Abstract
This study presents an innovative method for predicting ambient temperature fluctuations using a robust mathematical model that incorporates both environmental pollutants and other meteorological factors across different months. The primary objective was to establish a correlation model that integrates variables such as carbon monoxide, CO, nitrogen dioxide, NO2, carbon dioxide, CO2, ozone, O3, along with model-specific parameters like baseline temperature, Y0, phase shift, Xc, angular frequency, w, and amplitude, A). Data was collected monthly, from January to June, to analyse the direct impact of these pollutants and parameters on ambient temperature. The correlation constants calculated for each month demonstrate how environmental conditions and pollution levels dynamically influence temperature predictions. Initial findings reveal significant variations in the constants that correlate with changes in pollutant concentrations, suggesting a sensitive interplay between environmental quality and temperature. This study enhances our understanding of temperature dynamics in urban settings and could contribute to more effective environmental monitoring and climate management strategies. The approach underscores the importance of integrating comprehensive environmental data in predictive models to better anticipate temperature changes and potentially mitigate adverse climate impacts.