arXiv subjects

Matthew J. Graham

Publications and source records attributed to Matthew J. Graham.

At least 19 recordsLinked to original sources

arXiv2026

Six New Eclipsing AM CVn Binaries from the Zwicky Transient Facility

We present the discovery of six new eclipsing AM CVn binaries, helium-accreting ultracompact systems in which a cool donor eclipses the accreting white dwarf. The systems were found in a GPU-accelerated Box Least Squares (BLS) search of Zwicky Transient Facility (ZTF) photometry and have orbital periods of 39.3 to 59.9 minutes. We obtained spectroscopy with the Low Resolution Imaging Spectrometer (LRIS) on the Keck I telescope for all six systems, and every spectrum shows helium emission with no detectable hydrogen, confirming their AM CVn classification. Our discoveries increase the number of deeply eclipsing AM CVn from 11 to 17 (i.e., systems in which the accreting white dwarf is both the dominant source of optical light and eclipsed by the donor). With high-speed photometric follow-up, these systems will provide the mass ratios, inclinations, and fractional radii of both components. They will also provide new tests of AM CVn formation models and stronger constraints on the long-term evolution of these sources.

astro-ph.SR↗

arXiv2026

Photometric classification and out-of-taxonomy detection of ZTF transients with FLARE

Photometric classifiers decide which of the million nightly alerts of time-domain surveys receive one of the few thousand spectra taken each year, and they are the first place where a transient outside the trained classes can be noticed. We present flare, the photometric classification and anomaly-detection module of AppleCiDEr, evaluated on 10 497 spectroscopically confirmed ZTF transients in six classes and 53 objects from families outside the taxonomy. Catalogue context raises the macro F1 score, with the largest gains where the defining information is absent from the light curve. Blind detection recovers few out-of-taxonomy objects at a 1% false-alarm rate, while a simulated review loop recovers 83% of them after inspecting 15% of the stream. The first confirmations of a new family are most useful in the feature space: with the same eleven labels, a head on the frozen features detects 68% of the tidal disruption events hidden from the training against 57% for a combiner over the anomaly scores, and retraining with them as a new class reaches 85%. The module runs in production on Fritz, the ZTF instance of SkyPortal, and its alarm is reported as a false-alarm rate per unit time on the stream, calibrated on the photometry that the service receives

astro-ph.IM↗

arXiv2026

SN 2023iop: An Extreme 1987A-like Supernova and the Death of Very Massive Stars

Supernova (SN) 1987A showed that some hydrogen-rich core-collapse supernovae (SNe) rise slowly to peak, defining a distinct subclass. Wide-field surveys have uncovered more extreme members, such as OGLE-2014-SN-73, SN 2020faa, and SN 2023vbw, that challenge neutrino-driven explosion models. We present ultraviolet-to-infrared, radio, X-ray, and spectropolarimetric observations of SN 2023iop at $z = 0.1020$, the most extreme 87A-like event to date. It rose for $\gtrsim88$ rest-frame days to $M_r \approx -20.1$ mag, also placing it among the hydrogen-rich superluminous SNe, and radiated $\gtrsim4\times10^{50}$ erg. Its spectra resemble those of typical Type II SNe and remain photospheric at $\sim330$ days post-maximum. Continuum polarization of 0.8-1.0% indicates an aspherical system. Hydrogen-rich pair-instability supernova (PISN) models of a $190~M_\odot$ star reproduce the light-curve up to 150 days after peak, but not the late-time emission. A late-time spectrum shows a feature near 7300 Å, tentatively identified as [Ni II] $λ$7378. The implied $\approx0.02~M_\odot$ of stable $^{58}$Ni is reached only in the most massive PISN models. The low-mass host galaxy ($\sim10^{8.2}~M_\odot$) is consistent with a metal-poor progenitor as required by the PISN channel. Fallback accretion reproduces the light-curve morphology, but not the colors. We consider a pair-instability explosion the most plausible scenario, with the late-time light-curve excess powered by circumstellar interaction, which shows no signatures in the spectra. SN 2023iop shows that the most luminous 87A-like events occupy an underexplored region of massive-star evolution.

