To accurately forecast heat waves and cold spells, Rice University engineers developed a deep learning-based system that can accurately predict extreme weather events up to five days in advance with 85% accuracy.
“When you get these heat waves or cold spells, if you look at the weather map, you are often going to see some weird behavior in the jet stream, abnormal things like large waves or a big high-pressure system that is not moving at all,” said Rice’s Pedram Hassanzadeh. He is the co-author of the system study, along with Ashesh Chattopadhyay and Ebrahim Nabizadeh. The study, Analog forecasting of extreme‐causing weather patterns using deep learning[, was recently published in the American Geophysical Union’s Journal of Advances in Modeling Earth Systems.
Using NVIDIA P100 GPUs at the Comet and Bridge cluster of the San Diego and Pittsburgh supercomputing centers, with the cuDNN-accelerated TensorFlow deep learning framework, the engineers trained their models using historical weather data from 1920 to 2005.
“It seemed like this was a pattern recognition problem. So we decided to try to reformulate extreme weather forecasting as a pattern-recognition problem rather than a numerical problem.”
To do this, the team used both a convolutional neural network (CNN) and a capsule neural network (CapsNet). Unlike CNN’s, CapsNets can recognize relative spatial relationships, which are critical to the evolution of weather patterns.
“The relative positions of pressure patterns, the highs and lows you see on weather maps, are the key factor in determining how the weather evolves,” Hassanzadeh said..
The researchers are hopeful that their system can be used to provide early extreme weather warnings to the public and to identify the precursors of extreme events.
“We are not suggesting that at the end of the day this is going to replace numerical weather predictions (NWP),” Hassanzadeh said. “But this might be a useful guide for NWP. Computationally, this could be a super cheap way to provide some guidance, an early warning, that allows you to focus NWP resources specifically where extreme weather is likely.”