This study presents a physics-informed neural network framework to model droplet spreading dynamics on unstructured rough surfaces, using training data generated from high-fidelity lattice Boltzmann method simulations. The droplet is represented by phase-field density field, where interface evolution is governed by multiphase flow physics, surface tension, and wall wettability effects. Unlike conventional data-driven models, the PINN incorporates the underlying physi- cal laws such as mass and momentum conservation directly into the loss function, enabling accurate prediction even with the sparse data. The trained model successfully captures the droplet dynamics over different time periods, contact line evolution, and interfacial deformation across time, showing high accuracy as compared with the CNNs. This PINN-based surrogate offers a comutationally efficient, mesh-free alternatives to traditional solvers, making it ideal for rapid parametric studies and design optimized microfluidic devices and wettability-controlled systems.