A novel bagging ensemble approach for predicting summertime ground-level ozone concentration.
01 Feb 2019-Journal of The Air & Waste Management Association (Taylor & Francis)-Vol. 69, Iss: 2, pp 220-233
TL;DR: The feasibility of using ensemble model with seven meteorological parameters as input variables to predict the surface level O3 concentration andagged random forest predicted the ground level ozone better with higher Nash-Sutcliffe coefficient than conventional models.
Abstract: Ozone pollution appears as a major air quality issue, e.g. for the protection of human health and vegetation. Formation of ground level ozone is a complex photochemical phenomenon and involves numerous intricate factors most of which are interrelated with each other. Machine learning techniques can be adopted to predict the ground level ozone. The main objective of the present study is to develop the state-of-the-art ensemble bagging approach to model the summer time ground level ozone in an industrial area comprising a hazardous waste management facility. In this study, the feasibility of using ensemble model with seven meteorological parameters as input variables to predict the surface level O3 concentration. Multilayer perceptron, RTree, REPTree, and Random forest were employed as the base learners. The error measures used for checking the performance of each model includes IoAd, R2, and PEP. The model results were validated against an independent test data set. Bagged random forest predicted the ground level ozone better with higher Nash-Sutcliffe coefficient 0.93. This study scaffolded the current research gap in big data analysis identified with air pollutant prediction. Implications: The main focus of this paper is to model the summer time ground level O3 concentration in an Industrial area comprising of hazardous waste management facility. Comparison study was made between the base classifiers and the ensemble classifiers. Most of the conventional models can well predict the average concentrations. In this case the peak concentrations are of importance as it has serious effect on human health and environment. The models developed should also be homoscedastic.
Citations
More filters
TL;DR: In this article, the performance of photocatalysts is evaluated in terms of quantum yield, space-time yield, and other operational variables, including mode of operation, irradiation time, and relative humidity.
Abstract: Hydrogen sulfide (H2S) is regarded as a broad-spectrum poison associated with severe health consequences. Among the available treatment options, photocatalytic technology may be effectively applied to the production of hydrogen gas through the splitting of H2S molecules and the addition of 79.9 kJ mol−1 of energy. As a result, advanced photo-reactive media may provide a win-win strategy to treat the parent pollutant (H2S) while producing hydrogen gas. This review encompasses both TiO2 and non-TiO2 catalysts capable of operating under ultraviolet, visible, and solar light irradiation. The performances of photocatalysts are assessed in terms of quantum yield, space-time yield, and other operational variables, including mode of operation, irradiation time, and relative humidity. The concept of space velocity is used to compare photocatalysts in reference to benchmark parameters for the treatment of H2S. This review addresses current limitations and future prospects of the application of photocatalytic technology to efficiently mitigate H2S pollution.
68 citations
TL;DR: This study critically investigates, analyses, and summarizes the existing soft computing modeling approaches in air quality modeling, and reviews and discusses artificial neural network (ANN), support vector machine (SVM), evolutionary ANN and SVM, the fuzzy logic model, neuro-fuzzy systems, the deep learning model, ensemble, and other hybrid models.
Abstract: Air quality models simulate the atmospheric environment systems and provide increased domain knowledge and reliable forecasting. They provide early warnings to the population and reduce the number of measuring stations. Due to the complexity and non-linear behavior associated with air quality data, soft computing models became popular in air quality modeling (AQM). This study critically investigates, analyses, and summarizes the existing soft computing modeling approaches. Among the many soft computing techniques in AQM, this article reviews and discusses artificial neural network (ANN), support vector machine (SVM), evolutionary ANN and SVM, the fuzzy logic model, neuro-fuzzy systems, the deep learning model, ensemble, and other hybrid models. Besides, it sheds light on employed input variables, data processing approaches, and targeted objective functions during modeling. It was observed that many advanced, reliable, and self-organized soft computing models like functional network, genetic programming, type-2 fuzzy logic, genetic fuzzy, genetic neuro-fuzzy, and case-based reasoning are rarely explored in AQM. Therefore, the partially explored and unexplored soft computing techniques can be appropriate choices for research in the field of air quality modeling. The discussion in this paper will help to determine the suitability and appropriateness of a particular model for a specific modeling context.
20 citations
TL;DR: In this paper , a general framework for creating ensembles in the context of classification is proposed, which consists of four stages: objectives, data preparing, model training, and model testing.
7 citations
TL;DR: In this paper , the authors conducted a literature review on full-scale big data in forecasting research and provided an overall review of big data-based forecasting research, details what, where and how big data improved prediction, and offers insights into future prospects.
6 citations
TL;DR: In this article, the authors conduct a literature review on full-scale big data analytics in forecasting research and provide insights into future prospects, including where forecasting hotspots and analysis and forecasting methods used.
6 citations
References
More filters
TL;DR: The interplay between the ABL depth evolution and the onset of the upvalley wind during the morning transition period significantly governs the air quality in a valley and could be an important component in the studies of mountain meteorology and air quality.
61 citations
"A novel bagging ensemble approach f..." refers background in this paper
...fluctuations on shorter time scales and the possibility of overprediction during the periods of extensive cloud cover (Pal et al. 2014)....
[...]
...Also, these models tend to underestimate the magnitude of fluctuations on shorter time scales and the possibility of overprediction during the periods of extensive cloud cover (Pal et al. 2014)....
[...]
TL;DR: The results show that a combination of preprocessing methods and ensemble algorithms can effectively forecast ozone threshold exceedances and confirms that regional data facilitate better forecasting.
