Understanding how roadside concentrations of NO x are influenced by the background levels, traffic density, and meteorological conditions using Boosted Regression Trees

Sayegh, Arwa; Tate, James; Ropkins, Karl

doi:10.1016/j.atmosenv.2015.12.024

Cited by 59 publications

(40 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Carslaw and Taylor [41] analyzed the influence of each variable on nitrogen oxide (NOx) concentrations at a mixed source location using the BRT method. Similar research was conducted by Sayegh, Tate, and Ropkins [40] regarding roadside NOx concentrations, which also considered multiple variables, including background concentrations of NOx, traffic density, and meteorological conditions. In recent years, BRT models have been used for epidemiological studies, such as hand, foot and mouth disease [42][43][44].…”

Section: The Role Of Meteorological Elements In Relation To Pmmentioning

confidence: 96%

“…The BRT model contains two robust algorithms: regression trees and boosting. The regression trees technique eliminates interactions among predictors by recursive binary splits, while the boosting algorithm uses an iterative method to develop a tree ensemble consisting of many small regression trees to improve stability and predictive performance [37,40].…”

Section: The Role Of Meteorological Elements In Relation To Pmmentioning

confidence: 99%

See 1 more Smart Citation

Characteristics of Particulate Pollution (PM2.5 and PM10) and Their Spacescale-Dependent Relationships with Meteorological Elements in China

Chen

Zeng

et al. 2017

Sustainability

View full text Add to dashboard Cite

Particulate matter (PM) pollution in China has an obvious characteristic of spatial distribution. It is well known that intensive anthropogenic activities, such as fossil fuel combustion and biomass burning, have great influence on the spatial distribution of PM pollution. However, the spacescale-dependent relationships between PM concentrations and weather conditions remain unclear. Here, we investigated the characteristics of two types of particulate pollution, including PM 2.5 and PM 10 , and their spatial relationships with meteorological elements in 173 cities throughout China from March 2014 to February 2015. Results: (1) High PM 2.5 concentrations were distinctly located southeast of the Hu Line, and high PM 10 concentrations were distinctly situated north of the Yangtze River; (2) Spacescale-dependent relationships were found between PM pollution and meteorological elements. The influence of temperature had similar inverted V-shaped characteristics, namely, there was serious PM pollution when temperature was about 15 • C, and there was slight PM pollution when temperature was less or more than 15 • C. Annual precipitation, wind speed, and relative humidity were negatively correlated with PM, while annual atmospheric pressure was positively correlated with PM; (3) The ideal meteorological regions were identified according to the quantified spatial relationships between PM and meteorological elements, which could be defined by a combination of the following conditions: (a) temperature <10 • C or >21 • C; (b) precipitation >1500 mm; (c) atmospheric pressure <900 hPa; (d) wind speed >3 m/s; and (e) relative humidity >65%, where air pollutants can easily be scavenged. The success of this research provides a meteorological explanation to the spatial distribution characteristics of PM pollution in China.

show abstract

Section: The Role Of Meteorological Elements In Relation To Pmmentioning

confidence: 96%

Section: The Role Of Meteorological Elements In Relation To Pmmentioning

confidence: 99%

Characteristics of Particulate Pollution (PM2.5 and PM10) and Their Spacescale-Dependent Relationships with Meteorological Elements in China

Chen

Zeng

et al. 2017

Sustainability

View full text Add to dashboard Cite

show abstract

“…For instance, some data mining methods such as support vector machine [34] and artificial neural networks (ANNs) [59] have been applied in different realms of science and engineering. The Ensemble prediction has become increasingly popular in chemistry [60,61].…”

Section: Ensemble Prediction Modelsmentioning

confidence: 99%

Application of AI in Modeling of Real System in Chemistry

Azqhandi¹,

Shekari²

2018

Artificial Intelligence - Emerging Trends and Applications

View full text Add to dashboard Cite

In recent years, discharge of synthetic dye waste from different industries leading to aquatic and environmental pollution is a serious global problem of great concern. Hence, the removal of dye prediction plays an important role in wastewater management and conservation of nature. Artificial intelligence methods are popular owing due to its ease of use and high level of accuracy. This chapter proposes a detailed review of artificial intelligence-based removal dye prediction methods particularly multiple linear regression (MLR), artificial neural networks (ANNs), and least squares-support vector machine (LS-SVM). Furthermore, this chapter will focus on ensemble prediction models (EPMs) used for removal dye prediction. EPMs improve the prediction accuracy by integrating several prediction models. The principles, advantages, disadvantages, and applications of these artificial intelligence-based methods are explained in this chapter. Furthermore, future directions of the research on artificial intelligence-based removal dye prediction methods are discussed.

