Machine Learning Guided Synthesis of Multinary Chevrel Phase Chalcogenides
Machine Learning Guided Synthesis of Multinary Chevrel Phase Chalcogenides
复制标题
机器学习引导多元 Chevrel 相硫属化物的合成
DOI：
10.1021/jacs.1c02971
复制
发表时间：
2021
影响因子：
15
通讯作者：
Musgrave, Charles B.
中科院分区：
文献类型：
--
作者：
Singstock, Nicholas R.;Ortiz-Rodríguez, Jessica C.;Perryman, Joseph T.;Sutton, Christopher;Velázquez, Jesús M.;Musgrave, Charles B.
Chevrel相（CP）是一类钼硫属化物，在下一代电池材料、电催化剂和其他能源应用中表现出引人注目的性能。尽管有希望，但CP的探索不足，由于识别可合成相的挑战，迄今为止仅合成了1000种化合物。我们提出了一种可解释的机器学习描述符（Hδ），可以快速准确地估计分解焓（ΔHd）以评估CP稳定性。为了发展H δ，我们首先用密度泛函理论计算了438个CP组分的Δ Hd。然后，我们使用新的机器学习方法SIFT生成了超过56万个描述符，该方法为开发准确和可解释的化学模型提供了一种易于使用的方法。从一组> 200000的成分中，我们确定了48501个CP，H δ预测是可合成的，基于标准ΔHd< 65 meV/atom，这是从67个实验合成的CP中获得的统计边界。候选CP的集合包括2307 CP碲化物，一个未被探索的CP子集，其具有预测的对阳离子嵌入物占据通道位点的偏好，这在CP中是罕见的。我们成功地合成了五个新的CP碲化物尝试从这一组，并证实了他们的偏好通道网站占领。我们的联合计算和实验方法，用于开发和验证筛选工具，使可合成材料的快速识别在一个稀疏的类可能转移到其他材料的家庭，以加快他们的发现。
The Chevrel phase (CP) is a class of molybdenum chalcogenides that exhibit compelling properties for next-generation battery materials, electrocatalysts, and other energy applications. Despite their promise, CPs are underexplored, with only ∼100 compounds synthesized to date due to the challenge of identifying synthesizable phases. We present an interpretable machine-learned descriptor (Hδ) that rapidly and accurately estimates decomposition enthalpy (ΔHd) to assess CP stability. To developHδ, we first used density functional theory to compute ΔHdfor 438 CP compositions. We then generated >560 000 descriptors with the new machine learning method SIFT, which provides an easy-to-use approach for developing accurate and interpretable chemical models. From a set of >200 000 compositions, we identified 48 501 CPs thatHδpredicts are synthesizable based on the criterion that ΔHd< 65 meV/atom, which was obtained as a statistical boundary from 67 experimentally synthesized CPs. The set of candidate CPs includes 2307 CP tellurides, an underexplored CP subset with a predicted preference for channel site occupation by cation intercalants that is rare among CPs. We successfully synthesized five of five novel CP tellurides attempted from this set and confirmed their preference for channel site occupation. Our joint computational and experimental approach for developing and validating screening tools that enable the rapid identification of synthesizable materials within a sparse class is likely transferable to other materials families to accelerate their discovery.