No abstract

No abstract

India is a country where every religion and community celebrates their culture. Festivals have an important role in Indian culture and are celebrated whole-heartedly by the citizens. Most of these celebrations culminate to causing pollution especially noise pollution due to festivities and rituals. One such festival is Ganesh Chaturthi or Ganeshotsav which is magnificently celebrated in Maharashtra state of India. In the present study, noise pollution levels during Ganeshotsav at famous community pandals in Mumbai city were monitored in the year 2020. Noise level data was analyzed based on indices such as L 10, L 50, L 90, noise pollution level (LNP ) and noise climate (NC). Comparison of noise levels was carried out for the collected data during Ganesh Chaturthi in the previous years of 2018 and 2019. The city witnessed simple festival celebration in eco-friendly manner leading to significant decrease in noise levels due to CoVID-19 pandemic. The pandemic situation is an eye-opener for the city administration with demonstration in reduction of noise pollution. Many aspects of the pandemic can be carried forward in making new guidelines and policies to curtail pollution and eco-friendly celebration of festivals.

The artificial neural networks share its working analogous with the human brain; and by using these artificial neural models, various complex nonlinear relationships can be modeled which cannot be described easily using mathematical equations. In this study, groundwater quality at a sanitary landfill site used for solid waste disposal was modeled using artificial neural networks. The groundwater quality was assessed for two consecutive years 2016 and 2017 at ten locations near the site, and the data were used for modeling. Total hardness was predicted using neural networks by using three learning algorithms, and the best one was used in the final model for prediction. The interpolation maps were drawn for both the years to understand the total hardness concentrations at unsampled locations using ArcGIS Geostatistical Analyst Extension, and Inverse Distance Weighing method was used. The percentage effect of spatial and temporal changes on total hardness was calculated by doing the sensitivity analysis and thus finding the relative importance of each input parameter on total hardness. Different algorithms were tested to select the best-performing algorithm with optimal neural architecture.