气候变化领域集成服务门户(CCPortal): Evaluation of Machine Learning Classifiers for Predicting Deep Convection

CCPortal

DOI	10.1029/2018MS001561
	Evaluation of Machine Learning Classifiers for Predicting Deep Convection
	Ukkonen P.; Mäkelä A.
发表日期	2019
ISSN	19422466
起始页码	1784
结束页码	1802
卷号	11 期号:6
英文摘要	The realistic representation of convection in atmospheric models is paramount for skillful predictions of hazardous weather as well as climate, yet climate models especially suffer from large uncertainties in the parameterization of clouds and convection. In this work, we examine the use of machine learning (ML) to predict the occurrence of deep convection from a state-of-the-art atmospheric reanalysis (ERA5). Logistic regression, random forests, gradient-boosted decision trees, and deep neural networks were trained with lightning data to predict thunderstorm occurrence (TO) in Central and Northern Europe (2012–2017) and in Sri Lanka (2016–2017). Up to 40 input variables were used, representing, for example, instability, humidity, and inhibition. Feature importances derived for the various models emphasize the high importance of conditional instability for deep convection in Europe, while in Sri Lanka, TO is more strongly regulated by humidity. The Precision-Recall curve indicates more than a twofold improvement in skill over convective available potential energy for short-term (0–45 min) predictions of TO in Europe by using neural networks or gradient-boosted decision tree and a larger improvement in the tropical domain. The diurnal cycle of deep convection is closely reproduced, suggesting that ML could be used to trigger convection in climate models. Finally, a strong relationship was found between area-mean monthly TO and ML predictions, with correlation coefficients exceeding 0.94 in all domains. Convective available potential energy has a similar level of correlation with monthly thunderstorm activity only in Northern Europe. The results encourage the use of reanalyses and ML to study climate trends in convective storms. ©2019. The Authors.
英文关键词	convective trigger; deep convection; deep learning; lightning; machine learning; reanalysis
语种	英语
scopus关键词	Atmospheric humidity; Decision trees; Deep learning; Deep neural networks; Forecasting; Learning systems; Lightning; Machine learning; Meteorological problems; Molecular physics; Natural convection; Potential energy; Thunderstorms; Atmospheric reanalysis; Boosted decision trees; Convective available potential energies; convective trigger; Correlation coefficient; Deep convection; Reanalysis; Thunderstorm activity; Climate models; atmospheric correction; classification; cloud cover; convective system; humid environment; lightning; machine learning; parameterization; potential energy; prediction; tropical region; Northern Europe; Sri Lanka
来源期刊	Journal of Advances in Modeling Earth Systems
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/156893
作者单位	Danish Meteorological Institute, Copenhagen, Denmark; Finnish Meteorological Institute, Helsinki, Finland
推荐引用方式 GB/T 7714	Ukkonen P.,Mäkelä A.. Evaluation of Machine Learning Classifiers for Predicting Deep Convection[J],2019,11(6).
APA	Ukkonen P.,&Mäkelä A..(2019).Evaluation of Machine Learning Classifiers for Predicting Deep Convection.Journal of Advances in Modeling Earth Systems,11(6).
MLA	Ukkonen P.,et al."Evaluation of Machine Learning Classifiers for Predicting Deep Convection".Journal of Advances in Modeling Earth Systems 11.6(2019).