arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2302.13380cond-mat.mtrl-scics.LG
收藏

闭环纠错学习加速热电材料的实验发现

Closed-loop Error Correction Learning Accelerates Experimental Discovery of Thermoelectric Materials

University of Toronto(多伦多大学);King Abdullah University of Science and Technology (KAUST)(阿卜杜拉国王科技大学)

Hitarth Choubisa, Md Azimul Haque, Tong Zhu, Lewei Zeng, Maral Vafaie, Derya Baran, Edward H Sargent

AI总结:

针对热电材料探索空间大、掺杂与合成路径复杂的难题,提出结合历史数据与实验反馈的闭环纠错学习方法,发现新型高性能PbSe:SnSb热电材料,且实验效率较传统高通量机器学习搜索提升多达3倍。

摘要:

考虑到庞大的材料空间,再加上掺杂带来的指数级自由度以及合成路径的多样性,热电材料的探索极具挑战性。本研究旨在引入历史数据,并通过采用纠错学习(ECL)利用实验反馈来更新和优化数据。我们由此从先前的数据集中学习,随后让模型适配那些原本难以参数化的合成与表征差异。我们将这一策略应用于热电材料发现,优先选择在低于300°C的温度下进行合成。我们记录了一个此前未被报道的热电材料化学族PbSe:SnSb,发现该化学族中的最优候选材料——掺杂2 wt% SnSb的PbSe——的功率因子是PbSe的2倍以上。我们的研究表明,与由最先进机器学习模型驱动的高通量搜索相比,我们的闭环实验策略将发现优化材料所需的实验数量减少了多达3倍。我们还观察到,这种提升依赖于先前数据的准确性,呈现出收益递减的规律;在达到一定准确性后,与实验路径相关的因素将决定发展趋势。

英文摘要:

The exploration of thermoelectric materials is challenging considering the large materials space, combined with added exponential degrees of freedom coming from doping and the diversity of synthetic pathways. Here we seek to incorporate historical data and update and refine it using experimental feedback by employing error-correction learning (ECL). We thus learn from prior datasets and then adapt the model to differences in synthesis and characterization that are otherwise difficult to parameterize. We then apply this strategy to discovering thermoelectric materials where we prioritize synthesis at temperatures < 300°C. We document a previously unreported chemical family of thermoelectric materials, PbSe:SnSb, finding that the best candidate in this chemical family, 2 wt% SnSb doped PbSe, exhibits a power factor more than 2x that of PbSe. Our investigations show that our closed-loop experimentation strategy reduces the required number of experiments to find an optimized material by as much as 3x compared to high-throughput searches powered by state-of-the-art machine learning models. We also observe that this improvement is dependent on the accuracy of prior in a manner that exhibits diminishing returns, and after a certain accuracy is reached, it is factors associated with experimental pathways that dictate the trends.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