High-throughput screening and machine learning for the efficient growth of high-quality single-wall carbon nanotubes
High-throughput screening and machine learning for the efficient growth of high-quality single-wall carbon nanotubes
复制标题
DOI：
10.1007/s12274-021-3387-y
复制
发表时间：
2021-03
期刊：
影响因子：
9.9
通讯作者：
Zhonghai Ji;Lili Zhang;Daiming Tang;Chien-Ming Chen;Torbjörn E. M. Nordling;Zheng-De Zhang;C. Ren;B. Da;Xin Li;Shu-yu Guo;Chang Liu;Hui‐Ming Cheng
中科院分区：
文献类型：
--
作者：
Zhonghai Ji;Lili Zhang;Daiming Tang;Chien-Ming Chen;Torbjörn E. M. Nordling;Zheng-De Zhang;C. Ren;B. Da;Xin Li;Shu-yu Guo;Chang Liu;Hui‐Ming Cheng
单壁碳纳米管(SWCNTs)的结构控制生长条件的优化一直是一个巨大的挑战。在这里，我们报道了一种结合机器学习的高通量方法，它可以有效地筛选出合成高质量单壁碳纳米管的生长条件。在带有数字标记的硅片上沉积了图案化的钴(Co)纳米粒子作为催化剂，并优化了温度、还原时间和碳前驱体的参数。利用拉曼光谱对单壁碳纳米管的结晶度进行了表征，自动提取特征G/D峰强度(IG/ID)并映射到生长参数建立数据库。收集了1280个数据来训练机器学习模型。通过进一步的化学气相沉积(CVD)生长验证，随机森林回归(RFR)对高质量单壁碳纳米管生长条件的预测具有很高的精度。这种方法在单壁碳纳米管的结构控制生长方面显示出很大的潜力。
It has been a great challenge to optimize the growth conditions toward structure-controlled growth of single-wall carbon nanotubes (SWCNTs). Here, a high-throughput method combined with machine learning is reported that efficiently screens the growth conditions for the synthesis of high-quality SWCNTs. Patterned cobalt (Co) nanoparticles were deposited on a numerically marked silicon wafer as catalysts, and parameters of temperature, reduction time and carbon precursor were optimized. The crystallinity of the SWCNTs was characterized by Raman spectroscopy where the featured G/D peak intensity (IG/ID) was extracted automatically and mapped to the growth parameters to build a database. 1,280 data were collected to train machine learning models. Random forest regression (RFR) showed high precision in predicting the growth conditions for high-quality SWCNTs, as validated by further chemical vapor deposition (CVD) growth. This method shows great potential in structure-controlled growth of SWCNTs.