Anomaly detection in radio galaxy data with trainable COSFIRE filters

2025-05-24

AI Summary

In radio astronomy, detecting anomalous galaxy morphologies faces challenges of sparse annotations and massive datasets. To address this, we propose a semi-supervised anomaly detection method that requires no anomalous examples: we introduce trainable COSFIRE filters—novel in astronomical anomaly detection—to model canonical galaxy morphologies and identify deviations therefrom; further, we integrate Local Outlier Factor (LOF) for morphology-aware, unsupervised discrimination, thereby avoiding the high computational overhead of deep learning models. Evaluated on a benchmark radio-astronomy dataset, our approach achieves a G-Mean of 79%, outperforming a deep autoencoder baseline (77%). It delivers high accuracy, low computational cost, and strong real-time capability. This work establishes a scalable, efficient paradigm for anomalous galaxy discovery in next-generation radio telescope surveys.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Semi-Supervised Learning
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Detecting anomalies in radio astronomy is challenging due to the vast amounts of data and the rarity of labeled anomalous examples. Addressing this challenge requires efficient methods capable of identifying unusual radio galaxy morphologies without relying on extensive supervision. This work introduces an innovative approach to anomaly detection based on morphological characteristics of the radio sources using trainable COSFIRE (Combination of Shifted Filter Responses) filters as an efficient alternative to complex deep learning methods. The framework integrates COSFIRE descriptors with an unsupervised Local Outlier Factor (LOF) algorithm to identify unusual radio galaxy morphologies. Evaluations on a radio galaxy benchmark data set demonstrate strong performance, with the COSFIRE-based approach achieving a geometric mean (G-Mean) score of 79%, surpassing the 77% achieved by a computationally intensive deep learning autoencoder. By characterizing normal patterns and detecting deviations, this semi-supervised methodology overcomes the need for anomalous examples in the training set, a major limitation of traditional supervised methods. This approach shows promise for next-generation radio telescopes, where fast processing and the ability to discover unknown phenomena are crucial.

Problem

• Detect anomalies in radio galaxy data efficiently
• Identify unusual radio galaxy morphologies without supervision
• Overcome lack of labeled anomalies in training sets

Innovation

• Trainable COSFIRE filters for anomaly detection
• Unsupervised LOF algorithm integration
• Semi-supervised method without anomalous examples