TransitNet: A Compact Attention-Augmented Deep Learning Framework for Low-SNR Transit Blind Searches
Abstract
Motivated by the observational incompleteness of intermediate-to-long-period Earth-size planets, we present TransitNet, a compact attention-augmented deep-learning framework for low-SNR transit blind searches. To enable realistic method development and objective threshold calibration under blind-search conditions, we develop a unified dataset construction, benchmarking, and threshold-selection framework. On recovery benchmarks constructed from unseen Kepler targets, TransitNet attains 95.2 percent accuracy in the challenging SNR range of 6 to 8 and outperforms both TLS and BLS, achieving ROC-AUC and PR-AP values of 0.974 and 0.982, respectively. In an injected Earth-size and sub-Earth-size transit recovery experiment, TransitNet achieves a recovery rate of 93.0 percent, substantially exceeding those of TLS (63.1 percent) and BLS (60.0 percent). In addition to detection, TransitNet provides attention-based estimates of transit windows and midpoints. On an independent evaluation set, 97.4 percent of injected transits are fully covered by the estimated transit window. Applied to real Kepler observations, the model successfully recovers all 34 selected confirmed Kepler planets, with a mean absolute transit midpoint error of 1.24 hours. The model combines a compact footprint of about 1.5 MB with high inference efficiency, yielding speed-ups of about 12 to 25 times relative to CPU-TLS and about 4 to 5 times relative to CPU-BLS. These results demonstrate that TransitNet provides an accurate, scalable, and computationally efficient framework for low-SNR transit blind searches in the tested regime and motivate its extension to longer-period Earth-size planet searches.
Related
- Spectroscopy-informed Deep Learning Searches for Photometric Little Red Dots in JWST Surveys
- Reducing False Positives in Strong-Lens Searches with Generalized-Mean Consensus of Machine-Learning Ensembles in the Kilo-Degree Survey
- A Graph Attention Network Framework for Simultaneous Prediction of Galaxy and Dark Matter Halo Properties in GAMA DR4
- Multi-Scale Contrastive Attention for Light-Curve Representation Learning
- The pulsar population of Omega Centauri: New TRAPUM searches, timing, and cluster dynamics with MeerKAT and Parkes
BibTeX
@misc{yan2026transitnet,
title = {{TransitNet: A Compact Attention-Augmented Deep Learning Framework for Low-SNR Transit Blind Searches}},
author = {Xingchen Yan and Jian Ge and Qingtian Liu and Kevin Willis and Quanquan Hu and Jiapeng Zhu},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2606.18932},
eprint = {2606.18932},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.18932},
}
RIS
TY - UNPB
TI - TransitNet: A Compact Attention-Augmented Deep Learning Framework for Low-SNR Transit Blind Searches
AU - Xingchen Yan
AU - Jian Ge
AU - Qingtian Liu
AU - Kevin Willis
AU - Quanquan Hu
AU - Jiapeng Zhu
PY - 2026
DA - 2026/10/28
PB - arXiv
DO - 10.48550/arxiv.2606.18932
UR - https://arxiv.org/abs/2606.18932
AB - Motivated by the observational incompleteness of intermediate-to-long-period Earth-size planets, we present TransitNet, a compact attention-augmented deep-learning framework for low-SNR transit blind searches. To enable realistic method development and objective threshold calibration under blind-search conditions, we develop a unified dataset construction, benchmarking, and threshold-selection framework. On recovery benchmarks constructed from unseen Kepler targets, TransitNet attains 95.2 percent accuracy in the challenging SNR range of 6 to 8 and outperforms both TLS and BLS, achieving ROC-AUC and PR-AP values of 0.974 and 0.982, respectively. In an injected Earth-size and sub-Earth-size transit recovery experiment, TransitNet achieves a recovery rate of 93.0 percent, substantially exceeding those of TLS (63.1 percent) and BLS (60.0 percent). In addition to detection, TransitNet provides attention-based estimates of transit windows and midpoints. On an independent evaluation set, 97.4 percent of injected transits are fully covered by the estimated transit window. Applied to real Kepler observations, the model successfully recovers all 34 selected confirmed Kepler planets, with a mean absolute transit midpoint error of 1.24 hours. The model combines a compact footprint of about 1.5 MB with high inference efficiency, yielding speed-ups of about 12 to 25 times relative to CPU-TLS and about 4 to 5 times relative to CPU-BLS. These results demonstrate that TransitNet provides an accurate, scalable, and computationally efficient framework for low-SNR transit blind searches in the tested regime and motivate its extension to longer-period Earth-size planet searches.
ER -