Universal scaling relations for the rational design of molecular water oxidation catalysts with near-zero overpotential

Abstract

A major roadblock in realizing large-scale production of hydrogen via electrochemical water splitting is the cost and inefficiency of current catalysts for the oxygen evolution reaction (OER). Computational research has driven important developments in understanding and designing heterogeneous OER catalysts using linear scaling relationships derived from computed binding energies. Herein, we interrogate 17 of the most active molecular OER catalysts, based on different transition metals (Ru, Mn, Fe, Co, Ni, and Cu), and show they obey similar scaling relations to those established for heterogeneous systems. However, we find that the conventional OER descriptor underestimates the activity for very active OER complexes as the standard approach neglects a crucial one-electron oxidation that many molecular catalysts undergo prior to O-O bond formation. Importantly, this additional step allows certain molecular catalysts to circumvent the "overpotential wall", leading to enhanced performance. With this knowledge, we establish fundamental principles for the design of ideal molecular OER catalysts.

Fig. 1

Catalytic cycles for the two primary reaction pathways proposed for the OER

Fig. 2

Molecular OER catalysts investigated in this work, taken from refs. ^–,–. Chemical structures correspond to the vacancy intermediate in the OER mechanisms depicted in Fig. 1. The 4-picoline ligands in Ru-3-5 and Ru-9 have been replaced by “pic” for clarity

Fig. 3

Linear scaling relation between the HO^∗ and HOO^∗ intermediates for the molecular OER catalysts investigated in this work and depicted in Fig. 2. The shaded blue region represents a 99% confidence interval for the linear model

Fig. 4

2D-volcano representations featuring different OER descriptors. a Volcano plot using the conventional OER descriptor. Full markers denote catalysts which are theoretically predicted to undergo an additional ET step before O–O formation (see Supplementary Table 3). The red shaded area indicates the optimal range for the conventional OER descriptor. b Volcano plot including only the molecular catalysts predicted to undergo an additional ET. In this volcano, the calculated Gibbs energy for the additional ET from the M(IV)-oxo to M(V)-oxo intermediate is represented in the x-axis as a new OER descriptor. Note, the same scale and the left leg of the volcano in a has been used for comparability. The dotted line in b is drawn to guide the eye towards an ideal OER catalyst. The potential limiting step on each side of the two volcano plots is indicated in red text

Fig. 5

Three-dimensional volcano representations including. a OER catalysts following the conventional 4-PET pathway and b catalysts theoretically predicted to undergo the additional ET step before O–O formation. The PLS on each region of the volcano plots is indicated

Fig. 6

Gibbs energy diagram for Ru-1 calculated at 0 V (solid lines) and 1.98 V (dashed lines) vs. RHE. Blue lines represent the I2M mechanism while the pale orange lines represent the conventional WNA mechanism

Fig. 7

Proposed approach for the accelerated discovery of ideal OER catalysts