Abstract: The objective of this study was to apply preprocessing and ensemble artificial intelligence classifiers to forecast daily maximum ozone threshold exceedances in the Hong Kong area. Preprocessing methods, including over-sampling, under-sampling, and the synthetic minority over-sampling technique, were employed to address the imbalance data problem. Ensemble algorithms are proposed to improve the classifier's accuracy. Moreover, a distance-based regional data set was generated to capture ozone transportation characteristics. The results show that a combination of preprocessing methods and ensemble algorithms can effectively forecast ozone threshold exceedances. Furthermore, this study advises on the relative importance of the different variables for ozone pollution prediction and confirms that regional data facilitate better forecasting. The results of this research can be promoted by the Hong Kong authorities for improving the existing forecasting tools. Moreover, the results can facilitate researchers' selection of the appropriate techniques in their future research. Display Omitted Prediction of daily ozone exceedances in Hong Kong using Artificial Intelligence.Intelligent preprocessing methods and Ensemble models were applied for prediction.Forecast was based on the local and regional pollution and meteorological data.Regional data helped to perform better forecasting than local data did.Identification of ozone generation and ozone transportation behaviors.
60 citations
"A novel bagging ensemble approach f..." refers background or methods in this paper
...In recent years, researchers have focused on advanced models like ensemble models, which showed better performance than standard single machine learning classifiers (Gong and Ordieres-Meré 2016)....
[...]
...With the development of data mining tools, machine learning techniques such as multilayer perceptron (Mishra and Goyal 2016), support vector machine (Gong and Ordieres-Meré 2016), and the ensemble approach (bagging) (Al Abri et al. 2015) have gained much interest, For example, neural networks…...
[...]
TL;DR: Analysis of the role of temperature, wind speed, wind direction, and NO2 level on ground- level ozone concentrations over the region of Eastern Texas, USA showed that the spatial mean of ground-level ozone concentrations was highly dependent on the spatialmean of NO2 concentrations.
Abstract: The influence of local climatic factors on ground-level ozone concentrations is an area of increasing interest to air quality management in regards to future climate change. This study presents an analysis on the role of temperature, wind speed, wind direction, and NO2 level on ground-level ozone concentrations over the region of Eastern Texas, USA. Ozone concentrations at the ground level depend on the formation and dispersion processes. Formation process mainly depends on the precursor sources, whereas, the dispersion of ozone depends on meteorological factors. Study results showed that the spatial mean of ground-level ozone concentrations was highly dependent on the spatial mean of NO2 concentrations. However, spatial distributions of NO2 and ozone concentrations were not uniformed throughout the study period due to uneven wind speeds and wind directions. Wind speed and wind direction also played a significant role in the dispersion of ozone. Temperature profile in the area rarely had any effects on the ozone concentrations due to low spatial variations.
58 citations
"A novel bagging ensemble approach f..." refers background in this paper
...Owing to its strong oxidizing power, O3 can damage the lung tissue (Gorai et al. 2015) and weaken the immune system of human beings....
[...]
TL;DR: In this paper, the authors reviewed the interrelationship among boundary layer, urbanization, and evolution of ozone, with particular emphasis on how boundary layer dynamics and urbanization affects ozone under different meteorological and climatological conditions.
Abstract: This paper reviews the interrelationship among boundary layer, urbanization, and evolution of ozone, with particular emphasis on how boundary layer dynamics and urbanization affects the evolution of ozone under different meteorological and climatological conditions. The aim of this work is not only to provide an exhaustive investigation of individual ozone episodes but to look at the underlying issues and hypotheses that are available for understanding the evolution of ozone. The review concludes with a summary of the current state of knowledge and outlines some of the remaining questions. It is the intention of this paper to serve as an ecumenical reference to the community for reappraising the relation of boundary layer climate to the evolution of ozone in an urban setting, especially on a peculiar feature of ozone dynamic, nocturnal ozone maxima. To date, there is still no overarching consensus on the mechanisms that lead to its formation. The importance of levels of urbanization and advantage of ascertaining the substantial weights of the respective mixing height and emission structure in exploring the relationship between ozone evolutions should not be overlooked.
55 citations
TL;DR: The neural network models displayed a high degree of interaction among inputs, and it is likely the ability of these model types to account for interactions, rather than the nonlinearity of individual input variables, that explains their improved forecast skill.
Abstract: Empirical models for predicting daily maximum hourly average ozone concentrations were developed for 10 monitoring stations in the Lower Fraser Valley (LFV) of British Columbia. According to data from 1991 to 1996, ensemble neural network models increased explained variance an average of 7% over multiple linear regression models using the same input variables. Without modification, all models performed poorly on days when the observed peak ozone concentration exceeded 82 parts per billion, the National Ambient Air Quality Objective. When numbers of extreme events in training data were increased using a histogram equalization process, models were able to forecast exceedances with improved accuracy. Modified generalized additive model (GAM) plots and associated measures of input variable importance and interaction were generated for a subset of the trained models and used to investigate relationships between input variables and ozone levels. The neural network models displayed a high degree of interaction among inputs, and it is likely the ability of these model types to account for interactions, rather than the nonlinearity of individual input variables, that explains their improved forecast skill. Inspection of GAM-style plots indicated that the relative importance of input variables in the ensemble neural network models varied with geographic location within the LFV. Four distinct groups of stations were identified, and rankings of inputs within the groups were generally consistent with physical intuition and results of prior studies.
53 citations