astro-ph.HE↗

arXiv2026

SN 2025wiu: A Type Ib Supernova with Post-Peak Optical Rebrightening

We present optical photometric and optical/near-infrared spectroscopic observations of SN 2025wiu, a Type Ib supernova (SN) at z = 0.046927. The r-band light curve exhibits an initial maximum of approximately -18.2 mag, followed by a weaker optical rebrightening reaching approximately -17.8 mag at +38 days in the rest frame relative to the first maximum. However, the reconstructed bolometric light curve does not show a distinct second peak, but instead exhibits a reduced decline rate during the corresponding phase. The spectra consistently show Type Ib features without narrow emission components associated with circumstellar material. The late-time bolometric decline rate of 0.054 +/- 0.008 mag/day is faster than expected for complete trapping of 56Co decay. A radioactive-decay model for the first peak requires nickel mass = 0.47 solar masses, above the range typical of SNe Ib. A combined radioactive-decay and circumstellar-interaction model reproduces the full bolometric light curve with nickel mass ~ 0.38 solar masses, ejecta mass ~ 4.7 solar masses, and an effective circumstellar mass of ~ 0.10 solar masses, with the interaction contributing from the first peak onward. The lack of interaction signatures in the spectra favours an aspherical, disk-like circumstellar structure engulfed by the ejecta, in which the interaction energy is thermalized below the ejecta photosphere; the fitted circumstellar parameters are therefore effective values rather than direct measurements of the circumstellar geometry. SN 2025wiu demonstrates that optical rebrightening does not necessarily imply a genuine bolometric secondary maximum and highlights the importance of multi-band observations for identifying the powering mechanisms of double-peaked stripped-envelope supernovae.

astro-ph.HE↗

arXiv2026

Modeling Multi-band Active Galactic Nuclei Lightcurves Using an Self-supervised Attentive Neural Process Network

With the the Legacy Survey of Space and Time (LSST), observations of tens of millions of quasars are expected. We present a machine-learning framework based on an attentive neural process (ANP) that models stochastic quasar variability and jointly performs two tasks: (i) probabilistic reconstruction of quasar light curves in all six LSST bands, and (ii) inference of physical parameters of the AGN system --- black hole mass, Eddington ratio, and intrinsic variability timescale --- with joint, full-covariance posteriors. The model processes all six bands within a single masked attention mechanism, so that observations in any band constrain the shared driving process, and natively handles irregularly and asynchronously sampled light curves with realistic heteroscedastic noise. We train and evaluate on full ten-year light curves simulated with a relativistic accretion-disk reprocessing model, observed through the fielded Rubin baseline cadence with per-visit photometric noise. The light-curve model is trained with self-supervised, learning from the sparse noisy observations alone and never accessing the underlying noiseless light curves. On a held-out test set, we show that our ANP model reach comparable performances to that of the near-optimal baseline Gaussian process model, while exceeding it in power spectrum reconstruction and damped-random walk timescale estimation. The compact learned latent representation supports future downstream applications, and the fully observation-driven training objective enables direct fine-tuning on real LSST light curves.

