Geological sequestration of CO 2 in a coal seam is considered an attractive option to reduce the carbon footprint. It has an additional advantage of enhancing the recovery of coalbed methane, which has less sorption affinity toward coal in comparison to CO 2 . Desorption of gases from coal is controlled by various parameters, including reservoir depth and coal rank. A representative factor for desorption and diffusion in coal is the sorption time. It is an indicator which helps in estimation and evaluation of gas movement in the coal seam. Coals exhibiting high sorption time allow greater quantities of CO 2 injection and hold potential for CO 2 sequestration. Therefore, reliable and cost-effective estimation of sorption time is very important prior to investment in projects related to CO 2 sequestration. Generally, proximate and gas content analyses are part of the preliminary analysis of coal for the assessment of its potential as a coal-bed methane reservoir. In this study, data generated using these analyses were found very useful for estimating the sorption time and CO 2 sequestration potential of coal. The coal samples were collected from different depths of the Mand Raigarh coalfield for testing, and an empirical equation and artificial neural network (ANN)-based model have been developed to predict the sorption time of coal. The developed empirical equation predicts the sorption time with a coefficient of determination value of 0.88 and a root mean squared error value of ±1.07 days. Furthermore, the developed ANN model has been found to be very efficient in prediction with a correlation coefficient value of 0.97.