Classification Of Supernovae Research Articles

Harnessing edge-enhanced attention mechanisms for supernova detection in deep learning frameworks

Recent studies have shown the advantages of convolutional neural networks in the classification and detection of supernovae. In our prior work, we employed one-stage object detection frameworks to address the challenges of presupposed location and varying image sizes in supernova detection. Notably, the backbone of the object detectors naturally emphasized the edges of candidate regions in the visualized heatmap, reflecting the strategies adopted by human observers. Capitalizing on this similarity, we introduce an innovative edge attention module, tailored to prioritize the edges of candidate regions, and improved the performance of supernova detectors. In parallel, we have developed a three-channel supernova detection dataset by integrating science (current), template (reference), and difference images into a three-channel configuration. The candidates in the new dataset are more conspicuous. To assess the efficacy of our edge attention module, we conducted a series of experiments on the proposed dataset. The experimental results establish the superiority of the proposed method in detecting supernovae. Additionally, visualizations of the feature maps shows the proposed edge attention is able to reallocate weights around the candidate edges, corroborating its effectiveness.

First Impressions: Early-time Classification of Supernovae Using Host-galaxy Information and Shallow Learning

Substantial effort has been devoted to the characterization of transient phenomena from photometric information. Automated approaches to this problem have taken advantage of complete phase coverage of an event, limiting their use for triggering rapid follow-up of ongoing phenomena. In this work, we introduce a neural network with a single recurrent layer designed explicitly for early photometric classification of supernovae (SNe). Our algorithm leverages transfer learning to account for model misspecification, host-galaxy photometry to solve the data-scarcity problem soon after discovery, and a custom weighted loss to prioritize accurate early classification. We first train our algorithm using state-of-the-art transient and host-galaxy simulations, then adapt its weights and validate it on the spectroscopically confirmed SNe Ia, SNe II, and SNe Ib/c from the Zwicky Transient Facility Bright Transient Survey. On observed data, our method achieves an overall accuracy of 82% ± 2% within 3 days of an event’s discovery, and an accuracy of 87% ± 5% within 30 days of discovery. At both early and late phases, our method achieves comparable or superior results to the leading classification algorithms with a simpler network architecture. These results help pave the way for rapid photometric and spectroscopic follow-up of scientifically valuable transients discovered in massive synoptic surveys.

Spectroscopy of the supernova H0pe host galaxy at redshift 1.78

Supernova (SN) H0pe was discovered as a new transient in James Webb Space Telescope (JWST) NIRCam images of the galaxy cluster PLCK G165.7+67.0 taken as part of the Prime Extragalactic Areas for Reionization and Lensing Science (PEARLS) JWST GTO program (ID 1176) on 2023 March 30. The transient is a compact source associated with a background galaxy that is stretched and triply imaged by the strong gravitational lensing of the cluster. This paper reports spectra in the 950–1370 nm observer frame of two of the galaxy images obtained with Large Binocular Telescope (LBT) Utility Camera in the Infrared (LUCI) in long-slit mode two weeks after the JWST observations. The individual and average spectra show the [O II] λλ3727,3730 doublet and the Balmer and 4000 Å breaks at redshift z = 1.783 ± 0.002. The code investigating galaxy emission (CIGALE) best-fit model of the spectral energy distribution indicates that the host galaxy of SN H0pe is massive (Mstar ≃ 6 × 1010 M⊙ after correcting for a magnification factor μ ∼ 7) with a predominantly intermediate-age (∼2 Gyr) stellar population, moderate extinction, and a magnification-corrected star formation rate ≃13 M⊙ yr−1, consistent with being below the main sequence of star formation. These properties suggest that H0pe might be a type Ia SN. Additional observations of SN H0pe and its host recently carried out with JWST (JWST-DD-4446; PI: B. Frye) will be able to both determine the SN classification and confirm its association with the galaxy analyzed in this work.

Supernova Light Curves Approximation based on Neural Network Models

Photometric data-driven classification of supernovae becomes a challenge due to the appearance of real-time processing of big data in astronomy. Recent studies have demonstrated the superior quality of solutions based on various machine learning models. These models learn to classify supernova types using their light curves as inputs. Preprocessing these curves is a crucial step that significantly affects the final quality. In this talk, we study the application of multilayer perceptron (MLP), bayesian neural network (BNN), and normalizing flows (NF) to approximate observations for a single light curve. We use these approximations as inputs for supernovae classification models and demonstrate that the proposed methods outperform the state-of-the-art based on Gaussian processes applying to the Zwicky Transient Facility Bright Transient Survey light curves. MLP demonstrates similar quality as Gaussian processes and speed increase. Normalizing Flows exceeds Gaussian processes in terms of approximation quality as well.

