Atmosphere

Research

17 pages, 3948 KiB

Open AccessEditor’s ChoiceArticle

Modeling of Organic Aerosol in Seoul Using CMAQ with AERO7

by Hyeon-Yeong Park, Sung-Chul Hong, Jae-Bum Lee and Seog-Yeon Cho

Atmosphere 2023, 14(5), 874; https://doi.org/10.3390/atmos14050874 - 16 May 2023

Cited by 1 | Viewed by 1499

The Community Multiscale Air Quality (CMAQ) model with the 7th generation aerosol module (AERO7) was employed to simulate organic aerosol (OA) in Seoul, Korea, for the year 2016. The goal of the present study includes the 1-year simulation of OA using WRF-CMAQ with [...] Read more.

The Community Multiscale Air Quality (CMAQ) model with the 7th generation aerosol module (AERO7) was employed to simulate organic aerosol (OA) in Seoul, Korea, for the year 2016. The goal of the present study includes the 1-year simulation of OA using WRF-CMAQ with recently EPA-developed AERO7 with pcVOC (potential VOC from combustion) scale factor revision and analysis of the seasonal behavior of OA surrogate species in Seoul. The AERO7, the most recent version of the aerosol module of the CMAQ model, includes a new secondary organic aerosol (SOA) species, pcSOA (potential SOA from combustion), to resolve the inherent under-prediction problem of OA. The AERO7 classified OA into three groups: primary organic aerosol (POA), anthropogenic SOA (ASOA), and biogenic SOA (BSOA). Each OA group was further classified into 6~15 individual OA surrogate species according to volatility and oxygen content to model the aging of OA and the formation of SOA. The hourly emissions of POA and SOA precursors were compiled and fed into the CMAQ to successfully simulate seasonal variations of OA compositions and ambient organic-matter to organic-carbon ratios (OM/OC). The model simulation showed that the POA and ASOA were major organic groups in the cool months (from November to March) while BSOA was a major organic group in the warm months (from April to October) in Seoul. The simulated OM/OCs ranged from 1.5~2.1 in Seoul, which agreed well with AMS measurements in Seoul in May 2016. Full article

(This article belongs to the Special Issue Air Quality Prediction and Modeling)

► Show Figures

Figure 1

14 pages, 4316 KiB

Open AccessArticle

Correlating Air Pollution Concentrations and Vehicular Emissions in an Italian Roadway Tunnel by Means of Low Cost Sensors

by Saverio De Vito, Antonio Del Giudice, Gerardo D’Elia, Elena Esposito, Grazia Fattoruso, Sergio Ferlito, Fabrizio Formisano, Giuseppe Loffredo, Ettore Massera, Patrizia Bellucci, Francesca Ciarallo and Girolamo Di Francia

Atmosphere 2023, 14(4), 679; https://doi.org/10.3390/atmos14040679 - 4 Apr 2023

Cited by 1 | Viewed by 1567

Abstract

There is an increasing scientific interest in studying vehicular traffic pollution in road tunnels. This is due both to the interest in evaluating the effect that the different polluting gases can have on the driving style of motorists and also to the hypothesis [...] Read more.

There is an increasing scientific interest in studying vehicular traffic pollution in road tunnels. This is due both to the interest in evaluating the effect that the different polluting gases can have on the driving style of motorists and also to the hypothesis that tunnels could be considered as closed systems in which the vehicular traffic–pollution correlation is easier to study because it is more easily separated from other effects. In this work, a system of low-cost IoT sensor nodes for the detection of carbon monoxide (CO), nitrogen dioxide (NO₂), ozone (O₃), particulate matters (PM₁, PM_2.5, PM₁₀), relative humidity (RH) and temperature (T) has been installed in an Italian tunnel, where vehicular traffic has been measured and classified for type of vehicles. The results of the measurement campaign, which lasted 3 months, from April to June 2022, allowed us to state that road tunnels actually behave like closed and isolated systems in which pollution may be directly correlated to the traffic volume and type. Furthermore, data show that quite high values of the major pollutants are observable in the tunnel in comparison to the external environment. As such, IoT sensor nodes may contribute to a distributed measuring approach on the road tunnel system mechanics assessment including, as an example, the operational impacts of forced ventilation. Full article

(This article belongs to the Special Issue Air Quality Prediction and Modeling)

► Show Figures

Figure 1

32 pages, 6371 KiB

Open AccessArticle

Performance of Bayesian Model Averaging (BMA) for Short-Term Prediction of PM₁₀ Concentration in the Peninsular Malaysia

by Norazrin Ramli, Hazrul Abdul Hamid, Ahmad Shukri Yahaya, Ahmad Zia Ul-Saufie, Norazian Mohamed Noor, Nor Amirah Abu Seman, Ain Nihla Kamarudzaman and György Deák

Atmosphere 2023, 14(2), 311; https://doi.org/10.3390/atmos14020311 - 4 Feb 2023

Cited by 6 | Viewed by 2044

Abstract

In preparation for the Fourth Industrial Revolution (IR 4.0) in Malaysia, the government envisions a path to environmental sustainability and an improvement in air quality. Air quality measurements were initiated in different backgrounds including urban, suburban, industrial and rural to detect any significant [...] Read more.