astro-ph.HE↗

arXiv2026

Seeing Double: The Theory Defying Twin Flares of TDE 2022dbl

Partial tidal disruption events, in which a star survives a close passage by a supermassive black hole and may be disrupted again on a subsequent encounter, provide a unique probe of supermassive black hole properties and accretion physics. We examine TDE 2022dbl, a partial tidal disruption event candidate that exhibits two separate UV/optical flares, using 11 new optical spectra, updated UV/optical photometry, and a Keck-II/ESI host-galaxy spectrum. We trace the evolution of the prominent blended N III + He II feature across both flares and find that the blend evolves from N III-dominated to He II-dominated emission, which may reflect changing ionization conditions and a declining efficiency of Bowen fluorescence. The two flares show similar thermal evolution and spectral features, supporting a partial-disruption scenario. The second flare exhibits a broader, plateau-like peak, a longer decline timescale, and less extreme line velocities than the first flare. We suggest that these differences arise from the interaction between debris from the second disruption and an accretion disk formed during the first flare. From the host-galaxy velocity dispersion, we infer a black hole mass of $\log_{10}(M_{\rm BH}/M_\odot)=6.01\pm0.45$. No third flare has been detected at the expected recurrence epoch, leading us to propose a new interpretation in which a positive-energy kick during ballistic core reformation delays the return of the surviving remnant.

astro-ph.HE↗

arXiv2026

An Off-Nuclear Tidal Disruption Event Discovered At Late Times: The Case Of TDE 2023mfm

We present the discovery and analysis of the optically selected tidal disruption event (TDE) 2023mfm, which originates from a wandering massive black hole (MBH) in a massive ($\sim 10^{11} \,$M$_{\odot}$) galaxy hosting a central low-luminosity active galactic nucleus (AGN). Our analysis of the ZTF, Lick, Keck, Swift, Chandra, XMM-Newton, HST, and VLA observations reveals that TDE 2023mfm is a TDE-H from a $10^{6.2 \pm 0.5}\,$M$_{\odot}$ black hole which is offset by $0.66 \pm 0.02$" from the center of its host galaxy, corresponding to a projected distance of $1.08 \pm 0.04$ kpc. TDE 2023mfm displays all the traits of optically selected TDEs. The emission remains hot, $T_{\rm bb} \sim 22,000 \pm 1,000$ K, for more than a month after peak, and the $g$-band light curve peaks at $\left( 2.24^{+0.10} _{-0.11} \right) \times 10^{43} \, \rm erg \, s^{-1}$ and stays above half-maximum luminosity for $47.8^{+3.7}_{-3.5}$ days. The late-time optical-to-UV emission observed with the HST suggests the presence of an unresolved stellar population with a stellar mass of $10^7-10^8\,$M$_{\odot}$ at the position of the TDE, possibly being a low-mass dwarf galaxy or a stripped galaxy from a previous minor merger. The radio emission from TDE 2023mfm emerges at least a year after optical discovery, and we find it likely that it originates from a delayed outflow, however, further observations are needed to determine its true origin.

astro-ph.GA↗

arXiv2026

Illuminating the Local Universe: Large-Scale Structure from ZTF Type Ia Supernovae

Within the volume-limited subsample at $z<0.06$ of the Zwicky Transient Facility (ZTF) DR2 sample, we confirm a statistically significant excess of Type Ia supernovae (SNe Ia) around $z \simeq 0.02-0.04$, previously reported but not explained by survey selection effects. Forward simulations assuming a uniform volumetric SN Ia rate and realistic ZTF detection efficiencies fail to reproduce the feature, rejecting this hypothesis at a $12.2σ$ level for the volume-limited sample. We further detect excesses in the rates compared to our survey simulations at $z \simeq 0.08$ and $0.14$, increasing the significance to $14σ$ when extending the redshift range up to $0.12$. To investigate the origin of these inhomogeneities, we compare the observed SN Ia distribution to constrained reconstructions of the local matter density field from the Manticore project, based on Bayesian forward modelling of the 2M++ galaxy catalogue. While SN overdensities are spatially associated with prominent nearby structures such as the Perseus, Coma, and Hercules superclusters, the amplitude of the SN excesses significantly exceeds that expected from local matter overdensities alone. By reconstructing a redshift-dependent volumetric SN Ia rate, we find that local enhancements can reach factors of three to eight within specific clusters, while the sample-averaged rate remains consistent with previous low-redshift measurements. These results indicate that the SN Ia rate is not a linear tracer of the underlying matter density and suggest a strong environmental dependence in dense structures. We discuss possible physical origins and highlight the implications for low-redshift SN cosmology, including correlated peculiar velocities and additional covariance beyond standard linear corrections.

