Meteoroid stream identification with HDBSCAN unsupervised clustering algorithm

2025-07-02

AI Summary

Accurate identification of meteoroid streams is critical for understanding their origin and evolution, as well as for supporting lunar impact monitoring missions (e.g., ESA’s LUMIO). However, conventional methods suffer from poor statistical consistency and robustness due to overlapping clusters, background noise, and reliance on prior lookup tables. This paper proposes a novel unsupervised clustering paradigm based on HDBSCAN, integrating three complementary orbital feature vectors—geocentric (GEO), heliocentric orbital elements (ORBIT), and lookup-table-based ablation features (LUTAB)—and employing the Hungarian algorithm for precise alignment with standard classifications. Evaluation employs silhouette coefficient, normalized mutual information, and F1-score. Experiments identify 39 meteoroid streams, 21 of which show high concordance with CAMS; HDBSCAN under the “eom” configuration achieves superior performance over traditional approaches. The framework delivers a more rigorous, scalable, and automated solution for meteoroid stream identification.

Technology Category

• Data Mining & Knowledge Management: Data Stream Mining
• Machine Learning: Clustering
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Accurate identification of meteoroid streams is central to understanding their origins and evolution. However, overlapping clusters and background noise hinder classification, an issue amplified for missions such as ESA's LUMIO that rely on meteor shower observations to infer lunar meteoroid impact parameters. This study evaluates the performance of the Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) algorithm for unsupervised meteoroid stream identification, comparing its outcomes with the established Cameras for All-Sky Meteor Surveillance (CAMS) look-up table method. We analyze the CAMS Meteoroid Orbit Database v3.0 using three feature vectors: LUTAB (CAMS geocentric parameters), ORBIT (heliocentric orbital elements), and GEO (adapted geocentric parameters). HDBSCAN is applied with varying minimum cluster sizes and two cluster selection methods (eom and leaf). To align HDBSCAN clusters with CAMS classifications, the Hungarian algorithm determines the optimal mapping. Clustering performance is assessed via the Silhouette score, Normalized Mutual Information, and F1 score, with Principal Component Analysis further supporting the analysis. With the GEO vector, HDBSCAN confirms 39 meteoroid streams, 21 strongly aligning with CAMS. The ORBIT vector identifies 30 streams, 13 with high matching scores. Less active showers pose identification challenges. The eom method consistently yields superior performance and agreement with CAMS. Although HDBSCAN requires careful selection of the minimum cluster size, it delivers robust, internally consistent clusters and outperforms the look-up table method in statistical coherence. These results underscore HDBSCAN's potential as a mathematically consistent alternative for meteoroid stream identification, although further validation is needed to assess physical validity.

Problem

• Identify meteoroid streams accurately despite noise
• Compare HDBSCAN clustering with CAMS lookup method
• Evaluate clustering performance using multiple metrics

Innovation

• HDBSCAN algorithm for unsupervised meteoroid clustering
• Hungarian algorithm optimizes cluster-CAMS classification mapping
• GEO vector confirms 39 streams with high CAMS alignment