Improving the Accuracy of Subseasonal Forecasting of China Precipitation With a Machine Learning Approach

Precipitation change, which is closely related to drought and flood disasters in China, affects billions of people every year, and the demand for subseasonal forecasting of precipitation is even more urgent. Subseasonal forecasting, which is more difficult than weather forecasting, however, has remained as a blank area in meteorological service for a long period of time. In order to improve the accuracy of subseasonal forecasting of China precipitation, this work introduces the machine learning method proposed by Hwang et al.in 2019 to predict the precipitation in China two to six weeks in advance. The authors use a nonlinear regression model called Local Linear Regression together with Multitask Feature Selection (MultiLLR) model, and choose 21 meteorological elements as candidate predictors to integrate diverse meteorological observation data. This method automatically eliminates irrelevant predictors so as to establish the forecast equations by using multitask feature selection process. Our experiments demonstrate that the pressure and MJO are the most important physical factors. The average prediction skill is 0.11 during 2011-2016 period and there are seasonal differences in forecasting skills, evidenced by that higher forecast skills of winter and spring seasons than summer and autumn seasons. The proposed method can provide effective and indicative guidance for the subseasonal prediction of precipitation in China. By adding another three factors, Arctic Oscillation (AO) index, western North Pacific monsoon (WNPM) index and western North Pacific subtropical high (WNPSH) index into the MultiLLR model, the authors find that AO can improve the forecast skill of China precipitation to the maximum extent from 0.11 to 0.13, followed by WNPSH. Moreover, the ensemble skill of our model and CFSv2 could improve CFSv2 subseasonal forecast skill of China precipitation by nearly 40%. This work shows that our subseasonal prediction of China precipitation should be benefited from the MultiLLR model.