We present a catalog of 4539 fast radio bursts (FRBs) observed with the Canadian Hydrogen Intensity Mapping Experiment telescope between 2018 July 25 and 2023 September 15. These bursts originate from 3641 unique sources, including 981 bursts from 83 known repeating sources. For each FRB, the catalog provides an O(10 ') estimate of sky location along with corresponding measurements of cumulative exposure time and survey sensitivity over the observing period. It includes a total-intensity dynamic spectrum between 400 and 800 MHz at 0.983 ms resolution. From this spectrum, we constrain a model of the burst morphology and measure key parameters such as arrival time, intrinsic temporal width, dispersion measure, scattering time, and flux density. This second catalog includes all FRBs from the first catalog, with every event reprocessed using a uniform and improved analysis framework. We show that previously published inferences remain valid under the updated measurements. We assess consistency of the detection rate across observational parameters, present initial distributions of burst properties, and outline ongoing and future studies that will use this catalog to investigate the nature of FRBs and their utility as astrophysical and cosmological probes.

Integral Field Spectroscopy (IFS) surveys offer a unique new landscape in which to learn in both spatial and spectroscopic dimensions and could help uncover previously unknown insights into galaxy evolution. In this work, we demonstrate a new unsupervised deep learning framework using Convolutional Long-Short Term Memory Network Autoencoders to encode generalized feature representations across both spatial and spectroscopic dimensions spanning 19 optical emission lines (3800A < λ< 8000A) among a sample of ∼ 9000 galaxies from the MaNGA IFS survey. As a demonstrative exercise, we assess our model on a sample of 290 Active Galactic Nuclei (AGN) and highlight scientifically interesting characteristics of some highly anomalous AGN.

We present a catalogue of segmentation maps identifying the extent of spiral arms and bars of 639,636 galaxies in the DESI Legacy Survey. To produce these maps, we have trained a deep U-net-style neural network using the pixel masks from the Galaxy Zoo: 3D citizen science project. The resulting data products are "soft" segmentation maps, which show the confidence of the model that a pixel lies within the spiral arms or bars of a galaxy. In this paper we detail the sample selection from DESI-LS using the machine classifications from Galaxy Zoo: DESI, the architecture of the U-net model--dubbed ZooBot:3D. We demonstrate the ability of the model to identify spiral arms and bars in a wide range of face-on disks, and identify an emergent ability to identify rings--despite only a small number of ring-type galaxies being present in the training data. Finally, we discuss the practical application of these data products to photometric imaging and IFU spectroscopy. The ZooBot:3D dataset is available for use publicly, and contains the full catalogue presented in this paper, along with cross-matched subsamples for the MaNGA and SAMI IFU surveys.

We present morphological classifications of over 41 000 galaxies out to z(phot) similar to 2.5 across 6 deg(2) of the Euclid Deep Field North (EDFN) from the Hawaii Twenty Square Degree (H20) survey, a part of the wider Cosmic Dawn survey. Galaxy Zoo citizen scientists play a crucial role in the examination of large astronomical data sets through crowdsourced data mining of extragalactic imaging. This iteration, Galaxy Zoo: Cosmic Dawn (GZCD), saw tens of thousands of volunteers and the deep learning foundation model Zoobot collectively classify objects in ultra-deep multiband Hyper Suprime-Cam (HSC) imaging down to a depth of m(HSC-i) = 21.5. Here, we present the details and general analysis of this iteration, including the use of Zoobot in an active learning cycle to improve both model performance and volunteer experience, as well as the discovery of 51 new gravitational lenses in the EDFN. We also announce the public data release of the classifications for over 45 000 subjects, including more than 41 000 galaxies (median z(phot) of 0.4 +/- 0.23), along with their associated image cut-outs. This data set provides a valuable opportunity for follow-up imaging of objects in the EDFN as well as acting as a truth set for training deep learning models for application to ground-based surveys like that of the Ultraviolet Near-Infrared Optical Northern Survey (UNIONS) collaboration and the newly operational Vera C. Rubin Observatory.

We introduce Galaxy Zoo Evo, a labeled dataset for building and evaluating foundation models on images of galaxies. GZ Evo includes 104M crowdsourced labels for 823k images from four telescopes. Each image is labeled with a series of fine-grained questions and answers (e.g. "featured galaxy, two spiral arms, tightly wound, merging with another galaxy"). These detailed labels are useful for pretraining or finetuning. We also include four smaller sets of labels (167k galaxies in total) for downstream tasks of specific interest to astronomers, including finding strong lenses and describing galaxies from the new space telescope Euclid. We hope GZ Evo will serve as a real-world benchmark for computer vision topics such as domain adaption (from terrestrial to astronomical, or between telescopes) or learning under uncertainty from crowdsourced labels. We also hope it will support a new generation of foundation models for astronomy; such models will be critical to future astronomers seeking to better understand our universe.

At the peak of cosmic star formation (1 ≲ z ≲ 2), the majority of star-forming galaxies hosted compact, star-forming clumps, which were responsible for a large fraction of cosmic star formation. By comparison, ≲5% of local star-forming galaxies host comparable clumps. In this work, we investigate the link between the environmental conditions surrounding local ( z < 0.04) galaxies and the prevalence of clumps in these galaxies. To obtain our clump sample, we use a Faster R-CNN object detection network trained on the catalog of clump labels provided by the Galaxy Zoo: Clump Scout project, then apply this network to detect clumps in approximately 240,000 Sloan Digital Sky Survey galaxies (originally selected for Galaxy Zoo 2). The resulting sample of 41,445 u -band bright clumps in 34,246 galaxies is the largest sample of clumps yet assembled. We then select a volume-limited sample of 9964 galaxies and estimate the density of their local environment using the distance to their projected fifth nearest neighbor. We find a robust correlation between environment and the clumpy fraction ( f clumpy ) for star-forming galaxies (specific star formation rate, sSFR > 10 −2 Gyr −1 ) but find little to no relationship when controlling for galaxies’ sSFR or color. Further, f clumpy increases significantly with sSFR in local galaxies, particularly above sSFR > 10 −1 Gyr −1 . We posit that a galaxy’s gas fraction primarily controls the formation and lifetime of its clumps, and that environmental interactions play a smaller role.

We study the evolution of the bar fraction in disk galaxies between 0.5 < z < 4.0 using multiband colored images from JWST Cosmic Evolution Early Release Science Survey (CEERS). These images were classified by citizen scientists in a new phase of the Galaxy Zoo (GZ) project called GZ CEERS. Citizen scientists were asked whether a strong or weak bar was visible in the host galaxy. After considering multiple corrections for observational biases, we find that the bar fraction decreases with redshift in our volume-limited sample ( n = 398); from 2 5 − 4 + 6 % at 0.5 < z < 1.0 to 3 − 1 + 6 % at 3.0 < z < 4.0. However, we argue it is appropriate to interpret these fractions as lower limits. Disentangling real changes in the bar fraction from detection biases remains challenging. Nevertheless, we find a significant number of bars up to z = 2.5. This implies that disks are dynamically cool or baryon dominated, enabling them to host bars. This also suggests that bar-driven secular evolution likely plays an important role at higher redshifts. When we distinguish between strong and weak bars, we find that the weak bar fraction decreases with increasing redshift. In contrast, the strong bar fraction is constant between 0.5 < z < 2.5. This implies that the strong bars found in this work are robust long-lived structures, unless the rate of bar destruction is similar to the rate of bar formation. Finally, our results are consistent with disk instabilities being the dominant mode of bar formation at lower redshifts, while bar formation through interactions and mergers is more common at higher redshifts.

Hierarchical merging of galaxies plays an important role in galaxy formation and evolution. Mergers could trigger key evolutionary phases such as starburst activities and active accretion periods onto supermassive black holes at the centres of galaxies. We aim to detect mergers and merger stages (pre- and post-mergers) across cosmic history and test whether it is better to detect mergers and their merger stages simultaneously or hierarchically. In addition, we want to test the impact of merger time relative to the coalescence of merging galaxies. First, we generated realistic mock JWST images of simulated galaxies selected from the IllustrisTNG cosmological hydrodynamical simulations. Then we trained deep learning (DL) models in the Zoobot Python package to classify galaxies into merging/non-merging galaxies and their merger stages. We used two different set-ups: (i) two-stage, in which we classify galaxies into mergers and non-mergers and then classify the mergers into pre-mergers and post-mergers, and (ii) one-stage, in which merger/non-merger and merger stages are classified simultaneously. We found that the one-stage classification set-up moderately outperforms the two-stage set-up, offering better overall accuracy and precision, particularly for the non-merger class. Pre-mergers can be classified with the highest precision in both set-ups, possibly due to the more recognisable merging features and the presence of merging companions. The image signal-to-noise ratio affects the performance of the DL classifiers, but not much after a certain threshold is crossed. Both precision and recall of the classifiers depend strongly on merger time, finding it more difficult to identify true mergers observed at stages that are more distant to coalescence. For pre-mergers, we recommend selecting mergers which will merge in the next 0.4 Gyrs, to achieve a good balance between precision and recall.

In many real-world machine learning (ML) applications (e.g. detecting broken bones in x-ray images, detecting species in camera traps), in practice models need to perform well on specific deployments (e.g. a specific hospital, a specific national park) rather than the domain broadly. However, deployments often have imbalanced, unique data distributions. Discrepancy between the training distribution and the deployment distribution can lead to suboptimal performance, highlighting the need to select deployment-specialized subsets from the available training data. We formalize dataset subset selection for specialization (DS3): given a training set drawn from a general distribution and a (potentially unlabeled) query set drawn from the desired deployment-specific distribution, the goal is to select a subset of the training data that optimizes deployment performance. We introduce DataS^3; the first dataset and benchmark designed specifically for the DS3 problem. DataS^3 encompasses diverse real-world application domains, each with a set of distinct deployments to specialize in. We conduct a comprehensive study evaluating algorithms from various families–including coresets, data filtering, and data curation–on DataS^3, and find that general-distribution methods consistently fail on deployment-specific tasks. Additionally, we demonstrate the existence of manually curated (deployment-specific) expert subsets that outperform training on all available data with accuracy gains up to 51.3 percent. Our benchmark highlights the critical role of tailored dataset curation in enhancing performance and training efficiency on deployment-specific distributions, which we posit will only become more important as global, public datasets become available across domains and ML models are deployed in the real world.

Generating novel and creative scientific hypotheses is a cornerstone in achieving Artificial General Intelligence. Large language and reasoning models have the potential to aid in the systematic creation, selection, and validation of scientifically informed hypotheses. However, current foundation models often struggle to produce scientific ideas that are both novel and feasible. One reason is the lack of a dedicated dataset that frames Scientific Hypothesis Generation (SHG) as a Natural Language Generation (NLG) task. In this paper, we introduce HypoGen, the first dataset of approximately 5500 structured problem-hypothesis pairs extracted from top-tier computer science conferences structured with a Bit-Flip-Spark schema, where the Bit is the conventional assumption, the Spark is the key insight or conceptual leap, and the Flip is the resulting counterproposal. HypoGen uniquely integrates an explicit Chain-of-Reasoning component that reflects the intellectual process from Bit to Flip. We demonstrate that framing hypothesis generation as conditional language modelling, with the model fine-tuned on Bit-Flip-Spark and the Chain-of-Reasoning (and where, at inference, we only provide the Bit), leads to improvements in the overall quality of the hypotheses. Our evaluation employs automated metrics and LLM judge rankings for overall quality assessment. We show that by fine-tuning on our HypoGen dataset we improve the novelty, feasibility, and overall quality of the generated hypotheses. The HypoGen dataset is publicly available at huggingface.co/datasets/UniverseTBD/hypogen-dr1.

Galaxy Zoo is an online project to classify morphological features in extra-galactic imaging surveys with public voting. In this paper, we compare the classifications made for two different surveys, the Dark Energy Spectroscopic Instrument (DESI) imaging survey and a part of the Kilo-Degree Survey (KiDS), in the equatorial fields of the Galaxy And Mass Assembly (GAMA) survey. Our aim is to cross-validate and compare the classifications based on different imaging quality and depth. We find that generally the voting agrees globally but with substantial scatter i.e. substantial differences for individual galaxies. There is a notable higher voting fraction in favor of ``smooth'' galaxies in the DESI+\rev{{\sc zoobot}} classifications, most likely due to the difference between imaging depth. DESI imaging is shallower and slightly lower resolution than KiDS and the Galaxy Zoo images do not reveal details such as disk features \rev{and thus are missed in the {\sc zoobot} training sample}. \rev{We check against expert visual classifications and find good agreement with KiDS-based Galaxy Zoo voting.} We reproduce the results from Porter-Temple+ (2022), on the dependence of stellar mass, star-formation, and specific star-formation on the number of spiral arms. This shows that once corrected for redshift, the DESI Galaxy Zoo and KiDS Galaxy Zoo classifications agree well on population properties. The zoobot cross-validation increases confidence in its ability to compliment Galaxy Zoo classifications and its ability for transfer learning across surveys.

