hydrology

FLARE MCMC is a novel multi-fidelity method that enhances Markov chain Monte Carlo sampling by using layer-adaptive recursive proposals with lower-fidelity likelihood approximations, demonstrating improved efficiency in applications such as hydrology and cosmology.

A California aquifer may have passed an irreversible tipping point, raising concerns about permanent groundwater depletion.

This paper presents a Mass-Conserving Perceptron (MCP) framework that reformulates conceptual hydrologic models into physically constrained, interpretable neural networks, evaluated across 513 CAMELS-US basins for snow-water representation.

This paper presents a deep learning approach using a spatio-temporal graph neural network (MTGNN) to reconstruct GRACE terrestrial water storage anomalies back to 1940 for South America, achieving high accuracy and outperforming previous methods with fewer predictors.

Researchers propose a Physics-Informed Machine Learning (PIML) framework that integrates hydrological constraints into an LSTM loss function to improve short-term flood forecasting, particularly in data-scarce regimes. A 'Trend Alignment' constraint enforcing consistency between precipitation and discharge trends improves Nash-Sutcliffe Efficiency and eliminates unphysical predictions during extreme events.

This paper evaluates encoder-only Transformer and LSTM models for streamflow prediction in ungauged basins using NOAA's National Water Model simulations. Results show LSTM outperforms Transformer, and incorporating downstream information significantly improves prediction skill across both architectures.

This paper presents a Bayesian inverse problem framework for rain field reconstruction using Commercial Microwave Links and Diffusion Model priors, demonstrating improved accuracy over existing baselines.