Bayesian optimization of nanoporous materials
Bayesian optimization of nanoporous materials
复制标题
DOI：
10.1039/d1me00093d
复制
发表时间：
2021-10-06
影响因子：
3.6
通讯作者：
Doppa, Janardhan Rao
中科院分区：
文献类型：
--
作者：
Deshwal, Aryan;Simon, Cory M.;Doppa, Janardhan Rao
纳米多孔材料（npm）可用于存储、捕获和感知许多不同的气体。给定一个吸附任务，我们通常希望在npm库中搜索具有最佳吸附性能的npm。NPM合成和气体吸附测量的高成本，无论这些实验是在实验室还是在模拟中，往往排除了详尽的搜索。我们解释、演示并提倡贝叶斯优化（BO）在NPM库中主动搜索最优NPM，并使用最少的实验找到它。并购的两个组成部分是代理模型和获取函数。代理模型是一个概率模型，反映了我们对npm -结构-属性关系的看法，这是基于过去实验的观察结果。获取函数使用代理模型根据为下一个实验挑选NPM的效用对每个NPM进行评分。它平衡了两个相互竞争的目标：(a)利用我们当前对结构-属性关系的近似来选择我们认为[在不确定性下]将表现最好的NPM， (b)探索我们尚未访问过的NPM空间区域，选择我们不确定的NPM并改进我们对结构-属性关系的近似。我们通过搜索一个类似于70,000个假设共价有机框架（COFs）的开放数据库来证明BO具有最高模拟甲烷输送能力的COF（与车载吸附天然气储存相关）。BO找到了最优的COF，在仅评估了140个相似的COF后，获得了排名前100位最高的COF中的30%。此外，BO搜索比进化和单次监督机器学习方法更有效。
Nanoporous materials (NPMs) could be used to store, capture, and sense many different gases. Given an adsorption task, we often wish to search a library of NPMs for the one with the optimal adsorption property. The high cost of NPM synthesis and gas adsorption measurements, whether these experiments are in the lab or in a simulation, often precludes exhaustive search. We explain, demonstrate, and advocate Bayesian optimization (BO) to actively search for the optimal NPM in a library of NPMs-and find it using the fewest experiments. The two ingredients of BO are a surrogate model and an acquisition function. The surrogate model is a probabilistic model reflecting our beliefs about the NPM-structure-property relationship based on observations from past experiments. The acquisition function uses the surrogate model to score each NPM according to the utility of picking it for the next experiment. It balances two competing goals: (a) exploitation of our current approximation of the structure-property relationship to pick the NPM we believe [under uncertainty] will be the highest-performing, and (b) exploration of regions of NPM space we have not visited, to pick an NPM we are uncertain about and improve our approximation of the structure-property relationship. We demonstrate BO by searching an open database of similar to 70 000 hypothetical covalent organic frameworks (COFs) for the COF with the highest simulated methane deliverable capacity (pertinent for vehicular adsorbed natural gas storage). BO finds the optimal COF and acquires similar to 30% of the top 100 highest-ranked COFs after evaluating only similar to 140 COFs. More, BO searches more efficiently than evolutionary and one-shot supervised machine learning approaches.