EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Efficient Evaluation of Gravitational Lensing Amplification Factors: A Deep Learning Framework

Fan Zhang, Qikai Zhang, Qiyuan Yang, Yong Yuan, Xilong Fan

The Astrophysical Journal Supplement Series · 01.06.2026 · 284 (2) · 48

DOI: 10.3847/1538-4365/ae64e4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Astrophysical Journal Supplement Series, online erschienen am 19.05.2026. Verfasst von Fan Zhang und 4 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The National Natural Science Foundation of China, Ministry of Science and Technology of the People’s Republic of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wave optics is essential for analyzing lensed gravitational waves, yet evaluating the diffraction integral F ( ω , y ) is computationally expensive. We present a Sinusoidal Representation Networks (SIRENs) framework for the dimensionless amplification factor, demonstrating its efficacy and generalization through point mass lens and singular isothermal sphere test cases. Unlike standard architectures that suffer from spectral bias, the network’s periodic activation functions structurally align with the integral’s oscillatory kernel, effectively resolving high-frequency spectral features. The resulting estimator achieves O ( 1 0 − 3 ) relative accuracy and a ∼100× speedup compared to direct numerical integration. By shifting the computational burden to offline training, our framework yields a stable O ( 1 ) inference complexity. This guarantees constant, sub-millisecond evaluation times, even in the weak-lensing diffraction tail where traditional methods stagnate. Additionally, the dimensionless formulation ensures intrinsic scale invariance, enabling direct application across astrophysical regimes from stellar-mass lenses in the ground-based LIGO/Virgo/KAGRA (LVK) band to supermassive black holes in the space-based LISA band.

Förderung

  • The National Natural Science Foundation of China
  • Ministry of Science and Technology of the People’s Republic of China

Zitieren

APA

Zhang, F., Zhang, Q., Yang, Q., Yuan, Y., & Fan, X. (2026). Efficient Evaluation of Gravitational Lensing Amplification Factors: A Deep Learning Framework. The Astrophysical Journal Supplement Series, 284(2), 48. https://doi.org/10.3847/1538-4365/ae64e4

Vancouver

Zhang F, Zhang Q, Yang Q, Yuan Y, Fan X. Efficient Evaluation of Gravitational Lensing Amplification Factors: A Deep Learning Framework. The Astrophysical Journal Supplement Series. 2026;284(2):48. doi:10.3847/1538-4365/ae64e4

BibTeX
@article{Zhang2026,
  author = {Zhang, Fan and Zhang, Qikai and Yang, Qiyuan and Yuan, Yong and Fan, Xilong},
  title = {Efficient Evaluation of Gravitational Lensing Amplification Factors: A Deep Learning Framework},
  journal = {The Astrophysical Journal Supplement Series},
  year = {2026},
  volume = {284},
  number = {2},
  pages = {48},
  doi = {10.3847/1538-4365/ae64e4}
}
Kostenlos starten →