@article{,
title= {Machine learning-based dynamical seasonal prediction of summer rainfall in China},
journal= {},
author= {Jing Yang; Jialin Wang; Hongli Ren; Jinxiao Li; Qing Bao; Miaoni Gao},
year= {},
url= {},
abstract= {The seasonal prediction of summer rainfall is crucial for regional disaster reduction but currently has a low prediction skill. This study developed a machine learning-based dynamical (MLD) seasonal prediction system for summer rainfall in China based on suitable circulation fields from an operational prediction system named FGOALS-f2. Through choosing optimum hyperparameters for three ML methods to reach the best fitting and the least overfitting, gradient boosting regression trees eventually exhibit the highest prediction skill, obtaining values of 0.33 in the reference training period (1981-2010) and 0.19 in eight individual years (2011-2018) of independent prediction, which significantly improves the current dynamical prediction skill by 300%. Further study suggests that both reducing overfitting and using the best dynamical prediction are imperative in MLD application prospects, which warrants further investigation.},
keywords= {machine learning; seasonal prediction; precipitation prediction; China},
terms= {},
license= {},
superseded= {}
}