Water is an essential resource for human existence. In fact, more than 60% of the human body is made up of water. Our bodies consume water in every cell, in the different organisms and in the tissues. Hence, water allows stabilization of the body temperature and guarantees the normal functioning of the other bodily activities. Nevertheless, in recent years, water pollution has become a serious problem affecting water quality. Therefore, to design a model that predicts water quality is nowadays very important to control water pollution, as well as to alert users in case of poor quality detection. Motivated by these reasons, in this study, we take the advantages of machine learning algorithms to develop a model that is capable of predicting the water quality index and then the water quality class. The method we propose is based on four water parameters: temperature, pH, turbidity and coliforms. The use of the multiple regression algorithms has proven to be important and effective in predicting the water quality index. In addition, the adoption of the artificial neural network provides the most highly efficient way to classify the water quality.

Machine learning algorithms for efficient water quality prediction

https://doi.org/10.1016/j.apr.2022.101600

Increased tropospheric ozone levels as a public health issue during COVID-19 lockdown and estimation the related pulmonary diseases

Relative humidity plays an important role in climate change and global warming, making it a research area of greater concern in recent decades. The present study attempted to implement seasonal autoregressive moving average (SARIMA) and artificial neural network (ANN) with multilayer perceptron (MLP) models to forecast the monthly relative humidity in Delhi, India during 2017-2025. The average monthly relative humidity data for the period 2000-2016 have been used to carry out the objectives of the proposed study. The forecast trend in relative humidity declines from 2017 to 2025. The accuracy of the models has been measured using root mean squared error (RMSE) and mean absolute error (MAE). The results showed that the SARIMA model provides the forecasted relative humidity with RMSE of 6.04 and MAE of 4.56. On the other hand, MLP model reported the forecasted relative humidity with RMSE of 4.65 and MAE of 3.42. This study concluded that the ANN model was more reliable for predicting relative humidity than SARIMA model.The online version contains supplementary material available at 10.1007/s40808-022-01385-8. 

/pdf/forecasting-of-monthly-relative-humidity-in-delhi-india-3rc2lly1.pdf

Forecasting of monthly relative humidity in Delhi, India, using SARIMA and ANN models

Ozone pollution and related pulmonary diseases in Iran

Graph convolutional network – Long short term memory neural network- multi layer perceptron- Gaussian progress regression model: A new deep learning model for predicting ozone concertation

Tropospheric ozone (O3), as an air pollutant is increasing at an alarming rate in urban areas. The concentration of ozone is affected by precursor pollutants, such as particulate matter (PM10, PM2.5), carbon monoxide (CO), nitrogen dioxide (NO2), sulfur dioxide (SO2), carbon dioxide (CO2), and nitric oxide (NO), and meteorological parameters, such as air temperature (AT), relative humidity (RH), global solar radiation (SR), wind direction (WD), and wind speed (WS) of the area. Ozone is a secondary pollutant and strong oxidizing agent injurious to human health. The present study aimed to identify the most crucial factors that influence ozone formation and to develop an ozone prediction model using artificial neural network with optimal inputs. The data obtained from Limbayat, real-time air pollutants monitoring station of Surat city, have been used to evolve the model, followed by feature selection techniques, namely, sensitivity analysis, Boruta algorithm, and recursive feature elimination algorithm (RFE). Finally, 6/14 influencing parameters have been identified using an attribute selection approach. Interestingly, “hour of the day” was found the most prominent and governing parameter among the 14 parameters after applying various feature selection techniques in the experiments. The result showed that the efficiency of the prediction model was 79.4% when six parameters were used in the machine learning algorithms.

Prediction of tropospheric ozone using artificial neural network (ANN) and feature selection techniques

Introduction: Deteriorated air quality in nation like India contributes to the health burden. The AirQ+ is used to estimate short-term and long-term health impact attributable to surface Ozone (O3) in Surat city. Average hourly ozone concentration data and other criteria pollutants retrieved from January 2018 to December 2019 from two monitoring stations (Limbayat and Varachha). 
Materials and methods: In this study, the Respiratory Mortality (RM), Cardiovascular Mortality (CM), Total Mortality (TM), Hospital Admissions with Cardiovascular Disease (HACVD), and Hospital Admissions with Respiratory Disease (HARD), as well as Respiratory Mortality-Long-Term (LT-RM) were quantified. Baseline Incidence (BI) data were obtained from literature and Relative Risk (RR) values were referred from World Health Organization (WHO). An annual Sum of Maximum 8 h Ozone means over 35 ppb (SOMO35), 70 µg/m3, used as a predictor of potential long-term health effects. 
Results: More ozone concentration were observed in winter and pre-monsoon than concentration formed in southwest monsoon and post-monsoon seasons.The average of O3 concentration for Limbayat are 71.61 (±0.39) µg/m3 and 29.76 (±1.86) µg/m3 and for Varachha are 61.17 9 (±6.15) µg/m3, 11.32 (±1.35) µg/m3 during 2018 and 2019, respectively and the obtained cumulative number of cases of death are estimated 136, 45, 172 and 18 persons respectively. Total hospital admission due to cardiovascular and respiratory diseases are found 435, 134, 552 and 58 at Limbayat and Varachha during 2018 and 2019. LT- RM is attributed to ozone concentration having the most significant value, 6.8% and 4.62% at Limbayat and Varachha in 2018. 
Conclusion: More hospital admissions are found than mortality rates using AirQ+ tool. It can be used to estimate public health in context of mortality and morbidity rates which helps to develop air quality management programs and policy makers to reduce the impact of air pollution on health.

Drashti Kapadia

Papers

Prediction of tropospheric ozone using artificial neural network (ANN) and feature selection techniques

Estimation of health impact using AirQ+ model attributed to surface ozone in sub-regions of Surat city, India