Deep Learning Assisted Data Inspection for Radio Astronomy

Abstract

Modern radio telescopes combine thousands of receivers, long-distance networks, large-scale compute hardware, and intricate software. Due to this complexity, failures occur relatively frequently. In this work we propose novel use of unsupervised deep learning to diagnose system health for modern radio telescopes. The model is a convolutional Variational Autoencoder (VAE) that enables the projection of the high dimensional time-frequency data to a low-dimensional prescriptive space. Using this projection, telescope operators are able to visually inspect failures thereby maintaining system health. We have trained and evaluated the performance of the VAE quantitatively in controlled experiments on simulated data from HERA. Moreover, we present a qualitative assessment of the the model trained and tested on real LOFAR data. Through the use of a naive SVM classifier on the projected synthesised data, we show that there is a trade-off between the dimensionality of the projection and the number of compounded features in a given spectrogram. The VAE and SVM combination scores between 65% and 90% accuracy depending on the number of features in a given input. Finally, we show the prototype system-health-diagnostic web framework that integrates the evaluated model. The system is currently undergoing testing at the ASTRON observatory.

References in corpus (21)

• Variational Inference: A Review for Statisticians
• LOFAR: The LOw-Frequency ARray
• Hydrogen Epoch of Reionization Array (HERA)
• Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
• Observations of Fast Radio Bursts at Frequencies down to 400 Megahertz
• Classifying Radio Galaxies with Convolutional Neural Network
• FETCH: A deep-learning based classifier for fast transient classification
• Radio Galaxy Zoo: ClaRAN - A Deep Learning Classifier for Radio Morphologies
• Radio Galaxy Zoo: Compact and extended radio source classification with deep learning
• A Fourier Perspective on Model Robustness in Computer Vision
• Applying Deep Learning to Fast Radio Burst Classification
• Calibration Challenges for Future Radio Telescopes
• Morphological classification of radio galaxies: Capsule Networks versus Convolutional Neural Networks
• Optimizing Sparse RFI Prediction using Deep Learning
• Deep residual detection of radio frequency interference for FAST
• Radio Galaxy Zoo: Unsupervised Clustering of Convolutionally Auto-encoded Radio-astronomical Images
• Recurrent Neural Radio Anomaly Detection
• Cobalt: A GPU-based correlator and beamformer for LOFAR
• Engineering and Science Highlights of the KAT-7 Radio Telescope
• HIDE & SEEK: End-to-End Packages to Simulate and Process Radio Survey Data
• Data Challenges for Next-generation Radio Telescopes

Cited by in corpus (10)

• Intelligent Computing: The Latest Advances, Challenges and Future
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• A review of unsupervised learning in astronomy
• Learning to detect RFI in radio astronomy without seeing it
• The ROAD to discovery: machine learning-driven anomaly detection in radio astronomy spectrograms
• Morphological Classification of Radio Galaxies with wGAN-supported Augmentation
• Radio Sources Segmentation and Classification with Deep Learning
• A Deep Neural Network Based Reverse Radio Spectrogram Search Algorithm
• Simulating images of radio galaxies with diffusion models
• The Complexity and Information Content of Simulated Universes