Pan-chromatic photometric classification of supernovae from multiple surveys and transfer learning for future surveys

ABSTRACTTime-domain astronomy is entering a new era as wide-field surveys with higher cadences allow for more discoveries than ever before. The field has seen an increased use of machine learning and deep learning for automated classification of transients into established taxonomies. Training such classifiers requires a large enough and representative training set, which is not guaranteed for new future surveys such as the Vera Rubin Observatory, especially at the beginning of operations. We present the use of Gaussian processes to create a uniform representation of supernova light curves from multiple surveys, obtained through the Open Supernova Catalog for supervised classification with convolutional neural networks. We also investigate the use of transfer learning to classify light curves from the Photometric LSST Astronomical Time Series Classification Challenge (PLAsTiCC) data set. Using convolutional neural networks to classify the Gaussian process generated representation of supernova light curves from multiple surveys, we achieve an Area Under the Receiver Operating Characteristic curve (AUC) score of 0.859 for classification into Types Ia, Ibc, and II. We find that transfer learning improves the classification accuracy for the most under-represented classes by up to 18 per cent when classifying PLAsTiCC light curves, and is able to achieve an AUC score of 0.946 ± 0.001 when including photometric redshifts for classification into six classes (Ia, Iax, Ia-91bg, Ibc, II, and SLSN-I). We also investigate the usefulness of transfer learning when there is a limited labelled training set to see how this approach can be used for training classifiers in future surveys at the beginning of operations.

Deep Attention-based Supernovae Classification of Multiband Light Curves

In astronomical surveys, such as the Zwicky Transient Facility, supernovae (SNe) are relatively uncommon objects compared to other classes of variable events. Along with this scarcity, the processing of multiband light curves is a challenging task due to the highly irregular cadence, long time gaps, missing values, few observations, etc. These issues are particularly detrimental to the analysis of transient events: SN-like light curves. We offer three main contributions: (1) Based on temporal modulation and attention mechanisms, we propose a deep attention model (TimeModAttn) to classify multiband light curves of different SN types, avoiding photometric or hand-crafted feature computations, missing-value assumptions, and explicit imputation/interpolation methods. (2) We propose a model for the synthetic generation of SN multiband light curves based on the Supernova Parametric Model, allowing us to increase the number of samples and the diversity of cadence. Thus, the TimeModAttn model is first pretrained using synthetic light curves. Then, a fine-tuning process is performed. The TimeModAttn model outperformed other deep learning models, based on recurrent neural networks, in two scenarios: late-classification and early-classification. Also, the TimeModAttn model outperformed a Balanced Random Forest (BRF) classifier (trained with real data), increasing the balanced-F 1score from ≈.525 to ≈.596. When training the BRF with synthetic data, this model achieved a similar performance to the TimeModAttn model proposed while still maintaining extra advantages. (3) We conducted interpretability experiments. High attention scores were obtained for observations earlier than and close to the SN brightness peaks. This also correlated with an early highly variability of the learned temporal modulation.

Considerations for Optimizing the Photometric Classification of Supernovae from the Rubin Observatory

Abstract The Vera C. Rubin Observatory will increase the number of observed supernovae (SNe) by an order of magnitude; however, it is impossible to spectroscopically confirm the class for all SNe discovered. Thus, photometric classification is crucial, but its accuracy depends on the not-yet-finalized observing strategy of Rubin Observatory’s Legacy Survey of Space and Time (LSST). We quantitatively analyze the impact of the LSST observing strategy on SNe classification using simulated multiband light curves from the Photometric LSST Astronomical Time-Series Classification Challenge (PLAsTiCC). First, we augment the simulated training set to be representative of the photometric redshift distribution per SNe class, the cadence of observations, and the flux uncertainty distribution of the test set. Then we build a classifier using the photometric transient classification library snmachine, based on wavelet features obtained from Gaussian process fits, yielding a similar performance to the winning PLAsTiCC entry. We study the classification performance for SNe with different properties within a single simulated observing strategy. We find that season length is important, with light curves of 150 days yielding the highest performance. Cadence also has an important impact on SNe classification; events with median inter-night gap <3.5 days yield higher classification performance. Interestingly, we find that large gaps (>10 days) in light-curve observations do not impact performance if sufficient observations are available on either side, due to the effectiveness of the Gaussian process interpolation. This analysis is the first exploration of the impact of observing strategy on photometric SN classification with LSST.

