EGU General Assembly 2020
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

Forecasting North America Winter Surface Air Temperature Using Machine Learning Methods

Qifeng Qian1, Xiaojing Jia1, and Hai Lin2
Qifeng Qian et al.
  • 1Zhejiang University, School of Earth Science, Department of Atmospheric Science, Hangzhou, China
  • 2Recherche en prévision numérique atmosphérique, Environment and Climate Change Canada

Two machine learning (ML) models (Support Vector Regression and Extreme Gradient Boosting; SVR and XGBoost hereafter) have been developed to perform seasonal forecast for the winter (December–January–February, DJF) surface air temperature (SAT) in North America (NA) in this study. The seasonal forecast skills of the two ML models are evaluated in a cross-validated fashion. Forecast results from one Linear Regression (LR and hereafter) model and two Canadian dynamic climate models are used for the purpose of a comparison. In the take-one-out hindcast experiment, the two ML models and the LR model show reasonable seasonal forecast skills for the winter SAT in NA. Comparing to the two Canadian dynamic models, the two ML models and the LR model have better forecast skill for the winter SAT over the central NA which mainly get contribution of a skillful forecast of the second Empirical Orthogonal Function (EOF) mode of winter SAT over NA. In general, the SVR model and XGBoost model hindcasts show better forecast performances than LR model. However, the LR model shows less dependence on the size of the training dataset than SVR and XGBoost models. In the real forecast experiments during the period 2011-2017, compared to the two Canadian dynamic climate models, the two ML models clearly improve the forecast skill of winter SAT over northern and central NA. The results of this study suggest that ML models may provide real-time supplementary forecast tools to improve the forecast skill and may operationally facilitate the seasonal forecast of the winter climate of NA. 

How to cite: Qian, Q., Jia, X., and Lin, H.: Forecasting North America Winter Surface Air Temperature Using Machine Learning Methods, EGU General Assembly 2020, Online, 4–8 May 2020, EGU2020-4465,, 2020