Researchers have developed a new dataset called AmazonSWE and a corresponding model designed to improve the imputation of water surface elevation data. This dataset, which covers over 19,000 river sections in the Amazon basin over a decade, integrates satellite altimetry measurements, including data from the SWOT sensor, and is significantly sparser than existing benchmarks. The proposed bidirectional selective state space model demonstrates superior performance compared to current state-of-the-art methods, reducing RMSE against in-situ gauges by 18-39% and providing predictions for all river sections. AI
IMPACT This work could enhance flood forecasting and water resource management through improved data imputation techniques.
RANK_REASON The cluster contains an academic paper detailing a new dataset and model for a specific scientific application. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
