The impacts of armed con ict on the environment are extremely complex and di cult to investigate, given the impossibility of accessing the affected area and reliable data limitation. Very-high-resolution satellite imageries and highly reliable machine learning algorithms become very useful in studying direct and indirect impacts of war on the ecosystem, in addition to connected effects on human lives. The Rohingya con ict is described as one of the worst humanitarian crises and human-made disasters of the 21st Century. Quanti cation of damage due to the con ict and the suitability of human resettlement has been lacking despite the ongoing agreements to repatriate refugees and the importance of ecosystem services for the communities' survival. Here we report the investigation of environmental conditions pre-, during, and post-con ict in the con ict zone using satellite data. We implemented and experienced the Google Earth Engine (GEE) cloud-based computing platform with a widely applied algorithm, the Random Forest (RF) classi er. We found striking near-complete demolition of inhabited regions, dramatic and highly signi cant increase in burning areas, and substantial deforestation. We discuss the reasons behind such ndings from the Rakhine case and debate some general conservation lessons applicable to other countries undergoing post-con ict transitions.
IntroductionAll over the world, the environment is being affected by anthropogenic activities. From the disruption of the Earth's climate system, ocean lling up with plastic, pollution, and forest degradation to damaging the entire ecosystem, human actions have changed the make-up of Earth's surface. While these changes are easier to detect in a politically stable context, it is notoriously challenging to assess how the environment is affected in areas faced by armed con ict, either directly by the con ict or indirectly through the socio-economic and political conditions that con icts create. The impacts of violent con ict on human are generally well-understood and extensively documented (