Membrane electrode assembly (MEA) electrolyzers can perform stable, high-rate carbon dioxide (CO₂) electroreduction for renewable fuels and chemicals, thereby realizing effective carbon utilization to mitigate anthropogenic CO₂ emissions. Here, we present a numerical, multiphysics model, computationally intensified 60-fold with a machine learning analysis of computational and experimental data, to address the most urgent systems challenges in CO₂ MEA electrolyzers: mitigating carbonate and liquid product crossover to increase CO₂ utilization and energy efficiency. We explore the effect of varying the applied potential, CO₂ partial pressure, ion-exchange membrane thickness, membrane porosity, and membrane charge on these three metrics. By selectively tuning these physical system parameters, we identify conditions that realize negligible CO₂ reactant loss, a 2-fold enhancement in CO₂ utilization, and a 2-fold decrease in Nernstian overpotential, corresponding to a multi-carbon, full-cell energy efficiency of 21%. These results may direct future MEA system designs and motivate thin anion-exchange membrane structures.

膜电极组件 (MEA) 电解槽可以对可再生燃料和化学品进行稳定、高速率的二氧化碳 (CO ₂ ) 电还原，从而实现有效的碳利用以减少人为 CO ₂排放。在这里，我们提出了一个数值、多物理场模型，通过对计算和实验数据的机器学习分析，计算增强了 60 倍，以解决 CO ₂ MEA 电解槽中最紧迫的系统挑战：减轻碳酸盐和液体产品交叉以提高 CO ₂利用率和能源效率。我们探索改变外加电位 CO _{2 的影响}分压、离子交换膜厚度、膜孔隙率和膜电荷这三个指标。通过选择性地调整这些物理系统参数，我们确定了实现可忽略不计的 CO ₂反应物损失、CO ₂利用率提高2 倍以及能斯脱过电位降低 2 倍的条件，对应于多碳全电池能量效率为 21%。这些结果可能会指导未来的 MEA 系统设计并激发薄的阴离子交换膜结构。