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 1704.07423stat.MLcond-mat.mtrl-sci
收藏

使用数据驱动的试验设计和经过良好校准的不确定性估计进行高维材料和工艺优化

High-Dimensional Materials and Process Optimization using Data-driven Experimental Design with Well-Calibrated Uncertainty Estimates

Julia Ling, Max Hutchinson, Erin Antono, Sean Paradiso, Bryce Meredig

摘要:

为了获得表现出理想特性的材料,对成分和工艺进行优化,在历史上依赖于科学家直觉、试错和运气的结合。我们提出了一种方法,可以通过将数据驱动模型拟合到实验数据来加速这一过程,因为它被收集来建议下一步应该进行哪个实验。这种方法可以指导科学家更早地测试最有前途的候选人,并可以通过数据驱动的见解来补充科学直觉和知识。所提出的框架的一个关键优势是它可以扩展到高维参数空间,这在材料发现应用中是典型的。重要的是,数据驱动模型包含了不确定性分析,因此可以在探索高不确定性候选项和利用参数空间的高性能区域的基础上提出新的实验。在四个材料科学测试案例中,我们的方法导致最佳候选人被发现,所需的测量比平均随机猜测少三倍。

英文摘要:

The optimization of composition and processing to obtain materials that exhibit desirable characteristics has historically relied on a combination of scientist intuition, trial and error, and luck. We propose a methodology that can accelerate this process by fitting data-driven models to experimental data as it is collected to suggest which experiment should be performed next. This methodology can guide the scientist to test the most promising candidates earlier, and can supplement scientific intuition and knowledge with data-driven insights. A key strength of the proposed framework is that it scales to high-dimensional parameter spaces, as are typical in materials discovery applications. Importantly, the data-driven models incorporate uncertainty analysis, so that new experiments are proposed based on a combination of exploring high-uncertainty candidates and exploiting high-performing regions of parameter space. Over four materials science test cases, our methodology led to the optimal candidate being found with three times fewer required measurements than random guessing on average.

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。

↑