Author(s): Arun Kumar Chaudhary, Lal Babu Sah Telee, Murari Karki and Vijay Kumar

Abstract: This article analyzes the air quality status of the Kathmandu city using a novel and flexible probability distribution called the Modified Inverse Exponentiated Exponential Poisson distribution. This distribution is crafted by incorporating an extra shape parameter into the Inverse Exponentiated Exponential Poisson distribution. Several statistical features of the suggested model are derived and analyzed. A real data set was utilized to assess the model's suitability for the air quality data of Kathmandu, Nepal, spanning the years 2017 to 2021.In order to examine the actual ground-level air quality conditions, we conducted the data analysis for particulate matter 2.5 (P_2.5). Furthermore, we have studied the parameter estimation, model validation and model comparisons of proposed model with existing models for P2.5 at Ratnapark station, Kathmandu. The model's parameters are estimated through Maximum Likelihood estimation (MLE). The P-P and Q-Q charts are plotted to check the graphical validation of the model. To compare the suitability of the models, Akaike, Corrected Akaike, Hannan-Quinn and Bayesian Information criteria are used. Anderson-Darling (An) test, Cramer-Von Mises (CVM) test, Kolmogorov-Smirnov (KS) test, along with their corresponding p-values are used to show the better fitting of the proposed model. ARIMA model is applied for time series analysis of air pollution data of PM_2.5 from during years 2017-2021. We also discovered that the basic exponential smoothing approach gives a good forecast model for PM_2.5 data from 2017 to 2021.

DOI: 10.22271/maths.2024.v9.i4b.1783

Pages: 125-138 | Views: 167 | Downloads: 14

Download Full Article: Click Here