TransitNet: A Compact Attention-Augmented Deep Learning Framework for Low-SNR Transit Blind Searches
This study addresses the challenge of detecting mid- to long-period Earth-like exoplanet transit signals in low signal-to-noise ratio (SNR) regimes, where conventional methods such as TLS and BLS suffer from low detection rates. To overcome this limitation, the authors propose a lightweight attention-augmented deep learning framework—the first to incorporate attention mechanisms into transit signal detection. Leveraging a unified simulation pipeline, rigorous evaluation via ROC and PR metrics, and optimized inference design, the model achieves 95.2% detection accuracy in the SNR range of 6–8 with a compact size of approximately 1.5 MB. In injection-recovery experiments, it attains a 93.0% recovery rate for Earth-analog planets, operates 12–25× faster than CPU-based TLS, and successfully recovers all 34 known Kepler planets, substantially outperforming traditional approaches.