Search

Over the past few years, the concentration of fine particulate matter (PM2.5) in Delhi's atmosphere has progressively increased, resulting in smog episodes and affecting people's health. Therefore, accurate and reliable forecasting of PM2.5 concentration is essential to guide effective precautions before and during extreme pollution events. In this work, soft computing techniques, including Artificial Neural Network and Gaussian Process Regression are employed to predict PM2.5 concentrations in Delhi. Four models, namely, multi-layer feed-forward neural network (MLFFNN), General regression neural network, Gaussian process regression with ARD squared exponential kernel (GPARD_sqexp) and Gaussian process regression with ARD rational quadratic kernel (GPARD_rat_quad) are built using meteorological and air quality data corresponding to a two-year period (2015–2016). The results of the study suggested that MLFFNN showed the best prediction performance among the four models, with testing correlation coefficient (R) 0.949, Root mean square error 30.193, Nash–Sutcliffe efficiency index 0.892 and Mean absolute error 18.388. Moreover, sensitivity analysis performed to understand the importance of different input variables reported that PM10, wind speed, air quality index and aerodynamic roughness coefficient (Z0) are the most critical parameters influencing MLFFNN model forecasts. On the whole, the work has demonstrated that the artificial neural network model is more capable of dealing with PM2.5 forecasting in Delhi urban area than the Gaussian process regression model. [ABSTRACT FROM AUTHOR]

The present study intends to use machine learning (ML) and deep learning (DL) models to forecast PM2.5 concentration at a location in Delhi. For this purpose, multi-layer feed-forward neural network (MLFFNN), support vector machine (SVM), random forest (RF) and long short-term memory networks (LSTM) have been applied. The air pollutants, e.g., CO, Ozone, PM10, NO, NO2, NOx, NH3, SO2, benzene, toluene, as well as meteorological parameters (temperature, wind speed, wind direction, rainfall, evaporation, humidity, pressure, etc.), have been used as inputs in the present study. Moreover, this is one of the first papers that employ aerodynamic roughness coefficient as an input parameter for the prediction of PM2.5 concentration. The result of the study shows that the LSTM model with index of agreement (IA) 0.986, root mean square error (RMSE) 21.510, Nash–Sutcliffe efficiency index (NSE) 0.945, (coefficient of determination)R2 0.945, and (correlation coefficient)R 0.972 is the best performing technique for the prediction of PM2.5 followed by MLFFNN, SVM, and RF models. The sensitivity analysis for the LSTM model reported that PM10, wind speed, NH3, and benzene are the key influencing parameters for the estimation of PM2.5. The findings in this work suggest that the LSTM could advance in PM2.5 forecasting and thus would be useful for developing fine-scale, state-of-the-art air pollution forecasting models. [ABSTRACT FROM AUTHOR]

A part of Mansehra Granite was selected for the assessment of radiological hazards. The average activity concentrations of 226Ra, 232Th and 40K were found to be 27.32, 50.07 and 953.10 Bq kg−1, respectively. These values are in the median range when compared with the granites around the world. Radiological hazard indices and annual effective doses were estimated. All of these indices were found to be within the criterion limits except outdoor external dose (82.38 nGy h−1) and indoor external dose (156.04 nGy h−1), which are higher than the world's average background levels of 51 and 55 nGy h−1, respectively. These values correspond to an average annual effective dose of 0.867 mSv y−1, which is less than the criterion limit of 1 mSv y−1 (ICRP-103). Some localities in the Mansehra city have annual effective dose higher than the limit of 1 mSv y−1. Overall, the Mansehra Granite does not pose any significant radiological health hazard in the outdoor or indoor. [ABSTRACT FROM PUBLISHER]

The present study intends to use machine learning (ML) and deep learning (DL) models to forecast PM 2.5 concentration at a location in Delhi. For this purpose, multi-layer feed-forward neural network (MLFFNN), support vector machine (SVM), random forest (RF) and long short-term memory networks (LSTM) have been applied. The air pollutants, e.g., CO, Ozone, PM 10 , NO, NO 2 , NO x , NH 3 , SO 2 , benzene, toluene, as well as meteorological parameters (temperature, wind speed, wind direction, rainfall, evaporation, humidity, pressure, etc.), have been used as inputs in the present study. Moreover, this is one of the first papers that employ aerodynamic roughness coefficient as an input parameter for the prediction of PM 2.5 concentration. The result of the study shows that the LSTM model with index of agreement (IA) 0.986, root mean square error (RMSE) 21.510, Nash-Sutcliffe efficiency index (NSE) 0.945, (coefficient of determination)R 2 0.945, and (correlation coefficient)R 0.972 is the best performing technique for the prediction of PM 2.5 followed by MLFFNN, SVM, and RF models. The sensitivity analysis for the LSTM model reported that PM 10 , wind speed, NH 3 , and benzene are the key influencing parameters for the estimation of PM 2.5 . The findings in this work suggest that the LSTM could advance in PM 2.5 forecasting and thus would be useful for developing fine-scale, state-of-the-art air pollution forecasting models., (© 2022. The Author(s), under exclusive licence to Springer Nature Switzerland AG.)