A new machine learning tool can reduce errors in national flood prediction programing, resulting in more accurate predictions of where floods will occur.  In a new study published in AGU Advances, scientists found that when the AI was used in combination with the National Water Model, developed by the U.S. National Oceanic and Atmospheric Administration, the resulting hybrid model was four to six times more accurate.

Chapman University researchers, in collaboration with the U.S. Forest Service and others, published a study in Nature Communications showing that warming tropical rainforest soils release vast amounts of carbon dioxide, potentially accelerating climate change. In Puerto Rico, experimentally heated plots showed a 42–204% increase in soil respiration, among the highest CO₂ release rates ever recorded. The findings suggest that instead of acting as carbon sinks, tropical soils could become major carbon sources, intensifying global warming. Chapman’s Dr. Christine Sierra O’Connell co-led the research as part of the TRACE project.