ExoMiner++ on TESS with Transfer Learning from Kepler: Transit Classification and Vetting Catalog for 2-min Data

2025-02-13

AI Summary

Distinguishing low signal-to-noise ratio (SNR) planetary transit signals from false positives—such as stellar activity and instrumental systematics—in TESS 2-minute cadence photometry remains challenging. Method: We propose a multi-source feature fusion framework coupled with cross-task transfer learning: for the first time, we integrate heterogeneous diagnostic features—including periodograms, difference images, and spacecraft attitude control telemetry—and leverage high-confidence Kepler labels for pretraining. Our approach synergistically combines deep neural networks with domain-informed astronomical time-series feature engineering to enhance both classification robustness and interpretability. Results: Applied to 147,568 candidate signals, the method identifies 7,330 planetary candidates, encompassing 1,868 known TOIs and 50 newly identified CTOIs. It achieves a 71.7% recovery rate on 2,506 TOIs in ExoFOP, substantially reducing follow-up observational overhead.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Data transparency and provenance

Abstract

We present ExoMiner++, an enhanced deep learning model that builds on the success of ExoMiner to improve transit signal classification in 2-minute TESS data. ExoMiner++ incorporates additional diagnostic inputs, including periodogram, flux trend, difference image, unfolded flux, and spacecraft attitude control data, all of which are crucial for effectively distinguishing transit signals from more challenging sources of false positives. To further enhance performance, we leverage transfer learning from high-quality labeled data from the Kepler space telescope, mitigating the impact of TESS's noisier and more ambiguous labels. ExoMiner++ achieves high accuracy across various classification and ranking metrics, significantly narrowing the search space for follow-up investigations to confirm new planets. To serve the exoplanet community, we introduce new TESS catalogs containing ExoMiner++ classifications and confidence scores for each transit signal. Among the 147,568 unlabeled TCEs, ExoMiner++ identifies 7,330 as planet candidates, with the remainder classified as false positives. These 7,330 planet candidates correspond to 1,868 existing TESS Objects of Interest (TOIs), 69 Community TESS Objects of Interest (CTOIs), and 50 newly introduced CTOIs. 1,797 out of the 2,506 TOIs previously labeled as planet candidates in ExoFOP are classified as planet candidates by ExoMiner++. This reduction in plausible candidates combined with the excellent ranking quality of ExoMiner++ allows the follow-up efforts to be focused on the most likely candidates, increasing the overall planet yield.

Problem

• Improves transit signal classification
• Utilizes transfer learning from Kepler
• Reduces false positives in TESS data

Innovation

• Enhanced deep learning model
• Transfer learning from Kepler
• Additional diagnostic inputs integration