Axial Attention & MetNet: A Neural Weather Model for Precipitation Forecasting

MetNet is a predictive neural network model for weather prediction. It uses axial attention to capture long-range dependencies. Axial attention decomposes attention layers over images into row-attention and column-attention in order to save memory and computation. https://ift.tt/2ybtXIp https://ift.tt/36be9RR Abstract: Weather forecasting is a long standing scientific challenge with direct social and economic impact. The task is suitable for deep neural networks due to vast amounts of continuously collected data and a rich spatial and temporal structure that presents long range dependencies. We introduce MetNet, a neural network that forecasts precipitation up to 8 hours into the future at the high spatial resolution of 1 km2 and at the temporal resolution of 2 minutes with a latency in the order of seconds. MetNet takes as input radar and satellite data and forecast lead time and produces a probabilistic precipitation map. The architecture uses axial self-attention to aggregate the global context from a large input patch corresponding to a million square kilometers. We evaluate the performance of MetNet at various precipitation thresholds and find that MetNet outperforms Numerical Weather Prediction at forecasts of up to 7 to 8 hours on the scale of the continental United States. Authors: Casper Kaae Sønderby, Lasse Espeholt, Jonathan Heek, Mostafa Dehghani, Avital Oliver,Tim Salimans, Shreya Agrawal, Jason Hickey, Nal Kalchbrenner Links: YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher BitChute: https://ift.tt/38iX6OV Minds: https://ift.tt/37igBpB