Identification of Deforestation Areas in the Amazon Rainforest Using Change Detection Models

TL;DR

This study evaluates various change detection models, including modern architectures with self-attention, for identifying deforestation in the Amazon using satellite imagery, and demonstrates how preprocessing and model combination improve accuracy.

Contribution

It provides a unified evaluation framework for change detection models, incorporating modern architectures and preprocessing techniques, and explores model combination strategies for better deforestation detection.

Findings

Achieved an F1-score of 80.41%, comparable to recent studies.

Preprocessing techniques significantly improve model effectiveness.

Model combination strategies outperform individual models.

Abstract

The preservation of the Amazon Rainforest is one of the global priorities in combating climate change, protecting biodiversity, and safeguarding indigenous cultures. The Satellite-based Monitoring Project of Deforestation in the Brazilian Legal Amazon (PRODES), a project of the National Institute for Space Research (INPE), stands out as a fundamental initiative in this effort, annually monitoring deforested areas not only in the Amazon but also in other Brazilian biomes. Recently, machine learning models have been developed using PRODES data to support this effort through the comparative analysis of multitemporal satellite images, treating deforestation detection as a change detection problem. However, existing approaches present significant limitations: models evaluated in the literature still show unsatisfactory effectiveness, many do not incorporate modern architectures, such as those based on self-attention mechanisms, and there is a lack of methodological standardization that allows direct comparisons between different studies. In this work, we address these gaps by evaluating various change detection models in a unified dataset, including fully convolutional models and networks incorporating self-attention mechanisms based on Transformers. We investigate the impact of different pre- and post-processing techniques, such as filtering deforested areas predicted by the models based on the size of connected components, texture replacement, and image enhancements; we demonstrate that such approaches can significantly improve individual model effectiveness. Additionally, we test different strategies for combining the evaluated models to achieve results superior to those obtained individually, reaching an F1-score of 80.41%, a value comparable to other recent works in the literature.