nNPipe: a neural network pipeline for automated analysis of morphologically diverse catalyst systems
nNPipe: a neural network pipeline for automated analysis of morphologically diverse catalyst systems
复制标题
DOI：
10.1038/s41524-022-00949-7
复制
发表时间：
2023-02
影响因子：
9.7
通讯作者：
Kevin P. Treder;Chen Huang;Cameron G. Bell;T. Slater;Manfred E. Schuster;Doğan Özkaya;Judy S. Kim;A. Kirkland
中科院分区：
文献类型：
--
作者：
Kevin P. Treder;Chen Huang;Cameron G. Bell;T. Slater;Manfred E. Schuster;Doğan Özkaya;Judy S. Kim;A. Kirkland
我们描述了NPipe用于形态多样的催化剂材料的自动分析。自动成像程序和直接电子探测器已经能够以高时间分辨率在宽范围的样品位置上收集大数据堆栈。与此同时，传统的图像分析方法速度较慢，因此不适合大型数据堆栈，因此研究人员逐渐转向机器学习和深度学习方法。以前的研究经常详细描述形态均匀的材料系统，具有清晰可辨的特征，有限的可行图像尺寸和训练数据，这些数据可能由于手动标记而有偏见。ThenNPipedata处理方法由两个独立的卷积神经网络组成，它们专门在多层图像模拟上进行训练，可以快速分析2048 × 2048像素的图像。将理想化和真实的工业催化样品之间的推理性能比较以及从后续数据分析中获得的见解置于自动成像场景的上下文中。
We describenNPipefor the automated analysis of morphologically diverse catalyst materials. Automated imaging routines and direct-electron detectors have enabled the collection of large data stacks over a wide range of sample positions at high temporal resolution. Simultaneously, traditional image analysis approaches are slow and hence unsuitable for large data stacks and consequently, researchers have progressively turned towards machine learning and deep learning approaches. Previous studies often detail work on morphologically uniform material systems with clearly discernible features, limited workable image sizes and training data that may be biased due to manual labelling. ThenNPipedata-processing method consists of two standalone convolutional neural networks that were exclusively trained on multislice image simulations and enables fast analysis of 2048 × 2048 pixel images. Inference performance compared between idealised and real industrial catalytic samples and insights derived from subsequent data analysis are placed into the context of an automated imaging scenario.