Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “deep”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,783 records · Page 99

End-to-end deep learning pipeline for real-time Bragg peak segmentation: from training to large-scale deployment

X-ray crystallography reconstruction, which transforms discrete X-ray diffraction patterns into three-dimensional molecular structures, relies critically on accurate Bragg peak finding for structure determination. As X-ray free electron laser (XFEL) facilities advance toward MHz data rates (1 million images per second), traditional peak finding algorithms that require manual parameter tuning or exhaustive grid searches across multiple experiments become increasingly impractical. While deep learning approaches offer promising solutions, their deployment in high-throughput environments presents significant challenges in automated dataset labeling, model scalability, edge deployment efficiency, and distributed inference capabilities. We present an end-to-end deep learning pipeline with three key components: (1) a data engine that combines traditional algorithms with our peak matching algorithm to generate high-quality training data at scale, (2) a modular architecture that scales from a few million to hundreds of million parameters, enabling us to train large expert-level models offline while deploying smaller, distilled models at the edge, and (3) a decoupled producer-consumer architecture that separates specialized data source layer from model inference, enabling flexible deployment across diverse computing environments. Using this integrated approach, our pipeline achieves accuracy comparable to traditional methods tuned by human experts while eliminating the need for experiment-specific parameter tuning. Although current throughput requires optimization for MHz facilities, our system's scalable architecture and demonstrated model compression capabilities provide a foundation for future high-throughput XFEL deployments.

Wang, Cong↗

Cosmic Ray Background Removal With Deep Neural Networks in SBND

In liquid argon time projection chambers exposed to neutrino beams and running on or near surface levels, cosmic muons, and other cosmic particles are incident on the detectors while a single neutrino-induced event is being recorded. In practice, this means that data from surface liquid argon time projection chambers will be dominated by cosmic particles, both as a source of event triggers and as the majority of the particle count in true neutrino-triggered events. In this work, we demonstrate a novel application of deep learning techniques to remove these background particles by applying deep learning on full detector images from the SBND detector, the near detector in the Fermilab Short-Baseline Neutrino Program. We use this technique to identify, on a pixel-by-pixel level, whether recorded activity originated from cosmic particles or neutrino interactions.

79 ASTRONOMY AND ASTROPHYSICS↗

Deep Minima in the Triply Differential Cross Section for Ionization of Atomic Hydrogen by Electron and Positron Impact

We investigate ionization of atomic hydrogen by electron- and positron-impact. We apply the Coulomb–Born (CB1) approximation, various modified CB1 approximations, the three body distorted wave (3DW) approximation, and the time-dependent close-coupling (TDCC) method to electron-impact ionization of hydrogen. For electron-impact ionization of hydrogen for an incident energy of approximately 76.45 eV, we obtain a deep minimum in the CB1 triply differential cross section (TDCS). However, the TDCC for 74.45 eV and the 3DW for 74.46 eV gave a dip in the TDCS. For positron-hydrogen ionization (breakup) we apply the CB1 approximation and a modified CB1 approximation. We obtain a deep minimum in the TDCS and a zero in the CB1 transition matrix element for an incident energy of 100 eV with a gun angle of 56.13 °. Corresponding to a zero in the CB1 transition matrix element, there is a vortex in the velocity field associated with this element. For both electron- and positron-impact ionization of hydrogen the velocity field rotates in the same direction, which is anticlockwise. All calculations are performed for a doubly symmetric geometry; the electron-impact ionization is in-plane and the positron-impact ionization is out-of-plane.

