Machine Learning Tailored Anodes for Efficient Hydrogen Energy Generation in Proton-Conducting Solid Oxide Electrolysis Cells

Abstract

In the global trend of vigorously developing hydrogen energy, proton-conducting solid oxide electrolysis cells (P-SOECs) have attracted significant attention due to their advantages of high efficiency and not requiring precious metals. However, the application of P-SOECs faces challenges, particularly in developing high-performance anodes possessing both high catalytic activity and ionic conductivity. In this study, La0.9Ba0.1Co0.7Ni0.3O3−δ (LBCN9173) and La0.9Ca0.1Co0.7Ni0.3O3−δ (LCCN9173) oxides are tailored as promising anodes by machine learning model, achieving the synergistic enhancement of water oxidation reaction kinetics and proton conduction, which is confirmed by comprehensively analyzing experiment and density functional theory calculation results. Furthermore, the anodic reaction mechanisms for P-SOECs with these anodes are elucidated by analyzing distribution of relaxation time spectra and Gibbs energy of water oxidation reaction, manifesting that the dissociation of H2O is facilitated on LBCN9173 anode. As a result, P-SOEC with LBCN9173 anode demonstrates a top-rank current density of 2.45 A cm−2 at 1.3 V and an extremely low polarization resistance of 0.05 Ω cm2 at 650 °C. This multi-scale, multi-faceted research approach not only discovered a high-performance anode but also proved the robust framework for the machine learning-assisted design of anodes for P-SOECs.

1. Introduction

Hydrogen energy has emerged as a promising solution due to its eco-friendliness and high energy density. Current hydrogen energy production technologies operate across various temperature ranges: alkaline water electrolyzers (AWEs) and proton exchange membrane electrolysis cells (PEMECs) at low temperatures (50–90 °C), and oxide-ion conducting and proton-conducting solid oxide electrolysis cells (O-SOECs and P-SOECs) at intermediate-to-high temperatures (400–900 °C) [1]. Among these, AWEs are commercially mature, benefiting from their independence from noble metal catalysts, long-term stability, and low costs. However, they are hindered by high electrode overpotentials, gas crossover, and low current densities (0.2–0.4 A cm−2) [2]. PEMWEs, known for their rapid response and high efficiency, are promising for hydrogen generation but remain reliant on noble metal catalysts. In contrast, solid oxide electrolysis cells (SOECs), particularly P-SOECs, are attracting much attention in renewable energy applications for their high electrolysis efficiency (up to 1 A cm−2) and cost-effectiveness without the need for noble metal catalysts [2–6]. P-SOECs are especially promising for intermediate temperature (400–700 °C) hydrogen production, offering advantages such as lower activation energy and faster proton migration compared to oxide-ion conducting counterparts. This positions P-SOECs as a superior choice for efficient and sustainable hydrogen energy production.

However, the widespread application of P-SOECs still faces numerous challenges, including electrochemical performance optimization of key materials, interface issues, fabrication of large-scale high-performance cells, etc. [2, 6–10]. Developing high-performance anodes for P-SOECs is particularly challenging, which involves the adsorption and dissociation of steam, conduction of oxide ions (O2−) and protons, and the transfer of four electrons [2]. Therefore, achieving efficient synergy between the catalytic activity of steam oxidation and ionic/electronic conductivity is the key for designing high-performance anodes. Traditional Co-based perovskite oxides (such as La1−xSrxCo1−yFeyO3−δ (LSCF) and Ba1−xSrxCo1−yFeyO3−δ (BSCF)) exhibit good catalytic activity and O2−/e− conductivity, called mixed ionic-electronic conductors (MIECs) [11, 12]. However, these conventional materials, such as Ba0.5Sr0.5Co0.8Fe0.2O3−δ, exhibit significantly higher TECs (~19–21 × 10–6 K−1) compared to those (