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
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
Fig. 1: Overall experimental workflow for the comparative evaluation of the four Isolation Forest variants.
Expert score
Number of sources
Percentage
5
24
2.3%
4
62
6.0%
3
122
11.8%
2
439
42.6%
1
384
37.2%
Positive ( ≥ 4)
86
8.3%
TABLE I: Dataset composition.
Parameter
Value
Configuration
Number of trees
100
Common to all variants
Subsample size
256
Maximum samples per tree
Maximum tree depth
10
Common tree-building limit
Random state
42
Fixed for reproducibility
Feature dimension
52
BYOL + PCA representation
TABLE II: Experimental configuration.
Fig. 2: Comparison of the splitting and scoring strategies used by the four evaluated Isolation Forest variants.
Fig. 3: Precision–Recall curves for the four Isolation Forest variants, with expert scores ≥4 treated as the positive class.
Fig. 4: ROC curves for the four Isolation Forest variants, with expert scores ≥4 treated as the positive class.
Fig. 5: Cumulative detection of expert-validated scientifically interesting sources for the full evaluation set.
Fig. 6: Cumulative detection of expert-validated scientifically interesting sources among the first 200 ranked candidates.
Algorithm
AP
AUC
P@10
P@50
P@100
Standard Enhanced
0.198
0.677
0.400
0.320
0.210
Pooled Gain
0.201
0.653
0.600
0.280
0.180
Kurtosis-based
0.155
0.677
0.200
0.220
0.170
Hypervolume
0.184
0.674
0.400
0.300
0.200
TABLE III: Performance comparison of the four Isolation Forest variants using expert-validated labels.
Isolation Forest (IF) is a widely used baseline for unsupervised anomaly detection. Recent studies provide a closed-form expression for the infinite-forest limit for one-dimensional data. Inspired by the geometric interpretation of this formula, we introduce RIFT (Relative Isolation From Trees), a deterministic anomaly detection method that generates the minimum spanning tree and scores each point by the sum of the apparent sizes of tree edges as viewed from that point. For one-dimensional data, the RIFT score recovers the closed-form IF limit exactly. In higher dimensions, it provides a parameter-free generalization that is deterministic, robust to varying density and clustered anomalies and avoids the axis-parallel artifacts of IF. We further propose an ensemble variant for large datasets. Experiments on synthetic data and the ADBench benchmark demonstrate that the accuracy is comparable to IF, while the ensemble variant exhibits significantly lower variance across random seeds.
Mark Daniel Szalai, Gabor Horvath
Department of Networked Systems and Services, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, M˝uegyetem rkp. 3, Budapest, H-1111, Hungary
Unsupervised anomaly detection is widely used in transaction fraud detection where labels are scarce. Isolation Forest (IF) is among the most popular classical methods due to its scalability and ease of deployment. We propose SilIF, an augmentation of Isolation Forest that adds a silhouette-based scoring layer computed in a representation space induced by the trees of the forest. For each point, we extract a vector of per-tree path lengths, cluster these "fingerprints" into structural groups, and compute a silhouette score that measures how well the point fits its assigned group versus the nearest alternative. The silhouette signal is combined with the base IF score via a single hyperparameter alpha. On the IEEE-CIS Fraud Detection benchmark (~590K transactions, 3.5% fraud), SilIF with alpha=1.0 improves over plain Isolation Forest by +0.0080 AUC-PR on average across five seeds, with SilIF winning on all five seeds (paired t-test p=0.046). We also report results on a synthetic credit-card dataset (Sparkov) where the silhouette augmentation does not improve over plain IF, and we characterize the conditions that distinguish the two outcomes. The paper presents SilIF as a tunable, easy-to-deploy enhancement to Isolation Forest with honest reporting of when it helps and when it does not. Code at https://github.com/venkat15vk/silif-anomaly-detection.
Algorithm development for radioisotope identification in mobile urban search scenarios face significant challenges from non-uniform backgrounds, momentary source encounters, and severe class imbalance between rare threat signatures and background measurements. We present a machine learning-based approach to this problem that converts list-mode gamma-ray data into two-dimensional waterfall spectrograms and applies computer vision architectures to the resulting images. Rather than treating waterfalls as conventional images, we employ a representation where consecutive time spectra can form input channels, similar to RGB channels in color images. This representation encodes both spectral and temporal information, enabling neural networks to more effectively learn patterns that distinguish source signatures from background fluctuations. We evaluate three architectures, a multilayer perceptron (MLP), convolutional neural network (CNN), and vision transformer (ViT), on the Radiological Anomaly Detection and Identification (RADAI) benchmark dataset. At a false positive rate of less than one false alarm per hour, our CNN outperforms the previous-best non-negative matrix factorization (NMF) method across all global metrics, achieving true detection, classification, and identification rates of 0.4334, 0.3965, and 0.2950 respectively, compared to 0.4151, 0.3611, and 0.2625 for NMF. At lower false positive rate constraints, the neural network approaches show comparable but ultimately lower performance than NMF, indicating opportunities for further research.
Masen Bachleda, Peter Lalor
Pacific Northwest National Laboratory, Richland, WA 99354 USA