Rolling resistance (RR) is one of the key factors that researchers are trying to minimize due to its significant contribution to greenhouse gas emission and global climate change. This study investigates the impact of asphalt pavement surface distress on RR and its subsequent environmental cost. Motivated by the objective to quantify the environmental implications of deteriorating pavement surfaces, the research aims to facilitate improved prediction of RR using a data-driven Machine Learning (ML) approach, and quantify the environmental cost of surface distress attributable to RR. The study employs a multi-phase methodology, which begins with accurate estimation of pavement texture parameters, followed by an analysis of the effect of surface distress on texture properties. A Random Forest (RF) regression model is used for predicting rolling resistance coefficient (RRC) and the predictions by the model are compared with the predictions by an empirical linear regression model to demonstrate the improvement in prediction performance. RRC values predicted for pavements of different distress levels reveal a clear upward trend of RRC with increasing distress severity, which suggests a strong relation between surface distress and RR. Tire penetration level is calculated for surfaces with different distresses under varying loads. The results reveal non-linear growth in rubber deformation under load, with greater penetration for distressed surface, which suggests direct impact of surface distress on energy loss. Using the predicted RRC values, energy loss, fuel consumption and CO2 emissions associated with RR are calculated for each distress level. Standard carbon pricing is applied to estimate the associated environmental cost. The additional fuel cost borne by road users is also quantified. Results show that increased surface distress results in higher fuel consumption, CO2 emission and corresponding environmental cost attributable to RR. The findings demonstrate the dual economic and environmental burden of pavement distress and underscore the importance of timely pavement maintenance. The study contributes a comprehensive methodology for assessing pavement distress-induced environmental cost and supports data-driven decision-making in pavement asset management.