<ul><li>The paper discusses the use of AI models in meteorology to improve accuracy compared to traditional methods.</li><li>Meteorological data is transformed into 2D images or 3D videos and fed into AI models for learning.</li><li>Physical signals such as temperature, pressure, and wind speed are incorporated into the models to enhance accuracy and interpretability.</li><li>A new paradigm is proposed where multimodal data is integrated via transformers, with the ability to incorporate weather and climate knowledge.</li></ul>

A Physics-guided Multimodal Transformer Path to Weather and Climate Sciences

Discover more