Backward-Design Model for an Astronomy Course Using RSpec

The new normal imposed on us by the COVID-19 pandemic restricted the traditional ways we would teach high school students who are eager to participate in introductory astronomy projects on our university campus. This turned out to be a blessing in disguise as we were forced to come up with creative ways to get around this obstacle. The outcome is an outline of a pedagogically sound and even more robust instructional plan for an astronomy course using RSpec in conjunction with freely available databases. In addition to the traditional topics, the new model will allow an instructor to explore emission lines of variable Be stars like Gamma Cas and the classification of supernovae by an interpretation of their spectra. We argue that this new model should be used even if we return to the old normal.

A gravitationally lensed supernova with an observable two-decade time delay

When the light from a distant object passes very near to a foreground galaxy or cluster, gravitational lensing can cause it to appear as multiple images on the sky1. If the source is variable, it can be used to constrain the cosmic expansion rate2 and dark energy models3. Achieving these cosmological goals requires many lensed transients with precise time-delay measurements4. Lensed supernovae are attractive for this purpose because they have relatively simple photometric behaviour, with well-understood light curve shapes and colours—in contrast to the stochastic variation of quasars. Here we report the discovery of a multiply imaged supernova, AT 2016jka (‘SN Requiem’). It appeared in an evolved galaxy at redshift 1.95, gravitationally lensed by a foreground galaxy cluster5. It is probably a type Ia supernova—the explosion of a low-mass stellar remnant, whose light curve can be used to measure cosmic distances. In archival Hubble Space Telescope imaging, three lensed images of the supernova are detected with relative time delays of <200 d. We predict that a fourth image will appear close to the cluster core in the year 2037 ± 2. Observation of the fourth image could provide a time-delay precision of ~7 d, <1% of the extraordinary 20 yr baseline. The supernova classification and the predicted reappearance time could be improved with further lens modelling and a comprehensive analysis of systematic uncertainties.

Optimizing a magnitude-limited spectroscopic training sample for photometric classification of supernovae

ABSTRACT In preparation for photometric classification of transients from the Legacy Survey of Space and Time (LSST) we run tests with different training data sets. Using estimates of the depth to which the 4-m Multi-Object Spectroscopic Telescope (4MOST) Time Domain Extragalactic Survey (TiDES) can classify transients, we simulate a magnitude-limited sample reaching rAB ≈ 22.5 mag. We run our simulations with the software snmachine, a photometric classification pipeline using machine learning. The machine-learning algorithms struggle to classify supernovae when the training sample is magnitude limited, in contrast to representative training samples. Classification performance noticeably improves when we combine the magnitude-limited training sample with a simulated realistic sample of faint high-redshift supernovae observed from larger spectroscopic facilities; the algorithms’ range of average area under receiver operator characteristic curve (AUC) scores over 10 runs increases from 0.547–0.628 to 0.946–0.969 and purity of the classified sample reaches 95 per cent in all runs for two of the four algorithms. By creating new, artificial light curves using the augmentation software avocado, we achieve a purity in our classified sample of 95 per cent in all 10 runs performed for all machine-learning algorithms considered. We also reach a highest average AUC score of 0.986 with the artificial neural network algorithm. Having ‘true’ faint supernovae to complement our magnitude-limited sample is a crucial requirement in optimization of a 4MOST spectroscopic sample. However, our results are a proof of concept that augmentation is also necessary to achieve the best classification results.

SNIascore: Deep-learning Classification of Low-resolution Supernova Spectra

Abstract We present SNIascore, a deep-learning-based method for spectroscopic classification of thermonuclear supernovae (SNe Ia) based on very low-resolution (R ∼ 100) data. The goal of SNIascore is the fully automated classification of SNe Ia with a very low false-positive rate (FPR) so that human intervention can be greatly reduced in large-scale SN classification efforts, such as that undertaken by the public Zwicky Transient Facility (ZTF) Bright Transient Survey (BTS). We utilize a recurrent neural network architecture with a combination of bidirectional long short-term memory and gated recurrent unit layers. SNIascore achieves a &lt;0.6% FPR while classifying up to 90% of the low-resolution SN Ia spectra obtained by the BTS. SNIascore simultaneously performs binary classification and predicts the redshifts of secure SNe Ia via regression (with a typical uncertainty of &lt;0.005 in the range from z = 0.01 to z = 0.12). For the magnitude-limited ZTF BTS survey (≈70% SNe Ia), deploying SNIascore reduces the amount of spectra in need of human classification or confirmation by ≈60%. Furthermore, SNIascore allows SN Ia classifications to be automatically announced in real time to the public immediately following a finished observation during the night.

