Multimodal SuperCon: Classifier for Drivers of Deforestation in Indonesia

TL;DR

This paper introduces Multimodal SuperCon, a contrastive learning architecture that effectively classifies drivers of deforestation in Indonesia using satellite imagery, significantly improving accuracy over previous models.

Contribution

It presents a novel contrastive learning and multimodal fusion architecture specifically designed for classifying deforestation drivers from satellite data.

Findings

7% accuracy improvement over previous models

Effective handling of multimodal satellite data

Outperforms state-of-the-art in deforestation driver classification

Abstract

Deforestation is one of the contributing factors to climate change. Climate change has a serious impact on human life, and it occurs due to emission of greenhouse gases, such as carbon dioxide, to the atmosphere. It is important to know the causes of deforestation for mitigation efforts, but there is a lack of data-driven research studies to predict these deforestation drivers. In this work, we propose a contrastive learning architecture, called Multimodal SuperCon, for classifying drivers of deforestation in Indonesia using satellite images obtained from Landsat 8. Multimodal SuperCon is an architecture which combines contrastive learning and multimodal fusion to handle the available deforestation dataset. Our proposed model outperforms previous work on driver classification, giving a 7% improvement in accuracy in comparison to a state-of-the-art rotation equivariant model for the same task.