arXiv subjects

Nima Sedaghat

Publications and source records attributed to Nima Sedaghat.

12 recordsLinked to original sources

arXiv2025

Identification and photometric classification of extragalactic transients in the Vera C. Rubin Observatory's Data Preview 1

The Vera C. Rubin Observatory will soon survey the southern sky, delivering a depth and sky coverage that is unprecedented in time domain astronomy. As part of commissioning, Data Preview 1 (DP1) has been released. It comprises a LSSTComCam observing campaign between November and December 2024 with multi-band imaging of seven fields, covering roughly 0.4 square degrees each, providing a first glimpse into the data products that will become available once the Legacy Survey of Space and Time begins. In this work, we search three fields for extragalactic transients. We identify eight new likely supernovae, and three known ones from a sample of 369,644 difference image analysis objects. Photometric classification using Superphot+ assigns sub-classes with >95% confidence to only one SN Ia and one SN II in this sample. Our findings are in agreement with supernova detection rate predictions of $15\pm4$ supernovae from simulations using simsurvey. The supernova detection rate in the data is possibly affected by the lack of suitable templates. Nevertheless, this work demonstrates the quality of the data products delivered in DP1 and indicates that the Rubin Observatory's Legacy Survey of Space and Time (LSST) is well placed to fulfill its discovery potential in time domain astronomy.

astro-ph.HE↗

arXiv2025

Enabling Early Transient Discovery in LSST via Difference Imaging with DECam

We present SLIDE, a pipeline that enables transient discovery in data from the Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST), using archival images from the Dark Energy Camera (DECam) as templates for difference imaging. We apply this pipeline to the recently released Data Preview 1 (DP1; the first public release of Rubin commissioning data) and search for transients in the resulting difference images. The image subtraction, photometry extraction, and transient detection are all performed on the Rubin Science Platform. We demonstrate that SLIDE effectively extracts clean photometry by circumventing poor or missing LSST templates. We identified 29 previously unreported transients, 12 of which would not have been detected based on the DP1 DiaObject catalog. SLIDE will be especially useful for transient analysis in the early years of LSST, when template coverage will be largely incomplete or when templates may be contaminated by transients present at the time of acquisition. We present multiband light curves for a sample of known transients, along with new transient candidates identified through our search. Finally, we discuss the prospects of applying this pipeline during the main LSST survey. Our pipeline is broadly applicable and will support studies of all transients with slowly evolving phases.

astro-ph.HE↗

arXiv2024

Selfish Evolution: Making Discoveries in Extreme Label Noise with the Help of Overfitting Dynamics

Motivated by the scarcity of proper labels in an astrophysical application, we have developed a novel technique, called Selfish Evolution, which allows for the detection and correction of corrupted labels in a weakly supervised fashion. Unlike methods based on early stopping, we let the model train on the noisy dataset. Only then do we intervene and allow the model to overfit to individual samples. The ``evolution'' of the model during this process reveals patterns with enough information about the noisiness of the label, as well as its correct version. We train a secondary network on these spatiotemporal ``evolution cubes'' to correct potentially corrupted labels. We incorporate the technique in a closed-loop fashion, allowing for automatic convergence towards a mostly clean dataset, without presumptions about the state of the network in which we intervene. We evaluate on the main task of the Supernova-hunting dataset but also demonstrate efficiency on the more standard MNIST dataset.

cs.CV↗

arXiv2024

The Active Asteroids Citizen Science Program: Overview and First Results

We present the Citizen Science program Active Asteroids and describe discoveries stemming from our ongoing project. Our NASA Partner program is hosted on the Zooniverse online platform and launched on 2021 August 31, with the goal of engaging the community in the search for active asteroids -- asteroids with comet-like tails or comae. We also set out to identify other unusual active solar system objects, such as active Centaurs, active quasi-Hilda asteroids, and Jupiter-family comets (JFCs). Active objects are rare in large part because they are difficult to identify, so we ask volunteers to assist us in searching for active bodies in our collection of millions of images of known minor planets. We produced these cutout images with our project pipeline that makes use of publicly available Dark Energy Camera (DECam) data. Since the project launch, roughly 8,300 volunteers have scrutinized some 430,000 images to great effect, which we describe in this work. In total we have identified previously unknown activity on 15 asteroids, plus one Centaur, that were thought to be asteroidal (i.e., inactive). Of the asteroids, we classify four as active quasi-Hilda asteroids, seven as JFCs, and four as active asteroids, consisting of one Main-belt comet (MBC) and three MBC candidates. We also include our findings concerning known active objects that our program facilitated, an unanticipated avenue of scientific discovery. These include discovering activity occurring during an orbital epoch for which objects were not known to be active, and the reclassification of objects based on our dynamical analyses.

