A Machine Learning Approach for Air Quality Prediction: Model Regularization and Optimization
In this paper, we tackle air quality forecasting by using machine learning approaches to predict the hourly concentration of air pollutants (e.g., ozone, particle matter ( PM 2.5 )...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-02-01
|
Series: | Big Data and Cognitive Computing |
Subjects: | |
Online Access: | http://www.mdpi.com/2504-2289/2/1/5 |
id |
doaj-cbd6aae9088c4c2db38be46b7712cf5c |
---|---|
record_format |
Article |
spelling |
doaj-cbd6aae9088c4c2db38be46b7712cf5c2020-11-24T21:49:11ZengMDPI AGBig Data and Cognitive Computing2504-22892018-02-0121510.3390/bdcc2010005bdcc2010005A Machine Learning Approach for Air Quality Prediction: Model Regularization and OptimizationDixian Zhu0Changjie Cai1Tianbao Yang2Xun Zhou3Department of Computer Science, University of Iowa, Iowa City, IA 52242, USADepartment of Occupational and Environmental Health, University of Oklahoma Health Sciences Center, Oklahoma City, OK 73104, USADepartment of Computer Science, University of Iowa, Iowa City, IA 52242, USADepartment of Management Sciences, University of Iowa, Iowa City, IA 52242, USAIn this paper, we tackle air quality forecasting by using machine learning approaches to predict the hourly concentration of air pollutants (e.g., ozone, particle matter ( PM 2.5 ) and sulfur dioxide). Machine learning, as one of the most popular techniques, is able to efficiently train a model on big data by using large-scale optimization algorithms. Although there exist some works applying machine learning to air quality prediction, most of the prior studies are restricted to several-year data and simply train standard regression models (linear or nonlinear) to predict the hourly air pollution concentration. In this work, we propose refined models to predict the hourly air pollution concentration on the basis of meteorological data of previous days by formulating the prediction over 24 h as a multi-task learning (MTL) problem. This enables us to select a good model with different regularization techniques. We propose a useful regularization by enforcing the prediction models of consecutive hours to be close to each other and compare it with several typical regularizations for MTL, including standard Frobenius norm regularization, nuclear norm regularization, and ℓ 2 , 1 -norm regularization. Our experiments have showed that the proposed parameter-reducing formulations and consecutive-hour-related regularizations achieve better performance than existing standard regression models and existing regularizations.http://www.mdpi.com/2504-2289/2/1/5air pollutant predictionmulti-task learningregularizationanalytical solution |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Dixian Zhu Changjie Cai Tianbao Yang Xun Zhou |
spellingShingle |
Dixian Zhu Changjie Cai Tianbao Yang Xun Zhou A Machine Learning Approach for Air Quality Prediction: Model Regularization and Optimization Big Data and Cognitive Computing air pollutant prediction multi-task learning regularization analytical solution |
author_facet |
Dixian Zhu Changjie Cai Tianbao Yang Xun Zhou |
author_sort |
Dixian Zhu |
title |
A Machine Learning Approach for Air Quality Prediction: Model Regularization and Optimization |
title_short |
A Machine Learning Approach for Air Quality Prediction: Model Regularization and Optimization |
title_full |
A Machine Learning Approach for Air Quality Prediction: Model Regularization and Optimization |
title_fullStr |
A Machine Learning Approach for Air Quality Prediction: Model Regularization and Optimization |
title_full_unstemmed |
A Machine Learning Approach for Air Quality Prediction: Model Regularization and Optimization |
title_sort |
machine learning approach for air quality prediction: model regularization and optimization |
publisher |
MDPI AG |
series |
Big Data and Cognitive Computing |
issn |
2504-2289 |
publishDate |
2018-02-01 |
description |
In this paper, we tackle air quality forecasting by using machine learning approaches to predict the hourly concentration of air pollutants (e.g., ozone, particle matter (
PM
2.5
) and sulfur dioxide). Machine learning, as one of the most popular techniques, is able to efficiently train a model on big data by using large-scale optimization algorithms. Although there exist some works applying machine learning to air quality prediction, most of the prior studies are restricted to several-year data and simply train standard regression models (linear or nonlinear) to predict the hourly air pollution concentration. In this work, we propose refined models to predict the hourly air pollution concentration on the basis of meteorological data of previous days by formulating the prediction over 24 h as a multi-task learning (MTL) problem. This enables us to select a good model with different regularization techniques. We propose a useful regularization by enforcing the prediction models of consecutive hours to be close to each other and compare it with several typical regularizations for MTL, including standard Frobenius norm regularization, nuclear norm regularization, and
ℓ
2
,
1
-norm regularization. Our experiments have showed that the proposed parameter-reducing formulations and consecutive-hour-related regularizations achieve better performance than existing standard regression models and existing regularizations. |
topic |
air pollutant prediction multi-task learning regularization analytical solution |
url |
http://www.mdpi.com/2504-2289/2/1/5 |
work_keys_str_mv |
AT dixianzhu amachinelearningapproachforairqualitypredictionmodelregularizationandoptimization AT changjiecai amachinelearningapproachforairqualitypredictionmodelregularizationandoptimization AT tianbaoyang amachinelearningapproachforairqualitypredictionmodelregularizationandoptimization AT xunzhou amachinelearningapproachforairqualitypredictionmodelregularizationandoptimization AT dixianzhu machinelearningapproachforairqualitypredictionmodelregularizationandoptimization AT changjiecai machinelearningapproachforairqualitypredictionmodelregularizationandoptimization AT tianbaoyang machinelearningapproachforairqualitypredictionmodelregularizationandoptimization AT xunzhou machinelearningapproachforairqualitypredictionmodelregularizationandoptimization |
_version_ |
1725888969608003584 |