In preparation for the Fourth Industrial Revolution (IR 4.0) in Malaysia, the government envisions a path to environmental sustainability and an improvement in air quality. Air quality measurements were initiated in different backgrounds including urban, suburban, industrial and rural to detect any significant changes in air quality parameters. Due to the dynamic nature of the weather, geographical location and anthropogenic sources, many uncertainties must be considered when dealing with air pollution data. In recent years, the Bayesian approach to fitting statistical models has gained more popularity due to its alternative modelling strategy that accounted for uncertainties for all air quality parameters. Therefore, this study aims to evaluate the performance of Bayesian Model Averaging (BMA) in predicting the next-day PM₁₀ concentration in Peninsular Malaysia. A case study utilized seventeen years’ worth of air quality monitoring data from nine (9) monitoring stations located in Peninsular Malaysia, using eight air quality parameters, i.e., PM₁₀, NO₂, SO₂, CO, O₃, temperature, relative humidity and wind speed. The performances of the next-day PM₁₀ prediction were calculated using five models’ performance evaluators, namely Coefficient of Determination (R²), Index of Agreement (IA), Kling-Gupta efficiency (KGE), Mean Absolute Error (MAE), Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE). The BMA models indicate that relative humidity, wind speed and PM₁₀ contributed the most to the prediction model for the majority of stations with (R² = 0.752 at Pasir Gudang monitoring station), (R² = 0.749 at Larkin monitoring station), (R² = 0.703 at Kota Bharu monitoring station), (R² = 0.696 at Kangar monitoring station) and (R² = 0.692 at Jerantut monitoring station), respectively. Furthermore, the BMA models demonstrated a good prediction model performance, with IA ranging from 0.84 to 0.91, R² ranging from 0.64 to 0.75 and KGE ranging from 0.61 to 0.74 for all monitoring stations. According to the results of the investigation, BMA should be utilised in research and forecasting operations pertaining to environmental issues such as air pollution. From this study, BMA is recommended as one of the prediction tools for forecasting air pollution concentration, especially particulate matter level. Full article

(This article belongs to the Special Issue Air Quality Prediction and Modeling)

► Show Figures

Figure 1

16 pages, 3247 KiB

Open AccessArticle

Co-Training Semi-Supervised Learning for Fine-Grained Air Quality Analysis

by Yaning Zhao, Li Wang, Nannan Zhang, Xiangwei Huang, Lunke Yang and Wenbiao Yang

Atmosphere 2023, 14(1), 143; https://doi.org/10.3390/atmos14010143 - 9 Jan 2023

Viewed by 1640

Abstract

Due to the limited number of air quality monitoring stations, the data collected are limited. Using supervised learning for air quality fine-grained analysis, that is used to predict the air quality index (AQI) of the locations without air quality monitoring stations, may lead [...] Read more.

Due to the limited number of air quality monitoring stations, the data collected are limited. Using supervised learning for air quality fine-grained analysis, that is used to predict the air quality index (AQI) of the locations without air quality monitoring stations, may lead to overfitting in that the models have superior performance on the training set but perform poorly on the validation and testing set. In order to avoid this problem in supervised learning, the most effective solution is to increase the amount of data, but in this study, this is not realistic. Fortunately, semi-supervised learning can obtain knowledge from unlabeled samples, thus solving the problem caused by insufficient training samples. Therefore, a co-training semi-supervised learning method combining the K-nearest neighbors (KNN) algorithm and deep neural network (DNN) is proposed, named KNN-DNN, which makes full use of unlabeled samples to improve the model performance for fine-grained air quality analysis. Temperature, humidity, the concentrations of pollutants and source type are used as input variables, and the KNN algorithm and DNN model are used as learners. For each learner, the labeled data are used as the initial training set to model the relationship between the input variables and the AQI. In the iterative process, by labeling the unlabeled samples, a pseudo-sample with the highest confidence is selected to expand the training set. The proposed model is evaluated on a real dataset collected by monitoring stations from 1 February to 30 April 2018 over a region between 118° E–118°53′ E and 39°45′ N–39°89′ N. Practical application shows that the proposed model has a significant effect on the fine-grained analysis of air quality. The coefficient of determination between the predicted value and the true value is 0.97, which is better than other models. Full article

