Predicting Real‐Time Spectra from High‐Speed Imaging: An Ultrafast Machine Vision Framework for Online Optical Control in Microfluidics

Predicting Real‐Time Spectra from High‐Speed Imaging: An Ultrafast Machine Vision Framework for Online Optical Control in Microfluidics
复制标题

从高速成像预测实时光谱:用于微流体在线光学控制的超快机器视觉框架

DOI:
10.1002/admt.202101344
复制
发表时间:
2022-06
期刊:
Adv. Mater. Technol.
影响因子:
--
通讯作者:
Changchun Wang
Changchun Wang
中科院分区:
其他
文献类型:
--
作者:
Xucheng Zhang;Jia Guo;Changchun Wang

文献摘要

参考文献

相似文献

人工智能(AI)的出现赋予了自动化实验室管道的能力,它正在重塑化学和材料发现的范式。虽然已经开发了能够快速收敛到最佳反应条件的智能决策策略,但总体效率仍然受到在线表征单元缓慢获取的影响,特别是在基于微流体的系统中。因此,本文开发了一个超快机器视觉框架,用于直接从实时高速成像中预测光谱。利用独特的深度学习算法,该框架自动检测液滴,并在亚毫秒的时间内从嵌入的图像特征中重现高质量的光谱。在概念验证示例中,液滴在0.51 ms内以99.75%的平均精度被检测到,并且它们跨越整个可见波长的光谱被预测为具有5.32 nm的平均峰值误差,这相当于可见范围的1.6%。这项工作展示了第一个部署在实时环境中的基于全成像的机器学习框架的例子,用于完全替换分析仪器。它强调了人工智能在材料研究中的更广泛的可能性,以打破在线诊断的物理限制,并进一步提高自动驾驶实验室的效率。
Automated laboratory pipelines empowered by the advent of artificial intelligence (AI) have been reshaping the paradigm of chemical and material discovery. While intelligent decision-making strategies have been developed that enable fast convergence to optimal reaction conditions, the overall efficiency is still bottlenecked by the slow acquisition of online characterization units, especially in microfluidics-based systems. In response, an ultrafast machine vision framework is hereby developed to directly predict optical spectra from real-time high-speed imaging in this article. Utilizing uniquely engineered deep-learning algorithms, this framework automatically detects droplets and recapitulates high-quality spectra from embedded image features in a sub-millisecond timeframe. In a proof-of-concept example, droplets are detected with an average precision of 99.75% within 0.51 ms, and their spectra spanning the entire visible wavelengths are predicted with an average peak error of 5.32 nm, which is equivalent to 1.6% of the visible range. The work demonstrates the first example of an all-imaging-based machine learning framework deployed in a real-time environment for the full replacement of an analytical instrument. It highlights the broader possibility of AI in material researches to break the physical limitations of online diagnostics and to further boost efficiencies in self-driving laboratories.
DOI: 10.1002/adma.202001626
发表时间: 2020-06-04
期刊: ADVANCED MATERIALS
影响因子: 29.4
作者:
Epps, Robert W.;Bowen, Michael S.;Abolhasani, Milad
通讯作者: Abolhasani, Milad
由结合结构颜色和荧光颜色的双色调微滴编程的双生标签
DOI: 10.1038/s41467-021-20908-y
发表时间: 2021-01-29
影响因子: 16.6
作者:
Qin L;Liu X;He K;Yu G;Yuan H;Xu M;Li F;Yu Y
通讯作者: Yu Y
DOI: 10.1126/science.aax1566
发表时间: 2019-08-09
期刊: SCIENCE
影响因子: 56.9
作者:
Coley, Connor W.;Thomas, Dale A., III;Jensen, Klavs F.
通讯作者: Jensen, Klavs F.
DOI: 10.1021/ie900726s
发表时间: 2010-01
影响因子: 4.2
作者:
N. Steinfeldt;U. Bentrup;K. Jähnisch
通讯作者: N. Steinfeldt;U. Bentrup;K. Jähnisch
DOI: 10.1039/c2lc40938k
发表时间: 2012-01-01
期刊: LAB ON A CHIP
影响因子: 6.1
作者:
Romero, Philip A.;Abate, Adam R.
通讯作者: Abate, Adam R.