Predicting intraurban PM2.5 concentrations using enhanced machine learning approaches and incorporating human activity patterns

Ashayeri, Mehdi; Abbasabadi, Narjes; Heidarinejad, Mohammad; Stephens, Brent

doi:10.1016/j.envres.2020.110423

Cited by 23 publications

(11 citation statements)

References 91 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…2020) and similar studies. The impact of traffic data on AQ ML prediction models has been assumed in several studies such as (Ashayeri et al, 2021;Rossi et al, 2019a;Rossi et al, 2020), where it is undoubtedly believed that traffic pollution contributes immensely to air pollution. This alone is not enough to explain how the traffic data set influences the performance of AQ ML prediction models.…”

Section: Discussionmentioning

confidence: 99%

“…Traffic data has been in use in vehicle emission modelling for a long time as proven in Comert et al (2020), Hatzopoulou et al (2013), Pinto et al (2020), Rossi et al (2020) and similar studies. The impact of traffic data on AQ ML prediction models has been assumed in several studies such as (Ashayeri et al , 2021; Rossi et al , 2019a; Rossi et al , 2020), where it is undoubtedly believed that traffic pollution contributes immensely to air pollution. This alone is not enough to explain how the traffic data set influences the performance of AQ ML prediction models.…”

Section: Discussionmentioning

confidence: 99%

“…Many studies like Comert et al (2020), Hatzopoulou et al (2013), Pinto et al (2020) and Rossi et al (2020) have supported the theory that traffic emission contributes to air pollution. This has caused several studies such as Ashayeri et al (2021), Rossi et al (2019a) and Rossi et al (2020) in the domain of AQ forecast to use various forms of traffic data sets for prediction model development. There is no significant research that proves the impact of traffic datasets on the performance of air quality ML prediction models.…”

Section: Literature Reviewmentioning

confidence: 99%

See 2 more Smart Citations

Effect of traffic data set on various machine-learning algorithms when forecasting air quality

Sulaimon

Alaka

Olu-Ajayi

et al. 2022

JEDT

View full text Add to dashboard Cite

Purpose Road traffic emissions are generally believed to contribute immensely to air pollution, but the effect of road traffic data sets on air quality (AQ) predictions has not been fully investigated. This paper aims to investigate the effects traffic data set have on the performance of machine learning (ML) predictive models in AQ prediction. Design/methodology/approach To achieve this, the authors have set up an experiment with the control data set having only the AQ data set and meteorological (Met) data set, while the experimental data set is made up of the AQ data set, Met data set and traffic data set. Several ML models (such as extra trees regressor, eXtreme gradient boosting regressor, random forest regressor, K-neighbors regressor and two others) were trained, tested and compared on these individual combinations of data sets to predict the volume of PM2.5, PM10, NO2 and O3 in the atmosphere at various times of the day. Findings The result obtained showed that various ML algorithms react differently to the traffic data set despite generally contributing to the performance improvement of all the ML algorithms considered in this study by at least 20% and an error reduction of at least 18.97%. Research limitations/implications This research is limited in terms of the study area, and the result cannot be generalized outside of the UK as some of the inherent conditions may not be similar elsewhere. Additionally, only the ML algorithms commonly used in literature are considered in this research, therefore, leaving out a few other ML algorithms. Practical implications This study reinforces the belief that the traffic data set has a significant effect on improving the performance of air pollution ML prediction models. Hence, there is an indication that ML algorithms behave differently when trained with a form of traffic data set in the development of an AQ prediction model. This implies that developers and researchers in AQ prediction need to identify the ML algorithms that behave in their best interest before implementation. Originality/value The result of this study will enable researchers to focus more on algorithms of benefit when using traffic data sets in AQ prediction.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Effect of traffic data set on various machine-learning algorithms when forecasting air quality

