Cloud Spices: How a Neural Network Improves Climate ⚡ экспресс
The method reduces uncertainties in radiative emulators linked to sub-grid clouds by training ML on data from a storm-resolving model (5 km). Simulations are coarsened to the resolution of typical Earth system models, yielding heating rates that implicitly include the effect of small clouds without prior assumptions. The cloud contribution is isolated as the difference between total and clear-sky fluxes; ML is trained only on this. The clear-sky component is computed physically, making the scheme sensitive to greenhouse gases and aerosols. Applied to coarsened data, the hybrid solution cuts heating errors by 4–10 times compared to traditional coarse schemes, showing promise for next-generation models.
Climate forecasting is like a complex recipe: one wrong pinch and the whole dish is ruined. So it is with clouds — small but decisive. Climate models divide the sky into 50–100 km cells and don't see individual clouds. It's like throwing pepper by the handful when the recipe calls for a pinch.
Scientists trained a neural network on detailed calculations where clouds are visible down to the smallest details. It learned to predict the part of solar heat that depends on clouds. Cloud-free skies are still computed with physics — so the method doesn't become outdated at any level of CO₂ and solar activity. Errors shrank by a factor of 4–10.
An unexpected twist: the neural network never actually sees the clouds. It works with large cells but captures their hidden influence. A microscopic detail governs the global picture.
🎯 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.