Global Semantic Classification of Fluvial Landscapes with Attention-Based Deep Learning

Carbonneau, Patrice E.

Abstract

Rivers occupy less than 1% of the earth’s surface and yet they perform ecosystem service functions that are crucial to civilisation. Global monitoring of this asset is within reach thanks to the development of big data portals such as Google Earth Engine (GEE) but several challenges relating to output quality and processing efficiency remain. In this technical note, we present a new deep learning pipeline that uses attention-based deep learning to perform state-of-the-art semantic classification of fluvial landscapes with Sentinel-2 imagery accessed via GEE. We train, validate and test the network on a multi-seasonal and multi-annual dataset drawn from a study site that covers 89% of the Earth’s surface. F1-scores for independent test data not used in model training reach 92% for rivers and 96% for lakes. This is achieved without post-processing and significantly reduced computation times, thus making automated global monitoring of rivers achievable.

Citation

Carbonneau, P. E. (2024). Global Semantic Classification of Fluvial Landscapes with Attention-Based Deep Learning. Remote Sensing, 16(24), Article 4747. https://doi.org/10.3390/rs16244747

• Journal Article Type: Article
• Acceptance Date: Dec 18, 2024
• Online Publication Date: Dec 19, 2024
• Publication Date: Dec 19, 2024
• Deposit Date: Jan 15, 2025
• Publicly Available Date: Jan 15, 2025
• Journal: Remote Sensing
• Electronic ISSN: 2072-4292
• Publisher: MDPI
• Peer Reviewed: Peer Reviewed
• Volume: 16
• Issue: 24
• Article Number: 4747
• DOI: https://doi.org/10.3390/rs16244747
• Keywords: deep learning, Sentinel-2, semantic classification, attention, rivers
• Public URL: https://durham-repository.worktribe.com/output/3332409