Niche modeling of dengue fever using remotely sensed environmental factors and boosted regression trees

Jeffrey Ashby, Max ​Moreno Madrinan, Constantin Yiannoutsos, Austin Stanforth

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Dengue fever (DF), a vector-borne flavivirus, is endemic to the tropical countries of the world with nearly 400 million people becoming infected each year and roughly one-third of the world's population living in areas of risk. The main vector for DF is the Aedes aegypti mosquito, which is also the same vector of yellow fever, chikungunya, and Zika viruses. To gain an understanding of the spatial aspects that can affect the epidemiological processes across the disease's geographical range, and the spatial interactions involved, we created and compared Bernoulli and Poisson family Boosted Regression Tree (BRT) models to quantify the overall annual risk of DF incidence by municipality, using the Magdalena River watershed of Colombia as a study site during the time period between 2012 and 2014. A wide range of environmental conditions make this site ideal to develop models that, with minor adjustments, could be applied in many other geographical areas. Our results show that these BRT methods can be successfully used to identify areas at risk and presents great potential for implementation in surveillance programs.

Original languageEnglish (US)
Article number328
JournalRemote Sensing
Volume9
Issue number4
DOIs
StatePublished - Apr 1 2017

Fingerprint

dengue fever
niche
environmental factor
yellow fever
modeling
mosquito
virus
environmental conditions
watershed
river
world

Keywords

  • Aedes aegypti
  • Boosted regression tree
  • Dengue
  • GIS
  • Neglected tropical diseases
  • Remote sensing
  • Vector modeling

ASJC Scopus subject areas

  • Earth and Planetary Sciences(all)

Cite this

Niche modeling of dengue fever using remotely sensed environmental factors and boosted regression trees. / Ashby, Jeffrey; ​Moreno Madrinan, Max; Yiannoutsos, Constantin; Stanforth, Austin.

In: Remote Sensing, Vol. 9, No. 4, 328, 01.04.2017.

Research output: Contribution to journalArticle

@article{3d79304e7df543e39948f6bd8e620f82,
title = "Niche modeling of dengue fever using remotely sensed environmental factors and boosted regression trees",
abstract = "Dengue fever (DF), a vector-borne flavivirus, is endemic to the tropical countries of the world with nearly 400 million people becoming infected each year and roughly one-third of the world's population living in areas of risk. The main vector for DF is the Aedes aegypti mosquito, which is also the same vector of yellow fever, chikungunya, and Zika viruses. To gain an understanding of the spatial aspects that can affect the epidemiological processes across the disease's geographical range, and the spatial interactions involved, we created and compared Bernoulli and Poisson family Boosted Regression Tree (BRT) models to quantify the overall annual risk of DF incidence by municipality, using the Magdalena River watershed of Colombia as a study site during the time period between 2012 and 2014. A wide range of environmental conditions make this site ideal to develop models that, with minor adjustments, could be applied in many other geographical areas. Our results show that these BRT methods can be successfully used to identify areas at risk and presents great potential for implementation in surveillance programs.",
keywords = "Aedes aegypti, Boosted regression tree, Dengue, GIS, Neglected tropical diseases, Remote sensing, Vector modeling",
author = "Jeffrey Ashby and {​Moreno Madrinan}, Max and Constantin Yiannoutsos and Austin Stanforth",
year = "2017",
month = "4",
day = "1",
doi = "10.3390/rs9040328",
language = "English (US)",
volume = "9",
journal = "Remote Sensing",
issn = "2072-4292",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "4",

}

TY - JOUR

T1 - Niche modeling of dengue fever using remotely sensed environmental factors and boosted regression trees

AU - Ashby, Jeffrey

AU - ​Moreno Madrinan, Max

AU - Yiannoutsos, Constantin

AU - Stanforth, Austin

PY - 2017/4/1

Y1 - 2017/4/1

N2 - Dengue fever (DF), a vector-borne flavivirus, is endemic to the tropical countries of the world with nearly 400 million people becoming infected each year and roughly one-third of the world's population living in areas of risk. The main vector for DF is the Aedes aegypti mosquito, which is also the same vector of yellow fever, chikungunya, and Zika viruses. To gain an understanding of the spatial aspects that can affect the epidemiological processes across the disease's geographical range, and the spatial interactions involved, we created and compared Bernoulli and Poisson family Boosted Regression Tree (BRT) models to quantify the overall annual risk of DF incidence by municipality, using the Magdalena River watershed of Colombia as a study site during the time period between 2012 and 2014. A wide range of environmental conditions make this site ideal to develop models that, with minor adjustments, could be applied in many other geographical areas. Our results show that these BRT methods can be successfully used to identify areas at risk and presents great potential for implementation in surveillance programs.

AB - Dengue fever (DF), a vector-borne flavivirus, is endemic to the tropical countries of the world with nearly 400 million people becoming infected each year and roughly one-third of the world's population living in areas of risk. The main vector for DF is the Aedes aegypti mosquito, which is also the same vector of yellow fever, chikungunya, and Zika viruses. To gain an understanding of the spatial aspects that can affect the epidemiological processes across the disease's geographical range, and the spatial interactions involved, we created and compared Bernoulli and Poisson family Boosted Regression Tree (BRT) models to quantify the overall annual risk of DF incidence by municipality, using the Magdalena River watershed of Colombia as a study site during the time period between 2012 and 2014. A wide range of environmental conditions make this site ideal to develop models that, with minor adjustments, could be applied in many other geographical areas. Our results show that these BRT methods can be successfully used to identify areas at risk and presents great potential for implementation in surveillance programs.

KW - Aedes aegypti

KW - Boosted regression tree

KW - Dengue

KW - GIS

KW - Neglected tropical diseases

KW - Remote sensing

KW - Vector modeling

UR - http://www.scopus.com/inward/record.url?scp=85017604168&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85017604168&partnerID=8YFLogxK

U2 - 10.3390/rs9040328

DO - 10.3390/rs9040328

M3 - Article

AN - SCOPUS:85017604168

VL - 9

JO - Remote Sensing

JF - Remote Sensing

SN - 2072-4292

IS - 4

M1 - 328

ER -