(This article belongs to the Special Issue Air Quality Prediction and Modeling)

► Show Figures

Figure 1

15 pages, 2849 KiB

Open AccessArticle

A PM_2.5 Concentration Prediction Model Based on CART–BLS

by Lin Wang, Yibing Wang, Jian Chen and Xiuqiang Shen

Atmosphere 2022, 13(10), 1674; https://doi.org/10.3390/atmos13101674 - 13 Oct 2022

Cited by 1 | Viewed by 1366

Abstract

With the development of urbanization, the hourly PM_2.5 concentration in the air is constantly changing. In order to improve the accuracy of PM_2.5 prediction, a prediction model based on the Classification and Regression Tree (CART) and Broad Learning System (BLS) was [...] Read more.

With the development of urbanization, the hourly PM_2.5 concentration in the air is constantly changing. In order to improve the accuracy of PM_2.5 prediction, a prediction model based on the Classification and Regression Tree (CART) and Broad Learning System (BLS) was constructed. Firstly, the CART algorithm was used to segment the dataset in a hierarchical way to obtain a subset with similar characteristics. Secondly, the BLS model was trained by using the data of each subset, and the validation error of each model was minimized by adjusting the window number of the mapping layer in the BLS network. Finally, for each leaf in the tree, the global BLS model and the local BLS model on the path from the root node to the leaf node are compared, and the model with the smallest error is selected. The data collected in this paper come from the Chine Meteorological Historical Data website. We selected historical data from the Huaita monitoring station in Xuzhou city for experimental analysis, which included air pollutant content and meteorological data. Experimental results show that the prediction effect of the CART–BLS model is better than that of RF, V-SVR, and seasonal BLS models. Full article

(This article belongs to the Special Issue Air Quality Prediction and Modeling)

► Show Figures

Figure 1

16 pages, 3162 KiB

Open AccessArticle

Predictive Analysis of In-Vehicle Air Quality Monitoring System Using Deep Learning Technique

by Abdul Syafiq Abdull Sukor, Goh Chew Cheik, Latifah Munirah Kamarudin, Xiaoyang Mao, Hiromitsu Nishizaki, Ammar Zakaria and Syed Muhammad Mamduh Syed Zakaria

Atmosphere 2022, 13(10), 1587; https://doi.org/10.3390/atmos13101587 - 28 Sep 2022

Cited by 2 | Viewed by 2230

Abstract

In-vehicle air quality monitoring systems have been seen as promising paradigms for monitoring drivers’ conditions while they are driving. This is because some in-vehicle cabins contain pollutants that can cause drowsiness and fatigue to drivers. However, designing an efficient system that can predict [...] Read more.

In-vehicle air quality monitoring systems have been seen as promising paradigms for monitoring drivers’ conditions while they are driving. This is because some in-vehicle cabins contain pollutants that can cause drowsiness and fatigue to drivers. However, designing an efficient system that can predict in-vehicle air quality has challenges, due to the continuous variation in parameters in cabin environments. This paper presents a new approach, using deep learning techniques that can deal with the varying parameters inside the vehicle environment. In this case, two deep learning models, namely Long-short Term Memory (LSTM) and Gated Recurrent Unit (GRU) are applied to classify and predict the air quality using time-series data collected from the built-in sensor hardware. Both are compared with conventional methods of machine learning models, including Support Vector Regression (SVR) and Multi-layer Perceptron (MLP). The results show that GRU has an excellent prediction performance with the highest coefficient of determination value (R²) of 0.97. Full article

(This article belongs to the Special Issue Air Quality Prediction and Modeling)

► Show Figures

Figure 1

16 pages, 833 KiB

Open AccessArticle

A New Method for the Evaluation and Visualization of Air Pollutant Level Predictions

by Jana Faganeli Pucer

Atmosphere 2022, 13(9), 1456; https://doi.org/10.3390/atmos13091456 - 8 Sep 2022

Viewed by 1080

Abstract

Accurately predicting air pollutant levels is very important for mitigating their effects. Prediction models usually fail to predict sudden large increases or decreases in pollutant levels. Conventional measures for the assessment of the performance of air pollutant prediction models provide an overall assessment [...] Read more.

