Interpretable and Deblended Photometric Redshifts with a Deep Capsule Network

使用深胶囊网络可解释和去混合的光度红移

• 批准号: 2009251
• 负责人: Brett Andrews
• 金额: $ 53.56万
• 依托单位: University of Pittsburgh
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-09-01 至 2024-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2009251&HistoricalAwards=false
• 关键词: Interpretable; Deblended; Photometric; Redshifts; Deep

Studies of cosmology, galaxy evolution, and galaxy clustering all critically depend on redshift measurements. However, spectroscopic redshifts can only be obtained for a small fraction of the galaxies detected in current and next-generation deep imaging surveys, so most redshifts must be estimated from the images alone. This project introduces a promising new neural network architecture, called a deep capsule network, which will leverage pixel-level information from imaging surveys to estimate photometric redshifts. Principal objectives are 1) achieving state-of-the-art accuracy on a common wide-field test data set; 2) extending these methods to higher redshifts using Legacy Survey imaging and Dark Energy Spectroscopic Instrument data; and 3) combining the resolved optical imaging with integrated multiwavelength photometry in the ultraviolet and infrared, focusing on very low redshift galaxies that might host gravitational wave sources. The work includes graduate and undergraduate research, and a summer research boot camp and weekly seminar series. All course materials from the bootcamp will be made publicly available with open access.Estimating photometric redshifts is a well-posed problem for machine learning algorithms because spectroscopic redshifts can provide definitive measurements for training. The pooling operation that fueled the widespread success of convolutional neural networks throws away fine-grained spatial information and ultimately limits their ability to generalize to novel viewpoints and to parse blended objects. The deep capsule network overcomes these drawbacks of convolutional neural networks, and is much more easily interpreted. Projects to be carried out, and suitable for student research, include combining Sloan capsule network results with other photo-z methods to improve overall accuracy, and applying capsule networks to simulated data specifically to test performance on blended objects.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

宇宙学，星系进化和星系聚类的研究都取决于红移测量。 但是，只有对于在当前和下一代深层成像调查中检测到的一小部分星系中的一小部分星系才能获得光谱红移，因此必须仅从图像中估算大多数红移。 该项目介绍了一个有希望的新神经网络架构，称为“深胶囊网络”，该网络将利用像素级信息从成像调查到估计光度红移。 主要目标是1）在常见的宽场测试数据集上实现最先进的准确性； 2）使用传统调查成像和暗能量光谱仪器数据将这些方法扩展到更高的红移； 3）将解析的光学成像与紫外线和红外线中的集成多波长光度法结合在一起，重点是可能寄生引力波源的非常低的红移星系。 这项工作包括研究生和本科研究，以及夏季研究训练营和每周研讨会系列。 训练营的所有课程材料都将在开放式上公开提供。估计光度红移是机器学习算法的一个良好问题，因为光谱红移可以为培训提供明确的测量。 卷积神经网络的广泛成功的汇总操作抛弃了细粒的空间信息，并最终限制了它们将其推广到新观点和解析混合物体的能力。 深胶囊网络克服了卷积神经网络的这些缺点，并且更容易解释。 要进行的项目和适合学生研究，包括将斯隆胶囊网络结果与其他照片-Z方法相结合，以提高整体准确性，并将胶囊网络应用于模拟数据，专门用于测试混合对象上的性能。该奖项反映了NSF的法定任务，并被认为是通过基金会的知识优点和广泛的cribitia criperia criperia criperia criperia criperia criperia criperia criperia criperia criperia criperia criperia criperia criperia criperia criperia criperia criperia cristia criperia criperia criperia cristria均值得一提。

项目成果

Photometric redshifts from SDSS images with an interpretable deep capsule network

• DOI: 10.1093/mnras/stac2105
• 发表时间: 2021-12
• 期刊: Monthly Notices of the Royal Astronomical Society
• 影响因子: 4.8
• 作者: B. Dey;B. Andrews;J. Newman;Yao-Yuan Mao;M. Rau;R. Zhou

Calibrated Predictive Distributions for Photometric Redshifts

光度红移的校准预测分布

• 发表时间: 2022
• 期刊: proceedings of the Thirty-ninth International Conference on Machine Learning (ICML 2022
• 作者: Dey, Biprateep;Zhao, David;Andrews, Brett;Newman, Jeffrey;Izbicki, Rafael;Lee, Ann
• 通讯作者: Lee, Ann

Re-calibrating Photometric Redshift Probability Distributions Using Feature-space Regression

使用特征空间回归重新校准光度红移概率分布

• 发表时间: 2021
• 期刊: Advances in neural information processing systems
• 作者: Dey, Biprateep;Newman, Jeffrey A.;Andrews, Brett H.;Izbicki, Rafael;Lee, Ann B.;Zhao, David;Rau, Markus Michael;Malz, Alex I.
• 通讯作者: Malz, Alex I.