Improving Convection Trigger Functions in Deep Convective Parameterization Schemes Using Machine Learning

Abstract Deficiencies in convection trigger functions, used in deep convection parameterizations in General Circulation Models (GCMs), have critical impacts on climate simulations. A novel convection trigger function is developed using the machine learning (ML) classification model XGBoost. The larg...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Tao Zhang, Wuyin Lin, Andrew M. Vogelmann, Minghua Zhang, Shaocheng Xie, Yi Qin, Jean‐Christophe Golaz
Formato:	article
Lenguaje:	EN
Publicado:	American Geophysical Union (AGU) 2021
Materias:	Physical geography GB3-5030 Oceanography GC1-1581
Acceso en línea:	https://doaj.org/article/514db131478641698f3c9b4e958b6a6f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:514db131478641698f3c9b4e958b6a6f
record_format	dspace
spelling	oai:doaj.org-article:514db131478641698f3c9b4e958b6a6f2021-11-24T08:11:41ZImproving Convection Trigger Functions in Deep Convective Parameterization Schemes Using Machine Learning1942-246610.1029/2020MS002365https://doaj.org/article/514db131478641698f3c9b4e958b6a6f2021-05-01T00:00:00Zhttps://doi.org/10.1029/2020MS002365https://doaj.org/toc/1942-2466Abstract Deficiencies in convection trigger functions, used in deep convection parameterizations in General Circulation Models (GCMs), have critical impacts on climate simulations. A novel convection trigger function is developed using the machine learning (ML) classification model XGBoost. The large‐scale environmental information associated with convective events is obtained from the long‐term constrained variational analysis forcing data from the Atmospheric Radiation Measurement (ARM) program at its Southern Great Plains (SGP) and Manaus (MAO) sites representing, respectively, continental mid‐latitude and tropical convection. The ML trigger is separately trained and evaluated per site, and jointly trained and evaluated at both sites as a unified trigger. The performance of the ML trigger is compared with four convective trigger functions commonly used in GCMs: dilute convective available potential energy (CAPE), undilute CAPE, dilute dynamic CAPE (dCAPE), and undilute dCAPE. The ML trigger substantially outperforms the four CAPE‐based triggers in terms of the F1 score metric, widely used to estimate the performance of ML methods. The site‐specific ML trigger functions can achieve, respectively, 91% and 93% F1 scores at SGP and MAO. The unified trigger also has a 91% F1 score, with virtually no degradation from the site‐specific training, suggesting the potential of a global ML trigger function. The ML trigger alleviates a GCM deficiency regarding the overprediction of convection occurrence, offering a promising improvement to the simulation of the diurnal cycle of precipitation. Furthermore, to overcome the black box issue of the ML methods, insights derived from the ML model are discussed, which may be leveraged to improve traditional CAPE‐based triggers.Tao ZhangWuyin LinAndrew M. VogelmannMinghua ZhangShaocheng XieYi QinJean‐Christophe GolazAmerican Geophysical Union (AGU)articlePhysical geographyGB3-5030OceanographyGC1-1581ENJournal of Advances in Modeling Earth Systems, Vol 13, Iss 5, Pp n/a-n/a (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Physical geography GB3-5030 Oceanography GC1-1581
spellingShingle	Physical geography GB3-5030 Oceanography GC1-1581 Tao Zhang Wuyin Lin Andrew M. Vogelmann Minghua Zhang Shaocheng Xie Yi Qin Jean‐Christophe Golaz Improving Convection Trigger Functions in Deep Convective Parameterization Schemes Using Machine Learning
description	Abstract Deficiencies in convection trigger functions, used in deep convection parameterizations in General Circulation Models (GCMs), have critical impacts on climate simulations. A novel convection trigger function is developed using the machine learning (ML) classification model XGBoost. The large‐scale environmental information associated with convective events is obtained from the long‐term constrained variational analysis forcing data from the Atmospheric Radiation Measurement (ARM) program at its Southern Great Plains (SGP) and Manaus (MAO) sites representing, respectively, continental mid‐latitude and tropical convection. The ML trigger is separately trained and evaluated per site, and jointly trained and evaluated at both sites as a unified trigger. The performance of the ML trigger is compared with four convective trigger functions commonly used in GCMs: dilute convective available potential energy (CAPE), undilute CAPE, dilute dynamic CAPE (dCAPE), and undilute dCAPE. The ML trigger substantially outperforms the four CAPE‐based triggers in terms of the F1 score metric, widely used to estimate the performance of ML methods. The site‐specific ML trigger functions can achieve, respectively, 91% and 93% F1 scores at SGP and MAO. The unified trigger also has a 91% F1 score, with virtually no degradation from the site‐specific training, suggesting the potential of a global ML trigger function. The ML trigger alleviates a GCM deficiency regarding the overprediction of convection occurrence, offering a promising improvement to the simulation of the diurnal cycle of precipitation. Furthermore, to overcome the black box issue of the ML methods, insights derived from the ML model are discussed, which may be leveraged to improve traditional CAPE‐based triggers.
format	article
author	Tao Zhang Wuyin Lin Andrew M. Vogelmann Minghua Zhang Shaocheng Xie Yi Qin Jean‐Christophe Golaz
author_facet	Tao Zhang Wuyin Lin Andrew M. Vogelmann Minghua Zhang Shaocheng Xie Yi Qin Jean‐Christophe Golaz
author_sort	Tao Zhang
title	Improving Convection Trigger Functions in Deep Convective Parameterization Schemes Using Machine Learning
title_short	Improving Convection Trigger Functions in Deep Convective Parameterization Schemes Using Machine Learning
title_full	Improving Convection Trigger Functions in Deep Convective Parameterization Schemes Using Machine Learning
title_fullStr	Improving Convection Trigger Functions in Deep Convective Parameterization Schemes Using Machine Learning
title_full_unstemmed	Improving Convection Trigger Functions in Deep Convective Parameterization Schemes Using Machine Learning
title_sort	improving convection trigger functions in deep convective parameterization schemes using machine learning
publisher	American Geophysical Union (AGU)
publishDate	2021
url	https://doaj.org/article/514db131478641698f3c9b4e958b6a6f
work_keys_str_mv	AT taozhang improvingconvectiontriggerfunctionsindeepconvectiveparameterizationschemesusingmachinelearning AT wuyinlin improvingconvectiontriggerfunctionsindeepconvectiveparameterizationschemesusingmachinelearning AT andrewmvogelmann improvingconvectiontriggerfunctionsindeepconvectiveparameterizationschemesusingmachinelearning AT minghuazhang improvingconvectiontriggerfunctionsindeepconvectiveparameterizationschemesusingmachinelearning AT shaochengxie improvingconvectiontriggerfunctionsindeepconvectiveparameterizationschemesusingmachinelearning AT yiqin improvingconvectiontriggerfunctionsindeepconvectiveparameterizationschemesusingmachinelearning AT jeanchristophegolaz improvingconvectiontriggerfunctionsindeepconvectiveparameterizationschemesusingmachinelearning
_version_	1718415796914356224

Improving Convection Trigger Functions in Deep Convective Parameterization Schemes Using Machine Learning

Ejemplares similares