Search papers, labs, and topics across Lattice.
This study investigates the unexpected accuracy of AI weather prediction models compared to traditional physics-based models, revealing that while AI models can backcast skillfully, they systematically underperform in backcasting relative to forecasting. The research identifies that this discrepancy arises from the coarse-graining of training data, which eliminates small-scale dynamics and variables, leading to violations of the second law of thermodynamics and neglect of the butterfly effect. By reducing coarse-graining, the models become more aligned with physical principles, albeit at the cost of forecast accuracy, suggesting that AI models learn to capture large-scale dynamics without the rapid error propagation seen in physical models.
AI weather models can backcast effectively, but their surprising accuracy comes at the cost of physical fidelity, raising questions about the foundations of predictability in climate science.
AI weather prediction (AIWP) models rival physics-based models, yet the sources of their unexpected forecast accuracy and the degree of their physical fidelity remain unclear. Here, across a hierarchy spanning observation-based reanalysis, a general circulation model, and the multi-scale Lorenz system, we show that AI models can be trained to skillfully predict the past (backcast), though backcasts are systematically less accurate than forecasts. However, skillful backcasting appears to violate the second law of thermodynamics, and all these forecasting and backcasting models miss the butterfly effect. We trace the surprising forecast accuracy, missing butterfly, and skillful backcasting to a single cause: inevitable coarse-graining of training data, which removes fast, small scales and/or some variables. From the Lorenz system to official Pangu-Weather models, reducing coarse-graining makes AI predictions more physics-like (arrow of time and butterfly-like effects emerge), but forecast accuracy declines. Results offer an explanation for AIWP models'forecast skill: unlike physics-based models, they implicitly learn how fast, small scales affect large scales without inheriting their rapid error growth. Broader implications are that AI models'proliferation calls for revisiting predictability theories and long-term climate emulation strategies, and backcasting offers a useful, new lens for such analyses.
