Datacube segmentation via Deep Spectral Clustering

Abstract

Extended Vision techniques are ubiquitous in physics. However, the data cubes steaming from such analysis often pose a challenge in their interpretation, due to the intrinsic difficulty in discerning the relevant information from the spectra composing the data cube. Furthermore, the huge dimensionality of data cube spectra poses a complex task in its statistical interpretation; nevertheless, this complexity contains a massive amount of statistical information that can be exploited in an unsupervised manner to outline some essential properties of the case study at hand, e.g.~it is possible to obtain an image segmentation via (deep) clustering of data-cube's spectra, performed in a suitably defined low-dimensional embedding space. To tackle this topic, we explore the possibility of applying unsupervised clustering methods in encoded space, i.e. perform deep clustering on the spectral properties of datacube pixels. A statistical dimensional reduction is performed by an ad hoc trained (Variational) AutoEncoder, in charge of mapping spectra into lower dimensional metric spaces, while the clustering process is performed by a (learnable) iterative K-Means clustering algorithm. We apply this technique to two different use cases, of different physical origins: a set of Macro mapping X-Ray Fluorescence (MA-XRF) synthetic data on pictorial artworks, and a dataset of simulated astrophysical observations.

20 pages, 10 figures, doi for code repository, dataset and trained model available and reported in the paper. v2: paper accepted for publication on IOP Machine Learning: Science and Technology

References in corpus (19)

• An Introduction to Variational Autoencoders
• A survey of loss functions for semantic segmentation
• The MUSE second-generation VLT instrument
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Identifying Exoplanets with Deep Learning: A Five Planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90
• Recovering the number of clusters in data sets with noise features using feature rescaling factors
• A catalog of visual-like morphologies in the 5 CANDELS fields using deep-learning
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Applying Deep Learning to Fast Radio Burst Classification
• DeepCMB: Lensing Reconstruction of the Cosmic Microwave Background with Deep Neural Networks
• Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
• ExoMiner: A Highly Accurate and Explainable Deep Learning Classifier that Validates 301 New Exoplanets
• A diagnostic tool for the identification of Supernova Remnants
• Machine Learning for Observational Cosmology
• Recovering the CMB Signal with Machine Learning
• Identifying Exoplanets with Machine Learning Methods: A Preliminary Study
• DELIGHT: Deep Learning Identification of Galaxy Hosts of Transients using Multi-resolution Images
• Can Deep Learning Assist Automatic Identification of Layered Pigments From XRF Data?