74 ATOMIC AND MOLECULAR PHYSICS↗

Effect of Deep Drying and Torrefaction Temperature on Proximate, Ultimate Composition, and Heating Value of 2-mm Lodgepole Pine (Pinus contorta) Grind

Deep drying and torrefaction is a thermal pretreatment method, where biomass is heated in the temperature range of 150–300°C in an inert or reduced environment. The process parameters like temperature and residence time has a significant impact on proximate, ultimate, and energy properties of the biomass. In the present study, torrrefaction experiments were conducted on 2 mm lodgepole pine grind using a thermogravimetric analyzer. Both deep drying and torrefaction temperature (160–270°C) and time (15–120 min) were selected. Torrefied samples were analyzed for proximate, ultimate and energy properties. Results indicated that moisture content decreased with increases in torrefaction temperature and time, where at 270°C and 120 min, the moisture content was found to be 1.15% (w.b.). Volatile content in the biomass decreased from about 80% to about 45%, and ash content increased from 0.77 to about 1.91% at 270°C and 120 min. The hydrogen, oxygen and sulfur content decreased to 3%, 28.24%, and 0.01 whereas carbon content and higher heating value increased to 68.86% and 23.67 MJ/kg at 270°C and 120 min. H/C and O/C ratio calculated at 270°C and 120 min residence time were about 0.56 and 0.47. This study indicated that higher torrefaction temperatures >230°C and residence time >15 min influenced the proximate, ultimate, and energy properties.

09 BIOMASS FUELS↗

Impact of Misclassification Rates on Compression Efficiency of Red Blood Cell Images of Malaria Infection Using Deep Learning

Malaria is a severe public health problem worldwide, with some developing countries being most affected. Reliable remote diagnosis of malaria infection will benefit from efficient compression of high-resolution microscopic images. This paper addresses a lossless compression of malaria-infected red blood cell images using deep learning. Specifically, we investigate a practical approach where images are first classified before being compressed using stacked autoencoders. We provide probabilistic analysis on the impact of misclassification rates on compression performance in terms of the information-theoretic measure of entropy. We then use malaria infection image datasets to evaluate the relations between misclassification rates and actually obtainable compressed bit rates using Golomb–Rice codes. Simulation results show that the joint pattern classification/compression method provides more efficient compression than several mainstream lossless compression techniques, such as JPEG2000, JPEG-LS, CALIC, and WebP, by exploiting common features extracted by deep learning on large datasets. This study provides new insight into the interplay between classification accuracy and compression bitrates. The proposed compression method can find useful telemedicine applications where efficient storage and rapid transfer of large image datasets is desirable.

59 BASIC BIOLOGICAL SCIENCES↗

Post-Closure Performance Assessment for Deep Borehole Disposal of Cs/Sr Capsules

Post-closure performance assessment (PA) calculations suggest that deep borehole disposal of cesium (Cs)/strontium (Sr) capsules, a U.S. Department of Energy (DOE) waste form (WF), is safe, resulting in no releases to the biosphere over 10,000,000 years when the waste is placed in a 3–5 km deep waste disposal zone. The same is true when a hypothetical breach of a stuck waste package (WP) is assumed to occur at much shallower depths penetrated by through-going fractures. Cs and Sr retardation in the host rock is a key control over movement. Calculated borehole performance would be even stronger if credit was taken for the presence of the WP.

58 GEOSCIENCES↗

Closure Learning for Nonlinear Model Reduction Using Deep Residual Neural Network

Developing accurate, efficient, and robust closure models is essential in the construction of reduced order models (ROMs) for realistic nonlinear systems, which generally require drastic ROM mode truncations. We propose a deep residual neural network (ResNet) closure learning framework for ROMs of nonlinear systems. The novel ResNet-ROM framework consists of two steps: (i) In the first step, we use ROM projection to filter the given nonlinear system and construct a spatially filtered ROM. This filtered ROM is low-dimensional, but is not closed. (ii) In the second step, we use ResNet to close the filtered ROM, i.e., to model the interaction between the resolved and unresolved ROM modes. We emphasize that in the new ResNet-ROM framework, data is used only to complement classical physical modeling (i.e., only in the closure modeling component), not to completely replace it. We also note that the new ResNet-ROM is built on general ideas of spatial filtering and deep learning and is independent of (restrictive) phenomenological arguments, e.g., of eddy viscosity type. The numerical experiments for the 1D Burgers equation show that the ResNet-ROM is significantly more accurate than the standard projection ROM. The new ResNet-ROM is also more accurate and significantly more efficient than other modern ROM closure models.

