Abstract
Abstract. Running large-eddy simulations (LESs) can be burdensome and computationally too expensive from the application point of view, for example, to support urban planning. In this study, regression models are used to replicate modelled air pollutant concentrations from LES in urban boulevards. We study the performance of regression models and discuss how to detect situations where the models are applied outside their training domain and their outputs cannot be trusted. Regression models from 10 different model families are trained and a cross-validation methodology is used to evaluate their performance and to find the best set of features needed to reproduce the LES outputs. We also test the regression models on an independent testing dataset. Our results suggest that in general, log-linear regression gives the best and most robust performance on new independent data. It clearly outperforms the dummy model which would predict constant concentrations for all locations (multiplicative minimum RMSE (mRMSE) of 0.76 vs. 1.78 of the dummy model). Furthermore, we demonstrate that it is possible to detect concept drift, i.e. situations where the model is applied outside its training domain and a new LES run may be necessary to obtain reliable results. Regression models can be used to replace LES simulations in estimating air pollutant concentrations, unless higher accuracy is needed. In order to have reliable results, it is however important to do the model and feature selection carefully to avoid overfitting and to use methods to detect the concept drift.
Highlights
Exposure to ambient air pollution leads to cardiovascular and pulmonary diseases, and is estimated to cause 3 million premature deaths worldwide every year (Lelieveld et al, 2015; WHO, 2016), of which 0.8 million occur in Europe (Lelieveld et al, 2019)
Most of the previous studies on developing a statistical air pollution model using machine learning have been based on field measurements, and the spatiotemporal distribution of pollutants has been assessed by utilizing multiple stationary sites in model training (e.g. Araki et al, 2018; Yang et al, 2018)
Hierarchical model separating data based on rules A Bayesian kernel-based method for regression Ensemble method of decision trees Ordinary least squares linear regression Linear regression modelling log(pc + 1) Linear regression assuming Poisson distributed data Ensemble method of decision trees Non-linear kernel-based regression method Support vector regression modelling log(pc + 1) Combination of logistic regression and Poisson regression rpart kernlab xgboost lm lm glm randomForest e1071 e1071 pscl forest is an ensemble method that aggregates the predictions of multiple decision trees trained on random subsets of data and features
Summary
Exposure to ambient air pollution leads to cardiovascular and pulmonary diseases, and is estimated to cause 3 million premature deaths worldwide every year (Lelieveld et al, 2015; WHO, 2016), of which 0.8 million occur in Europe (Lelieveld et al, 2019). In contrast to CFD, statistical models based on machine learning may offer a significantly less expensive alternative to predict urban air quality and pollutant dispersion. The number of studies conducting machine-learning-based air quality modelling has increased rapidly (Rybarczyk and Zalakeviciute, 2018). Machine learning allows finding a relationship between a target variable, e.g. the concentration of air pollutants in a certain location, and its predictors, which are often called features. Most of the previous studies on developing a statistical air pollution model using machine learning have been based on field measurements, and the spatiotemporal distribution of pollutants has been assessed by utilizing multiple stationary sites in model training The application of machine learning for emulating LES outputs of local-scale air pollutant dispersion in urban areas is investigated.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
