We present an application of deep-learning convolutional neural network of atomic surface structures using atomic and Voronoi polyhedra-based neighbor information to predict adsorbate binding energies for the application in catalysis.

We present an application of deep-learning convolutional neural network of atomic surface structures using atomic and Voronoi polyhedra-based neighbor information to predict adsorbate binding energies for the application in catalysis.

Titanium dioxide is the most studied photocatalytic material and has been reported to be active for a wide range of reactions including oxidation of hydrocarbons and reduction of nitrogen. However, the molecular-scale interactions between the titania photocatalyst and dinitrogen are still debated, particularly in the presence of hydrocarbons. Here, we used several spectroscopic and computational techniques to identify interactions between nitrogen, methanol, and titania under illumination. Electron paramagnetic resonance spectroscopy (EPR) allowed us to observe the formation of carbon radicals upon exposure to ultraviolet radiation. These carbon radicals are observed to transform into diazo- and nitrogen-centered radicals (e.g., CHxN2* and CHxNHy*) during photocatalysis in nitrogen. In situ infrared (IR) spectroscopy under the same conditions revealed C-N stretching on titania. Furthermore, density functional theory (DFT) calculations reveal that nitrogen adsorption and the thermodynamic barrier to photocatalytic nitrogen fixation are significantly more favorable in the presence of methanol or surface carbon. These results provide compelling evidence that carbon radicals formed from the oxidation of hydrocarbons interact with dinitrogen, and suggest that the role of carbon-based ``hole scavengers'' and the inertness of nitrogen atmospheres should be reevaluated in the field of photocatalysis.