Researchers from Karlsruhe Institute of Technology (KIT) in Germany have compared methods of statistics and machine learning for forecasts of wind gusts with a view to making predictions of extreme weather phenomena more accurate and reliable.
They found that accounting for geographical information and additional meteorological variables, such as temperature, significantly improves the forecast quality of strong wind gusts, such as squalls with a speed of more than 65km per hour, particularly when using modern AI methods based on neural networks.
Benedikt Schulz, doctoral researcher at KIT’s Institute of Stochastics, said, “Wind gusts are difficult to model, as they are driven by small-scale processes and are locally limited. Their predictability with the numerical weather forecast models used by weather services is limited and subject to uncertainties.”
To better estimate such uncertainties of forecasts, meteorologists make ensemble forecasts. Based on the current state of the atmosphere, they make several model calculations in parallel for slightly different conditions. In this way, various future weather development scenarios are covered.
“In spite of continuous improvements, however, such ensemble weather forecasts still have systematic errors, as local temporally varying conditions cannot be considered by the models,” Schulz said. “With the help of AI, we want to correct these systematic errors, improve the forecasts, and more reliably predict dangerous weather phenomena.”
Working with Schulz, Dr Sebastian Lerch, who heads the junior research group AI Methods for Probabilistic Weather Forecasts funded by the Vector Foundation at KIT’s Institute for Economic Policy Research, compared different statistics and AI methods for the post-processing of ensemble forecasts of wind gusts. “We analyzed both existing and novel methods for statistical post-processing of numerical weather forecasts and systematically compared their forecast qualities,” Lerch said.
All post-processing methods were found to produce reliable forecasts of the speed of wind gusts. “Yet, AI methods are far superior to classical statistical approaches and produce far better results, as they allow for a better consideration of new information sources, such as geographical conditions or other meteorological variables, such as temperature and solar radiation,” said Lerch.
Schulz added, “AI methods reduce the forecast errors of weather models by about 36% on the average.”
The researchers analyzed the forecasts made with the weather model of the German Weather Service (DWD) at 175 observation stations in Germany and found that AI methods produced better forecasts at more than 92% of the stations. Neural networks can learn complex and non-linear relationships from the big data sets available. This plays a central role when correcting systematic errors of ensemble forecasts. “Analysis of which information is particularly relevant to the methods also allows conclusions to be drawn with respect to meteorological processes,” Schulz said.
Through this work, the researchers aim to contribute to the development of weather forecast methods at the interface of statistics and AI. “Weather services might use these methods to improve their forecasts,” Lerch said. “For this, we are in close contact with the German and other international weather services.”
To read more from the original study, click here.
