Predicting and Accelerating Nanomaterial Synthesis Using Machine Learning Featurization

Christopher C. Price

doi:10.1021/acs.nanolett.4c04500

2024-11-12

PRE

Christopher L. Hinkle *

DOI：10.1021/acs.nanolett.4c04500

原文链接

原文求助

摘要

En 中文

Materials synthesis optimization is constrained by serial feedback processes that rely on manual tools and intuition across multiple siloed modes of characterization. We automate and generalize feature extraction of reflection high-energy electron diffraction (RHEED) data with machine learning to establish quantitatively predictive relationships in small sets (similar to 10) of expert-labeled data, saving significant time on subsequently grown samples. These predictive relationships are evaluated in a representative material system (W1-x V x Se2 on c-plane sapphire (0001)) with two aims: 1) predicting grain alignment of the deposited film using pregrowth substrate data and 2) estimating vanadium dopant concentration using in situ RHEED as a proxy for ex situ methods (e.g., X-ray photoelectron spectroscopy). Both tasks are accomplished using the same materials-agnostic features, avoiding specific system retraining and leading to a potential 80% time saving over a 100-sample synthesis campaign. These predictions provide guidance to avoid doomed trials, reduce follow-on characterization, and improve control resolution for materials synthesis.

Keyword:

Machine Learning

Epitaxial Growth

2D Materials

Electron Diffraction

Synthesis Control

期刊

Nano Letters

IF:

9.1

论文数:

2.7W

被引数:

16.5W

机构

University of Notre Dame

学者数:

1.2W

论文数: 1.1W

被引数: 1.7W

引用论文

Accelerating advanced-materials commercialization

NATURE MATERIALS

IF38.5

2016-04-26

PREAI

Maine, Elicia; Seegopaul, Purnesh

Toward autonomous design and synthesis of novel inorganic materials 走向新型无机材料的自主设计与合成

MATERIALS HORIZONS

IF10.7

2021-01-01

OAAI

Szymanski, Nathan J.; Zeng, Yan; Huo, Haoyan; Bartel, Christopher J.; Kim, Haegyeom; Ceder, Gerbrand

Recent advances and applications of deep learning methods in materials science 深度学习方法在材料科学中的最新进展与应用

NPJ COMPUTATIONAL MATERIALS

IF11.9

2022-04-05

407

OAAI

Choudhary, Kamal; DeCost, Brian; Chen, Chi; Jain, Anubhav; Tavazza, Francesca; Cohn, Ryan; Park, Cheol Woo; Choudhary, Alok; Agrawal, Ankit; Billinge, Simon J. L.; Holm, Elizabeth; Ong, Shyue Ping; Wolverton, Chris

Polymers from sugars and CO₂: ring-opening polymerisation and copolymerisation of cyclic carbonates derived from 2-deoxy-d-ribose

Polymer Chemistry

IF0

2017-01-01

OAAI

Georgina L. Gregory; Gabriele Kociok-Köhn; Antoine Buchard

CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling CHGNet作为预训练的通用神经网络，具有用于电荷信息原子建模的潜力

NATURE MACHINE INTELLIGENCE

IF23.9

2023-09-14

152