Remote Sensing for Water Quality: A Multi-Task, Metadata-Driven Hypernetwork Approach
Remote Sensing for Water Quality: A Multi-Task, Metadata-Driven Hypernetwork Approach
Olivier Graffeuille, Yun Sing Koh, Jörg Wicker, Moritz Lehmann
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence
AI for Good. Pages 7287-7295.
https://doi.org/10.24963/ijcai.2024/806
Inland water quality monitoring is vital for clean water access and aquatic ecosystem management. Remote sensing machine learning models enable large-scale observations, but are difficult to train due to data scarcity and variability across many lakes. Multi-task learning approaches enable learning of lake differences by learning multiple lake functions simultaneously. However, they suffer from a trade-off between parameter efficiency and the ability to model task differences flexibly, and struggle to model many diverse lakes with few samples per task. We propose Multi-Task Hypernetworks, a novel multi-task learning architecture which circumvents this trade-off using a shared hypernetwork to generate different network weights for each task from small task-specific embeddings. Our approach stands out from existing works by providing the added capacity to leverage task-level metadata, such as lake depth and temperature, explicitly. We show empirically that Multi-Task Hypernetworks outperform existing multi-task learning architectures for water quality remote sensing and other tabular data problems, and leverages metadata more effectively than existing methods.
Keywords:
Machine Learning: General
Multidisciplinary Topics and Applications: General