WaterMark
Accurately predicting water levels is one of the most important tasks for monitoring climate change and coastal flooding. Traditionally, water level measurements have been collected by monitoring stations deployed by the National Oceanographic and Atmospheric Administration (NOAA) and the United States Geological Survey (USGS). These two organizations deploy the majority of US-based water level sensors in riverine and coastal environments.
WaterMark establishes a benchmark for water level prediction using modern AI methods. We evaluate a variety of neural network approaches to modeling the temporal and spatial components of these sensor networks. Our goal is to improve predictions in these sensor networks, while developing novel methods to induce inductive biases in spatio-temporal networks.
Publications
Coming soon!
Funding and Acknowledgements
This work is partially funded by the NSF CSGrad4US Fellowship.