SCONE: Supernova Classification with a Convolutional Neural Network

Abstract We present a novel method of classifying Type Ia supernovae using convolutional neural networks, a neural network framework typically used for image recognition. Our model is trained on photometric information only, eliminating the need for accurate redshift data. Photometric data is preprocessed via 2D Gaussian process regression into two-dimensional images created from flux values at each location in wavelength-time space. These “flux heatmaps” of each supernova detection, along with “uncertainty heatmaps” of the Gaussian process uncertainty, constitute the data set for our model. This preprocessing step not only smooths over irregular sampling rates between filters but also allows SCONE to be independent of the filter set on which it was trained. Our model has achieved impressive performance without redshift on the in-distribution SNIa classification problem: 99.73 ± 0.26% test accuracy with no over/underfitting on a subset of supernovae from PLAsTiCC’s unblinded test data set. We have also achieved 98.18 ± 0.3% test accuracy performing six-way classification of supernovae by type. The out-of-distribution performance does not fully match the in-distribution results, suggesting that the detailed characteristics of the training sample in comparison to the test sample have a big impact on the performance. We discuss the implication and directions for future work. All of the data processing and model code developed for this paper can be found in the SCONE software package located at github.com/helenqu/scone.

Supernovae Detection with Fully Convolutional One-Stage Framework.

A series of sky surveys were launched in search of supernovae and generated a tremendous amount of data, which pushed astronomy into a new era of big data. However, it can be a disastrous burden to manually identify and report supernovae, because such data have huge quantity and sparse positives. While the traditional machine learning methods can be used to deal with such data, deep learning methods such as Convolutional Neural Networks demonstrate more powerful adaptability in this area. However, most data in the existing works are either simulated or without generality. How do the state-of-the-art object detection algorithms work on real supernova data is largely unknown, which greatly hinders the development of this field. Furthermore, the existing works of supernovae classification usually assume the input images are properly cropped with a single candidate located in the center, which is not true for our dataset. Besides, the performance of existing detection algorithms can still be improved for the supernovae detection task. To address these problems, we collected and organized all the known objectives of the Panoramic Survey Telescope and Rapid Response System (Pan-STARRS) and the Popular Supernova Project (PSP), resulting in two datasets, and then compared several detection algorithms on them. After that, the selected Fully Convolutional One-Stage (FCOS) method is used as the baseline and further improved with data augmentation, attention mechanism, and small object detection technique. Extensive experiments demonstrate the great performance enhancement of our detection algorithm with the new datasets.

Photometric Classification of 2315 Pan-STARRS1 Supernovae with Superphot

Abstract The classification of supernovae (SNe) and its impact on our understanding of explosion physics and progenitors have traditionally been based on the presence or absence of certain spectral features. However, current and upcoming wide-field time-domain surveys have increased the transient discovery rate far beyond our capacity to obtain even a single spectrum of each new event. We must therefore rely heavily on photometric classification—connecting SN light curves back to their spectroscopically defined classes. Here, we present Superphot, an open-source Python implementation of the machine-learning classification algorithm of Villar et al., and apply it to 2315 previously unclassified transients from the Pan-STARRS1 Medium Deep Survey for which we obtained spectroscopic host-galaxy redshifts. Our classifier achieves an overall accuracy of 82%, with completenesses and purities of &gt;80% for the best classes (SNe Ia and superluminous SNe). For the worst performing SN class (SNe Ibc), the completeness and purity fall to 37% and 21%, respectively. Our classifier provides 1257 newly classified SNe Ia, 521 SNe II, 298 SNe Ibc, 181 SNe IIn, and 58 SLSNe. These are among the largest uniformly observed samples of SNe available in the literature and will enable a wide range of statistical studies of each class.

