• DOI:10.1029/2021GL093704
• Corpus ID: 233024747

A Bayesian Machine Learning Algorithm for Predicting ENSO Using Short Observational Time Series

@article{Chen2021ABM,
  title={A Bayesian Machine Learning Algorithm for Predicting ENSO Using Short Observational Time Series},
  author={Nan Chen and Faheem Gilani and John Harlim},
  journal={Geophysical Research Letters},
  year={2021},
  volume={48}
}

• N. Chen, Faheem Gilani, J. Harlim
• Published 3 April 2021
• Environmental Science, Computer Science
• Geophysical Research Letters

A simple and efficient Bayesian machine learning (BML) training algorithm, which exploits only a 20‐year short observational time series and an approximate prior model, is developed to predict the Niño 3 sea surface temperature (SST) index. The BML forecast significantly outperforms model‐based ensemble predictions and standard machine learning forecasts. Even with a simple feedforward neural network (NN), the BML forecast is skillful for 9.5 months. Remarkably, the BML forecast overcomes the spring predictability barrier to a large extent: the forecast starting from spring remains skillful for nearly 10 months. The BML algorithm can also effectively utilize multiscale features: the BML forecast of SST using SST, thermocline, and windburst improves on the BML forecast using just SST by at least 2 months. Finally, the BML algorithm also reduces the forecast uncertainty of NNs and is robust to input perturbations.