show abstract

“…Three methods can be used to estimate the optimal number of iterations through the fitted GBM: the independent test set (test), out-of-bag estimation (OOB), and cross-validation [21], [18]. In a recent study, [23] extended the model developed by [22] to model nitrogen oxides (NO x ), meteorological variables and traffic variables from the City of Leeds UK data. Results show an agreement that BRT technique showing a good result to visualize BRT output graphically in term of the partial dependence plots [23].…”

mentioning

confidence: 99%

“…In a recent study, [23] extended the model developed by [22] to model nitrogen oxides (NO x ), meteorological variables and traffic variables from the City of Leeds UK data. Results show an agreement that BRT technique showing a good result to visualize BRT output graphically in term of the partial dependence plots [23].…”

mentioning

confidence: 99%

The used of the Boosted Regression Tree Optimization Technique to Analyse an Air Pollution data.

Yahaya¹,

Ibrahim²,

Yahaya³

2019

IJRTE

View full text Add to dashboard Cite

The stochastic boosted regression trees (BRT) technique has the capability to quantify and explain the relationships between explanatory variables. We applied this machine learning modelling technique to derive the relationships between the gases air pollutants, meteorological conditions and time system variables of particulate matter (PM10) concentrations. In order to get lowest prediction error and to avoid over-fitting, the parameters of the BRT model need to be tuned. In this experiment, 25 BRT models were generated from 14 years’ worth of hourly data (122,736 a one hour averaged data from January 2000 to December 2013 gathered from four Continuous Automated Air Quality Monitoring Stations in peninsular Malaysia (located in Klang, Selangor (CA0011), Perai, Penang (CA0003), Kota Bharu, Kelantan (CA0022) and Kemaman, Terengganu (CA0002)). Seventy percent of the data were used for training and 30 percent for validation of the models. An experiment was conducted to determine the best iteration that could model hourly PM10 concentrations by optimizing the BRT parameter which are learning rate (lr), tree complexity (tc) and number of trees (nt). Five different lr (0.001, 0.005, 0.01, 0.05 and 0.1) were tested with different tree complexities (1 to 20) in the BRT model development process. From the experiment, the combination of lr = 0.05 and tc = 5 for the training set for the BRT model achieved the lowest root mean squared error (RMSE) compared to the other tested combinations. It was also found that the number of trees increased with the increment in the number of samples. A high coefficient of determinant (R2 ) value (0.90) for the linear relationship between the number of samples and nt was found for all the four stations. The optimum number of trees for the model was estimated by using 10-fold cross-validation. It was found that the best number of iterations for Klang, Perai, Kota Bahru and Kemaman were 12,327, 32,987, 16,370 and 57,634, respectively. The prediction accuracy of the model was tested by using the fraction of prediction namely a factor of two (FAC2), mean bias, mean gross error, RMSE, correlation coefficient (R), and index of agreement (IOA). The prediction performance of the final BRT model based on the R value was 0.81, 0.78, 0.85 and 0.81 for for Perai, Kemaman, Klang and Kota Bahru, respectively, which indicates that the BRT model developed and applicability of this can be used in other atmospheric environment data.

show abstract

Understanding how roadside concentrations of NO x are influenced by the background levels, traffic density, and meteorological conditions using Boosted Regression Trees

Cited by 59 publications

References 21 publications

Characteristics of Particulate Pollution (PM2.5 and PM10) and Their Spacescale-Dependent Relationships with Meteorological Elements in China

Characteristics of Particulate Pollution (PM2.5 and PM10) and Their Spacescale-Dependent Relationships with Meteorological Elements in China

Application of AI in Modeling of Real System in Chemistry

The used of the Boosted Regression Tree Optimization Technique to Analyse an Air Pollution data.

Contact Info

Product

Resources

About