Exploring LaCoO₃'s Catalytic Efficiency for Water Splitting Through Computational Methods

Water splitting, a promising approach for renewable energy production, relies on efficient catalysts to drive the oxygen and hydrogen evolution reactions. In this study, we investigated the potential of the perovskite oxide LaCoO ₃ as an effective water splitting catalyst by analyzing its catalytic properties using a combination of density functional theory (DFT) calculations and machine learning techniques. The LaCoO ₃ catalyst was modeled as a slab and subjected to DFT calculations in a 8 by 8 grid of multiple adsorbates. The calculations revealed the different adsorption energies involved in the water splitting process, providing valuable insights into the interactions between LaCoO ₃ and water molecules as well as a measurement of its overall catalytic efficiency. To speed up the computational process, machine learning algorithms were utilized to predict DFT calculations without the need for time-consuming calculations. By training the model on our dataset of precomputed DFT results, we developed a predictive model capable of estimating the adsorption energies for LaCoO ₃ and other similar perovskites.