LATIDIA · Investigación

Una nueva investigación podría dar lugar a modelos de IA más rápidos y fiables para la predicción climática

Unos científicos del MIT desarrollaron un método de entrenamiento para generar modelos que simulan los efectos de las actividades humanas sobre el clima mucho más rápidamente que otros enfoques.

La noticia

Accurate, up-to-date climate projections are essential for planning decisions that enhance the resilience of power grids, protect public health, maximize agricultural yields, and more. Now, MIT researchers have developed a technique that streamlines the production of fast, trustworthy, and adaptable artificial intelligence models for climate prediction. These specialized AI models, known as climate emulators, can rapidly simulate the effects of human activities onto a future climate, predicting impacts on temperatures or sea level, for example. Because emulators run in a matter of seconds, scientists use them to efficiently test thousands of varied climate scenarios. This provides more reliable estimates and can identify unexpected outcomes of regional interventions. The MIT researchers