Xie, Xuping↗

Hardware-Based Emulator with Deep Learning Model for Building Energy Control and Prediction Based on Occupancy Sensors’ Data

Heating, ventilation, and air conditioning (HVAC) is the largest source of residential energy consumption. Occupancy sensors’ data can be used for HVAC control since it indicates the number of people in the building. HVAC and sensors form a typical cyber-physical system (CPS). In this paper, we aim to build a hardware-based emulation platform to study the occupancy data’s features, which can be further extracted by using machine learning models. In particular, we propose two hardware-based emulators to investigate the use of wired/wireless communication interfaces for occupancy sensor-based building CPS control, and the use of deep learning to predict the building energy consumption with the sensor data. We hypothesize is that the building energy consumption may be predicted by using the occupancy data collected by the sensors, and question what type of prediction model should be used to accurately predict the energy load. Another hypothesis is that an in-lab hardware/software platform could be built to emulate the occupancy sensing process. The machine learning algorithms can then be used to analyze the energy load based on the sensing data. To test the emulator, the occupancy data from the sensors is used to predict energy consumption. The synchronization scheme between sensors and the HVAC server will be discussed. We have built two hardware/software emulation platforms to investigate the sensor/HVAC integration strategies, and used an enhanced deep learning model—which has sequence-to-sequence long short-term memory (Seq2Seq LSTM)—with an attention model to predict the building energy consumption with the preservation of the intrinsic patterns. Because the long-range temporal dependencies are captured, the Seq2Seq models may provide a higher accuracy by using LSTM architectures with encoder and decoder. Meanwhile, LSTMs can capture the temporal and spatial patterns of time series data. The attention model can highlight the most relevant input information in the energy prediction by allocating the attention weights. The communication overhead between the sensors and the HVAC control server can also be alleviated via the attention mechanism, which can automatically ignore the irrelevant information and amplify the relevant information during CNN training. Our experiments and performance analysis show that, compared with the traditional LSTM neural network, the performance of the proposed method has a 30% higher prediction accuracy.

Ye, Zhijing↗

Integrating Deep Learning and Hydrodynamic Modeling to Improve the Great Lakes Forecast

The Laurentian Great Lakes, one of the world’s largest surface freshwater systems, pose a modeling challenge in seasonal forecast and climate projection. While physics-based hydrodynamic modeling is a fundamental approach, improving the forecast accuracy remains critical. In recent years, machine learning (ML) has quickly emerged in geoscience applications, but its application to the Great Lakes hydrodynamic prediction is still in its early stages. This work is the first one to explore a deep learning approach to predicting spatiotemporal distributions of the lake surface temperature (LST) in the Great Lakes. Our study shows that the Long Short-Term Memory (LSTM) neural network, trained with the limited data from hypothetical monitoring networks, can provide consistent and robust performance. The LSTM prediction captured the LST spatiotemporal variabilities across the five Great Lakes well, suggesting an effective and efficient way for monitoring network design in assisting the ML-based forecast. Furthermore, we employed an explainable artificial intelligence (XAI) technique named SHapley Additive exPlanations (SHAP) to uncover how the features impact the LSTM prediction. Our XAI analysis shows air temperature is the most influential feature for predicting LST in the trained LSTM. The relatively large bias in the LSTM prediction during the spring and fall was associated with substantial heterogeneity of air temperature during the two seasons. In contrast, the physics-based hydrodynamic model performed better in spring and fall yet exhibited relatively large biases during the summer stratification period. Finally, we developed a statistical integration of the hydrodynamic modeling and deep learning results based on the Best Linear Unbiased Estimator (BLUE). The integration further enhanced prediction accuracy, suggesting its potential for next-generation Great Lakes forecast systems.

