Applying Convolutional LSTM Network to Predict El Niño Events: Transfer Learning from The Data of Dynamical Model and Observation
- Resource Type
- Conference
- Authors
- Mu, Bin; Ma, Shaoyang; Yuan, Shijin; Xu, Hui
- Source
- 2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC) Electronics Information and Emergency Communication (ICEIEC), 2020 IEEE 10th International Conference on. :215-219 Jul, 2020
- Subject
- Communication, Networking and Broadcast Technologies
Computing and Processing
Fields, Waves and Electromagnetics
Robotics and Control Systems
Signal Processing and Analysis
Data models
Predictive models
Ocean temperature
Machine learning
Spatiotemporal phenomena
Mathematical model
Sea surface
component
Deep learning
transfer learning
convolutional LSTM
dynamical models
El Niño prediction
- Language
- ISSN
- 2377-844X
Neural network as a statistical method is widely used for weather forecasting. But for the prediction of El Niño grid data, the data record is short. In this paper, we use deep learning to handle spatiotemporal information and transfer learning to transfer knowledge from dynamical model (Zebiak–Cane model) data to the prediction of realistic El Niño. A ConvLSTM (Convolutional Long Short-Term Memory Network) architecture is constructed to predict the grid data of sea surface temperature and thermocline depth at lead times from 3 to 12 months. Cross-validation is used to evaluate the predictions. The entire data record from 1980 to 2018 is divided into 10 groups and used for training and validation. The experiment results show that transfer learning have a positive impact on the El Niño prediction, especially for the strong Eastern-Pacific type. Compared with the predictions of the Zebiak-Cane model, it can be inferred that the role of the model data in transfer learning is greater than the observation data.