A Deep Learning Algorithm of Neural Network for the Parameterization of Typhoon‐Ocean Feedback in Typhoon Forecast Models

TLDR

Existing SSTC algorithms struggle to accurately predict typhoon‑induced sea surface temperature cooling because they rely on historical data rather than the target typhoon itself. This study proposes two machine‑learning neural‑network algorithms—shallow and deep—to supply flow‑dependent SSTC to atmosphere‑only typhoon forecast models and enhance prediction accuracy. The shallow model uses a single‑layer network combining atmospheric and oceanic factors, while the deep model employs a 4 × 5 neuron matrix with separate layers for atmospheric and oceanic inputs, allowing the network to learn their distinct contributions to SSTC. The shallow model fails to capture the physics, producing unstable SSTC patterns, whereas the deep model yields a stable crescent‑shaped SSTC distribution and reduces maximum wind‑intensity errors by 60–70 % in four case‑study simulations compared to atmosphere‑only runs.

Abstract

Abstract Two algorithms based on machine learning neural networks are proposed—the shallow learning (S‐L) and deep learning (D‐L) algorithms—that can potentially be used in atmosphere‐only typhoon forecast models to provide flow‐dependent typhoon‐induced sea surface temperature cooling (SSTC) for improving typhoon predictions. The major challenge of existing SSTC algorithms in forecast models is how to accurately predict SSTC induced by an upcoming typhoon, which requires information not only from historical data but more importantly also from the target typhoon itself. The S‐L algorithm composes of a single layer of neurons with mixed atmospheric and oceanic factors. Such a structure is found to be unable to represent correctly the physical typhoon‐ocean interaction. It tends to produce an unstable SSTC distribution, for which any perturbations may lead to changes in both SSTC pattern and strength. The D‐L algorithm extends the neural network to a 4 × 5 neuron matrix with atmospheric and oceanic factors being separated in different layers of neurons, so that the machine learning can determine the roles of atmospheric and oceanic factors in shaping the SSTC. Therefore, it produces a stable crescent‐shaped SSTC distribution, with its large‐scale pattern determined mainly by atmospheric factors (e.g., winds) and small‐scale features by oceanic factors (e.g., eddies). Sensitivity experiments reveal that the D‐L algorithms improve maximum wind intensity errors by 60–70% for four case study simulations, compared to their atmosphere‐only model runs.