“It doesn't seem like MetNet outputs a complete 3D atmospheric state, just specific (and mostly surface-level) forecast predictands [1]. The analysis you're describing could be done with a traditional numerical weather prediction and data assimilation system (especially if that system implements 4DVar, since you'll already have the model adjoint available …”
Deep Learning for Day Forecasts from Sparse Observations
Deep neural networks offer an alternative paradigm for modeling weather conditions. The ability of neural models to make a prediction in less than a second once the data is available and to do so with very high temporal and spatial resolution, and the ability to learn directly from atmospheric observations, are just some of these models' unique advantages. Neural models trained using atmospheric observations, the highest fidelity and lowest latency data, have to date achieved good performance only up to twelve hours of lead time when compared with state-of-the-art probabilistic Numerical Weather Prediction models and only for the sole variable of precipitation. In this paper, we present MetNet-3 that extends significantly both the lead time range and the variables that an observation based neural model can predict well. MetNet-3 learns from both dense and sparse data sensors and makes predictions up to 24 hours ahead for precipitation, wind, temperature and dew point. MetNet-3 introduces a key densification technique that implicitly captures data assimilation and produces spatially dense forecasts in spite of the network training on extremely sparse targets. MetNet-3 has a high temporal and spatial resolution of, respectively, up to 2 minutes and 1 km as well as a low operational latency. We find that MetNet-3 is able to outperform the best single- and multi-member NWPs such as HRRR and ENS over the CONUS region for up to 24 hours ahead setting a new performance milestone for observation based neural models. MetNet-3 is operational and its forecasts are served in Google Search in conjunction with other models.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“When it comes to medium range predictions. If you look at nowcasting, I believe the top dog is metnet 3 (https://arxiv.org/abs/2306.06079). On a tangential note, I worked on weather forecasting a bit before, and talking with some people still in the field it seems that these organizations (NOAA, ECMWF) are stuck with NWP and refuse to embrace AI models. …”
“> When it comes to medium range predictions. If you look at nowcasting, I believe the top dog is metnet 3 (https://arxiv.org/abs/2306.06079). I don't consider 24 hour forecasts "medium range". And I don't really view MetNet-3 a competitor to GFS or ECMWF at all (currently).”