Zhuoya Qin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhuoya Qin has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Lianjie Qin
School of Safety Science, Tsinghua University, Beijing, 100084, China
1 shared publication Lin Wan
School of Computer Science China University of Geosciences Wuhan China
1 shared publication- Linshu Hu
School of the Earth Sciences, Zhejiang University, Hangzhou, China
1 shared publication - Mengjiao Qin
School of Earth Sciences Zhejiang University Hangzhou China
1 shared publication - Sensen Wu
Zhejiang University
1 shared publication Wenting Cao
State Key Laboratory of Satellite Ocean Environment Dynamics Second Institute of Oceanography Ministry of Natural Resources Hangzhou China
1 shared publication
Latest Publications
- Open Access
- 23 August 2023
- Published by American Geophysical Union (AGU) in Geophysical Research Letters
- Vol. 50 (16)
Pacific Decadal Oscillation Forecasting With Spatiotemporal Embedding Network
The Pacific decadal oscillation (PDO) is a decadal variability phenomenon occurring in the North Pacific Ocean. It has substantial impacts on marine ecosystems and the global climate. Due to the high complexity and unclear evolution mechanism, the accurate long‐term prediction of PDO remains a challenge. In this paper, a deep spatiotemporal embedding network (DSEN) is proposed to extract the spatiotemporal features from historical climate data and achieve end‐to‐end forecasting of the PDO index. The spatiotemporal features are recursive in the continuous forecasting of the PDO index on seasonal time scales, thus the cumulative error is largely reduced. During the test period of 39 years (1982–2020), our model can skillfully predict the PDO index up to 1 year, outperforming six methods used as benchmark. By contrast with physically‐based methods, DSEN can accurately predict the PDO index from a data‐driven perspective.
- 23 August 2023
- Published by American Geophysical Union (AGU) in Geophysical Research Letters
- Vol. 50 (16)
Open AccessPacific Decadal Oscillation Forecasting With Spatiotemporal Embedding Network
The Pacific decadal oscillation (PDO) is a decadal variability phenomenon occurring in the North Pacific Ocean. It has substantial impacts on marine ecosystems and the global climate. Due to the high complexity and unclear evolution mechanism, the accurate long‐term prediction of PDO remains a challenge. In this paper, a deep spatiotemporal embedding network (DSEN) is proposed to extract the spatiotemporal features from historical climate data and achieve end‐to‐end forecasting of the PDO index. The spatiotemporal features are recursive in the continuous forecasting of the PDO index on seasonal time scales, thus the cumulative error is largely reduced. During the test period of 39 years (1982–2020), our model can skillfully predict the PDO index up to 1 year, outperforming six methods used as benchmark. By contrast with physically‐based methods, DSEN can accurately predict the PDO index from a data‐driven perspective.