Urban air quality forecasting based on multi-dimensional collaborative Support Vector Regression (SVR): A case study of Beijing-Tianjin-Shijiazhuang

Liu, Bingchun; Binaykia, Arihant; Chang, Pei‐Chann; Tiwari, Manoj Kumar; Tsao, Cheng-Chin

doi:10.1371/journal.pone.0179763

Cited by 92 publications

(54 citation statements)

References 21 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning algorithms are attractive methods for analyzing large data sets due to their computational speed and easy implementation for massive data, partly driven by the recent availability of highly optimized computing software. In this review paper, we have chosen Random Forest, Support Vector Regression and Neural Network for comparison, because these methods have already been used for exposure modeling (Hu et al, 2017;Liu et al, 2017;Reid et al, 2015) and software within R is readily available.…”

Section: Discussionmentioning

confidence: 99%

A comparison of statistical and machine learning methods for creating national daily maps of ambient PM2.5 concentration

Berrocal

Guan

Muyskens

et al. 2020

Atmospheric Environment

View full text Add to dashboard Cite

A typical problem in air pollution epidemiology is exposure assessment for individuals for which health data are available. Due to the sparsity of monitoring sites and the limited temporal frequency with which measurements of air pollutants concentrations are collected (for most pollutants, once every 3 or 6 days), epidemiologists have been moving away from characterizing ambient air pollution exposure solely using measurements. In the last few years, substantial research efforts have been placed in developing statistical methods or machine learning techniques to generate estimates of air pollution at finer spatial and temporal scales (daily, usually) with complete coverage. Some of these methods include: geostatistical techniques, such as kriging; spatial statistical models that use the information contained in air quality model outputs (statistical downscaling models); linear regression modeling approaches that leverage the information in GIS covariates (land use regression); or machine learning methods that mine the information contained in relevant variables (neural network and deep learning approaches). Although some of these exposure modeling approaches have been used in several air pollution epidemiological studies, it is not clear how much the predicted exposures generated by these methods differ, and which method generates more reliable estimates. In this paper, we aim to address this gap by evaluating a variety of exposure modeling approaches, comparing their predictive performance and computational difficulty. Using PM 2.5 in year 2011 over the continental U.S. as case study, we examine the methods' performances across seasons, rural vs urban settings, and levels of PM 2.5 concentrations (low, medium, high).

show abstract

Section: Discussionmentioning

confidence: 99%

A comparison of statistical and machine learning methods for creating national daily maps of ambient PM2.5 concentration

Berrocal

Guan

Muyskens

et al. 2020

Atmospheric Environment

View full text Add to dashboard Cite

show abstract

“…Liu et al [23] also employ SVM to get the most reliable predictive model of air quality (AQI) by considering monitoring data of three cities in China (Beijing, Tianjin, and Shijiazhuang). Two years of last-day AQI values, pollutant concentrations (PM 2.5 , PM 10 , SO 2 , CO, NO 2 , and O 3 ), meteorological factors (temperature, wind direction and velocity), and weather description (ex.…”

Section: Category 1: Identifying Relevant Predictors and Understandinmentioning

confidence: 99%

Machine Learning Approaches for Outdoor Air Quality Modelling: A Systematic Review

2018

View full text Add to dashboard Cite

Current studies show that traditional deterministic models tend to struggle to capture the non-linear relationship between the concentration of air pollutants and their sources of emission and dispersion. To tackle such a limitation, the most promising approach is to use statistical models based on machine learning techniques. Nevertheless, it is puzzling why a certain algorithm is chosen over another for a given task. This systematic review intends to clarify this question by providing the reader with a comprehensive description of the principles underlying these algorithms and how they are applied to enhance prediction accuracy. A rigorous search that conforms to the PRISMA guideline is performed and results in the selection of the 46 most relevant journal papers in the area. Through a factorial analysis method these studies are synthetized and linked to each other. The main findings of this literature review show that: (i) machine learning is mainly applied in Eurasian and North American continents and (ii) estimation problems tend to implement Ensemble Learning and Regressions, whereas forecasting make use of Neural Networks and Support Vector Machines. The next challenges of this approach are to improve the prediction of pollution peaks and contaminants recently put in the spotlights (e.g., nanoparticles).

show abstract

“…We compared DENCAST with: (i) a baseline strategy, which predicts the value of the target attributes using the average value in the training set (AVG); (ii) four distributed regression algorithms, i.e., linear regression (LR), isotonic regression (ISO), ARIMA and a distributed implementation, based on DeepLearning4J, of long short-term memory neural networks (LSTM) for regression; (iii) the K-means clustering algorithm, extended to solve regression tasks. 10 Methodologically, LR trains an elastic net regularized linear regression model [30], which overcomes the limitations of the LASSO method by combining the L1 and L2 penalties of the LASSO and ridge methods. ISO is capable of fitting a non-decreasing free-form line to a set of points, without assuming the linearity of the target function [31].…”

Section: Experimental Setting and Competitor Systemsmentioning

confidence: 99%

“…In this context, multi-step ahead forecasting (usually 24 h) is necessary to predict the energy produced by renewable sources, in order to minimize the production from polluting sources and possible money losses [8]. Other domains where multi-target regression finds application include traffic flow forecasting [9], air quality forecasting [10], bike demand forecasting [11,12], life sciences (e.g., predicting Fig. 1 Overview of the environment in which DENCAST works.…”

mentioning

confidence: 99%

DENCAST: distributed density-based clustering for multi-target regression

et al. 2019

View full text Add to dashboard Cite

The generation of massive amounts of data in different forms (such as activity logs and sensor measurements) has increased the need for novel data mining algorithms, which are capable of building accurate models efficiently and in a distributed fashion. In recent years, several researchers proposed novel approaches to distribute the workload among several machines for classical clustering, classification and regression tasks [1]. However, only a few of them tackle the specific problem of density-based clustering. This problem has received much attention in the last decades, because of many desirable properties of the extracted clusters (arbitrarily-shaped, noise-free, robustness to outliers) which turn out the be useful in many application domains (e.g., spatial data analysis). Starting from the seminal work of DBSCAN [2], many algorithms have been proposed, but only a few of them are distributed. Unfortunately, existing distributed methods for density-based clustering suffer from several limitations. In particular, they are limited to data organized in a specific structure (e.g., they can analyze only low-dimensional feature spaces), or they suffer from overhead and scalability issues when the number of instances and attributes increase considerably [3-5]. These limitations depend from the

show abstract

Urban air quality forecasting based on multi-dimensional collaborative Support Vector Regression (SVR): A case study of Beijing-Tianjin-Shijiazhuang

Cited by 92 publications

References 21 publications

A comparison of statistical and machine learning methods for creating national daily maps of ambient PM2.5 concentration

A comparison of statistical and machine learning methods for creating national daily maps of ambient PM2.5 concentration

Machine Learning Approaches for Outdoor Air Quality Modelling: A Systematic Review

DENCAST: distributed density-based clustering for multi-target regression

Contact Info

Product

Resources

About