[论文解读] Open Catalyst Experiments 2024 (OCx24): Bridging Experiments and Computational Models

Jehad Abed, Jiheon Kim+18 more|arXiv (Cornell University)|Nov 18, 2024

Catalytic Processes in Materials Science被引用 17

一句话总结

OCx24 创建了一个大规模、多样化的金属间化合物纳米颗粒实验数据集，并将其与广泛的 AI 加速的 DFT 吸附能筛选相结合，以弥合实验和用于 HER 与 CO2RR 的计算催化模型。

ABSTRACT

The search for low-cost, durable, and effective catalysts is essential for green hydrogen production and carbon dioxide upcycling to help in the mitigation of climate change. Discovery of new catalysts is currently limited by the gap between what AI-accelerated computational models predict and what experimental studies produce. To make progress, large and diverse experimental datasets are needed that are reproducible and tested at industrially-relevant conditions. We address these needs by utilizing a comprehensive high-throughput characterization and experimental pipeline to create the Open Catalyst Experiments 2024 (OCX24) dataset. The dataset contains 572 samples synthesized using both wet and dry methods with X-ray fluorescence and X-ray diffraction characterization. We prepared 441 gas diffusion electrodes, including replicates, and evaluated them using zero-gap electrolysis for carbon dioxide reduction (CO$_2$RR) and hydrogen evolution reactions (HER) at current densities up to $300$ mA/cm$^2$. To find correlations with experimental outcomes and to perform computational screens, DFT-verified adsorption energies for six adsorbates were calculated on $\sim$20,000 inorganic materials requiring 685 million AI-accelerated relaxations. Remarkably from this large set of materials, a data driven Sabatier volcano independently identified Pt as being a top candidate for HER without having any experimental measurements on Pt or Pt-alloy samples. We anticipate the availability of experimental data generated specifically for AI training, such as OCX24, will significantly improve the utility of computational models in selecting materials for experimental screening.

研究动机与目标

• 通过解决 AI 预测性能与实际观测性能之间的差距，推动绿色氢气生产和 CO2 利用的催化剂发现。
• 提供一个可重复、具有工业相关性的实验流程，涵盖用于 AI 训练的多样材料样品。
• 将高通量实验数据与大规模计算筛选相结合，推动对实验结果的预测模型的发展。
• 开发预处理和匹配方法，将实验结果与计算描述符关联起来。

提出的方法

• 使用两种技术（化学还原和火花刻蚀）合成 572 例金属间化合物纳米颗粒样品，以最大化成分与结构的多样性。
• 利用 X 射线荧光（XRF）和 X 射线衍射（XRD）对样品进行表征，以筛选单相、目标结构材料。
• 在工业相关的电流密度高达 300 mA/cm2 下，使用改进的 MEA 设置测试 CO2 还原（CO2RR）和析氢（HER）的电化学性能。
• 通过 AdsorbML 流水线（结合 AI 与 DFT 弛豫）在 ~19,406 种材料中计算六个中间体（OH、CO、CHO、C、COCOH、H）的吸附能（685 百万次松弛；~2000 万个 DFT 点）。
• 使用线性回归和随机森林回归，结合表面层和体相描述符，建立将计算描述符与实验结果联系起来的预测模型；通过 LOOC 和 LOCO 交叉验证进行评估。

Figure 1 : A summary of the computational and experimental screening efforts, and the resulting outcomes. Computationally, six adsorbates were used as descriptors and their adsorption energies were calculated across a wide swath of materials. Experimentally, two synthesis techniques were used to pre

实验结果

研究问题

• RQ1 AI 加速的计算描述符是否能够在多样化的金属间化合物集合中预测实验 HER 与 CO2RR 的性能？
• RQ2 匹配（XRD/XRF 确认）样品与未匹配样品在预测实验结果方面的泛化能力有多高？
• RQ3 在材料层面的表现中，包含吸附能描述符与包含 bulk Matminer 特征相比，额外带来的预测价值是多少？
• RQ4 是否能够从没有 Pt 含量训练样本的数据中出现 Sabatier 风险的火山型规律，这对发现低成本催化剂意味着什么？
• RQ5 数据集规模如何影响将计算与实验联系起来的模型的预测能力？

主要发现

• 对于 HER，出现了数据驱动的 Sabatier 火山图，Pt 位于顶点，但 Pt 未出现在训练数据中。
• 使用吸附能作为特征的线性模型在 HER 预测中的 R2 约为 ≈0.59（LOO），并在包含更多能量时约为 ≈0.61，在某些情况下优于仅 Matminer 的模型。
• 对于 CO2RR，LOCO 指示泛化能力较弱（H2 和液体显示适度相关；CO 几乎无相关）。
• 在匹配和未匹配样本上的联合训练比仅使用匹配样本的预测性能更好。
• 预测的 HER 催化候选材料包括低成本、非 Pt 成分的材料；大量材料（包括含 Se 的和 Mo 基合金）成为潜在催化剂。
• 模型性能随训练数据集增大而提升，预测在 10^4–10^5 样本时预计有显著提升。

Figure 2 : This figure illustrates the experimental pipeline, detailing the process from synthesis to characterization and testing. (right) Cu baselines for the two synthesis techniques and a reference technique using spray coated nanoparticles. Similar trends across current densities are seen for a