Traditional models still ‘outperform AI’ for extreme weather forecasts
A new study finds that AI climate models underperform traditional models in forecasting record-breaking extreme weather events. The authors tested both AI and traditional weather models on thousands of record-breaking hot, cold, and windy events recorded in 2018 and 2020.
A study published in Science Advances compared the performance of AI and traditional climate models in forecasting extreme weather events. The authors tested both models on thousands of record-breaking hot, cold, and windy events recorded in 2018 and 2020. They found that AI models underestimated the frequency and intensity of these events. Traditional models, which rely on complex equations rooted in fundamental laws of physics, outperformed AI models. The study's findings serve as a warning against replacing traditional models with AI models for weather forecasting too quickly. AI models use a statistical approach and require less computing power than traditional models.
This content was automatically generated and/or translated by AI. It may contain inaccuracies. Please refer to the original sources for verification.