A Comparison of Machine Learning Methods to Forecast Tropospheric Ozone Levels in Delhi

IoT-based monitoring system and air quality prediction using machine learning for a healthy environment in Cameroon

This paper is aimed at developing an air quality monitoring system using machine learning (ML), Internet of Things (IoT), and other elements to predict the level of particulate matter and gases in the air based on the air quality index (AQI). It is an air quality assessor and therefore a means of achieving the Sustainable Development Goals (SDGs), in particular, SDG 3.9 (substantial reduction of the health impacts of hazardous substances) and SDG 11.6 (reduction of negative impacts on cities and populations). AQI quantifies and informs the public about air pollutants and their adverse effects on public health. The proposed air quality monitoring device is low-cost and operates in real-time. It consists of a hardware unit that detects various pollutants to assess air quality as well as other airborne particles such as carbon dioxide (CO2), methane (CH4), volatile organic compounds (VOCs), nitrogen dioxide (NO2), carbon monoxide (CO), and particulate matter with an aerodynamic diameter of 2.5 microns or less (PM2.5). To predict air quality, the device was deployed from November 1, 2022, to February 4, 2023, in certain bauxite-rich areas of Adamawa and certain volcanic sites in western Cameroon. Therefore, machine learning algorithm models, namely, multiple linear regression (MLR), support vector regression (SVR), random forest regression (RFR), XGBoost (XGB), and K-nearest neighbors (KNN) were applied to analyze the collected concentrations and predict the future state of air quality. The performance of these models was evaluated using mean absolute error (MAE), coefficient of determination (R-square), and root mean square error (RMSE). The obtained data in this study show that these pollutants are present in selected localities albeit to different extents. Moreover, the AQI values obtained range from 10 to 530, with a mean of 132.380 ± 63.705, corresponding to moderate air quality state but may induce an adverse effect on sensitive members of the population. This study revealed that XGB regression performed better in air quality forecasting with the highest R-squared (test score of 0.9991 and train score of 0.9999) and lowest RMSE (test score of 1.5748 and train score of 0. 0073) and MAE (test score of 0.0872 and train score of 0.0020), while the KNN model had the worst prediction (lowest R-squared and highest RMSE and MAE). This embryonic work is a prototype for projects in Cameroon as measurements are underway for a national spread over a longer period of time.

Urban ozone variability using automated machine learning: inference from different feature importance schemes

Tropospheric ozone is an air pollutant at the ground level and a greenhouse gas which significantly contributes to the global warming. Strong anthropogenic emissions in and around urban environments enhance surface ozone pollution impacting the human health and vegetation adversely. However, observations are often scarce and the factors driving ozone variability remain uncertain in the developing regions of the world. In this regard, here, we conducted machine learning (ML) simulations of ozone variability and comprehensively examined the governing factors over a major urban environment (Ahmedabad) in western India. Ozone precursors (NO2, NO, CO, C5H8 and CH2O) from the CAMS (Copernicus Atmosphere Monitoring Service) reanalysis and meteorological parameters from the ERA5 (European Centre for Medium-Range Weather Forecast's (ECMWF) fifth-generation reanalysis) were included as features in the ML models. Automated ML (AutoML) fitted the deep learning model optimally and simulated the daily ozone with root mean square error (RMSE) of ~2 ppbv reproducing 84-88% of variability. The model performance achieved here is comparable to widely used ML models (RF-Random Forest and XGBoost-eXtreme Gradient Boosting). Explainability of the models is discussed through different schemes of feature importance, including SAGE (Shapley Additive Global importancE) and permutation importance. The leading features are found to be different from different feature importance schemes. We show that urban ozone could be simulated well (RMSE = 2.5 ppbv and R2 = 0.78) by considering first four leading features, from different schemes, which are consistent with ozone photochemistry. Our study underscores the need to conduct science-informed analysis of feature importance from multiple schemes to infer the roles of input variables in ozone variability. AutoML-based studies, exploiting potentials of long-term observations, can strongly complement the conventional chemistry-transport modelling and can also help in accurate simulation and forecast of urban ozone.

Classification of COVID-19 X-ray images using transfer learning with visual geometrical groups and novel sequential convolutional neural networks

COVID-19 is a highly transmissible infectious disease that remains a substantial challenge. The utilization of chest radiology, particularly X-ray imaging, has proven to be highly effective, easily accessible, and cost-efficient in detecting COVID-19. A dataset named COVID-Xray-5k, consisting of imbalanced X-ray images of COVID-19-positive and normal subjects, is employed for investigation. The research introduces a novel methodology that utilizes conventional machine learning (ML), such as local binary patterns (LBP) for feature extraction and support vector machines (SVM) for classification. In addition, transfer learning is employed with the Visual Geometry Group 16-layer (VGG16) and 19-layer (VGG19) models. Besides, novel sequential convolutional neural network (CNN) architectures are presented to develop an autonomous system for classifying COVID-19. One of the proposed CNN architectures classifies the test dataset with an F1 score of 91.00% and an accuracy of 99.45% based on an empirical investigation to determine optimal hyper-parameters. The methods presented in the research show promising potential for COVID-19 classification, irrespective of class imbalance.•Employment of ML models to investigate subjective feature engineering and classification.•Transfer learning was employed for VGG16 and VGG19 with eight distinct models.•Illustration of two novel CNN sequential architectures; all the investigation is performed with and without weighted sampling.

Importance of ozone precursors information in modelling urban surface ozone variability using machine learning algorithm

Surface ozone (O\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$_3$$\end{document}3) is primarily formed through complex photo-chemical reactions in the atmosphere, which are non-linearly dependent on precursors. Even though, there have been many recent studies exploring the potential of machine learning (ML) in modeling surface ozone, the inclusion of limited available ozone precursors information has received little attention. The ML algorithm with in-situ NO information and meteorology explains 87% (R\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$^{2}$$\end{document}2 = 0.87) of the ozone variability over Munich, a German metropolitan area, which is 15% higher than a ML algorithm that considers only meteorology. The ML algorithm trained for the urban measurement station in Munich can also explain the ozone variability of the other three stations in the same city, with R\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$^{2}$$\end{document}2 = 0.88, 0.91, 0.63. While the same model robustly explains the ozone variability of two other German cities’ (Berlin and Hamburg) measurement stations, with R\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$^{2}$$\end{document}2 ranges from 0.72 to 0.84, giving confidence to use the ML algorithm trained for one location to other locations with sparse ozone measurements. The inclusion of satellite O\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$_3$$\end{document}3 precursors information has little effect on the ML model’s performance.