astro-ph.CO↗

arXiv2026

First Pre-peak Ultraviolet Spectrum of a Tidal Disruption Event: A Fast Outflow Revealed Prior to Maximum Light in TDE2025aarm

The tidal disruption and eventual accretion of a star by a massive black hole can lead to the launching of outflows and winds that encode important information about the tidal disruption and accretion processes. However, little is known about the existence and behavior of these outflows before optical light-curve peak, when processes such as stream-stream collisions and disk formation may be important. Here, we present the first pre-peak ultraviolet (UV) spectrum of a tidal disruption event (TDE), obtained $\sim 20$ days before optical maximum light of the nearby (redshift $z=0.0137$) TDE2025aarm, along with quasi-simultaneous infrared (IR) through X-ray observations. Our HST/STIS spectrum shows strong evidence for an early-time outflow through broad near-UV (NUV) and far-UV (FUV) absorption lines blueshifted by $\sim$10,000 km s$^{-1}$, including two new UV broad absorption features not yet identified in a TDE. We find that the FUV--IR continuum deviates significantly from a blackbody ($f_λ\propto λ^{-3.08}$), which we interpret as a signature of reprocessing through the outflow. This deviation implies that the bolometric luminosity in optical TDEs may be underestimated by a significant factor ($\sim$9 in this case) when inferred from single-temperature blackbody fits to NUV--optical photometry alone. This work further confirms that TDEs are capable of launching fast outflows at very early times and emphasizes the importance of prompt FUV spectroscopic observations of TDEs that can capture the full continuum emission and energetics.

astro-ph.HE↗

arXiv2026

Stellar flare detection and characterization in ZTF High-cadence light curves

Stellar flares are brief, intense increases in brightness resulting from magnetic reconnection events in stellar atmospheres. In this paper, we have developed a pipeline to detect and characterize flares in short-duration (approximately 6.2-hour) light curves from the Zwicky Transient Facility (ZTF) Extended Deep-Drilling survey. This method involves robust detrending with Tukey's biweight estimator, followed by sigma-based thresholding and visual scrutiny to identify flare candidates. It is applied to 28 million light curves, and we found 331 flaring events from 310 stars across evolutionary stages and spectral types. We estimated flare energies by assuming a blackbody emission model for 234 flares with reliable distance, and flare morphologies were classified based on flare modeling using the template by Mendoza et al.(2022). We obtained a power law correlation between energy and duration with an index of $0.19 \pm 0.01$. We also find similar power law correlation between the flare energy and $T_{decay}$, $T_{rise}$ and FWHM. This study demonstrates the power of high-cadence ground-based surveys for statistical and morphological flare studies across a broad stellar sample.

astro-ph.SR↗

arXiv2026

AppleCiDEr. II. SpectraNet: A Spectroscopic Neural Network Classifier for Transients Demonstrated on ZTF Follow-up Data

Time-domain surveys such as the Zwicky Transient Facility have opened a new frontier in the discovery and characterization of transients. While photometric light curves provide broad temporal coverage, spectroscopic observations remain crucial for physical interpretation and source classification. However, existing spectral analysis methods, often reliant on template fitting or parametric models, are limited in their ability to capture the complex and evolving spectra characteristic of such sources, which are sometimes only available at low resolution. In this work, we introduce SpectraNet, a deep convolutional neural network designed to learn robust representations of optical spectra from transients. Our model combines multi-scale convolution kernels and pooling operations to extract features from preprocessed spectra in a hierarchical and interpretable manner. We train and validate SpectraNet on low-resolution time-series spectra obtained from the Spectral Energy Distribution Machine and other instruments, demonstrating better performance in classification compared to other known pipelines.

astro-ph.IM↗

arXiv2026

Extreme AGN Variability in WISE: Powerful Flares and Candidate Tidal Disruption Events in AGN

