RELand: Risk Estimation of Landmines via Interpretable Invariant Risk Minimization

TL;DR

RELand introduces an interpretable invariant risk minimization system that enhances landmine risk assessment, providing a practical tool for demining efforts with improved accuracy and usability in real-world scenarios.

Contribution

The paper presents a novel interpretable model based on invariant risk minimization for landmine detection, along with guidelines for feature engineering and an interactive web interface.

Findings

Significant improvement over state-of-the-art landmine risk models

Effective general feature engineering guidelines for demining datasets

Successful deployment in real-world Colombian demining operations

Abstract

Landmines remain a threat to war-affected communities for years after conflicts have ended, partly due to the laborious nature of demining tasks. Humanitarian demining operations begin by collecting relevant information from the sites to be cleared, which is then analyzed by human experts to determine the potential risk of remaining landmines. In this paper, we propose RELand system to support these tasks, which consists of three major components. We (1) provide general feature engineering and label assigning guidelines to enhance datasets for landmine risk modeling, which are widely applicable to global demining routines, (2) formulate landmine presence as a classification problem and design a novel interpretable model based on sparse feature masking and invariant risk minimization, and run extensive evaluation under proper protocols that resemble real-world demining operations to show a significant improvement over the state-of-the-art, and (3) build an interactive web interface to suggest priority areas for demining organizations. We are currently collaborating with a humanitarian demining NGO in Colombia that is using our system as part of their field operations in two areas recently prioritized for demining.