Nanometric solid solution alloys are utilized in a broad range of fields, including catalysis, energy storage, medical application, and sensor technology. Unfortunately, the synthesis of these alloys becomes increasingly challenging as the disparity between the metal elements grows, due to differences in atomic sizes, melting points, and chemical affinities. This study utilized a data-driven approach incorporating sample balancing enhancement techniques and multilayer perceptron (MLP) algorithms to improve the model's ability to handle imbalanced data, significantly boosting the efficiency of experimental parameter optimization. Building on this enhanced data processing framework, we developed an entropy-engineered synthesis approach specifically designed to produce stable, nanometric copper and cobalt (CuCo) solid solution alloys. Under conditions of -0.425 V (vs RHE), the CuCo alloy exhibited nearly 100% Faraday efficiency (FE) and a high ammonia production rate of 232.17 mg h-1 mg-1. Stability tests in a simulated industrial environment showed that the catalyst maintained over 80% FE and an ammonia production rate exceeding 170 mg h-1 mg-1 over a testing period of 120 h, outperforming most reported catalysts. To delve deeper into the synergistic interaction mechanisms between Cu and Co, in situ Raman spectroscopy was utilized for real-time monitoring, and density functional theory (DFT) calculations further substantiated our findings. These results not only highlight the exceptional catalytic performance of the CuCo alloy but also reflect the effective electronic and energy interactions between the two metals.
Keywords: AI for Material; CuCo Nanocrystals; Entropy Engineer; Machine Learning; Nitrate Reduction Reaction; Solid Solution Alloy.