Xue, Pengfei (ORCID:000000025702421X)↗

Simple Statistical Models for Predicting Overpressure Due to CO2 and Low-Salinity Waste-Fluid Injection into Deep Saline Formations

Deep saline aquifers have been used for waste-fluid disposal for decades and are the proposed targets for large-scale CO2 storage to mitigate CO2 concentration in the atmosphere. Due to relatively limited experience with CO2 injection in deep saline formations and given that the injection targets for CO2 sometimes are the same as waste-fluid disposal formations, it could be beneficial to model and compare both practices and learn from the waste-fluid disposal industry. In this paper, we model CO2 injection in the Patterson Field, which has been proposed as a site for storage of 50 Mt of industrial CO2 over 25 years. We propose general models that quickly screen the reservoir properties and calculate pressure changes near and far from the injection wellbore, accounting for variable reservoir properties. The reservoir properties we investigated were rock compressibility, injection rate, vertical-to-horizontal permeability ratio, average reservoir permeability and porosity, reservoir temperature and pressure, and the injectant total dissolved solids (TDS) in cases of waste-fluid injection. We used experimental design to select and perform simulation runs, performed a sensitivity analysis to identify the important variables on pressure build-up, and then fit a regression model to the simulation runs to obtain simple proxy models for changes in average reservoir pressure and bottomhole pressure. The CO2 injection created more pressure compared to saline waste-fluids, when similar mass was injected. However, we found a more significant pressure buildup at the caprock-reservoir interface and lower pressure buildup at the bottom of the reservoir when injecting CO2 compared with waste-fluid injection.

Ansari, Esmail↗

Deep Learning and Photogrammetric Reconstruction for Automated Crack Detection and Dimensional Measurement in Mining Operations

Surface crack detection and dimensional measurement at active mining sites present significant safety and operational challenges. Manual inspection methods are labor-intensive, spatially incomplete, and expose personnel to hazardous environments, while existing automated approaches have been developed primarily for concrete civil infrastructure and have not been validated on the complex, variable surfaces characteristic of mining environments. This dissertation presents an automated pipeline that integrates deep learning semantic segmentation with Structure-from-Motion photogrammetry to detect surface cracks and measure their aperture, length, and vertical displacement from standard RGB imagery acquired during routine Uncrewed Aerial Vehicle (UAV) survey operations, without requiring additional sensor hardware or manual measurement. The pipeline combines a U-Net architecture with an EfficientNet-B0 encoder, pretrained on the SDNET2018 concrete crack dataset and fine-tuned on a mining-specific dataset spanning laboratory concrete specimens, coal refuse impoundment embankments, and post-blast limestone quarry benches. Photogrammetric reconstruction is performed using COLMAP Structure-from-Motion and Multi-View Stereo, with crack segmentation masks projected into the reconstructed point cloud to enable three-dimensional vertical displacement measurement through local plane fitting and bimodal surface detection. The pipeline was validated across 36 controlled laboratory specimens at three imaging distances and four vertical displacement levels, achieving aperture measurement RMSE of 0.047 cm and R² of 0.954, and vertical displacement RMSE of 0.140 cm and R² of 0.966, against independent caliper measurements. Field application at a coal refuse impoundment in southwestern Pennsylvania detected 71 crack components across the embankment crest, with a dominant longitudinal crack exhibiting aperture values reaching 28 cm and a 95th percentile vertical displacement of 35.53 cm, consistent in magnitude and spatial distribution with simultaneously acquired LiDAR-derived estimates. Application across four post-blast limestone quarry bench datasets in California successfully characterized blast-induced fracture networks at ground sampling distances ranging from 0.59 to 1.23 cm/pixel, with detected crack geometries physically consistent with observable surface conditions at each site. The results demonstrate that deep learning-based crack detection and photogrammetric measurement can be integrated into routine UAV inspection workflows at mining sites, providing repeatable, scalable, and quantitative crack characterization across surface types, crack scales, and displacement magnitudes not previously addressed in the literature. The pipeline requires no dedicated surveying equipment beyond the UAV platforms already deployed at mine sites for survey and monitoring purposes, supporting practical adoption within existing operational workflows.

