunt@gmail.com) [https://doi.org/10.1080/17489725.2023.2298803](https://doi.org/10.1080/17489725.2023.2298803) 2023) . Humanitarian demining is the process of removing landmines and other explosive remnants of war from areas affected by a conflict. The goal of humanitarian demining is to reduce the risk of injury or death to civilians, facilitate the return of refugees and displaced persons, and support longterm development efforts in affected areas. It involves several steps, including surveying and mapping affected areas to identify the locations of landmines, clearing and removi

FAQs

Why is humanitarian demining considered dangerous and time-consuming?

Landmines and ERW are hazardous and often difficult to detect, so surveys and clearance require careful on-site work and specialized procedures.

What does the proposed model predict and how does it support operations?

It predicts landmine location areas and classifies affected regions by clearance priority and difficulty, helping organizations allocate resources and reduce survey time.

Which machine learning techniques are used and how is data imbalance handled?

The study combines SVM, Random Forest, and XGBoost, explicitly considering the imbalanced data problem and adjusting the training for better performance and accuracy.

Aug 5, 2026

Upload by Eliana