Analog forecasting of extreme-causing weather patterns using deep learning

This is a Preprint and has not been peer reviewed. The published version of this Preprint is available: This is version 1 of this Preprint.


Download Preprint

Supplementary Files

Ashesh Chattopadhyay, Pedram Hassanzadeh, Ebrahim Nabizadeh 


Numerical weather prediction (NWP) models require ever-growing computing time/resources, but still, have difficulties with predicting weather extremes. Here we introduce a data-driven framework that is based on analog forecasting (prediction using past similar patterns) and employs a novel deep learning pattern-recognition technique (capsule neural networks, CapsNets) and impact-based auto-labeling strategy. CapsNets are trained on mid-tropospheric large-scale circulation patterns (Z500) labeled $0-4$ depending on the existence and geographical region of surface temperature extremes over North America several days ahead. The trained networks predict the occurrence/region of cold or heat waves, only using Z500, with accuracies (recalls) of $69\%-45\%$ $(77\%-48\%)$ or $62\%-41\%$ $(73\%-47\%)$ $1-5$ days ahead. CapsNets outperform simpler techniques such as convolutional neural networks and logistic regression. Using both temperature and Z500, accuracies (recalls) with CapsNets increase to $\sim 80\%$ $(88\%)$, showing the promises of multi-modal data-driven frameworks for accurate/fast extreme weather predictions, which can augment NWP efforts in providing early warnings.



Artificial Intelligence and Robotics, Atmospheric Sciences, Computational Engineering, Computer Sciences, Engineering, Oceanography and Atmospheric Sciences and Meteorology, Physical Sciences and Mathematics


fluid dynamics, Deep learning, Climate modeling, Atmospheric Science, analog forecasting, artificial intelliegence, capsule neural networks, extreme weather events, numerical weather prediction


Published: 2019-07-31 08:39


GNU Lesser General Public License (LGPL) 2.1

Add a Comment

You must log in to post a comment.


There are no comments or no comments have been made public for this article.