arXiv subjects

Brian Bue

Publications and source records attributed to Brian Bue.

10 recordsLinked to original sources

arXiv2026

Fully Automatic Trace Gas Plume Detection

Future imaging spectrometers will expand contemporary data volumes by orders of magnitude, requiring automated methods to upscale labor-intensive detection of trace gas point sources. Here we present a fully-automated approach that achieves operational performance for plume detection and labelling without human participation. Our method combines machine learning (ML)-based morphological analysis with physics-based spectroscopic model fitting. We deploy it on data from the EMIT imaging spectrometer, operating in two modes. First, we present a "daily digest" that runs automatically on all downlinked data, flagging the largest events for immediate response. The daily digest demonstrates that a significant fraction of the largest plumes can be detected automatically with negligible false positives. This represents a significant new high-water mark in plume detection accuracy. Second, we use it for retrospective analysis to find plumes that were missed by the existing human review process. We observe that at least 25% of large plumes may have been passed over in the existing workflow due to confirmation bias and ambiguity in the visual cues used by human reviewers. Finally, we extend detection to three understudied trace gases: NH3, NO2 and the first observations of carbon monoxide (CO) plume in EMIT imagery.

cs.LG↗

arXiv2026

MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applications

We introduce MOMO, the first multi-sensor foundation model for Mars remote sensing. MOMO uses model merge to integrate representations learned independently from three key Martian sensors (HiRISE, CTX, and THEMIS), spanning resolutions from 0.25 m/pixel to 100 m/pixel. Central to our method is our novel Equal Validation Loss (EVL) strategy, which aligns checkpoints across sensors based on validation loss similarity before fusion via task arithmetic. This ensures models are merged at compatible convergence stages, leading to improved stability and generalization. We train MOMO on a large-scale, high-quality corpus of $\sim 12$ million samples curated from Mars orbital data and evaluate it on 9 downstream tasks from Mars-Bench. MOMO achieves better overall performance compared to ImageNet pre-trained, earth observation foundation model, sensor-specific pre-training, and fully-supervised baselines. Particularly on segmentation tasks, MOMO shows consistent and significant performance improvement. Our results demonstrate that model merging through an optimal checkpoint selection strategy provides an effective approach for building foundation models for multi-resolution data. The model weights, pretraining code, pretraining data, and evaluation code are available at: https://github.com/kerner-lab/MOMO.

cs.CV↗

arXiv2025

Multi-Platform Methane Plume Detection via Model and Domain Adaptation

Prioritizing methane for near-term climate action is crucial due to its significant impact on global warming. Previous work used columnwise matched filter products from the airborne AVIRIS-NG imaging spectrometer to detect methane plume sources; convolutional neural networks (CNNs) discerned anthropogenic methane plumes from false positive enhancements. However, as an increasing number of remote sensing platforms are used for methane plume detection, there is a growing need to address cross-platform alignment. In this work, we describe model- and data-driven machine learning approaches that leverage airborne observations to improve spaceborne methane plume detection, reconciling the distributional shifts inherent with performing the same task across platforms. We develop a spaceborne methane plume classifier using data from the EMIT imaging spectroscopy mission. We refine classifiers trained on airborne imagery from AVIRIS-NG campaigns using transfer learning, outperforming the standalone spaceborne model. Finally, we use CycleGAN, an unsupervised image-to-image translation technique, to align the data distributions between airborne and spaceborne contexts. Translating spaceborne EMIT data to the airborne AVIRIS-NG domain using CycleGAN and applying airborne classifiers directly yields the best plume detection results. This methodology is useful not only for data simulation, but also for direct data alignment. Though demonstrated on the task of methane plume detection, our work more broadly demonstrates a data-driven approach to align related products obtained from distinct remote sensing instruments.

eess.SP↗

arXiv2019

The Zwicky Transient Facility: Data Processing, Products, and Archive

The Zwicky Transient Facility (ZTF) is a new robotic time-domain survey currently in progress using the Palomar 48-inch Schmidt Telescope. ZTF uses a 47 square degree field with a 600 megapixel camera to scan the entire northern visible sky at rates of ~3760 square degrees/hour to median depths of g ~ 20.8 and r ~ 20.6 mag (AB, 5sigma in 30 sec). We describe the Science Data System that is housed at IPAC, Caltech. This comprises the data-processing pipelines, alert production system, data archive, and user interfaces for accessing and analyzing the products. The realtime pipeline employs a novel image-differencing algorithm, optimized for the detection of point source transient events. These events are vetted for reliability using a machine-learned classifier and combined with contextual information to generate data-rich alert packets. The packets become available for distribution typically within 13 minutes (95th percentile) of observation. Detected events are also linked to generate candidate moving-object tracks using a novel algorithm. Objects that move fast enough to streak in the individual exposures are also extracted and vetted. The reconstructed astrometric accuracy per science image with respect to Gaia is typically 45 to 85 milliarcsec. This is the RMS per axis on the sky for sources extracted with photometric S/N >= 10. The derived photometric precision (repeatability) at bright unsaturated fluxes varies between 8 and 25 millimag. Photometric calibration accuracy with respect to Pan-STARRS1 is generally better than 2%. The products support a broad range of scientific applications: fast and young supernovae, rare flux transients, variable stars, eclipsing binaries, variability from active galactic nuclei, counterparts to gravitational wave sources, a more complete census of Type Ia supernovae, and Solar System objects.

