Using machine learning to estimate atmospheric pollen concentrations in Tulsa, OK

This article describes an example of using machine learning to estimate the abundance of airborne Ambrosia pollen for Tulsa, OK. Twenty-seven years of historical pollen observations were used. These pollen observations were combined with machine learning and a very complete meteorological and land s...

Full description

Bibliographic Details
Main Authors:	Xun Liu, Daji Wu, Gebreab K Zewdie, Lakitha Wijerante, Christopher I Timms, Alexander Riley, Estelle Levetin, David J Lary
Format:	Article
Language:	English
Published:	SAGE Publishing 2017-03-01
Series:	Environmental Health Insights
Online Access:	https://doi.org/10.1177/1178630217699399

id	doaj-8916581d304743d7abe961e679946ee2
record_format	Article
spelling	doaj-8916581d304743d7abe961e679946ee22020-11-25T03:24:38ZengSAGE PublishingEnvironmental Health Insights1178-63022017-03-011110.1177/117863021769939910.1177_1178630217699399Using machine learning to estimate atmospheric pollen concentrations in Tulsa, OKXun Liu0Daji Wu1Gebreab K Zewdie2Lakitha Wijerante3Christopher I Timms4Alexander Riley5Estelle Levetin6David J Lary7The University of Texas at Dallas, Richardson, TX, USAThe University of Texas at Dallas, Richardson, TX, USAThe University of Texas at Dallas, Richardson, TX, USAThe University of Texas at Dallas, Richardson, TX, USAThe University of Texas at Dallas, Richardson, TX, USAThe University of Texas at Dallas, Richardson, TX, USAThe University of Tulsa, Tulsa, OK, USAThe University of Texas at Dallas, Richardson, TX, USAThis article describes an example of using machine learning to estimate the abundance of airborne Ambrosia pollen for Tulsa, OK. Twenty-seven years of historical pollen observations were used. These pollen observations were combined with machine learning and a very complete meteorological and land surface context of 85 variables to estimate the daily Ambrosia abundance. The machine learning algorithms employed were Least Absolute Shrinkage and Selection Operator (LASSO), neural networks, and random forests. The best performance was obtained using random forests. The physical insights provided by the random forest are also discussed.https://doi.org/10.1177/1178630217699399
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Xun Liu Daji Wu Gebreab K Zewdie Lakitha Wijerante Christopher I Timms Alexander Riley Estelle Levetin David J Lary
spellingShingle	Xun Liu Daji Wu Gebreab K Zewdie Lakitha Wijerante Christopher I Timms Alexander Riley Estelle Levetin David J Lary Using machine learning to estimate atmospheric pollen concentrations in Tulsa, OK Environmental Health Insights
author_facet	Xun Liu Daji Wu Gebreab K Zewdie Lakitha Wijerante Christopher I Timms Alexander Riley Estelle Levetin David J Lary
author_sort	Xun Liu
title	Using machine learning to estimate atmospheric pollen concentrations in Tulsa, OK
title_short	Using machine learning to estimate atmospheric pollen concentrations in Tulsa, OK
title_full	Using machine learning to estimate atmospheric pollen concentrations in Tulsa, OK
title_fullStr	Using machine learning to estimate atmospheric pollen concentrations in Tulsa, OK
title_full_unstemmed	Using machine learning to estimate atmospheric pollen concentrations in Tulsa, OK
title_sort	using machine learning to estimate atmospheric pollen concentrations in tulsa, ok
publisher	SAGE Publishing
series	Environmental Health Insights
issn	1178-6302
publishDate	2017-03-01
description	This article describes an example of using machine learning to estimate the abundance of airborne Ambrosia pollen for Tulsa, OK. Twenty-seven years of historical pollen observations were used. These pollen observations were combined with machine learning and a very complete meteorological and land surface context of 85 variables to estimate the daily Ambrosia abundance. The machine learning algorithms employed were Least Absolute Shrinkage and Selection Operator (LASSO), neural networks, and random forests. The best performance was obtained using random forests. The physical insights provided by the random forest are also discussed.
url	https://doi.org/10.1177/1178630217699399
work_keys_str_mv	AT xunliu usingmachinelearningtoestimateatmosphericpollenconcentrationsintulsaok AT dajiwu usingmachinelearningtoestimateatmosphericpollenconcentrationsintulsaok AT gebreabkzewdie usingmachinelearningtoestimateatmosphericpollenconcentrationsintulsaok AT lakithawijerante usingmachinelearningtoestimateatmosphericpollenconcentrationsintulsaok AT christopheritimms usingmachinelearningtoestimateatmosphericpollenconcentrationsintulsaok AT alexanderriley usingmachinelearningtoestimateatmosphericpollenconcentrationsintulsaok AT estellelevetin usingmachinelearningtoestimateatmosphericpollenconcentrationsintulsaok AT davidjlary usingmachinelearningtoestimateatmosphericpollenconcentrationsintulsaok
_version_	1724601025763999744

Using machine learning to estimate atmospheric pollen concentrations in Tulsa, OK

Similar Items