Enhancing thermoelectric properties of isotope graphene nanoribbons via machine learning guided manipulation of disordered antidots and interfaces

•The thermoelectric properties of isotope graphene nanoribbons via machine learning guided manipulation of disordered antidots and interfaces is enhanced up to 5.69 times that of the pristine one.•The heteroatoms (isotope) tend to form a continuous interface barrier perpendicular to the carrier transport direction to suppress the propagation of phonons through pure isotope-substituted armchair graphene nanoribbons.•The antidot structure significantly improves armchair graphene nanoribbon thermoelectric properties by reducing thermal conductivity and increasing thermoelectric power factor compared to the pure isotope structure.