XGBOOST and Multitemporal DETER Data for Deforestation Forecasting
Abstract. This paper reports research that is part of a project to combat deforestation in the Brazilian Amazon rainforest by developing an online system designed to forecast deforestation risk over the short term, spanning 2 to 4 weeks. This online platform aims to empower stakeholders with timely data, facilitating proactive conservation and intervention strategies to safeguard the Amazon rainforest. We built a multitemporal database that compiles weekly deforestation alerts from the DETER project, forming our analysis’s backbone. Utilizing the XGBOOST regression algorithm, we have crafted a predictive model that identifies areas within the Amazon at imminent risk of more intensive deforestation. Preliminary results reveal an RMSE of 0.29 for predicting areas under deforestation risk, as validated against early alert data from 2020 to 2023. Our work advances environmental monitoring by focusing on a spatial resolution of 25 km × 25 km, providing accessible, near real-time information on deforestation risks.
Authors
- Ana Paula Aguiar (ORCID: https://orcid.org/0000-0002-0683-1142)
- Felipe Ferrari (ORCID: https://orcid.org/0000-0003-0705-9593)
- Lúbia Vinhas (ORCID: https://orcid.org/0000-0003-1104-3607)
- Francisco Gilney Silva Bezerra (ORCID: https://orcid.org/0000-0001-9635-0336)
- Laura Elena Cué La Rosa (ORCID: https://orcid.org/0000-0002-6284-9494)
- Patrick Nigri Happ (ORCID: https://orcid.org/0000-0003-3280-5471)
- Raian Vargas Maretto (ORCID: https://orcid.org/0000-0002-4983-2700)
- Raul Queiroz Feitosa (ORCID: https://orcid.org/0000-0001-8344-5096)
- Rodrigo Antônio de Souza (ORCID: https://orcid.org/0000-0003-2278-3221)
Institutions
- Brazilian Institute of Environment and Renewable Natural Resources (BR)
- Stockholm Resilience Centre (SE)
- Stockholm University (SE)
- Pontifícia Universidade Católica do Rio de Janeiro (BR)
- Instituto Nacional de Pesquisas Espaciais (BR)
- Wageningen University & Research (NL)
- University of Twente (NL)
Publication Details
- Journal
- ISPRS annals of the photogrammetry, remote sensing and spatial information sciences
- Published
- 2024-11-04
- DOI
- https://doi.org/10.5194/isprs-annals-x-3-2024-193-2024
- Citations
- 1
- Primary Topic
- Remote Sensing and LiDAR Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.21