Rapid Deforestation and Burned Area Detection using Deep Multimodal Learning on Satellite Imagery

TL;DR

This paper presents a deep multimodal learning approach using CNNs and a new satellite imagery dataset to accurately detect deforestation and burned areas in the Amazon, addressing environmental challenges with high precision.

Contribution

Introduces a curated multimodal satellite dataset and a CNN-based method for precise deforestation and fire detection in the Amazon region.

Findings

High-precision deforestation estimation achieved

Effective burned area detection demonstrated

Dataset and models are publicly available

Abstract

Deforestation estimation and fire detection in the Amazon forest poses a significant challenge due to the vast size of the area and the limited accessibility. However, these are crucial problems that lead to severe environmental consequences, including climate change, global warming, and biodiversity loss. To effectively address this problem, multimodal satellite imagery and remote sensing offer a promising solution for estimating deforestation and detecting wildfire in the Amazonia region. This research paper introduces a new curated dataset and a deep learning-based approach to solve these problems using convolutional neural networks (CNNs) and comprehensive data processing techniques. Our dataset includes curated images and diverse channel bands from Sentinel, Landsat, VIIRS, and MODIS satellites. We design the dataset considering different spatial and temporal resolution requirements. Our method successfully achieves high-precision deforestation estimation and burned area detection on unseen images from the region. Our code, models and dataset are open source: https://github.com/h2oai/cvpr-multiearth-deforestation-segmentation