According to the United States Environmental Protection Agency, 81% of greenhouse gas emission is due to Carbon-dioxide. When fossil fuels, solid waste, trees, and wood products are burnt, Carbon-dioxide emission occurs. The concentration of Carbon-dioxide in the atmosphere is reduced when it is absorbed by plants as a part of the biological carbon cycle. The major sources of CO2 emission are from fossil fuel such as coal, natural gas, oil, cement production, gas flares used in industrial plants and bunker fuels used in ships. Increase in CO2 emission leads to the increase in global warming. Climate change, change in seasonal events and decrease in agricultural productivity are the major impacts of global warming. Hence it is important to study and analyse CO2 emission based on the recorded data across the globe. Further the major source of emission must be detected and alert messages must be sent to the pollution control boards in various countries to take necessary remedial actions. This work focuses on predicting the CO2 emission in the near future in various countries based upon the “Fossil-Fuel CO2 Emissions by Nation” dataset recorded by Carbon Dioxide Information Analysis Center (CDIAC), Oak Ridge National Laboratory. This system comprises of data cleaning, data normalization, optimization, and model building. The model built using Multiple Kernel Gaussian Process (MKGP) will predict the concentration of CO2 that may be present in the atmosphere in upcoming years. Based on the prediction the major source of CO2 emission is identified. We have studied the effects of Radial Basis Function kernel, Rational Quadratic, Periodic kernel and combinations of the kernels on India USA and China dataset. We have proposed a Multi-Kernel Gaussian Process for predicting the fossil fuel emission (MKGP - FFE). It has been inferred that combination of kernels performed well when compared to individual kernels in most of the cases.