Guo Zijie, Lyu Pumeng, Ling Fenghua, Bai Lei, Luo Jing-Jia, Boers Niklas, Yamagata Toshio, Izumo Takeshi, Cravatte Sophie, Capotondi Antonietta, Ouyang Wanli
School of Computer Science, Fudan University, Shanghai, China.
Shanghai Artificial Intelligence Laboratory, Shanghai, China.
Sci Adv. 2025 Aug 15;11(33):eadu2488. doi: 10.1126/sciadv.adu2488. Epub 2025 Aug 13.
Accurate modeling of ocean dynamics is crucial for enhancing our understanding of complex ocean circulation processes, predicting climate variability, and tackling challenges posed by climate change. Although great efforts have been made to improve traditional numerical models, predicting global ocean variability over multiyear scales remains challenging. Here, we propose ORCA-DL (Oceanic Reliable foreCAst via Deep Learning), a data-driven three-dimensional ocean model for seasonal to decadal prediction of global ocean dynamics. ORCA-DL accurately simulates the three-dimensional structure of global ocean dynamics with high physical consistency and outperforms state-of-the-art numerical models in capturing extreme events, including El Niño-Southern Oscillation and upper ocean heat waves. Moreover, ORCA-DL stably emulates ocean dynamics at decadal timescales, demonstrating its potential even for skillful decadal predictions and climate projections. Our results demonstrate the high potential of data-driven models for providing efficient and accurate global ocean modeling and prediction.
准确模拟海洋动力学对于增进我们对复杂海洋环流过程的理解、预测气候变率以及应对气候变化带来的挑战至关重要。尽管人们已付出巨大努力来改进传统数值模型，但预测多年尺度上的全球海洋变率仍然具有挑战性。在此，我们提出了ORCA-DL（通过深度学习实现的海洋可靠预测），这是一种基于数据驱动的三维海洋模型，用于对全球海洋动力学进行季节到年代际预测。ORCA-DL以高度的物理一致性准确模拟全球海洋动力学的三维结构，并且在捕捉极端事件（包括厄尔尼诺-南方涛动和上层海洋热浪）方面优于当前最先进的数值模型。此外，ORCA-DL在年代际时间尺度上稳定地模拟海洋动力学，这表明其甚至在进行有效的年代际预测和气候预测方面也具有潜力。我们的结果证明了数据驱动模型在提供高效且准确的全球海洋建模和预测方面具有很高的潜力。
