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

TL;DR

DeepAP introduces a two-stage deep learning framework combining Vision Transformer and ResNet to assess aperture photometry feasibility and predict optimal aperture sizes, significantly improving speed and accuracy for high-precision optical surveys.

Contribution

The paper presents a novel deep learning approach that automates aperture photometry assessment and optimization, outperforming classical methods in speed and bias mitigation.

Findings

ViT achieves ROC AUC of 0.96 for feasibility assessment.

ResNet effectively predicts aperture sizes, improving SNR.

Framework speeds up processing by 59,000 times compared to exhaustive methods.

Abstract

Aperture photometry is a fundamental technique widely used to obtain high-precision light curves in optical survey projects like Tianyu. However, its effectiveness is limited in crowded fields, and the choice of aperture size critically impacts photometric precision. To address these challenges, we propose DeepAP, an efficient and accurate two-stage deep learning framework for aperture photometry. Specifically, for a given source, we first train a Vision Transformer (ViT) model to assess its feasibility of aperture photometry. We then train the Residual Neural Network (ResNet) to predict its optimal aperture size. For aperture photometry feasibility assessment, the ViT model yields an ROC AUC value of 0.96, and achieves a precision of 0.974, a recall of 0.930, and an F1 score of 0.952 on the test set. For aperture size prediction, the ResNet model effectively mitigates biases inherent in classical growth curve methods by adaptively selecting apertures appropriate for sources of varying brightness, thereby enhancing the signal-to-noise ratio (SNR) across a wide range of targets. Meanwhile, some samples in the test set have a higher SNR than those obtained by exhaustive aperture size enumeration because of the finer granularity of aperture size estimation. By integrating ResNet with the ViT network, the DeepAP framework achieves a median total processing time of 18 milliseconds for a batch of 10 images, representing a speed-up of approximately 59000 times compared to exhaustive aperture size enumeration. This work paves the way for the automatic application of aperture photometry in future high-precision surveys such as Tianyu and LSST. The source code and model are available at https://github.com/ruiyicheng/DeepAP.