We present first results from a systematic study of extreme mid-infrared variability of active galaxies across the $>10$-year baseline of the Wide-field Infrared Survey Explorer (WISE) mission. WISE, which observed the full sky with a six-month cadence, is sensitive to transient events in both unobscured and obscured galaxies. This paper focuses on extreme flares in active galactic nuclei (AGNs). Previous studies identified flares such as tidal disruption events (TDEs) in inactive galaxies, typically from optical or X-ray surveys. However, flares are also expected in AGN and optical/X-ray searches are insensitive to events in dust-enshrouded AGN. In this pilot study, we present flares in two AGN identified from extreme mid-infrared color variability. One flare was also detected at optical wavelengths. While both events showed broadened H$α$ emission several years after the flare peak, more recent spectroscopy reveals continued broadened emission only from the source with the optical flare. After considering several potential physical causes of the flares, including supernovae and micro-lensing, we suggest both events are TDEs in AGN. Intriguingly, the optical flare decays much faster than the expected $t^{-5/3}$ fallback rate expected for TDEs in quiescent galaxies, suggesting either a partial disruption or the tidal disruption of a star by an intermediate mass black hole embedded in the accretion disk of an AGN. This work demonstrates the power of WISE to identify the full census of TDEs, including events in dust-obscured AGN. Mid-infrared data probes the nature of the event and provides a bolometric measure of the flare energetics.

astro-ph.HE↗

arXiv2026

Classifying Quasar Types Without a Spectrum

Distinguishing between Type 1 and Type 2 quasars is important because it helps us understand accretion regimes, black hole mass scaling, disk instabilities and feedback processes in active galaxies. Although spectroscopy provides robust classification, it does not scale well with the millions of quasars observed in modern surveys, as it requires substantial time and resources to acquire a good spectrum. On the photometry side, quasar light curves are always irregularly sampled and affected by the specifics of photometric surveys, making them difficult to analyze. In this work, we show that we can use irregularly sampled light curves from the Zwicky Transient Facility to classify quasar types without a spectrum, using Slepian Wavelet Variance. This technique allows us to decompose the variance of light curves into multiple timescales. We use agglomerative hierarchical clustering to classify 516 Type 1 and 238 Type 2 quasars from the MILLIQUAS catalogue, solely based on their wavelet variance curves. We obtain a recovery rate of 99% for Type 1 and 87% for Type 2 quasars, and the few misclassified quasars show the opposite variability behaviour to their spectral type. In contrast to structure functions and the Damped Random Walk model, Slepian Wavelet Variance offers a complementary, model-independent view of variability across short and long timescales.

astro-ph.GA↗

arXiv2026

Circumstellar interaction in the extreme white dwarf merger remnant ZTF\,J1901+1458: A new class of white dwarf merger remnants with X-ray emission

Double degenerate white dwarf (WD) mergers can exhibit extreme magnetic fields exceeding $10^{8}$ G and rapid rotation, but their spectral-energy distributions and high-energy emission mechanisms remain poorly characterised. ZTF J1901+1458 stands out as the most compact and strongly magnetised object discovered in this class to date. Recent Chandra observations have revealed that the white dwarf is also a source of soft X-ray emission, inconsistent with a photospheric origin. We analyse new phase resolved UV spectroscopy from the HST combined with optical and near-infrared photometry and spectroscopy, with newly developed magnetic atmosphere models to determine its effective temperature, radius, mass, average surface magnetic field strength, and cooling age. Our results demonstrate that the spectral break at $\approx$3000 Å, observed in several highly magnetised WDs, is well-reproduced by our new models, which take into account the effect of magnetic opacities on the structure of the atmosphere. Our best-fit parameters for the WD yield an effective temperature ($T_{\rm{eff}}=28,015\pm 20$ K) and larger radius ($2630\pm10$ km) than previously reported. Furthermore, the near-infrared data exclude the presence of a stellar or brown dwarf companion hotter than $\approx$700 K. We also jointly analyse the previously published Chandra data and new XMM-Newton X-ray spectra. The faint X-ray emission, $L_X =(1.3\pm0.2)\times10^{27}$ erg/s is very soft and highly pulsed on the rotation period of the WD. We suggest that the X-rays are powered by accretion or via the interaction of the WD magnetosphere with CSM. If the rapidly rotating magnetic field could power a weak wind along open field lines, material could be extracted directly from the surface of the WD. Alternatively, accretion of fallback material from the merger or the tidal disruption of a planetary body are possible sources of CSM.

