Making the Black Box More Transparent: Understanding the Physical Implications of Machine Learning

McGovern, Amy; Lagerquist, Ryan; Gagne, David John; Jergensen, G. Eli; Elmore, Kimberly L.; Homeyer, Cameron R.; Smith, Travis M.

doi:10.1175/bams-d-18-0195.1

articleBulletin of the American Meteorological SocietyAug 22, 2019BRONZE OA

Making the Black Box More Transparent: Understanding the Physical Implications of Machine Learning

AMAmy McGovern RLRyan Lagerquist DJDavid John Gagne GEG. Eli Jergensen KLKimberly L. Elmore

NSF National Center for Atmospheric Research · Cooperative Institute for Mesoscale Meteorological Studies · +2 more institutions

Indexed incrossref

Abstract

Abstract This paper synthesizes multiple methods for machine learning (ML) model interpretation and visualization (MIV) focusing on meteorological applications. ML has recently exploded in popularity in many fields, including meteorology. Although ML has been successful in meteorology, it has not been as widely accepted, primarily due to the perception that ML models are “black boxes,” meaning the ML methods are thought to take inputs and provide outputs but not to yield physically interpretable information to the user. This paper introduces and demonstrates multiple MIV techniques for both traditional ML and deep learning, to enable meteorologists to understand what ML models have learned. We discuss…

Citation impact

545

total citations

FWCI: 29.58
Percentile: 100%
References: 121

Citations per year

Authors

7

Topics & keywords

Topics

Keywords

Computer science
Visualization
Artificial intelligence
Novelty
Machine learning
Toolbox
Black box
Class (philosophy)

UN Sustainable Development Goals

Climate action

No related works found for this paper.