SuperRAENN: A Semisupervised Supernova Photometric Classification Pipeline Trained on Pan-STARRS1 Medium-Deep Survey Supernovae

Abstract Automated classification of supernovae (SNe) based on optical photometric light-curve information is essential in the upcoming era of wide-field time domain surveys, such as the Legacy Survey of Space and Time (LSST) conducted by the Rubin Observatory. Photometric classification can enable real-time identification of interesting events for extended multiwavelength follow-up, as well as archival population studies. Here we present the complete sample of 5243 “SN-like” light curves (in g P1 r P1 i P1 z P1) from the Pan-STARRS1 Medium-Deep Survey (PS1-MDS). The PS1-MDS is similar to the planned LSST Wide-Fast-Deep survey in terms of cadence, filters, and depth, making this a useful training set for the community. Using this data set, we train a novel semisupervised machine learning algorithm to photometrically classify 2315 new SN-like light curves with host galaxy spectroscopic redshifts. Our algorithm consists of an RF supervised classification step and a novel unsupervised step in which we introduce a recurrent autoencoder neural network (RAENN). Our final pipeline, dubbed SuperRAENN, has an accuracy of 87% across five SN classes (Type Ia, Ibc, II, IIn, SLSN-I) and macro-averaged purity and completeness of 66% and 69%, respectively. We find the highest accuracy rates for SNe Ia and SLSNe and the lowest for SNe Ibc. Our complete spectroscopically and photometrically classified samples break down into 62.0% Type Ia (1839 objects), 19.8% Type II (553 objects), 4.8% Type IIn (136 objects), 11.7% Type Ibc (291 objects), and 1.6% Type I SLSNe (54 objects).

Star Formation and Morphological Properties of Galaxies in the Pan-STARRS 3π Survey. I. A Machine-learning Approach to Galaxy and Supernova Classification

Abstract We present a classification of galaxies in the Pan-STARRS1 (PS1) 3π survey based on their recent star formation history and morphology. Specifically, we train and test two Random Forest (RF) classifiers using photometric features (colors and moments) from the PS1 data release 2. The labels for the morphological classification are taken from Huertas-Company et al., while labels for the star formation fraction (SFF) are from the Blanton et al. catalog. We find that colors provide more predictive accuracy than photometric moments. We morphologically classify galaxies as either early- or late-type, and our RF model achieves a 78% classification accuracy. Our second model classifies galaxies as having either a low-to-moderate or high SFF. This model achieves an 89% classification accuracy. We apply both RF classifiers to the entire PS1 3π dataset, which allows us to assign two scores to each PS1 source: P HSFF, which quantifies the probability of having a high SFF; and P spiral, which quantifies the probability of having a late-type morphology. Finally, as a proof of concept, we apply our classification framework to supernova (SN) host galaxies from the Zwicky Transient Factory and the Lick Observatory Supernova Search samples. We show that by selecting P HSFF or P spiral, it is possible to significantly enhance or suppress the fraction of core-collapse SNe (or thermonuclear SNe) in the sample with respect to random guessing. This result demonstrates how contextual information can aid transient classifications at the time of first detection. In the current era of spectroscopically starved time-domain astronomy, prompt automated classification is paramount. Our table is available at 10.5281/zenodo.3990545.

SuperNNova: an open-source framework for Bayesian, neural network-based supernova classification

ABSTRACTWe introduce SuperNNova, an open-source supernova photometric classification framework that leverages recent advances in deep neural networks. Our core algorithm is a recurrent neural network (RNN) that is trained to classify light curves using only photometric information. Additional information such as host-galaxy redshift can be incorporated to improve performance. We evaluate our framework using realistic supernova simulations that include survey detection. We show that our method, for the type Ia versus non-Ia supernova classification problem, reaches accuracies greater than 96.92 ± 0.09 without any redshift information and up to 99.55 ± 0.06 when redshift, either photometric or spectroscopic, is available. Further, we show that our method attains unprecedented performance for the classification of incomplete light curves, reaching accuracies &amp;gt;86.4 ± 0.1 (&amp;gt;93.5 ± 0.8) without host-galaxy redshift (with redshift information) 2 d before maximum light. In contrast with previous methods, there is no need for time-consuming feature engineering and we show that our method scales to very large data sets with a modest computing budget. In addition, we investigate often neglected pitfalls of machine learning algorithms. We show that commonly used algorithms suffer from poor calibration and overconfidence on out-of-distribution samples when applied to supernova data. We devise extensive tests to estimate the robustness of classifiers and cast the learning procedure under a Bayesian light, demonstrating a much better handling of uncertainties. We study the benefits of Bayesian RNNs for SN Ia cosmology. Our code is open sourced and available on github1.

