This study seeks to comprehend the complicated processes impacting carbon emissions by studying historical data on energy use, population dynamics, and economic growth. Particularly in a growing country like India, the importance of exact models in capturing the delicate interplay between many factors and carbon emissions is stressed. To determine the association between independent factors and carbon emissions, the research uses regression models, such as Linear Regression, Random Forest Regressor, Gradient Boosting Regressor, and Support Vector Regressor (SVR). Additionally, time series models such as Autoregressive Integrated Moving Average with Exogenous Variable (ARIMAX) and Seasonal Autoregressive Integrated Moving Average with Exogenous variable (SARIMAX) are employed to identify temporal patterns in the data. The findings reveal that the Linear Regression model outperformed all other models across key metrics, demonstrating its accuracy and ability to explain variance in carbon emissions, particularly when trained on resampled data, which significantly improved model performance. Through the evaluation of performance metrics and visual representations, the results and discussion section analyze the accuracy and robustness of the models. The linear regression model is the most proficient in forecasting carbon emissions, exhibiting consistently low errors, a high R-squared score, and an Explained Variance Score.