Cloud Spices: How a Neural Network Improves Climate ⚡ экспресс
Original: "Representing Subgrid-Scale Cloud Effects in a Radiation Parameterization using Machine Learning: MLe-radiation v1.0"
A hybrid AI method is 4–10 times more accurate at predicting clouds' impact on planetary heating.
Links in the knowledge graph 1
Conventional climate models poorly account for small clouds. Researchers trained artificial intelligence on ultra-detailed simulations so it could accurately predict how clouds heat or cool the air. A hybrid of physical laws and neural networks reduced errors by 4–10 times and paved the way for more reliable climate forecasts.
🎯 In climate models, a typical grid cell is 50×100 km, while a cloud is just hundreds of meters. Stuffing a whole 'jumble' of clouds into one cell—that's where creativity was needed.
🎬 Computer-controlled climate management is a familiar sci-fi theme: in Kim Stanley Robinson's novel 'Red Mars', the heroes terraform Mars by calculating every degree.