astro-ph.IM↗

arXiv2019

The Zwicky Transient Facility: System Overview, Performance, and First Results

The Zwicky Transient Facility (ZTF) is a new optical time-domain survey that uses the Palomar 48-inch Schmidt telescope. A custom-built wide-field camera provides a 47 deg$^2$ field of view and 8 second readout time, yielding more than an order of magnitude improvement in survey speed relative to its predecessor survey, the Palomar Transient Factory (PTF). We describe the design and implementation of the camera and observing system. The ZTF data system at the Infrared Processing and Analysis Center provides near-real-time reduction to identify moving and varying objects. We outline the analysis pipelines, data products, and associated archive. Finally, we present on-sky performance analysis and first scientific results from commissioning and the early survey. ZTF's public alert stream will serve as a useful precursor for that of the Large Synoptic Survey Telescope.

astro-ph.IM↗

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↗

arXiv2019

The Zwicky Transient Facility: Science Objectives

The Zwicky Transient Facility (ZTF), a public-private enterprise, is a new time domain survey employing a dedicated camera on the Palomar 48-inch Schmidt telescope with a 47 deg$^2$ field of view and 8 second readout time. It is well positioned in the development of time domain astronomy, offering operations at 10% of the scale and style of the Large Synoptic Survey Telescope (LSST) with a single 1-m class survey telescope. The public surveys will cover the observable northern sky every three nights in g and r filters and the visible Galactic plane every night in g and r. Alerts generated by these surveys are sent in real time to brokers. A consortium of universities which provided funding ("partnership") are undertaking several boutique surveys. The combination of these surveys producing one million alerts per night allows for exploration of transient and variable astrophysical phenomena brighter than r $\sim$ 20.5 on timescales of minutes to years. We describe the primary science objectives driving ZTF including the physics of supernovae and relativistic explosions, multi-messenger astrophysics, supernova cosmology, active galactic nuclei and tidal disruption events, stellar variability, and Solar System objects.

astro-ph.IM↗

arXiv2017

Energetic eruptions leading to a peculiar hydrogen-rich explosion of a massive star

Every supernova hitherto observed has been considered to be the terminal explosion of a star. Moreover, all supernovae with absorption lines in their spectra show those lines decreasing in velocity over time, as the ejecta expand and thin, revealing slower moving material that was previously hidden. In addition, every supernova that exhibits the absorption lines of hydrogen has one main light-curve peak, or a plateau in luminosity, lasting approximately 100 days before declining. Here we report observations of iPTF14hls, an event that has spectra identical to a hydrogen-rich core-collapse supernova, but characteristics that differ extensively from those of known supernovae. The light curve has at least five peaks and remains bright for more than 600 days; the absorption lines show little to no decrease in velocity; and the radius of the line-forming region is more than an order of magnitude bigger than the radius of the photosphere derived from the continuum emission. These characteristics are consistent with a shell of several tens of solar masses ejected by the star at supernova-level energies a few hundred days before a terminal explosion. Another possible eruption was recorded at the same position in 1954. Multiple energetic pre-supernova eruptions are expected to occur in stars of 95-130 solar masses, which experience the pulsational pair instability. That model, however, does not account for the continued presence of hydrogen, or the energetics observed here. Another mechanism for the violent ejection of mass in massive stars may be required.

astro-ph.HE↗

arXiv2017

Processing Images from the Zwicky Transient Facility

The Zwicky Transient Facility is a new robotic-observing program, in which a newly engineered 600-MP digital camera with a pioneeringly large field of view, 47~square degrees, will be installed into the 48-inch Samuel Oschin Telescope at the Palomar Observatory. The camera will generate $\sim 1$~petabyte of raw image data over three years of operations. In parallel related work, new hardware and software systems are being developed to process these data in real time and build a long-term archive for the processed products. The first public release of archived products is planned for early 2019, which will include processed images and astronomical-source catalogs of the northern sky in the $g$ and $r$ bands. Source catalogs based on two different methods will be generated for the archive: aperture photometry and point-spread-function fitting.

astro-ph.IM↗

arXiv2016

Small near-Earth asteroids in the Palomar Transient Factory survey: A real-time streak-detection system

Near-Earth asteroids (NEAs) in the 1-100 meter size range are estimated to be $\sim$1,000 times more numerous than the $\sim$15,000 currently-catalogued NEAs, most of which are in the 0.5-10 kilometer size range. Impacts from 10-100 meter size NEAs are not statistically life-threatening but may cause significant regional damage, while 1-10 meter size NEAs with low velocities relative to Earth are compelling targets for space missions. We describe the implementation and initial results of a real-time NEA-discovery system specialized for the detection of small, high angular rate (visually-streaked) NEAs in Palomar Transient Factory (PTF) images. PTF is a 1.2-m aperture, 7.3-deg$^2$ field-of-view optical survey designed primarily for the discovery of extragalactic transients (e.g., supernovae) in 60-second exposures reaching $\sim$20.5 visual magnitude. Our real-time NEA discovery pipeline uses a machine-learned classifier to filter a large number of false-positive streak detections, permitting a human scanner to efficiently and remotely identify real asteroid streaks during the night. Upon recognition of a streaked NEA detection (typically within an hour of the discovery exposure), the scanner triggers follow-up with the same telescope and posts the observations to the Minor Planet Center for worldwide confirmation. We describe our ten initial confirmed discoveries, all small NEAs that passed 0.3-15 lunar distances from Earth. Lastly, we derive useful scaling laws for comparing streaked-NEA-detection capabilities of different surveys as a function of their hardware and survey-pattern characteristics. This work most directly informs estimates of the streak-detection capabilities of the Zwicky Transient Facility (ZTF, planned to succeed PTF in 2017), which will apply PTF's current resolution and sensitivity over a 47-deg$^2$ field-of-view.

astro-ph.EP↗