This award supports a summer workshop for graduate students and early-career scientists that combines lectures with hands-on small groups research projects in hackathon-style format. The workshop addresses the growing need for more accurate forecasts of conditions that affect daily life, from severe storms to heat waves to long-term shifts in weather patterns. Reliable forecasts across a wide range of time scales are essential for protecting life and property, and supporting preparedness and planning. By bringing together emerging researchers, the workshop also helps build the skilled workforce needed to advance forecasting science. The theme of this year's workshop is understanding the Earth systems across scales, motivated by the need for better predictions of weather phenomena. Participants will explore several key challenges, including why forecasts often lose accuracy in the period between about two weeks and one month; how interactions across scales, from local weather systems to broader environmental patterns, can be better represented in forecast models; and how recent advances in artificial intelligence and machine-learning approaches are enabling new forecasting systems that can match or even surpass the performance of traditional models. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.