fig1

From: From descriptors to machine learning interatomic potentials: a review of AI-accelerated electrocatalyst design

Figure 1. Workflow of ARSC descriptors generation: (i) ϕ_xx, a primitive descriptor mapping atomic-property effects via d-band shape; (ii) ϕ_opt, a reactant-effect-based screening for heteronuclear DACs; (iii) ϕ_xy, ML descriptors of synergy built from ϕ_xx with physics-guided features and sparsified selection; and (iv) Φ, a universal model quantifying coordination effects with experimental verification. Reproduced with permission from Lin et al.^[12] (CC BY-NC-ND 4.0); no changes made. ARSC: Atomic property (A), Reactant (R), Synergistic (S), and Coordination effects (C); DFT: density functional theory; DACs: dual-atom catalysts; PFESS: physically meaningful feature engineering and feature selection/sparsification; ML: machine learning; CC BY-NC-ND 4.0: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.