DASH: Deep Learning for the Automated Spectral Classification of Supernovae and Their Hosts

Abstract We present DASH (Deep Automated Supernova and Host classifier), a novel software package that automates the classification of the type, age, redshift, and host galaxy of supernova spectra. DASH makes use of a new approach that does not rely on iterative template-matching techniques like all previous software, but instead classifies based on the learned features of each supernova’s type and age. It has achieved this by employing a deep convolutional neural network to train a matching algorithm. This approach has enabled DASH to be orders of magnitude faster than previous tools, being able to accurately classify hundreds or thousands of objects within seconds. We have tested its performance on 4 yr of data from the Australian Dark Energy Survey (OzDES). The deep learning models were developed using TensorFlow and were trained using over 4000 supernova spectra taken from the CfA Supernova Program and the Berkeley SN Ia Program as used in SNID (Supernova Identification software). Unlike template-matching methods, the trained models are independent of the number of spectra in the training data, which allows for DASH's unprecedented speed. We have developed both a graphical interface for easy visual classification and analysis of supernovae and a Python library for the autonomous and quick classification of several supernova spectra. The speed, accuracy, user-friendliness, and versatility of DASH present an advancement to existing spectral classification tools. We have made the code publicly available on GitHub and PyPI (pip install astrodash) to allow for further contributions and development. The package documentation is available at https://astrodash.readthedocs.io.

Supernova Photometric Classification Pipelines Trained on Spectroscopically Classified Supernovae from the Pan-STARRS1 Medium-deep Survey

Abstract Photometric classification of supernovae (SNe) is imperative as recent and upcoming optical time-domain surveys, such as the Large Synoptic Survey Telescope (LSST), overwhelm the available resources for spectrosopic follow-up. Here we develop a range of light curve (LC) classification pipelines, trained on 513 spectroscopically classified SNe from the Pan-STARRS1 Medium-Deep Survey (PS1-MDS): 357 Type Ia, 93 Type II, 25 Type IIn, 21 Type Ibc, and 17 Type I superluminous SNe (SLSNe). We present a new parametric analytical model that can accommodate a broad range of SN LC morphologies, including those with a plateau, and fit this model to data in four PS1 filters (g P1 r P1 i P1 z P1). We test a number of feature extraction methods, data augmentation strategies, and machine-learning algorithms to predict the class of each SN. Our best pipelines result in ≈90% average accuracy, ≈70% average purity, and ≈80% average completeness for all SN classes, with the highest success rates for SNe Ia and SLSNe and the lowest for SNe Ibc. Despite the greater complexity of our classification scheme, the purity of our SN Ia classification, ≈95%, is on par with methods developed specifically for Type Ia versus non-Type Ia binary classification. As the first of its kind, this study serves as a guide to developing and training classification algorithms for a wide range of SN types with a purely empirical training set, particularly one that is similar in its characteristics to the expected LSST main survey strategy. Future work will implement this classification pipeline on ≈3000 PS1/MDS LCs that lack spectroscopic classification.

Optimal Classification and Outlier Detection for Stripped-envelope Core-collapse Supernovae

Abstract In the current era of time-domain astronomy, it is increasingly important to have rigorous, data-driven models for classifying transients, including supernovae. We present the first application of principal component analysis to the photospheric spectra of stripped-envelope core-collapse supernovae. We use one of the largest compiled optical data sets of stripped-envelope supernovae, containing 160 SNe and 1551 spectra. We find that the first five principal components capture 79% of the variance of our spectral sample, which contains the main families of stripped supernovae: Ib, IIb, Ic, and broad-lined Ic. We develop a quantitative, data-driven classification method using a support vector machine, and explore stripped-envelope supernovae classification as a function of phase relative to V-band maximum light. Our classification method naturally identifies “transition” supernovae and supernovae with contested labels, which we discuss in detail. We find that the stripped-envelope supernovae types are most distinguishable in the later phase ranges of 10 ± 5 days and 15 ± 5 days relative to V-band maximum, and we discuss the implications of our findings for current and future surveys such as Zwicky Transient Factory and Large Synoptic Survey Telescope.