The Colorado River's flow projections already looked bleak as March began. A regional heatwave has worsened them.

New research reveals that "foundation models" trained on vast, general time-series data may be able to forecast river flows accurately, even in regions with little or no local hydrological records.

New paired studies from the University of Minnesota Twin Cities show that machine learning can improve the prediction of floods. The studies, published in Water Resources Research and the Proceedings ...