Applying machine learning methods to better understand, model and estimate mass concentrations of traffic-related pollutants at a typical street canyon

Šimić, Iva; Lovrić, Mario; Godec, Ranka; Kroll, Mark W.; Bešlić, Ivan

doi:10.1016/j.envpol.2020.114587

Cited by 41 publications

(38 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For machine learning one needs a set of predictive variables and a target variable. The methodology follows closely the procedures described previously in [13]. The target variables in the models are the various pollutant concentrations.…”

Section: Exploratory Analysis and Machine Learning Methodsmentioning

confidence: 99%

“…The machine learning algorithm used was random forest regression (RF) [22] which has been utilized in a number of previous air pollution models and air quality data analysis studies [13], [19]. The differences between past work and this analysis include: the exclusion of lagvalues of the respective (predicted) pollutant and exclusion of other pollutant concentrations in the respective models.…”

Section: Exploratory Analysis and Machine Learning Methodsmentioning

confidence: 99%

“…Data processing and model training was conducted with Python. The functions, scripts and libraries are presented in prior work [13], [23].…”

Section: Exploratory Analysis and Machine Learning Methodsmentioning

confidence: 99%

“…Ox was included because it will indicate if the hypothesized changes in NO2 and O3 due to the lockdown measures were caused by a repartitioning of these two species which has consequences for air quality management. (13) x (14) x (15) x (31) x (30)…”

Section: Data Processingmentioning

confidence: 99%

“…We discuss and explore that for complete understanding of the true factors influencing pollutant concentrations, pure statistical tests or single-day comparisons might be inadequate since weather conditions, particle persistence and seasonality affect concentrations by linear and non-linear processes [13]. We investigate the effects of the gradually introduced lockdown on air quality in an urbanized area in Graz, Styria, Austria.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Understanding the true effects of the COVID-19 lockdown on air pollution by means of machine learning

Lovrić

Pavlović

Vuković

et al. 2021

Environmental Pollution

Self Cite

View full text Add to dashboard Cite

During March, 2020, most European countries implemented lockdowns to restrict the transmission of SARS-CoV-2, the virus which causes COVID-19 through their populations. These restrictions had positive impacts for air quality due to a dramatic reduction of economic activity and emissions. In this work, a machine learning approach was designed and implemented to analyze local air quality improvements during the COVID-19 lockdown in Graz, Austria. The machine learning approach was used as a robust alternative to simple, historical measurement comparisons for various individual pollutants. Concentrations of NO2 (nitrogen dioxide), PM10, O3 (ozone) and Ox (total oxidant) were selected from five measurement sites in Graz and were set as target variables for random forest regression models to predict their expected values during the city's lockdown period. The true vs. expected difference is presented here as an indicator of true pollution during the lockdown. The machine learning models showed a high level of generalization for predicting the concentrations. Therefore, the approach was suitable for analyzing reductions in pollution concentrations. Results on the validation set showed very good performance for Ox and NO2 when compared to PM10 and O3. The analysis indicated that the city's average concentration reductions for the lockdown period were:-36.9 to-41.6%, and-6.6 to-14.2% for NO2 and PM10, respectively. However, an increase of 11.6 to 33.8% for O3 was estimated. The reduction in pollutant concentration, especially NO2 can be explained by significant drops in traffic-flows during the lockdown period (-51.6 to-43.9%). The results presented give a real-world example of what pollutant concentration reductions can be achieved by reducing traffic-flows and other economic activities.

show abstract

Section: Exploratory Analysis and Machine Learning Methodsmentioning

confidence: 99%

Section: Exploratory Analysis and Machine Learning Methodsmentioning

confidence: 99%

“…Data processing and model training was conducted with Python. The functions, scripts and libraries are presented in prior work [13], [23].…”

Section: Exploratory Analysis and Machine Learning Methodsmentioning

confidence: 99%

Section: Data Processingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Understanding the true effects of the COVID-19 lockdown on air pollution by means of machine learning

Lovrić

Pavlović

Vuković

et al. 2021

Environmental Pollution

Self Cite

View full text Add to dashboard Cite

show abstract

Evidence driven indoor air quality improvement: An innovative and interdisciplinary approach to improving indoor air quality

Lovrić,

Gajski,

Fernández‐Agüera

et al. 2024

BioFactors

View full text Add to dashboard Cite

Indoor air pollution is a recognized emerging threat, claiming millions of lives annually. People are constantly exposed to ambient and indoor air pollution. The latest research shows that people in developed countries spend up to 90% of their time indoors and almost 70% at home. Although impaired IAQ represents a significant health risk, it affects people differently, and specific populations are more vulnerable: children, the elderly, and people with respiratory illnesses are more sensitive to these environmental risks. Despite rather extensive research on IAQ, most of the current understanding about the subject, which includes pollution sources, indoor–outdoor relationships, and ventilation/filtration, is still quite limited, mainly because air quality monitoring in the EU is primarily focused on ambient air quality and regulatory requirements are lacking for indoor environments. Therefore, the EDIAQI project aims to improve guidelines and awareness for advancing the IAQ in Europe and beyond by allowing user‐friendly access to information about indoor air pollution exposures, sources, and related risk factors. The solution proposed with EDIAQI consists of conducting a characterization of sources and routes of exposure and dispersion of chemical, biological, and emerging indoor air pollution in multiple cities in the EU. The project will deploy cost‐effective/user‐friendly monitoring solutions to create new knowledge on sources, exposure routes, and indoor multipollutant body burdens. The EDIAQI project brings together 18 organizations from 11 different European countries that provide interdisciplinary skills and expertise in various fields, including environmental science and technology, medicine, and toxicology, as well as policy design and public engagement.

show abstract

Machine learning in prediction of intrinsic aqueous solubility of drug‐like compounds: Generalization, complexity, or predictive ability?

Lovrić

Pavlović

Žuvela

et al. 2021

Journal of Chemometrics

Self Cite

View full text Add to dashboard Cite

We present a collection of publicly available intrinsic aqueous solubility data of 829 drug-like compounds. Four different machine learning algorithms (random forests [RF], LightGBM, partial least squares, and least absolute shrinkage and selection operator [LASSO]) coupled with multistage permutation importance for feature selection and Bayesian hyperparameter optimization were used for the prediction of solubility based on chemical structural information. Our results show that LASSO yielded the best predictive ability on an external test set with a root mean square error (RMSE) (test) of 0.70 log points, an R 2 (test) of 0.80, and 105 features. Taking into account the number of descriptors as well, an RF model achieves the best balance between complexity and predictive ability with an RMSE(test) of 0.72 log points, an R 2 (test) of 0.78, and with only 17 features. On a more aggressive test set (principal component analysis [PCA]-based split), better generalization was observed for the RFmodel. We propose a ranking score for choosing the best model, as test set performance is only one of the factors in creating an applicable model. The ranking score is a weighted combination of generalization, number of features, and test performance. Out of the two best learners, a consensus model was built exhibiting the best predictive ability and generalization with RMSE(test) of 0.67 log points and a R 2 (test) of 0.81.

show abstract

Applying machine learning methods to better understand, model and estimate mass concentrations of traffic-related pollutants at a typical street canyon

Cited by 41 publications

References 61 publications

Understanding the true effects of the COVID-19 lockdown on air pollution by means of machine learning

Understanding the true effects of the COVID-19 lockdown on air pollution by means of machine learning

Evidence driven indoor air quality improvement: An innovative and interdisciplinary approach to improving indoor air quality

Machine learning in prediction of intrinsic aqueous solubility of drug‐like compounds: Generalization, complexity, or predictive ability?

Contact Info

Product

Resources

About