Photometric Measurement Algorithm for SDSS Survey Images Based on Deep Learning

The Sloan Digital Sky Survey (SDSS) offers extensive spectral and imaging data encompassing galactic and extragalactic objects. As a fundamental task in astronomical data analysis, photometric measurement plays a vital role in understanding the physical characteristics of celestial bodies, their evolutionary history, and the universe's large-scale structure. Traditional methods like Point Spread Function (PSF) fitting have been widely used for this purpose. However, they often face challenges such as computational inefficiency and sensitivity to noise, especially when dealing with large datasets. Consequently, a growing focus is on developing more efficient and accurate photometric measurement techniques. In this study, we introduce a deep learning model called CSMR-Net, specifically designed for photometric measurement tasks in SDSS survey images. The model combines convolutional layers with Self-Attention mechanisms to efficiently extract spatial and channel features, thereby improving the accuracy and robustness of photometric measurements. Experimental results show that CSMR-Net surpasses traditional methods in both accuracy and computational speed, demonstrating its superior performance in processing large-scale astronomical datasets.