Hybrid Neural Networks and Boosted Regression Tree Models for Predicting Roadside Particulate MatterReport as inadecuate

Hybrid Neural Networks and Boosted Regression Tree Models for Predicting Roadside Particulate Matter - Download this document for free, or read online. Document in PDF available to download.

Environmental Modeling and Assessment

, Volume 21, Issue 6, pp 731–750

First Online: 30 March 2016Received: 18 March 2015Accepted: 07 March 2016


This paper examines the application of artificial neural network ANN and boosted regression tree BRT methods in air quality modelling. The methods were applied to developing air quality models for predicting roadside particle mass concentration PM10, PM2.5 and particle number counts PNC based on air pollution, traffic and meteorological data from Marylebone Road in London. Elastic net, Lasso and principal components analysis were used as feature selection methods for the ANN models to reduce the number of predictor variables and improve their generalisation. The performance of the ANN with feature selection ANN hybrid and the BRT models was evaluated and compared using statistical performance metrics. The performance parameters include root mean square error RMSE, fraction of prediction within a factor of two of the observation FAC2, mean bias MB, mean gross error MGE, the coefficient of correlation R and coefficient of efficiency CoE values. The input variables selected by the elastic net produced the best performing ANN models. The ANN hybrid produced models performed only slightly better than the BRT models. The R values of the ANN elastic net and BRT models were 0.96 and 0.95 for PM10, 0.96 and 0.96 for PM2.5 and 0.89 and 0.87 for PNC, respectively. Their corresponding CoE values were 0.72 and 0.70 for PM10, 0.74 and 0.76 for PM2.5 and 0.81 and 0.71 for PNC respectively. About 80–99% of all the model predictions are within a factor of two of the observed particle concentrations. The BRT models offer more advantages regarding model interpretation and permit feature selection. Therefore, the study recommends the use of BRT over ANN where the model interpretation is a priority.

KeywordsAir quality Boosted regression trees Neural network Particulate matter HighlightsThree hybrid ANN and a BRT model for predicting roadside particulate matter were investigated.

Elastic-net regression was found to be a better feature selection method for ANN models than LASSO and PCA.

Hybrid models combining elastic-net and ANN methods were developed, and their performance was better than a standalone ANN model.

The BRT models gave far-reaching information about the relationships between the input variables and the target variables.

Both the ANN and BRT methods produced interpretable models for predicting particulate matter with good model—observation agreement.

Download fulltext PDF

Author: A. Suleiman - M. R. Tight - A. D. Quinn

Source: https://link.springer.com/

Related documents