Reproduce “Basin2Vec: Learning Basin-Centric Embeddings for Scalable Hydrological Modeling” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Muhammad Talha, Xiaofeng Liu, Yuan Yang, Pang-Ning Tan, A. Pouyan Nejadhashemi
Basin2Vec learns compact basin descriptors from basin-aligned weather and landscape grids, basin scale, and relationships among basins, without using streamflow during pretraining. Downstream forecasting models use training-basin streamflow. On 671 U.S. basins, it ranks first across five architectures; in unseen-basin LSTM tests, median NSE is 0.460 versus 0.132 for SatCLIP, on this U.S. benchmark.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.