Accurately predicting air pollutant levels is very important for mitigating their effects. Prediction models usually fail to predict sudden large increases or decreases in pollutant levels. Conventional measures for the assessment of the performance of air pollutant prediction models provide an overall assessment of model behavior, but do not explicitly address model behavior when large changes are observed. In our work, we propose a method to automatically label the observed large changes. We also propose two visualization methods and two measures that can help assess model performance when sudden large changes in pollutant levels occur. The developed measures enable the assessment of model performance only for large changes (MAE of large changes), or weigh the model residuals by the rate of change (WErr), making the evaluation measures “cost-sensitive”. To show the value of the novel evaluation and visualization methods, we employ them in the evaluation of three empirical examples—different statistical models used in real-life settings and a popular atmospheric dispersion model. The proposed visualizations and measures can be a valuable complement to conventional model assessment measures when the prediction of large changes is as important as (even if they are rare) or more important than predictions of other levels. Full article

(This article belongs to the Special Issue Air Quality Prediction and Modeling)

► Show Figures

Figure 1

14 pages, 1727 KiB

Open AccessArticle

Using Machine Learning Methods to Forecast Air Quality: A Case Study in Macao

by Thomas M. T. Lei, Shirley W. I. Siu, Joana Monjardino, Luisa Mendes and Francisco Ferreira

Atmosphere 2022, 13(9), 1412; https://doi.org/10.3390/atmos13091412 - 1 Sep 2022

Cited by 17 | Viewed by 3437

Abstract

Despite the levels of air pollution in Macao continuing to improve over recent years, there are still days with high-pollution episodes that cause great health concerns to the local community. Therefore, it is very important to accurately forecast air quality in Macao. Machine [...] Read more.

Despite the levels of air pollution in Macao continuing to improve over recent years, there are still days with high-pollution episodes that cause great health concerns to the local community. Therefore, it is very important to accurately forecast air quality in Macao. Machine learning methods such as random forest (RF), gradient boosting (GB), support vector regression (SVR), and multiple linear regression (MLR) were applied to predict the levels of particulate matter (PM₁₀ and PM_2.5) concentrations in Macao. The forecast models were built and trained using the meteorological and air quality data from 2013 to 2018, and the air quality data from 2019 to 2021 were used for validation. Our results show that there is no significant difference between the performance of the four methods in predicting the air quality data for 2019 (before the COVID-19 pandemic) and 2021 (the new normal period). However, RF performed significantly better than the other methods for 2020 (amid the pandemic) with a higher coefficient of determination (R²) and lower RMSE, MAE, and BIAS. The reduced performance of the statistical MLR and other ML models was presumably due to the unprecedented low levels of PM₁₀ and PM_2.5 concentrations in 2020. Therefore, this study suggests that RF is the most reliable prediction method for pollutant concentrations, especially in the event of drastic air quality changes due to unexpected circumstances, such as a lockdown caused by a widespread infectious disease. Full article

(This article belongs to the Special Issue Air Quality Prediction and Modeling)

► Show Figures

Figure 1

13 pages, 5930 KiB

Open AccessArticle

Modeling PM2.5 and PM10 Using a Robust Simplified Linear Regression Machine Learning Algorithm

by João Gregório, Carla Gouveia-Caridade and Pedro J. S. B. Caridade

Atmosphere 2022, 13(8), 1334; https://doi.org/10.3390/atmos13081334 - 22 Aug 2022

Cited by 11 | Viewed by 2519

Abstract

The machine learning algorithm based on multiple-input multiple-output linear regression models has been developed to describe PM2.5 and PM10 concentrations over time. The algorithm is fact-acting and allows for speedy forecasts without requiring demanding computational power. It is also simple enough that it [...] Read more.

The machine learning algorithm based on multiple-input multiple-output linear regression models has been developed to describe PM2.5 and PM10 concentrations over time. The algorithm is fact-acting and allows for speedy forecasts without requiring demanding computational power. It is also simple enough that it can self-update by introducing a recursive step that utilizes newly measured values and forecasts to continue to improve itself. Starting from raw data, pre-processing methods have been used to verify the stationary data by employing the Dickey–Fuller test. For comparison, weekly and monthly decompositions have been achieved by using Savitzky–Golay polynomial filters. The presented algorithm is shown to have accuracies of

30 %

for PM2.5 and

26 %

for PM10 for a forecasting horizon of 24 h with a quarter-hourly data acquisition resolution, matching other results obtained using more computationally demanding approaches, such as neural networks. We show the feasibility of using multivariate linear regression (together with the small real-time computational costs for the training and testing procedures) to forecast particulate matter air pollutants and avoid environmental threats in real conditions. Full article

(This article belongs to the Special Issue Air Quality Prediction and Modeling)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Air Quality Prediction and Modeling

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Published Papers (9 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI