Search

Generative models producing images have enormous potential to advance discoveries across scientific fields and require metrics capable of quantifying the high dimensional output. We propose that astrophysics data, such as galaxy images, can test generative models with additional physics-motivated ground truths in addition to human judgment. For example, galaxies in the Universe form and change over billions of years, following physical laws and relationships that are both easy to characterize and difficult to encode in generative models. We build a conditional denoising diffusion probabilistic model (DDPM) and a conditional variational autoencoder (CVAE) and test their ability to generate realistic galaxies conditioned on their redshifts (galaxy ages). This is one of the first studies to probe these generative models using physically motivated metrics. We find that both models produce comparable realistic galaxies based on human evaluation, but our physics-based metrics are better able to discern the strengths and weaknesses of the generative models. Overall, the DDPM model performs better than the CVAE on the majority of the physics-based metrics. Ultimately, if we can show that generative models can learn the physics of galaxy evolution, they have the potential to unlock new astrophysical discoveries., Comment: 20 pages, 14 figures, 1 Table, code: https://github.com/astrodatalab/li2024_public, training data: https://zenodo.org/records/11117528

We present results exploring the role that probabilistic deep learning models can play in cosmology from large-scale astronomical surveys through photometric redshift (photo-z) estimation. Photo-z uncertainty estimates are critical for the science goals of upcoming large-scale surveys such as LSST, however common machine learning methods typically provide only point estimates and lack uncertainties on predictions. We turn to Bayesian neural networks (BNNs) as a promising way to provide accurate predictions of redshift values with uncertainty estimates. We have compiled a galaxy data set from the Hyper Suprime-Cam Survey with grizy photometry, which is designed to be a smaller scale version of large surveys like LSST. We use this data set to investigate the performance of a neural network (NN) and a probabilistic BNN for photo-z estimation and evaluate their performance with respect to LSST photo-z science requirements. We also examine the utility of photo-z uncertainties as a means to reduce catastrophic outlier estimates. The BNN outputs the estimate in the form of a Gaussian probability distribution. We use the mean and standard deviation as the redshift estimate and uncertainty. We find that the BNN can produce accurate uncertainties. Using a coverage test, we find excellent agreement with expectation -- 67.2$\%$ of galaxies between $0 < 2.5$ have 1-$\sigma$ uncertainties that cover the spectroscopic value. We also include a comparison to alternative machine learning models using the same data. We find the BNN meets two out of three of the LSST photo-z science requirements in the range $0 < z < 2.5$., Comment: 17 pages, 23 figures, 4 tables

In this work, we identify elements of effective machine learning datasets in astronomy and present suggestions for their design and creation. Machine learning has become an increasingly important tool for analyzing and understanding the large-scale flood of data in astronomy. To take advantage of these tools, datasets are required for training and testing. However, building machine learning datasets for astronomy can be challenging. Astronomical data is collected from instruments built to explore science questions in a traditional fashion rather than to conduct machine learning. Thus, it is often the case that raw data, or even downstream processed data is not in a form amenable to machine learning. We explore the construction of machine learning datasets and we ask: what elements define effective machine learning datasets? We define effective machine learning datasets in astronomy to be formed with well-defined data points, structure, and metadata. We discuss why these elements are important for astronomical applications and ways to put them in practice. We posit that these qualities not only make the data suitable for machine learning, they also help to foster usable, reusable, and replicable science practices., Comment: 5 pages, 1 figure, accepted to the peer-reviewed NeurIPS Machine Learning in the Physical Sciences Workshop, 2022

We present results exploring the role that probabilistic deep learning models can play in cosmology from large scale astronomical surveys through estimating the distances to galaxies (redshifts) from photometry. Due to the massive scale of data coming from these new and upcoming sky surveys, machine learning techniques using galaxy photometry are increasingly adopted to predict galactic redshifts which are important for inferring cosmological parameters such as the nature of dark energy. Associated uncertainty estimates are also critical measurements, however, common machine learning methods typically provide only point estimates and lack uncertainty information as outputs. We turn to Bayesian neural networks (BNNs) as a promising way to provide accurate predictions of redshift values. We have compiled a new galaxy training dataset from the Hyper Suprime-Cam Survey, designed to mimic large surveys, but over a smaller portion of the sky. We evaluate the performance and accuracy of photometric redshift (photo-z) predictions from photometry using machine learning, astronomical and probabilistic metrics. We find that while the Bayesian neural network did not perform as well as non-Bayesian neural networks if evaluated solely by point estimate photo-z values, BNNs can provide uncertainty estimates that are necessary for cosmology, Comment: 5 pages, 3 figures. Machine Learning and the Physical Sciences, NeurIPS 2021

We present results of using individual galaxies' redshift probability information derived from a photometric redshift (photo-z) algorithm, SPIDERz, to identify potential catastrophic outliers in photometric redshift determinations. By using two test data sets comprised of COSMOS multi-band photometry spanning a wide redshift range (050%) of the catastrophic outlier galaxies, while only flagging a small fraction (<5%) of the total non-outlier galaxies, depending on parameter choices. The fraction of non-outlier galaxies flagged varies significantly with redshift and magnitude, however. We examine the performance of this strategy in photo-z determinations using a range of flagging parameter values. These results could potentially be useful for utilization of photometric redshifts in future large scale surveys where catastrophic outliers are particularly detrimental to the science goals., Comment: 12 pages, 9 figures, 2 tables; updated to PASP accepted version

Aims: We present a custom support vector machine classification package for photometric redshift estimation, including comparisons with other methods. We also explore the efficacy of including galaxy shape information in redshift estimation. Support vector machines, a type of machine learning, utilize optimization theory and supervised learning algorithms to construct predictive models based on the information content of data in a way that can treat different input features symmetrically. Methods: The custom support vector machine package we have developed is designated SPIDERz and made available to the community. As test data for evaluating performance and comparison with other methods, we apply SPIDERz to four distinct data sets: 1) the publicly available portion of the PHAT-1 catalog based on the GOODS-N field with spectroscopic redshifts in the range $z < 3.6$, 2) 14365 galaxies from the COSMOS bright survey with photometric band magnitudes, morphology, and spectroscopic redshifts inside $z < 1.4$, 3) 3048 galaxies from the overlap of COSMOS photometry and morphology with 3D-HST spectroscopy extending to $z < 3.9$, and 4) 2612 galaxies with five-band photometric magnitudes and morphology from the All-wavelength Extended Groth Strip International Survey and $z < 1.57$. Results: We find that SPIDER-z achieves results competitive with other empirical packages on the PHAT-1 data, and performs quite well in estimating redshifts with the COSMOS and AEGIS data, including in the cases of a large redshift range ($0 < z < 3.9$). We also determine from analyses with both the COSMOS and AEGIS data that the inclusion of morphological information does not have a statistically significant benefit for photometric redshift estimation with the techniques employed here., Comment: Submitted to A&A, 11 pages, 10 figures, 1 table, updated to version in revision