(WUTR/WFXV/WPNY) – Researchers at the Pacific Northwest National Laboratory have recently developed a new model that aids in predicting hurricane intensity. It’s one of several models that are used to track hurricane movement and intensity. Although this model will be using the same data that other models use, it differs in its use of “neural networks”. PNNL data scientist Wenwei Xu explains this network as a system of artificial neurons that mimic the computation of the human brain, empowering the model to make predictions.

When experimenting with the model’s accuracy, the PNNL research team conducted tests to simulate a real-time forecast. They first trained the new model by providing climate data from past hurricanes, up to 2018. The model then formed predictions for years 2019 and 2020 based on what it had learned from the past data. The researchers compared the new model’s predictions against other forecasting models used at the national level by tallying up each model’s prediction errors.

The new model reduced intensity prediction errors by as much as 22% when compared to conventional models. “Even a five percent improvement is a big deal,” said PNNL Earth scientist Karthik Balaguru. He added that on average, the magnitude of error is reduced in conventional hurricane models by roughly one percent each year. The new technique also correctly predicted more instances of rapid intensification than the comparison models. 

The new model also uses significantly less computing power than many other models. It can even run on a standard laptop, bringing access to those who don’t work with high-performance computers.