In this work, we apply self-supervised learning with instance differentiation to learn a robust, multi-purpose representation for image analysis of resolved extragalactic continuum images. We train a multi-use model which compresses our unlabelled data into a structured, low dimensional representation which can be used for a variety of downstream tasks (e.g. classification, similarity search). We exceed baseline supervised Fanaroff-Riley classification performance by a statistically significant margin, with our model reducing the test set error by up to half. Our model is also able to maintain high classification accuracy with very few labels, with only 7.79% error when only using 145 labels. We further demonstrate that by using our foundation model, users can efficiently trade off compute, human labelling cost and test set accuracy according to their respective budgets, allowing for efficient classification in a wide variety of scenarios. We highlight the generalizability of our model by showing that it enables accurate classification in a label scarce regime with data from the new MIGHTEE survey without any hyper-parameter tuning, where it improves upon the baseline by ~8%. Visualizations of our labelled and un-labelled data show that our model's representation space is structured with respect to physical properties of the sources, such as angular source extent. We show that the learned representation is scientifically useful even if no labels are available by performing a similarity search, finding hybrid sources in the RGZ DR1 data-set without any labels. We show that good augmentation design and hyper-parameter choice can help achieve peak performance, while emphasising that optimal hyper-parameters are not required to obtain benefits from self-supervised pre-training.

We present morphological classifications based on Galaxy Zoo analysis of 71,052 galaxies with imaging from the United Kingdom Infrared Telescope Infrared Deep Sky Survey (UKIDSS). Galaxies were selected out of the Galaxy Zoo 2 (GZ2) sample, so also have gri imaging from the Sloan Digital Sky Survey. An identical classification tree, and vote weighting/aggregation was applied to both UKIDSS and GZ2 classifications enabling direct comparisons. With this Research Note we provide a public release of the GZ:UKIDSS morphologies and discuss some initial comparisons with GZ2.

We present the MULTIMODAL UNIVERSE, a large-scale multimodal dataset of scientific astronomical data, compiled specifically to facilitate machine learning research. Overall, the MULTIMODAL UNIVERSE contains hundreds of millions of astronomical observations, constituting 100 TB of multi-channel and hyper-spectral images, spectra, multivariate time series, as well as a wide variety of associated scientific measurements and "metadata". In addition, we include a range of benchmark tasks representative of standard practices for machine learning methods in astrophysics. This massive dataset will enable the development of large multi-modal models specifically targeted towards scientific applications. All codes used to compile the MULTIMODAL UNIVERSE and a description of how to access the data is available at https://github.com/MultimodalUniverse/MultimodalUniverse

Despite the evidence that supermassive black holes (SMBHs) co-evolve with their host galaxy, and that most of the growth of these SMBHs occurs via merger-free processes, the underlying mechanisms which drive this secular co-evolution are poorly understood. We investigate the role that both strong and weak large-scale galactic bars play in mediating this relationship. Using 72,940 disc galaxies in a volume-limited sample from Galaxy Zoo DESI, we analyse the active galactic nucleus (AGN) fraction in strongly barred, weakly barred, and unbarred galaxies up to z = 0.1 over a range of stellar masses and colours. After controlling for stellar mass and colour, we find that the optically selected AGN fraction is 31.6 +/- 0.9 per cent in strongly barred galaxies, 23.3 +/- 0.8 per cent in weakly barred galaxies, and 14.2 +/- 0.6 per cent in unbarred disc galaxies. These are highly statistically robust results, strengthening the tantalising results in earlier works. Strongly barred galaxies have a higher fraction of AGNs than weakly barred galaxies, which in turn have a higher fraction than unbarred galaxies. Thus, while bars are not required in order to grow a SMBH in a disc galaxy, large-scale galactic bars appear to facilitate AGN fuelling, and the presence of a strong bar makes a disc galaxy more than twice as likely to host an AGN than an unbarred galaxy at all galaxy stellar masses and colours.

Modern astronomical surveys are producing datasets of unprecedented size and richness, increasing the potential for high-impact scientific discovery. This possibility, coupled with the challenge of exploring a large number of sources, has led to the development of novel machine-learning-based anomaly detection approaches, such as Astronomaly. For the first time, we test the scalability of Astronomaly by applying it to almost 4 million images of galaxies from the Dark Energy Camera Legacy Survey. We use a trained deep learning algorithm to learn useful representations of the images and pass these to the anomaly detection algorithm isolation forest, coupled with Astronomaly's active learning method, to discover interesting sources. We find that data selection criteria have a significant impact on the trade-off between finding rare sources such as strong lenses and introducing artefacts into the dataset. We demonstrate that active learning is required to identify the most interesting sources and reduce artefacts, while anomaly detection methods alone are insufficient. Using Astronomaly, we find 1635 anomalies among the top 2000 sources in the dataset after applying active learning, including eight strong gravitational lens candidates, 1609 galaxy merger candidates, and 18 previously unidentified sources exhibiting highly unusual morphology. Our results show that by leveraging the human-machine interface, Astronomaly is able to rapidly identify sources of scientific interest even in large datasets.

