Classification of GLM Flashes Using Random Forests

Abstract [The Geostationary Lightning Mapper (GLM) detects total lightning continuously from space, and does not distinguish intra‐cloud (IC) from cloud‐to‐ground (CG) lightning. This research focuses on differentiating CG and IC lightning detected by GLM using a random forests (RF) model. GLM flash...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jacquelyn Ringhausen, Phillip Bitzer, William Koshak, John Mecikalski
Formato:	article
Lenguaje:	EN
Publicado:	American Geophysical Union (AGU) 2021
Materias:	GLM machine learning lightning flash type random forests ENTLN Astronomy QB1-991 Geology QE1-996.5
Acceso en línea:	https://doaj.org/article/311c091b9197497ea65c02533733b067
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:311c091b9197497ea65c02533733b067
record_format	dspace
spelling	oai:doaj.org-article:311c091b9197497ea65c02533733b0672021-11-23T21:03:09ZClassification of GLM Flashes Using Random Forests2333-508410.1029/2021EA001861https://doaj.org/article/311c091b9197497ea65c02533733b0672021-11-01T00:00:00Zhttps://doi.org/10.1029/2021EA001861https://doaj.org/toc/2333-5084Abstract [The Geostationary Lightning Mapper (GLM) detects total lightning continuously from space, and does not distinguish intra‐cloud (IC) from cloud‐to‐ground (CG) lightning. This research focuses on differentiating CG and IC lightning detected by GLM using a random forests (RF) model. GLM flash and group characteristics are implemented into the RF model and used to predict flash type. The most important flash characteristic for distinguishing flash type is the maximum group area. Other features with high feature importance include time‐of‐day, elongation, propagation, footprint, slope, maximum distance between groups and events, and mean energy. Skill scores showcase the model's ability to distinguish flash type with moderate skill, with 81% probability of detection, 71% percent correct, 36% false alarm rate, 36% false alarm ratio, and 56% critical success index. These scores improve further when study area is limited to CONUS and the Southeastern United States. These results can be used to aid in future climatological analysis of flash type.]Jacquelyn RinghausenPhillip BitzerWilliam KoshakJohn MecikalskiAmerican Geophysical Union (AGU)articleGLMmachine learninglightningflash typerandom forestsENTLNAstronomyQB1-991GeologyQE1-996.5ENEarth and Space Science, Vol 8, Iss 11, Pp n/a-n/a (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	GLM machine learning lightning flash type random forests ENTLN Astronomy QB1-991 Geology QE1-996.5
spellingShingle	GLM machine learning lightning flash type random forests ENTLN Astronomy QB1-991 Geology QE1-996.5 Jacquelyn Ringhausen Phillip Bitzer William Koshak John Mecikalski Classification of GLM Flashes Using Random Forests
description	Abstract [The Geostationary Lightning Mapper (GLM) detects total lightning continuously from space, and does not distinguish intra‐cloud (IC) from cloud‐to‐ground (CG) lightning. This research focuses on differentiating CG and IC lightning detected by GLM using a random forests (RF) model. GLM flash and group characteristics are implemented into the RF model and used to predict flash type. The most important flash characteristic for distinguishing flash type is the maximum group area. Other features with high feature importance include time‐of‐day, elongation, propagation, footprint, slope, maximum distance between groups and events, and mean energy. Skill scores showcase the model's ability to distinguish flash type with moderate skill, with 81% probability of detection, 71% percent correct, 36% false alarm rate, 36% false alarm ratio, and 56% critical success index. These scores improve further when study area is limited to CONUS and the Southeastern United States. These results can be used to aid in future climatological analysis of flash type.]
format	article
author	Jacquelyn Ringhausen Phillip Bitzer William Koshak John Mecikalski
author_facet	Jacquelyn Ringhausen Phillip Bitzer William Koshak John Mecikalski
author_sort	Jacquelyn Ringhausen
title	Classification of GLM Flashes Using Random Forests
title_short	Classification of GLM Flashes Using Random Forests
title_full	Classification of GLM Flashes Using Random Forests
title_fullStr	Classification of GLM Flashes Using Random Forests
title_full_unstemmed	Classification of GLM Flashes Using Random Forests
title_sort	classification of glm flashes using random forests
publisher	American Geophysical Union (AGU)
publishDate	2021
url	https://doaj.org/article/311c091b9197497ea65c02533733b067
work_keys_str_mv	AT jacquelynringhausen classificationofglmflashesusingrandomforests AT phillipbitzer classificationofglmflashesusingrandomforests AT williamkoshak classificationofglmflashesusingrandomforests AT johnmecikalski classificationofglmflashesusingrandomforests
_version_	1718416085300019200

Classification of GLM Flashes Using Random Forests

Ejemplares similares