Error growth dynamics and predictability of tropical cyclones in machine‐learning weather prediction models

Abstract

Predictability analysis, which focuses on perturbation growth dynamics, is a key problem in both weather and climate prediction. Among all perturbations, the conditional nonlinear optimal perturbation (CNOP) explores maximum uncertainties in forecasts, which is fundamentally important for theoretical studies and applications. Traditionally, CNOPs are solved through iterative optimization of numerical weather prediction (NWP) systems. Their large computational demands pose significant challenges to long‐term predictability analysis. In our study, using a fast and accurate Artificial Intelligence (AI) model, i.e. FuXi, a low‐cost optimization framework for solving five‐day tropical cyclone (TC) CNOP is developed. For the first time, CNOPs that achieve the optimal (i.e., fastest) nonlinear development of long‐term TC forecast errors are solved, with their optimality and physical explainability verified. Results demonstrate that perturbations with specific spatial structures undergo significant development. In both AI and NWP models, AI‐based CNOPs exhibit rapid and physically consistent error growth across diverse TC cases, faster compared to random and lagged forecast perturbations. Furthermore, sensitivity analysis reveals that far‐environment systems and processes are more crucial for long‐term TC forecasts. Structural analyses of the CNOP emphasize the interactions between TC internal and external processes for rapid perturbation growth. The successful derivation of AI‐based CNOPs, with their rapid growth and physical explainability verified in both AI and NWP models, suggests that AI models can capture the most rapidly growing perturbation patterns and their subsequent nonlinear evolution. Thus, the potential of AI models is highlighted for advancing atmospheric predictability studies, including theoretical analysis, targeting observations and ensemble forecasts.