astro-ph.EP↗

arXiv2023

Stellar Karaoke: deep blind separation of terrestrial atmospheric effects out of stellar spectra by velocity whitening

We report a study exploring how the use of deep neural networks with astronomical Big Data may help us find and uncover new insights into underlying phenomena: through our experiments towards unsupervised knowledge extraction from astronomical Big Data we serendipitously found that deep convolutional autoencoders tend to reject telluric lines in stellar spectra. With further experiments we found that only when the spectra are in the barycentric frame does the network automatically identify the statistical independence between two components, stellar vs telluric, and rejects the latter. We exploit this finding and turn it into a proof-of-concept method for removal of the telluric lines from stellar spectra in a fully unsupervised fashion: we increase the inter-observation entropy of telluric absorption lines by imposing a random, virtual radial velocity to the observed spectrum. This technique results in a non-standard form of ``whitening'' in the atmospheric components of the spectrum, decorrelating them across multiple observations. We process more than 250,000 spectra from the High Accuracy Radial velocity Planetary Search (HARPS) and with qualitative and quantitative evaluations against a database of known telluric lines, show that most of the telluric lines are successfully rejected. Our approach, `Stellar Karaoke', has zero need for prior knowledge about parameters such as observation time, location, or the distribution of atmospheric molecules and processes each spectrum in milliseconds. We also train and test on Sloan Digital Sky Survey (SDSS) and see a significant performance drop due to the low resolution. We discuss directions for developing tools on top of the introduced method in the future.

astro-ph.SR↗

arXiv2020

Machines Learn to Infer Stellar Parameters Just by Looking at a Large Number of Spectra

Machine learning has been widely applied to clearly defined problems of astronomy and astrophysics. However, deep learning and its conceptual differences to classical machine learning have been largely overlooked in these fields. The broad hypothesis behind our work is that letting the abundant real astrophysical data speak for itself, with minimal supervision and no labels, can reveal interesting patterns which may facilitate discovery of novel physical relationships. Here as the first step, we seek to interpret the representations a deep convolutional neural network chooses to learn, and find correlations in them with current physical understanding. We train an encoder-decoder architecture on the self-supervised auxiliary task of reconstruction to allow it to learn general representations without bias towards any specific task. By exerting weak disentanglement at the information bottleneck of the network, we implicitly enforce interpretability in the learned features. We develop two independent statistical and information-theoretical methods for finding the number of learned informative features, as well as measuring their true correlation with astrophysical validation labels. As a case study, we apply this method to a dataset of ~270000 stellar spectra, each of which comprising ~300000 dimensions. We find that the network clearly assigns specific nodes to estimate (notions of) parameters such as radial velocity and effective temperature without being asked to do so, all in a completely physics-agnostic process. This supports the first part of our hypothesis. Moreover, we find with high confidence that there are ~4 more independently informative dimensions that do not show a direct correlation with our validation parameters, presenting potential room for future studies.

astro-ph.IM↗

arXiv2019

Photometry of high-redshift blended galaxies using deep learning

The new generation of deep photometric surveys requires unprecedentedly precise shape and photometry measurements of billions of galaxies to achieve their main science goals. At such depths, one major limiting factor is the blending of galaxies due to line-of-sight projection, with an expected fraction of blended galaxies of up to 50%. Current deblending approaches are in most cases either too slow or not accurate enough to reach the level of requirements. This work explores the use of deep neural networks to estimate the photometry of blended pairs of galaxies in monochrome space images, similar to the ones that will be delivered by the Euclid space telescope. Using a clean sample of isolated galaxies from the CANDELS survey, we artificially blend them and train two different network models to recover the photometry of the two galaxies. We show that our approach can recover the original photometry of the galaxies before being blended with $\sim$7% accuracy without any human intervention and without any assumption on the galaxy shape. This represents an improvement of at least a factor of 4 compared to the classical SExtractor approach. We also show that forcing the network to simultaneously estimate a binary segmentation map results in a slightly improved photometry. All data products and codes will be made public to ease the comparison with other approaches on a common data set.

