A Satellite Band Selection Framework for Amazon Forest Deforestation Detection Task

TL;DR

This paper presents a novel satellite band selection framework using UMDA to optimize deforestation detection in the Amazon, improving segmentation accuracy and challenging the notion that more spectral data always yields better results.

Contribution

Introduces a UMDA-based spectral band selection method that enhances deep learning segmentation for deforestation detection, outperforming existing approaches.

Findings

Selected bands outperform traditional combinations in accuracy.

Optimal band sets improve DeepLabv3+ performance.

Fewer bands can be more effective than using all available data.

Abstract

The conservation of tropical forests is a topic of significant social and ecological relevance due to their crucial role in the global ecosystem. Unfortunately, deforestation and degradation impact millions of hectares annually, necessitating government or private initiatives for effective forest monitoring. This study introduces a novel framework that employs the Univariate Marginal Distribution Algorithm (UMDA) to select spectral bands from Landsat-8 satellite, optimizing the representation of deforested areas. This selection guides a semantic segmentation architecture, DeepLabv3+, enhancing its performance. Experimental results revealed several band compositions that achieved superior balanced accuracy compared to commonly adopted combinations for deforestation detection, utilizing segment classification via a Support Vector Machine (SVM). Moreover, the optimal band compositions identified by the UMDA-based approach improved the performance of the DeepLabv3+ architecture, surpassing state-of-the-art approaches compared in this study. The observation that a few selected bands outperform the total contradicts the data-driven paradigm prevalent in the deep learning field. Therefore, this suggests an exception to the conventional wisdom that 'more is always better'.