DART-Vetter: A Deep LeARning Tool for automatic triage of exoplanet candidates

2025-06-05

AI Summary

To address the insufficient robustness in distinguishing planetary candidates (PCs) from non-planetary signals (NPCs) in multi-survey transit data (Kepler, TESS, PLATO), this paper proposes a lightweight, single-modality convolutional neural network that performs end-to-end classification solely from phase-folded light curves. The method employs a unified preprocessing pipeline to ensure cross-survey data consistency. Our key contribution is the first general-purpose, compact light-curve classifier specifically designed for multi-survey transit candidate validation. Evaluated on a joint Kepler–TESS dataset, the model achieves a 91% recall rate and demonstrates generalization performance on TCEs with MES > 20 and periods < 50 days comparable to ExoMiner and AstroNet-Triage—while significantly improving both cross-survey generalizability and deployment efficiency.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Security and Privacy: Data transparency and provenance

Abstract

In the identification of new planetary candidates in transit surveys, the employment of Deep Learning models proved to be essential to efficiently analyse a continuously growing volume of photometric observations. To further improve the robustness of these models, it is necessary to exploit the complementarity of data collected from different transit surveys such as NASA's Kepler, Transiting Exoplanet Survey Satellite (TESS), and, in the near future, the ESA PLAnetary Transits and Oscillation of stars (PLATO) mission. In this work, we present a Deep Learning model, named DART-Vetter, able to distinguish planetary candidates (PC) from false positives signals (NPC) detected by any potential transiting survey. DART-Vetter is a Convolutional Neural Network that processes only the light curves folded on the period of the relative signal, featuring a simpler and more compact architecture with respect to other triaging and/or vetting models available in the literature. We trained and tested DART-Vetter on several dataset of publicly available and homogeneously labelled TESS and Kepler light curves in order to prove the effectiveness of our model. Despite its simplicity, DART-Vetter achieves highly competitive triaging performance, with a recall rate of 91% on an ensemble of TESS and Kepler data, when compared to Exominer and Astronet-Triage. Its compact, open source and easy to replicate architecture makes DART-Vetter a particularly useful tool for automatizing triaging procedures or assisting human vetters, showing a discrete generalization on TCEs with Multiple Event Statistic (MES)>20 and orbital period<50 days.

Problem

• Automatically distinguish exoplanet candidates from false positives
• Improve robustness using data from multiple transit surveys
• Simplify and compact deep learning model for triaging

Innovation

• Deep Learning model for exoplanet candidate triage
• Convolutional Neural Network processing folded light curves
• Compact, open source architecture for automated vetting