Conventional catalyst design has enhanced reactivity and product selectivity through control of surface thermochemistry by tunable surface composition and the surrounding environment (e.g., pore structure). In this work, the prospect for electric field towards controlling product selectivity and reaction networks on the Pt(111) surface was evaluated with periodic density functional theory (DFT) calculations in concert with machine learning (ML) algorithms. Linear scaling relationships (LSRs) for adsorption energies of surface species in electric field were shown to: (i) be distinct as compared to zero-field LSRs across metals, and (ii) linearly correlate with adsorption energies of H* rather than the binding element. The slope of LSRs linearly correlated with the zero-field dipole moment. A random forest ML regression algorithm predicted field-dependent adsorption energies with a mean absolute error (0.12 eV) comparable to DFT. Overall, this study identifies the path forward for electric field-assisted catalysis, specifically towards catalyst poisoning, product selectivity, and control of reaction pathways.