Machine learning approach to forecasting urban pollution: a case study of Quito, Ecuador

Yves Philippe Rybarczyk; Rasa Zalakeviciute

doi:10.1109/ETCM.2016.7750810

Machine learning approach to forecasting urban pollution: a case study of Quito, Ecuador

Yves Philippe Rybarczyk, Rasa Zalakeviciute

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

22 Citations (Scopus)

Abstract

This work addresses the question of how to predict fine particulate matter given a combination of weather conditions. A compilation of several years of meteorological data in the city of Quito, Ecuador, are used to build models using a machine learning approach. The study presents a decision tree algorithm that learns to classify the concentrations of fine aerosols, into two categories (>15μg/m3 vs. <15μg/m3), from a limited number of parameters such as the level of precipitation and the wind speed and direction. Requiring few rules, the resulting models are able to infer the concentration outcome with significant accuracy. This fundamental research intends to be a preliminary step in the development of a web-based platform and smartphone app to alert the inhabitants of Ecuador's capital about the risk to human health, with potential future application in other urban areas

Original language	English
Title of host publication	2016 IEEE Ecuador Technical Chapters Meeting, ETCM 2016
Publisher	IEEE
ISBN (Electronic)	978-1-5090-1629-7
DOIs	https://doi.org/10.1109/ETCM.2016.7750810
Publication status	Published - 2016
Event	2016 IEEE Ecuador Technical Chapters Meeting - Guayaquil, Ecuador Duration: 12 Oct 2016 → 14 Oct 2016

Conference

Conference	2016 IEEE Ecuador Technical Chapters Meeting
Abbreviated title	ETCM
Country/Territory	Ecuador
City	Guayaquil
Period	12/10/16 → 14/10/16

Keywords

machine learning
decision tree
predictive model
urban pollution
fine particulate matter

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ETCM.2016.7750810

Cite this

@inproceedings{a572c4b3660f422bb21e923c9cc9f69c,

title = "Machine learning approach to forecasting urban pollution: a case study of Quito, Ecuador",

abstract = "This work addresses the question of how to predict fine particulate matter given a combination of weather conditions. A compilation of several years of meteorological data in the city of Quito, Ecuador, are used to build models using a machine learning approach. The study presents a decision tree algorithm that learns to classify the concentrations of fine aerosols, into two categories (>15μg/m3 vs. <15μg/m3), from a limited number of parameters such as the level of precipitation and the wind speed and direction. Requiring few rules, the resulting models are able to infer the concentration outcome with significant accuracy. This fundamental research intends to be a preliminary step in the development of a web-based platform and smartphone app to alert the inhabitants of Ecuador's capital about the risk to human health, with potential future application in other urban areas",

keywords = "machine learning, decision tree, predictive model, urban pollution, fine particulate matter",

author = "Rybarczyk, {Yves Philippe} and Rasa Zalakeviciute",

year = "2016",

doi = "10.1109/ETCM.2016.7750810",

language = "English",

booktitle = "2016 IEEE Ecuador Technical Chapters Meeting, ETCM 2016",

publisher = "IEEE",

note = "2016 IEEE Ecuador Technical Chapters Meeting, ETCM ; Conference date: 12-10-2016 Through 14-10-2016",

}

TY - GEN

T1 - Machine learning approach to forecasting urban pollution

T2 - 2016 IEEE Ecuador Technical Chapters Meeting

AU - Rybarczyk, Yves Philippe

AU - Zalakeviciute, Rasa

PY - 2016

Y1 - 2016

N2 - This work addresses the question of how to predict fine particulate matter given a combination of weather conditions. A compilation of several years of meteorological data in the city of Quito, Ecuador, are used to build models using a machine learning approach. The study presents a decision tree algorithm that learns to classify the concentrations of fine aerosols, into two categories (>15μg/m3 vs. <15μg/m3), from a limited number of parameters such as the level of precipitation and the wind speed and direction. Requiring few rules, the resulting models are able to infer the concentration outcome with significant accuracy. This fundamental research intends to be a preliminary step in the development of a web-based platform and smartphone app to alert the inhabitants of Ecuador's capital about the risk to human health, with potential future application in other urban areas

AB - This work addresses the question of how to predict fine particulate matter given a combination of weather conditions. A compilation of several years of meteorological data in the city of Quito, Ecuador, are used to build models using a machine learning approach. The study presents a decision tree algorithm that learns to classify the concentrations of fine aerosols, into two categories (>15μg/m3 vs. <15μg/m3), from a limited number of parameters such as the level of precipitation and the wind speed and direction. Requiring few rules, the resulting models are able to infer the concentration outcome with significant accuracy. This fundamental research intends to be a preliminary step in the development of a web-based platform and smartphone app to alert the inhabitants of Ecuador's capital about the risk to human health, with potential future application in other urban areas

KW - machine learning

KW - decision tree

KW - predictive model

KW - urban pollution

KW - fine particulate matter

U2 - 10.1109/ETCM.2016.7750810

DO - 10.1109/ETCM.2016.7750810

M3 - Conference contribution

BT - 2016 IEEE Ecuador Technical Chapters Meeting, ETCM 2016

PB - IEEE

Y2 - 12 October 2016 through 14 October 2016

ER -

Machine learning approach to forecasting urban pollution: a case study of Quito, Ecuador

Abstract

Conference

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this