astro-ph.SR↗

arXiv2026

Multiwavelength Analysis of Six Luminous Fast Blue Optical Transients

We present multiwavelength observations and analysis of six luminous fast blue optical transients (LFBOTs) discovered in Zwicky Transient Facility (ZTF) survey data. We identified these LFBOTs from their fast light-curve evolution ($t_{1/2}\leq 12 $d), blue colors at peak brightness ($g-r\leq-0.5 $mag), a visible host galaxy, high optical luminosity ($M_g<-20$), and an X-ray or radio detection. With the exception of AT2024aehp (ZTF24abygbss), these transients exhibit peaks in their $10\,$GHz radio light curves at $t_{\text{rest}} \approx 50-100$ d, with peak radio luminosities ranging from $10^{38}-10^{40}$ erg s$^{-1}$. Modeling the radio emission as synchrotron radiation indicates a fast ($v=0.1-0.3c$) shock in a dense ($n_e\approx10^{3}-10^{4}$ cm$^{-3}$) medium. The X-ray emission varies by $\approx2$ orders of magnitude in luminosity ($10^{42}-10^{44}$ erg s$^{-1}$) at $t_{\text{rest}}\sim20 $d. Analysis of the host-galaxy photometry and spectroscopy for each transient shows that they are predominantly nonnuclear (a few kpc offset) with star-forming host galaxies of stellar masses $10^{9}-10^{11} ,M_\odot$. Unlike all other LFBOTs to date, AT2024aehp exhibited a luminous ($M<-19 $mag) plateau in the optical light curve; spectra during this plateau phase showed a featureless blue continuum. The $6-15$ GHz radio emission of AT2024aehp brightened by over an order of magnitude from $t_{\text{rest}} \approx70 $d to $t_{\mathrm{rest}} \approx130 $d. The mostly consistent radio behavior between optically selected LFBOTs implies a similar circumburst medium, leading us to prefer a progenitor scenario in which mass is lost in a consistent way shortly prior to the terminal event, such as a massive star merging with a compact object.

astro-ph.HE↗

arXiv2026

Catching Disguised Transients with ASTRANet: Anomaly-Aware Spectroscopic Classification and Conformal Calibration

Time-domain surveys discover thousands of transients per year, but the spectroscopic identification of rare and physically peculiar objects remains rate-limited by closed-set classifiers that confidently assign every input to a known class -- including spectra that genuinely belong to no known class. We present the \texttt{ASTRANet} framework, a confidence-aware infrastructure for spectroscopic transient classification built around three coupled modules: a hierarchical spectral classifier that operates directly on observer-frame spectra without requiring host-galaxy redshift or spectral phase as inputs; an anomaly detection layer (\texttt{ASTRANet-Sentinel}) that non-linearly combines $16$ embedding-space anomaly scores spanning four physically motivated families; and a conformal uncertainty quantification layer (\texttt{ASTRANet-CP}). We validate the framework on a held-out evaluation set of $289$ rare and out-of-taxonomy transients spanning $11$ classes deliberately excluded from training, chosen to span the full physical diversity of the rare-anomaly population: AGN-related outliers, GRB-related events, gap transients, novae, and peculiar supernovae. Through five astrophysically distinct failure modes of closed-set classifiers, we show that classifier-internal uncertainty and embedding-based anomaly detection are structurally complementary axes of confidence rather than alternative implementations of the same estimator. We further introduce AD-stratified Mondrian conformal prediction (AD-MCP) within \texttt{ASTRANet-CP}, achieving uniform conditional coverage across anomaly-score strata where vanilla Mondrian under-covers in the operational regime. This establishes the methodological infrastructure for confidence-aware spectroscopic discovery in the Vera C.\ Rubin Observatory era.

