Improving Convection Trigger Functions in Deep Convective Parameterization Schemes Using Machine Learning
Open Access
- 12 May 2021
- journal article
- research article
- Published by American Geophysical Union (AGU) in Journal of Advances in Modeling Earth Systems
- Vol. 13 (5)
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 theF1 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.Keywords
Funding Information
- U.S. Department of Energy (DE‐SC0012704)
- U.S. Department of Energy (DE‐AC52‐07NA27344)
This publication has 66 references indexed in Scilit:
- The Impact of Convection on ENSO: From a Delayed Oscillator to a Series of EventsJournal of Climate, 2008
- Impact of a revised convective triggering mechanism on Community Atmosphere Model, Version 2, simulations: Results from short‐range weather forecastsJournal of Geophysical Research: Atmospheres, 2004
- A Multiple Resampling Method for Learning from Imbalanced Data SetsComputational Intelligence, 2004
- Developing long‐term single‐column model/cloud system–resolving model forcing data using numerical weather prediction products constrained by surface and top of the atmosphere observationsJournal of Geophysical Research: Atmospheres, 2004
- Boundary layer control on convective available potential energy: Implications for cumulus parameterizationJournal of Geophysical Research: Atmospheres, 2003
- The Changing Character of PrecipitationBulletin of the American Meteorological Society, 2003
- A mass‐flux convection scheme for regional and global modelsQuarterly Journal of the Royal Meteorological Society, 2001
- Objective Analysis of ARM IOP Data: Method and SensitivityMonthly Weather Review, 2001
- Impact of the convection triggering function on single‐column model simulationsJournal of Geophysical Research: Atmospheres, 2000
- A non-classical logic for information retrievalThe Computer Journal, 1986