High-resolution nowcasting is an essential tool needed for effective adaptation to climate change, particularly for extreme weather. As Deep Learning (DL) techniques have shown dramatic promise in many domains, including the geosciences, we present an application of DL to the problem of precipitation nowcasting, i.e., high-resolution (1 km x 1 km) short-term (1 hour) predictions of precipitation. We treat forecasting as an image-to-image translation problem and leverage the power of the ubiquitous UNET convolutional neural network. We find this performs favorably when compared to three commonly used models: optical flow, persistence and NOAA's numerical one-hour HRRR nowcasting prediction.
%0 Generic
%1 agrawal_machine_2019
%A Agrawal, Shreya
%A Barrington, Luke
%A Bromberg, Carla
%A Burge, John
%A Gazen, Cenk
%A Hickey, Jason
%D 2019
%I arXiv
%K - Computer Learning Learning, Machine Pattern Recognition, Science Statistics Vision and ecomodelling
%R 10.48550/arXiv.1912.12132
%T Machine Learning for Precipitation Nowcasting from Radar Images
%U http://arxiv.org/abs/1912.12132
%X High-resolution nowcasting is an essential tool needed for effective adaptation to climate change, particularly for extreme weather. As Deep Learning (DL) techniques have shown dramatic promise in many domains, including the geosciences, we present an application of DL to the problem of precipitation nowcasting, i.e., high-resolution (1 km x 1 km) short-term (1 hour) predictions of precipitation. We treat forecasting as an image-to-image translation problem and leverage the power of the ubiquitous UNET convolutional neural network. We find this performs favorably when compared to three commonly used models: optical flow, persistence and NOAA's numerical one-hour HRRR nowcasting prediction.
@misc{agrawal_machine_2019,
abstract = {High-resolution nowcasting is an essential tool needed for effective adaptation to climate change, particularly for extreme weather. As Deep Learning (DL) techniques have shown dramatic promise in many domains, including the geosciences, we present an application of DL to the problem of precipitation nowcasting, i.e., high-resolution (1 km x 1 km) short-term (1 hour) predictions of precipitation. We treat forecasting as an image-to-image translation problem and leverage the power of the ubiquitous UNET convolutional neural network. We find this performs favorably when compared to three commonly used models: optical flow, persistence and NOAA's numerical one-hour HRRR nowcasting prediction.},
added-at = {2023-07-31T08:05:54.000+0200},
author = {Agrawal, Shreya and Barrington, Luke and Bromberg, Carla and Burge, John and Gazen, Cenk and Hickey, Jason},
biburl = {https://www.bibsonomy.org/bibtex/2ff6af76bc03f031d160d62dd1b1ef135/jascal_panetzky},
doi = {10.48550/arXiv.1912.12132},
file = {arXiv Fulltext PDF:/Users/pascal/Zotero/storage/5BNH72LN/Agrawal et al. - 2019 - Machine Learning for Precipitation Nowcasting from.pdf:application/pdf;arXiv.org Snapshot:/Users/pascal/Zotero/storage/6TYSIDR2/1912.html:text/html},
interhash = {eacb27493c04f65865a65f986073caf5},
intrahash = {ff6af76bc03f031d160d62dd1b1ef135},
keywords = {- Computer Learning Learning, Machine Pattern Recognition, Science Statistics Vision and ecomodelling},
month = dec,
note = {arXiv:1912.12132 [cs, stat]},
publisher = {arXiv},
timestamp = {2023-07-31T08:07:14.000+0200},
title = {Machine {Learning} for {Precipitation} {Nowcasting} from {Radar} {Images}},
url = {http://arxiv.org/abs/1912.12132},
urldate = {2023-07-11},
year = 2019
}