Climate change since the 1950s has doubled the amount of time per year that millions of people around the world must endure heat so extreme that everyday physical activities cannot be done safely, a new study concludes. Instead of relying on simple measures of heat danger, the researchers used a modeling approach to estimate how much physical activity people of varying ages could perform in different ranges of heat and humidity without their core body temperature rising uncontrollably. Several areas across the South and Southwestern U.S. show hundreds of hours a year of severe limitations.

Computer scientists and weather scientists have taken the first steps toward creating an AI agent capable of analyzing and answering questions in natural language, such as English, about data from AI-driven weather and climate forecasting models. Recently, models driven by AI and deep learning have considerably improved weather forecasting. But analyzing the resulting data remains difficult and time-consuming. A main issue is that these types of AI models are not able to describe their findings in plain language. A secondary issue is that these models are not able to reason about text information, such as meteorology reports and weather bulletins. The UC San Diego research team aims to address both.

First study to use crowdsourced comments to assess effects of heat underground. Researchers collected comments from X and Google Reviews published between 2008 and 2024. Study focused on subway systems in Boston, New York and London. As above-ground temperatures rise, below-ground thermal complaints increase. Knowing when people are uncomfortable could inform targeted interventions.