Stochastic multiscale modeling of heat conductivity of Polymeric clay nanocomposites

•We propose a stochastic multiscale method to quantify the heat conductivity of polymeric nanocomposites (PNCs) with clay reinforcement•We systematically studied the effects of different parameters on the thermal conductivity of composites.•The most influential input parameters are the aspect ratio followed by the volume fraction.•The Kapitza Resistance has no significant effect on the thermal conductivity of the PNCs.•We show that the most accurate surrogate model is the moving least square (MLS).