Sulaimon

Alaka

Olu-Ajayi

et al. 2022

JEDT

View full text Add to dashboard Cite

show abstract

“…Bu çalışmada yapay sinir ağı modeli olarak her birinde 3 nöron bulunan 3 gizli katman kullanılmış, iterasyon sayısı 500 ve ağırlık optimizasyonu için Kısıtlı Hafıza Broyden-Fletcher-Goldfarb-Shanno (Limited Memory Broyden-Fletcher-Goldfarb-Shanno -LBFGS) algoritması seçilmiştir. DVR algoritması model performansını yıl boyunca %18,4 ve aylık veri kümeleri için %98,7'ye kadar arttırdığı belirtilmiştir [46]. Bu çalışmada tahmin edilen hava kalitesi parametresi ile aynı parametrenin kullanıldığı Choubin vd., tarafından yapılan çalışmada Barselona Eyaletindeki 75 istasyondaki yıllık PM10 için tehlikeli alanları tahmin etmek adına RF, Torbalı Sınıflandırma ve Regresyon Ağaçları (Torbalı CART) ve Karışım Ayırım Analizi (MDA) gibi makine öğrenmesi algoritmaları kullanmışlardır.…”

Section: Yapay Sinir Ağlarıunclassified

PM10 Parametresinin Makine Öğrenmesi Algoritmalari ile Mekânsal Analizi, Kayseri İli Örneği

GÖKÇEK¹,

ŞAŞA²,

Dokuz³

et al. 2022

Deu Muhendislik Fakultesi Fen Ve Muhendislik

View full text Add to dashboard Cite

Hava kirliliğinin son yıllarda artışı ile alınacak olan erken önlemler dâhilinde hava kirliliği tahmininin yapılması insan ve çevre sağlığına verilebilecek zararın en aza indirilmesinde önemlidir. Bu çalışmada günlük ortalama hava kirliliği miktarının, önemli bir hava kirletici olan PM10 konsantrasyonu üzerinden tahminlenmesi ve hava kirliliğinin çevresel ve mekânsal modellenmesi amaçlanmıştır.

show abstract

“…On the other hand, it can model the spatial correlation and heterogeneous effects in the spatial distribution of PM 2.5 concentrations. There appears to be a consensus that the spatial distribution of PM 2.5 concentrations is significantly affected by both natural factors, such as elevation, landform, vegetation, and meteorological conditions [ 19 , 20 ], and human factors, such as population density, energy consumption, and economy [ 21 , 22 ]. The corresponding effects were treated as the determinate part (or global trends) in classic spatial statistical modelling [ 18 ].…”

Section: Introductionmentioning

confidence: 99%

PM2.5 Concentrations Variability in North China Explored with a Multi-Scale Spatial Random Effect Model

Zhang

Liu

Yang

et al. 2022

IJERPH

View full text Add to dashboard Cite

Compiling fine-resolution geospatial PM2.5 concentrations data is essential for precisely assessing the health risks of PM2.5 pollution exposure as well as for evaluating environmental policy effectiveness. In most previous studies, global and local spatial heterogeneity of PM2.5 is captured by the inclusion of multi-scale covariate effects, while the modelling of genuine scale-dependent variabilities pertaining to the spatial random process of PM2.5 has not yet been much studied. Consequently, this work proposed a multi-scale spatial random effect model (MSSREM), based a recently developed fixed-rank Kriging method, to capture both the scale-dependent variabilities and the spatial dependence effect simultaneously. Furthermore, a small-scale Monte Carlo simulation experiment was conducted to assess the performance of MSSREM against classic geospatial Kriging models. The key results indicated that when the multiple-scale property of local spatial variabilities were exhibited, the MSSREM had greater ability to recover local- or fine-scale variations hidden in a real spatial process. The methodology was applied to the PM2.5 concentrations modelling in North China, a region with the worst air quality in the country. The MSSREM provided high prediction accuracy, 0.917 R-squared, and 3.777 root mean square error (RMSE). In addition, the spatial correlations in PM2.5 concentrations were properly captured by the model as indicated by a statistically insignificant Moran’s I statistic (a value of 0.136 with p-value > 0.2). Overall, this study offers another spatial statistical model for investigating and predicting PM2.5 concentration, which would be beneficial for precise health risk assessment of PM2.5 pollution exposure.

show abstract

Predicting intraurban PM2.5 concentrations using enhanced machine learning approaches and incorporating human activity patterns

Cited by 23 publications

References 91 publications

Effect of traffic data set on various machine-learning algorithms when forecasting air quality

Effect of traffic data set on various machine-learning algorithms when forecasting air quality

PM10 Parametresinin Makine Öğrenmesi Algoritmalari ile Mekânsal Analizi, Kayseri İli Örneği

PM2.5 Concentrations Variability in North China Explored with a Multi-Scale Spatial Random Effect Model

Contact Info

Product

Resources

About