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

Abstract

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. 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 2–6 weeks in advance. The authors used a non-linear regression model called local linear regression together with multitask feature election (MultiLLR) model and chosen 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 using multitask feature selection process. The experiments demonstrate that the pressure and Madden–Julian Oscillation (MJO) are the most important physical factors. The average prediction skill is 0.11 during 2011–2016, and there are seasonal differences in forecasting skills, evidenced by 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 is 0.16. This work shows that our subseasonal prediction of China precipitation should be benefited from the MultiLLR model.

A comparative study of extensive machine learning models for predicting long‐term monthly rainfall with an ensemble of climatic and meteorological predictors

“…Compared with previous studies, the lagged relationship between climatic phenomena and rainfall in the East China region is addressed in this study. In future research, more climatic variables (Ouyang et al, 2014a; Tang et al, 2021; Wang et al, 2021) can be considered in the rainfall prediction to explore their relative importance in this region.…”

A Stacking Ensemble Learning Model for Monthly Rainfall Prediction in the Taihu Basin, China

“…The sea level pressure (SLP) in the Indian Ocean is relevant to rainfall in the study region [42]. The meridional wind at 850 mb (V-wind) is commonly used as the large-scale atmospheric predictor for rainfall in varying regions [5,[43][44][45]. Correlation coefficient between the large-scale atmospheric variables and rainfall was used to select the spatial grid and the lag month of the large-scale atmospheric variables.…”

Learned Benchmarks for Subseasonal Forecasting

“…The MultiLLR model of Hwang et al (2019) was also part of a winning solution in the Subseasonal Climate Forecast Rodeo I (Nowak et al, 2020) and has since been used to improve subseasonal precipitation prediction in China (Wang et al, 2021). For each target date, MultiLLR uses a customized backward stepwise procedure to select SubseasonalClimateUSA features relevant for prediction and local linear regression to combine those features into a forecast for each grid point.…”

“…Indeed, subseasonal forecasting has long been considered a "predictability desert" due to its complex dependence on both local weather and global climate variables (Vitart et al, 2012). Nevertheless, recent large-scale research efforts have advanced the subseasonal capabilities of operational physics-based models (Vitart et al, 2017;Pegion et al, 2019;Lang et al, 2020), while parallel efforts have demonstrated the value of machine learning and deep learning methods in improving subseasonal forecasting (Li et al, 2016;Cohen et al, 2018;Hwang et al, 2019;Arcomano et al, 2020;He et al, 2020;Yamagami & Matsueda, 2020;Wang et al, 2021;Watson-Parris, 2021;Weyn et al, 2021;Srinivasan et al, 2021).…”