astro-ph.IM↗

arXiv2026

Decoding the Early-Time Light Curves of Type Ia Supernovae. II. Population Parameters of One Thousand ZTF Supernovae

Early-time light curves of Type Ia Supernovae (SNe Ia) encode critical information about their progenitor systems. We characterize the rise of normal SNe Ia using a volume-complete sample of 972 events from the Zwicky Transient Facility Data Release 2, an order of magnitude larger than any previous dataset for similar analyses. Fitting light curves up to $30\%$ of peak flux with a power-law model under a hierarchical Bayesian framework, we provide robust population-level constraints on the rise time ($t_\mathrm{rise}$; $μ=18.55\pm0.08$ days, $σ=1.42\pm0.07$ days), rise index ($α$; $μ=2.10\pm0.04$, $σ=0.48\pm0.03$ in ZTF $r$), and $g-r$ color evolution ($α_g - α_r$; $μ=0.20\pm0.02$, $σ=0.17\pm0.02$). These power-law fits are sensitive to the chosen truncation epoch if data beyond $\sim$$40\%$ of peak flux are included, but generally converge when restricted to earlier epochs. The relation between rise morphology and light-curve width ($\texttt{SALT2}$ $x_1$ stretch) bifurcates into two distinct regimes: high-stretch SNe Ia show clear trends where a higher $x_1$ correlates with shallower rises and more persistent blue colors, whereas low-stretch SNe Ia lack such trends. While rise times correlate positively with $x_1$ overall, this relation flattens significantly within the high-stretch population. Searching for anomalies, we identify several normal SNe Ia with unusually long rise times, which potentially exhibit short-duration ($\lesssim$2 days) flux excesses over a smooth rise. Long-duration ($\sim$5 days) flux excesses appear common within the high-stretch population and are tied to the shallow rises and early blue colors, pointing to widespread outward $^{56}$Ni mixing. Multi-dimensional explosion models with more realistic progenitor setups are needed to fully reproduce the observed dichotomy in rise morphology and stretch.

astro-ph.HE↗

arXiv2026

Leveraging Multimodality for Real-Time Classification of Transients and Variables found by the Zwicky Transient Facility

Modern time-domain surveys such as the Zwicky Transient Facility (ZTF) generate hundreds of thousands of alerts each night, making real-time decisions for follow-up observations a central challenge in time-domain astronomy. Robust early classification is crucial for making informed decisions, but is hindered by sparse light curves and degeneracies between classes. In this work, we leverage multimodality to substantially improve real-time classification and demonstrate the practicality of our approach by deploying our model on the ZTF alert stream. Building on the Online Ranked Astrophysical CLass Estimator (ORACLE), we introduce the ORACLE-2 models, which combine light curves, metadata, and images for real-time hierarchical classification. Using both real and simulated datasets, we show that incorporating additional modalities consistently improves classification performance. On observations from ZTF's Bright Transient Survey, our best-performing model, ORACLE-2 Omni, achieves a macro F1 score of 0.73 -- an improvement of up to 11% over models using light curves and metadata alone, and up to 40% over light-curve-only models, with the strongest gains realized at early times. To demonstrate applicability to the Legacy Survey of Space and Time, which will increase alert volume by more than an order of magnitude, we train a light curve + metadata variant on the simulated ELAsTiCC dataset. This model achieves a macro F1 score of 0.88, an improvement of up to 13% over the light-curve-only variant, matching the performance of other state-of-the-art models. Finally, we quantify the trade-offs between performance and throughput, identifying regimes where multimodal approaches offer the greatest benefit. These results show that combining multiple modalities improves early-time classification, enabling more effective triage of high-volume alert streams for current and future time-domain surveys.

astro-ph.IM↗