Fig. 1: High-throughput virtual screening schematics and performance of ML model. | Nature Communications

Fig. 1: High-throughput virtual screening schematics and performance of ML model.

From: Data-driven discovery of electrocatalysts for CO2 reduction using active motifs-based machine learning

Fig. 1

a Schematics of the high-throughput virtual screening strategy to discover selective CO2RR catalysts. b Parity plots of ML-predicted (∆EML) and DFT-calculated (∆EDFT) binding energy of CO* (red), H* (green) and OH* (blue). The prediction mean absolute error (MAE) values were calculated by averaging MAEs of fivefold splits (Table S1).

Back to article page