Giant Star-forming Clumps (GSFCs) are areas of intensive star-formation that are commonly observed in high-redshift (z>1) galaxies but their formation and role in galaxy evolution remain unclear. High-resolution observations of low-redshift clumpy galaxy analogues are rare and restricted to a limited set of galaxies but the increasing availability of wide-field galaxy survey data makes the detection of large clumpy galaxy samples increasingly feasible. Deep Learning, and in particular CNNs, have been successfully applied to image classification tasks in astrophysical data analysis. However, one application of DL that remains relatively unexplored is that of automatically identifying and localising specific objects or features in astrophysical imaging data. In this paper we demonstrate the feasibility of using Deep learning-based object detection models to localise GSFCs in astrophysical imaging data. We apply the Faster R-CNN object detection framework (FRCNN) to identify GSFCs in low redshift (z<0.3) galaxies. Unlike other studies, we train different FRCNN models not on simulated images with known labels but on real observational data that was collected by the Sloan Digital Sky Survey Legacy Survey and labelled by volunteers from the citizen science project `Galaxy Zoo: Clump Scout'. The FRCNN model relies on a CNN component as a `backbone' feature extractor. We show that CNNs, that have been pre-trained for image classification using astrophysical images, outperform those that have been pre-trained on terrestrial images. In particular, we compare a domain-specific CNN -`Zoobot' - with a generic classification backbone and find that Zoobot achieves higher detection performance and also requires smaller training data sets to do so. Our final model is capable of producing GSFC detections with a completeness and purity of >=0.8 while only being trained on ~5,000 galaxy images.

Abstract We present the Multimodal Universe, a new framework collating over 100 TB of multimodal astronomical data for its first release, spanning images, spectra, time series, tabular and hyper-spectral data. This unified collection enables a wide variety of machine learning (ML) applications and research across astronomical domains. The dataset brings together observations from multiple surveys, facilities, and wavelength regimes, providing standardized access to diverse data types. By providing uniform access to this diverse data, the Multimodal Universe aims to accelerate the development of ML methods for observational astronomy that can work across the large differences in astronomical datasets. The framework is actively supported and is designed to be extended whilst enforcing minimal self consistent conventions making contributing data as simple and practical as possible.

The exponential growth of astronomical literature poses significant challenges for researchers navigating and synthesizing general insights or even domain-specific knowledge. We present pathfinder, a machine learning framework designed to enable literature review and knowledge discovery in astronomy, focusing on semantic searching with natural language instead of syntactic searches with keywords. Utilizing state-of-the-art large language models (LLMs) and a corpus of 385,166 peer-reviewed papers from the Astrophysics Data System, pathfinder offers an innovative approach to scientific inquiry and literature exploration. Our framework couples advanced retrieval techniques with LLM-based synthesis to search astronomical literature by semantic context as a complement to currently existing methods that use keywords or citation graphs. It addresses complexities of jargon, named entities, and temporal aspects through time-based and citation-based weighting schemes. We demonstrate the tool's versatility through case studies, showcasing its application in various research scenarios. The system's performance is evaluated using custom benchmarks, including single-paper and multipaper tasks. Beyond literature review, pathfinder offers unique capabilities for reformatting answers in ways that are accessible to various audiences (e.g., in a different language or as simplified text), visualizing research landscapes, and tracking the impact of observatories and methodologies. This tool represents a significant advancement in applying artificial intelligence to astronomical research, aiding researchers at all career stages in navigating modern astronomy literature.

We present the first systematic investigation of supervised scaling laws outside of an ImageNet-like context - on images of galaxies. We use 840k galaxy images and over 100M annotations by Galaxy Zoo volunteers, comparable in scale to Imagenet-1K. We find that adding annotated galaxy images provides a power law improvement in performance across all architectures and all tasks, while adding trainable parameters is effective only for some (typically more subjectively challenging) tasks. We then compare the downstream performance of finetuned models pretrained on either ImageNet-12k alone vs. additionally pretrained on our galaxy images. We achieve an average relative error rate reduction of 31% across 5 downstream tasks of scientific interest. Our finetuned models are more label-efficient and, unlike their ImageNet-12k-pretrained equivalents, often achieve linear transfer performance equal to that of end-to-end finetuning. We find relatively modest additional downstream benefits from scaling model size, implying that scaling alone is not sufficient to address our domain gap, and suggest that practitioners with qualitatively different images might benefit more from in-domain adaption followed by targeted downstream labelling.