Deep Learning for Multi‐Timescales Pacific Decadal Oscillation Forecasting

Variations in the Pacific decadal oscillation (PDO) can influence marine ecosystems and regional climate phenomena. Accurate long-term forecasts of PDO are therefore crucial for governance. This paper presents a novel seasonal gated recurrent unit (SGRU) model, based on deep learning, forecasting at multiple time scales. The model first decomposes complex nonlinear index series into three separate components, each retaining distinct pattern PDO. Next, three-pathway GRU is constructed to forecast index. A test applying SGRU period from 1979 2020 demonstrates its superiority over eight state-of-the-art models forecasting. Additionally, flexibly produce high-performance In view that physical dynamical rely clear evolutionary mechanisms, overcomes complexities these models.