An Open-Source Tool for Mapping War Destruction at Scale in Ukraine using Sentinel-1 Time Series

2024-06-04

arXiv.org

AI Summary

This paper addresses the challenge of large-scale, high-temporal-resolution assessment of building damage in protracted conflict zones—exemplified by Ukraine. We propose a scalable SAR time-series analysis framework that, for the first time, tightly integrates Sentinel-1 SAR time-series modeling with the Google Earth Engine (GEE) cloud platform and OpenStreetMap building footprints to construct an all-weather, region-wide, optical-free automated war-damage probability model (using XGBoost/Random Forest). Our contributions are threefold: (1) the first publicly released nationwide, building-level war-damage probability map for Ukraine; (2) two open-source, ready-to-use tools—Ukraine Damage Explorer (for interactive visualization) and Rapid Damage Mapping Tool (for user-defined, rapid damage mapping); and (3) state-of-the-art performance with an 87% F1-score, supporting adjustable confidence thresholds and fully reproducible analysis.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Intelligent Robots: State Estimation
• Machine Learning: Time-Series/Data Streams

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Access to detailed war impact assessments is crucial for humanitarian organizations to assist affected populations effectively. However, maintaining a comprehensive understanding of the situation on the ground is challenging, especially in widespread and prolonged conflicts. Here we present a scalable method for estimating building damage resulting from armed conflicts. By training a machine learning model on Synthetic Aperture Radar image time series, we generate probabilistic damage estimates at the building level, leveraging existing damage assessments and open building footprints. To allow large-scale inference and ensure accessibility, we tie our method to run on Google Earth Engine. Users can adjust confidence intervals to suit their needs, enabling rapid and flexible assessments of war-related damage across large areas. We provide two publicly accessible dashboards: a Ukraine Damage Explorer to dynamically view our precomputed estimates, and a Rapid Damage Mapping Tool to run our method and generate custom maps.

Problem

• Mapping war destruction in Ukraine
• Estimating building damage using SAR
• Open-source tools for damage assessment

Innovation

• Machine learning model training
• Synthetic Aperture Radar analysis
• Google Earth Engine integration