Using transfer learning to study burned area dynamics: A case study of refugee settlements in West Nile, Northern Uganda

TL;DR

This study employs transfer learning with deep learning models trained on Portuguese data to analyze burned area dynamics in refugee settlements in Northern Uganda, addressing data scarcity and assessing environmental impacts.

Contribution

It introduces a scalable transfer learning approach for burned area mapping in data-scarce regions, applying models trained elsewhere to study land management impacts of refugee settlements.

Findings

Model successfully transferred from Portugal to Uganda.

Burned area dynamics linked to refugee settlement activities.

Provides insights into land management impacts in West Nile.

Abstract

With the global refugee crisis at a historic high, there is a growing need to assess the impact of refugee settlements on their hosting countries and surrounding environments. Because fires are an important land management practice in smallholder agriculture in sub-Saharan Africa, burned area (BA) mappings can help provide information about the impacts of land management practices on local environments. However, a lack of BA ground-truth data in much of sub-Saharan Africa limits the use of highly scalable deep learning (DL) techniques for such BA mappings. In this work, we propose a scalable transfer learning approach to study BA dynamics in areas with little to no ground-truth data such as the West Nile region in Northern Uganda. We train a deep learning model on BA ground-truth data in Portugal and propose the application of that model on refugee-hosting districts in West Nile between 2015 and 2020. By comparing the district-level BA dynamic with the wider West Nile region, we aim to add understanding of the land management impacts of refugee settlements on their surrounding environments.