astro-ph.GA↗

arXiv2019

Machine Learning for the Zwicky Transient Facility

The Zwicky Transient Facility is a large optical survey in multiple filters producing hundreds of thousands of transient alerts per night. We describe here various machine learning (ML) implementations and plans to make the maximal use of the large data set by taking advantage of the temporal nature of the data, and further combining it with other data sets. We start with the initial steps of separating bogus candidates from real ones, separating stars and galaxies, and go on to the classification of real objects into various classes. Besides the usual methods (e.g., based on features extracted from light curves) we also describe early plans for alternate methods including the use of domain adaptation, and deep learning. In a similar fashion we describe efforts to detect fast moving asteroids. We also describe the use of the Zooniverse platform for helping with classifications through the creation of training samples, and active learning. Finally we mention the synergistic aspects of ZTF and LSST from the ML perspective.

astro-ph.IM↗

arXiv2017

Orientation-boosted Voxel Nets for 3D Object Recognition

Recent work has shown good recognition results in 3D object recognition using 3D convolutional networks. In this paper, we show that the object orientation plays an important role in 3D recognition. More specifically, we argue that objects induce different features in the network under rotation. Thus, we approach the category-level classification task as a multi-task problem, in which the network is trained to predict the pose of the object in addition to the class label as a parallel task. We show that this yields significant improvements in the classification results. We test our suggested architecture on several datasets representing various 3D data sources: LiDAR data, CAD models, and RGB-D images. We report state-of-the-art results on classification as well as significant improvements in precision and speed over the baseline on 3D detection.

cs.CV↗

arXiv2017

Effective Image Differencing with ConvNets for Real-time Transient Hunting

Large sky surveys are increasingly relying on image subtraction pipelines for real-time (and archival) transient detection. In this process one has to contend with varying PSF, small brightness variations in many sources, as well as artifacts resulting from saturated stars, and, in general, matching errors. Very often the differencing is done with a reference image that is deeper than individual images and the attendant difference in noise characteristics can also lead to artifacts. We present here a deep-learning approach to transient detection that encapsulates all the steps of a traditional image subtraction pipeline -- image registration, background subtraction, noise removal, psf matching, and subtraction -- into a single real-time convolutional network. Once trained the method works lighteningly fast, and given that it does multiple steps at one go, the advantages for multi-CCD, fast surveys like ZTF and LSST are obvious.

astro-ph.IM↗

arXiv2017

Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection

General human action recognition requires understanding of various visual cues. In this paper, we propose a network architecture that computes and integrates the most important visual cues for action recognition: pose, motion, and the raw images. For the integration, we introduce a Markov chain model which adds cues successively. The resulting approach is efficient and applicable to action classification as well as to spatial and temporal action localization. The two contributions clearly improve the performance over respective baselines. The overall approach achieves state-of-the-art action classification performance on HMDB51, J-HMDB and NTU RGB+D datasets. Moreover, it yields state-of-the-art spatio-temporal action localization results on UCF101 and J-HMDB.

cs.CV↗

arXiv2017

Hybrid Learning of Optical Flow and Next Frame Prediction to Boost Optical Flow in the Wild

CNN-based optical flow estimation has attracted attention recently, mainly due to its impressively high frame rates. These networks perform well on synthetic datasets, but they are still far behind the classical methods in real-world videos. This is because there is no ground truth optical flow for training these networks on real data. In this paper, we boost CNN-based optical flow estimation in real scenes with the help of the freely available self-supervised task of next-frame prediction. To this end, we train the network in a hybrid way, providing it with a mixture of synthetic and real videos. With the help of a sample-variant multi-tasking architecture, the network is trained on different tasks depending on the availability of ground-truth. We also experiment with the prediction of "next-flow" instead of estimation of the current flow, which is intuitively closer to the task of next-frame prediction and yields favorable results. We demonstrate the improvement in optical flow estimation on the real-world KITTI benchmark. Additionally, we test the optical flow indirectly in an action classification scenario. As a side product of this work, we report significant improvements over state-of-the-art in the task of next-frame prediction.

cs.CV↗