astro-ph.IMNov 14, 2026

Improving Early Detection of Scientifically Interesting Radio Sources Using Enhanced Isolation Forest

Authors: Pfunzo Thavhana, Clement Nyirenda, Michelle Lochner

Organizations: Department of Computer Science, University of the Western Cape, Cape Town, South Africa · Department of Computer Science, eResearch Office, University of the Western Cape, Cape Town, South Africa · University of the Western Cape, Department of Physics and Astronomy, Cape Town, South Africa

Abstract

The rapid growth of radio astronomical surveys has created a major challenge in identifying scientifically interesting sources from large populations of observed objects. This study investigates whether enhanced Isolation Forest (iForest) methods can improve the early detection and ranking of scientifically interesting radio sources. Four iForest variants, Standard Enhanced, Pooled Gain, Kurtosis-based, and Hypervolume, are evaluated using 1,031 extended radio sources from the MeerKAT Galaxy Cluster Legacy Survey (MGCLS). Each source is represented by a 52-dimensional feature set derived using Bootstrap Your Own Latent (BYOL) self-supervised learning and principal component analysis (PCA), while expert scientific-interest ratings are used to define the ground-truth labels. The methods are evaluated using Average Precision (AP), receiver operating characteristic area under the curve (ROC AUC), Precision@10, Precision@50, and cumulative anomaly detection. Pooled Gain achieves the highest Average Precision (AP = 0.201) and the strongest early-stage ranking performance (P@10 = 0.600), identifying six expert-validated anomalies among the ten highest-ranked sources. Standard Enhanced and Kurtosis-based achieve the highest ROC AUC (0.677), while the AUC values of the four variants range from 0.653 to 0.677. These results indicate that feature-aware isolation strategies can improve the prioritization of scientifically interesting sources at the top of the ranked list, although overall discrimination remains comparable across the evaluated variants. The findings support the use of enhanced Isolation Forest methods as an initial ranking mechanism within human-in-the-loop systems for large-scale radio astronomical surveys.

Figures & tables

Explore similar work

CardsList
  1. RIFT: Relative Isolation From Trees For Anomaly Detection

    Oct 8, 2026Mark Daniel Szalai, Gabor HorvathUnsupervised Anomaly DetectionAnomaly Detection

  2. Computer vision-based neural networks for radioisotope identification in urban environments

    Jun 30, 2026Masen Bachleda, Peter LalorConvolutional Neural Networks