Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025Research in Astronomy and Astrophysics

DeepAP: Deep Learning-based Aperture Photometry Feasibility Assessment and Aperture Size Prediction

View Full Paper
Ask AI
Bookmark
Share

Authors

ZDZheng-Jun DuQLQ.-B. LiYRYicheng Rui

Discussion

Loading...

Member takes

Overview

DeepAP shows improved aperture photometry accuracy in crowded fields, indicating its potential for high-precision surveys.

Key Points

  • The DeepAP framework improves aperture photometry accuracy with a ROC AUC of 0.96, which significantly enhances precision.
  • The Residual Neural Network helps predict optimal aperture sizes, better adapting to various brightness levels to increase signal-to-noise ratio.
  • Utilizing a Vision Transformer model, DeepAP assesses feasibility, achieving a precision of 0.974 and recall of 0.930 for data from Tianyu.
  • DeepAP processes 10 images in 18 milliseconds, representing a speed-up of approximately 59,000 times compared to traditional methods.

Cite This Study

Du et al. (2025) studied this question.

synapsesocial.com/papers/68c1aad354b1d3bfb60e3859https://doi.org/10.1088/1674-4527/adf716
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Aperture-X: Physics-informed aperture feature learning for robust photometry2026
  2. 2ATD-DL: a deep learning framework for faint astronomical target detection2026
  3. 3Optimizing Dynamic Aperture Studies with Active Learning2024
  4. 4Synthetic aperture imaging by distributed arrays of space telescopes2024
  5. 5Synthetic aperture imaging by distributed arrays of space telescopes2024 · 1 citations