Deep Generative Modeling of Infrared Images Provides Signature of Cracking in Cross-Linked Polyethylene Pipe.
Michael GrossuttiJoseph D'AmicoJonathan QuintalHugh MacFarlaneW Callum WarehamAmanda QuirkJohn R DutcherPublished in: ACS applied materials & interfaces (2023)
Hyperspectral infrared (IR) images contain a large amount of highly spatially resolved information about the chemical composition of a sample. However, the analysis of hyperspectral IR imaging data for complex heterogeneous systems can be challenging because of the spectroscopic and spatial complexity of the data. We implement a deep generative modeling approach using a β-variational autoencoder to learn disentangled representations of the generative factors of variance in a data set of cross-linked polyethylene (PEX-a) pipe. We identify three distinct physicochemical factors of aging and degradation learned by the model and apply the trained model to high-resolution hyperspectral IR images of cross-sectional slices of unused virgin, used in-service, and cracked PEX-a pipe. By mapping the learned representations of aging and degradation to the IR images, we extract detailed information on the physicochemical changes that occur during aging, degradation, and cracking in PEX-a pipe. This study shows how representation learning by deep generative modeling can significantly enhance the analysis of high-resolution IR images of complex heterogeneous samples.
Keyphrases
- high resolution
- deep learning
- convolutional neural network
- optical coherence tomography
- electronic health record
- cross sectional
- big data
- working memory
- healthcare
- mass spectrometry
- oxidative stress
- mental health
- machine learning
- health information
- high speed
- tandem mass spectrometry
- high intensity
- resistance training
- liquid chromatography