RoBo6: Standardized MMT Light Curve Dataset for Rocket Body Classification

TL;DR

This paper introduces RoBo6, a standardized light curve dataset for rocket body classification, providing a benchmark for future research in space debris identification using machine learning models.

Contribution

The paper presents the RoBo6 dataset, derived from the Mini Mega Tortora database, with extensive preprocessing and evaluation of ML models, establishing a new benchmark for rocket body classification.

Findings

Astroconformer achieved the best classification performance.

The dataset includes 6 rocket classes with over 7,000 samples.

Preprocessing techniques improved model accuracy.

Abstract

Space debris presents a critical challenge for the sustainability of future space missions, emphasizing the need for robust and standardized identification methods. However, a comprehensive benchmark for rocket body classification remains absent. This paper addresses this gap by introducing the RoBo6 dataset for rocket body classification based on light curves. The dataset, derived from the Mini Mega Tortora database, includes light curves for six rocket body classes: CZ-3B, Atlas 5 Centaur, Falcon 9, H-2A, Ariane 5, and Delta 4. With 5,676 training and 1,404 test samples, it addresses data inconsistencies using resampling, normalization, and filtering techniques. Several machine learning models were evaluated, including CNN and transformer-based approaches, with Astroconformer reporting the best performance. The dataset establishes a common benchmark for future comparisons and advancements in rocket body classification tasks.