Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userPaying Attention to Astronomical Transients: Photometric Classification with the Time-Series Transformer
116
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
Future surveys such as the Legacy Survey of Space and Time (LSST) of the Vera C. Rubin Observatory will observe an order of magnitude more astrophysical transient events than any previous survey before. With this deluge of photometric data, it will be impossible for all such events to be classified by humans alone. Recent efforts have sought to leverage machine learning methods to tackle the challenge of astronomical transient classification, with ever improving success. Transformers are a recently developed deep learning architecture, first proposed for natural language processing, that have shown a great deal of recent success. In this work we develop a new transformer architecture, which uses multi-head self attention at its core, for general multi-variate time-series data. Furthermore, the proposed time-series transformer architecture supports the inclusion of an arbitrary number of additional features, while also offering interpretability. We apply the time-series transformer to the task of photometric classification, minimising the reliance of expert domain knowledge for feature selection, while achieving results comparable to state-of-the-art photometric classification methods. We achieve a weighted logarithmic-loss of 0.507 on imbalanced data in a representative setting using data from the Photometric LSST Astronomical Time-Series Classification Challenge (PLAsTiCC). Moreover, we achieve a micro-averaged receiver operating characteristic area under curve of 0.98 and micro-averaged precision-recall area under curve of 0.87.
rate research
Read More
Next-generation surveys like the Legacy Survey of Space and Time (LSST) on the Vera C. Rubin Observatory will generate orders of magnitude more discoveries of transients and variable stars than previous surveys. To prepare for this data deluge, we developed the Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC), a competition which aimed to catalyze the development of robust classifiers under LSST-like conditions of a non-representative training set for a large photometric test set of imbalanced classes. Over 1,000 teams participated in PLAsTiCC, which was hosted in the Kaggle data science competition platform between Sep 28, 2018 and Dec 17, 2018, ultimately identifying three winners in February 2019. Participants produced classifiers employing a diverse set of machine learning techniques including hybrid combinations and ensemble averages of a range of approaches, among them boosted decision trees, neural networks, and multi-layer perceptrons. The strong performance of the top three classifiers on Type Ia supernovae and kilonovae represent a major improvement over the current state-of-the-art within astronomy. This paper summarizes the most promising methods and evaluates their results in detail, highlighting future directions both for classifier development and simulation needs for a next generation PLAsTiCC data set.
Upcoming astronomical surveys such as the Large Synoptic Survey Telescope (LSST) will rely on photometric classification to identify the majority of the transients and variables that they discover. We present a set of techniques for photometric classification that can be applied even when the training set of spectroscopically-confirmed objects is heavily biased towards bright, low-redshift objects. Using Gaussian process regression to model arbitrary light curves in all bands simultaneously, we augment the training set by generating n
We describe the simulated data sample for the Photometric LSST Astronomical Time Series Classification Challenge (PLAsTiCC), a publicly available challenge to classify transient and variable events that will be observed by the Large Synoptic Survey Telescope (LSST), a new facility expected to start in the early 2020s. The challenge was hosted by Kaggle, ran from 2018 September 28 to 2018 December 17, and included 1,094 teams competing for prizes. Here we provide details of the 18 transient and variable source models, which were not revealed until after the challenge, and release the model libraries at https://doi.org/10.5281/zenodo.2612896. We describe the LSST Operations Simulator used to predict realistic observing conditions, and we describe the publicly available SNANA simulation code used to transform the models into observed fluxes and uncertainties in the LSST passbands (ugrizy). Although PLAsTiCC has finished, the publicly available models and simulation tools are being used within the astronomy community to further improve classification, and to study contamination in photometrically identified samples of type Ia supernova used to measure properties of dark energy. Our simulation framework will continue serving as a platform to improve the PLAsTiCC models, and to develop new models.
Classification of transient and variable light curves is an essential step in using astronomical observations to develop an understanding of their underlying physical processes. However, upcoming deep photometric surveys, including the Large Synoptic Survey Telescope (LSST), will produce a deluge of low signal-to-noise data for which traditional labeling procedures are inappropriate. Probabilistic classification is more appropriate for the data but are incompatible with the traditional metrics used on deterministic classifications. Furthermore, large survey collaborations intend to use these classification probabilities for diverse science objectives, indicating a need for a metric that balances a variety of goals. We describe the process used to develop an optimal performance metric for an open classification challenge that seeks probabilistic classifications and must serve many scientific interests. The Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC) is an open competition aiming to identify promising techniques for obtaining classification probabilities of transient and variable objects by engaging a broader community both within and outside astronomy. Using mock classification probability submissions emulating archetypes of those anticipated of PLAsTiCC, we compare the sensitivity of metrics of classification probabilities under various weighting schemes, finding that they yield qualitatively consistent results. We choose as a metric for PLAsTiCC a weighted modification of the cross-entropy because it can be meaningfully interpreted. Finally, we propose extensions of our methodology to ever more complex challenge goals and suggest some guiding principles for approaching the choice of a metric of probabilistic classifications.
The growing field of large-scale time domain astronomy requires methods for probabilistic data analysis that are computationally tractable, even with large datasets. Gaussian Processes are a popular class of models used for this purpose but, since the computational cost scales, in general, as the cube of the number of data points, their application has been limited to small datasets. In this paper, we present a novel method for Gaussian Process modeling in one-dimension where the computational requirements scale linearly with the size of the dataset. We demonstrate the method by applying it to simulated and real astronomical time series datasets. These demonstrations are examples of probabilistic inference of stellar rotation periods, asteroseismic oscillation spectra, and transiting planet parameters. The method exploits structure in the problem when the covariance function is expressed as a mixture of complex exponentials, without requiring evenly spaced observations or uniform noise. This form of covariance arises naturally when the process is a mixture of stochastically-driven damped harmonic oscillators -- providing a physical motivation for and interpretation of this choice -- but we also demonstrate that it can be a useful effective model in some other cases. We present a mathematical description of the method and compare it to existing scalable Gaussian Process methods. The method is fast and interpretable, with a range of potential applications within astronomical data analysis and beyond. We provide well-tested and documented open-source implementations of this method in C++, Python, and Julia.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
