Sensing Gas Mixtures by Analyzing the Spatiotemporal Optical Responses of Liquid Crystals Using 3D Convolutional Neural Networks
Sensing Gas Mixtures by Analyzing the Spatiotemporal Optical Responses of Liquid Crystals Using 3D Convolutional Neural Networks
复制标题
使用 3D 卷积神经网络分析液晶的时空光学响应来传感气体混合物
DOI：
10.1021/acssensors.2c00362
复制
发表时间：
2022
期刊：
影响因子：
8.9
通讯作者：
Abbott, Nicholas L.
中科院分区：
文献类型：
--
作者：
Bao, Nanqi;Jiang, Shengli;Smith, Alexander;Schauer, James J.;Mavrikakis, Manos;Van Lehn, Reid C.;Zavala, Victor M.;Abbott, Nicholas L.
我们报告了如何分析液晶（LC）薄膜对目标气体的空间和时间光学响应，当使用机器学习方法进行时，可以推进气体混合物的传感，并为传感器响应的物理过程提供重要的见解。我们开发的方法使用O3和Cl2混合物（代表一类重要的分析物）和LC支持金属高氯酸盐装饰的表面作为模型系统。虽然O3和Cl2都扩散通过LC膜和经历氧化还原反应与支持金属高氯酸盐表面生成类似的初始和最终的光学状态的LC，我们表明，一个三维卷积神经网络可以提取特征信息，编码在时空的颜色模式的LC检测O3和Cl2物种的混合物中的存在，并量化它们的浓度。我们的分析表明，O3检测驱动的过渡时间超过LC的亮度变化，而Cl2检测驱动的颜色波动，开发后期的LC的光学响应。我们还表明，我们可以检测到Cl2的存在，即使当O3的浓度是数量级大于Cl2浓度。所提出的方法可推广到广泛的分析物、反应性表面和LC，并且具有推进便携式LC监测装置（例如，可穿戴设备），用于使用时空颜色波动分析气体混合物。
We report how analysis of the spatial and temporal optical responses of liquid crystal (LC) films to targeted gases, when performed using a machine learning methodology, can advance the sensing of gas mixtures and provide important insights into the physical processes that underlie the sensor response. We develop the methodology using O3and Cl2mixtures (representative of an important class of analytes) and LCs supported on metal perchlorate-decorated surfaces as a model system. Although O3and Cl2both diffuse through LC films and undergo redox reactions with the supporting metal perchlorate surfaces to generate similar initial and final optical states of the LCs, we show that a three-dimensional convolutional neural network can extract feature information that is encoded in the spatiotemporal color patterns of the LCs to detect the presence of both O3and Cl2species in mixtures and to quantify their concentrations. Our analysis reveals that O3detection is driven by the transition time over which the brightness of the LC changes, while Cl2detection is driven by color fluctuations that develop late in the optical response of the LC. We also show that we can detect the presence of Cl2even when the concentration of O3is orders of magnitude greater than the Cl2concentration. The proposed methodology is generalizable to a wide range of analytes, reactive surfaces, and LCs and has the potential to advance the design of portable LC monitoring devices (e.g., wearable devices) for analyzing gas mixtures using spatiotemporal color fluctuations.