Aleksandra Gruca, Federico Serva, Llorenç Lliso, Pilar Rípodas, Xavier Calbet, Pedro Herruzo, Jiřı́ Pihrt, Rudolf Raevskyi, Petr Šimánek, Matej Choma, Yang Li, Haiyu Dong, Yury Belousov, Sergey Polezhaev, Brian Pulfer, Minseok Seo, Doyi Kim, Seungheon Shin, Eunbin Kim, Sewoong Ahn, Yeji Choi, Jinyoung Park, Minseok Son, Seungju Cho, Inyoung Lee, Changick Kim, Taehyeon Kim, Shinhwan Kang, Hyeonjeong Shin, Deukryeol Yoon, Seongha Eom, Kijung Shin, Se-Young Yun, Bertrand Le Saux, Michael K Kopp, Sepp Hochreiter, and David P Kreil
Longitude-latitude maps for the MSG band radiances and OPERA binary mask ground truth (bottom right).
Weather4cast again advanced modern algorithms in AI and machine learning through a highly topical interdisciplinary competition challenge: The prediction of hi-res rain radar movies from multi-band satellite sensors, requiring data fusion, multi-channel video frame prediction, and super-resolution. Accurate predictions of rain events are becoming ever more critical, with climate change increasing the frequency of unexpected rainfall. The resulting models will have a particular impact where costly weather radar is not available. We here present highlights and insights emerging from the thirty teams participating from over a dozen countries.
To extract relevant patterns, models were challenged by spatio-temporal shifts. Geometric data augmentation and test-time ensemble models with a suitable smoother loss helped this transfer learning. Even though, in ablation, static information like geographical location and elevation was not linked to performance, the general success of models incorporating physics in this competition suggests that approaches combining machine learning with application domain knowledge seem a promising avenue for future research.
Weather4cast will continue to explore the powerful benchmark reference data set introduced here, advancing competition tasks to quantitative predictions, and exploring the effects of metric choice on model performance and qualitative prediction properties.
Proceedings of the NeurIPS 2022 Competitions Track, PMLR, 220, 292-313, 2023-09-04.