In this week’s Physics of Fluids, researchers employ machine learning to more accurately model the boundary layer wind field of tropical cyclones. Conventional approaches to storm forecasting involve large numerical simulations run on supercomputers incorporating mountains of observational data, and they still often result in inaccurate or incomplete predictions. In contrast, the author’s machine learning algorithm is equipped with atmospheric physics equations that can produce more accurate results faster and with less data.

In this week’s Physics of Fluids, researchers study how Champatis roll and bounce down inclines. The authors released a heap of the seeds down an inclined plane while a camera recorded their descent to analyze their speed and the dynamics of their movement. The grains start to spread out slowly, then decrease quickly as they move downstream, akin to rock avalanches. This research may provide valuable insights into geological flows, including hyperspreading of rock avalanches, and could contribute to resolving challenges in this area.