Crack detection, Dimensional Measurement↗

Robust High-Throughput Phenotyping with Deep Segmentation Enabled by a Web-Based Annotator

The abilities of plant biologists and breeders to characterize the genetic basis of physiological traits are limited by their abilities to obtain quantitative data representing precise details of trait variation, and particularly to collect this data at a high-throughput scale with low cost. Although deep learning methods have demonstrated unprecedented potential to automate plant phenotyping, these methods commonly rely on large training sets that can be time-consuming to generate. Intelligent algorithms have therefore been proposed to enhance the productivity of these annotations and reduce human efforts. We propose a high-throughput phenotyping system which features a Graphical User Interface (GUI) and a novel interactive segmentation algorithm: Semantic-Guided Interactive Object Segmentation (SGIOS). By providing a user-friendly interface and intelligent assistance with annotation, this system offers potential to streamline and accelerate the generation of training sets, reducing the effort required by the user. Our evaluation shows that our proposed SGIOS model requires fewer user inputs compared to the state-of-art models for interactive segmentation. As a case study of the use of the GUI applied for genetic discovery in plants, we present an example of results from a preliminary genome-wide association study (GWAS) of in planta regeneration in Populus trichocarpa (poplar). We further demonstrate that the inclusion of a semantic prior map with SGIOS can accelerate the training process for future GWAS, using a sample of a dataset extracted from a poplar GWAS of in vitro regeneration. The capabilities of our phenotyping system surpass those of unassisted humans to rapidly and precisely phenotype our traits of interest. The scalability of this system enables large-scale phenomic screens that would otherwise be time-prohibitive, thereby providing increased power for GWAS, mutant screens, and other studies relying on large sample sizes to characterize the genetic basis of trait variation. Our user-friendly system can be used by researchers lacking a computational background, thus helping to democratize the use of deep segmentation as a tool for plant phenotyping.

54 ENVIRONMENTAL SCIENCES↗

Deep-blue emitting 9,10-bis(perfluorobenzyl)anthracene

A new deep-blue emitting and highly fluorescent anthracene (ANTH) derivative containing perfluorobenzyl (Bn F ) groups, 9,10-ANTH(Bn F ) 2 , was synthesized in a single step reaction of ANTH or ANTH(Br) 2 with Bn F I, using either a high-temperature Cu-/Na 2 S 2 O 3 -promoted reaction or via a room-temperature photochemical reaction. Its structure was elucidated by NMR spectroscopy and single crystal X-ray diffractometry. The latter revealed no π–π interaction between neighboring ANTH cores. A combination of high photoluminescence quantum yield (PLQY) of 0.85 for 9,10-ANTH(Bn F ) 2 , its significantly improved photostability compared to ANTH and 9,10-ANTH derivatives, and a simple synthetic access makes it an attractive material as a deep-blue OLED emitter and an efficient fluorescent probe.

Chemistry↗

DEEP NEAR-IR OBSERVATIONS OF THE GLOBULAR CLUSTER M4: HUNTING FOR BROWN DWARFS

We present an analysis of deep Hubble Space Telescope (HST)/Wide Field Camera 3 near-IR (NIR) imaging data of the globular cluster (GC) M4. The best-photometry NIR color–magnitude diagram (CMD) clearly shows the main sequence extending toward the expected end of the hydrogen-burning limit and going beyond this point toward fainter sources. The white dwarf (WD) sequence can be identified. As such, this is the deepest NIR CMD of a GC to date. Archival HST optical data were used for proper-motion cleaning of the CMD and for distinguishing the WDs from brown dwarf (BD) candidates. Detection limits in the NIR are around F110W ≈ 26.5 mag and F160W ≈ 27 mag, and in the optical around F775W ≈ 28 mag. Comparing our observed CMDs with theoretical models, we conclude that we have reached beyond the H-burning limit in our NIR CMD and are probably just above or around this limit in our optical–NIR CMDs. Thus, any faint NIR sources that have no optical counterpart are potential BD candidates, since the optical data are not deep enough to detect them. We visually inspected the positions of NIR sources that are fainter than the H-burning limit in F110W and for which the optical photometry did not return a counterpart. We found in total five sources for which we did not get an optical measurement. For four of these five sources, a faint optical counterpart could be visually identified, and an upper optical magnitude was estimated. Based on these upper optical magnitude limits, we conclude that one source is likely a WD, one source could be either a WD or BD candidate, and the remaining two sources agree with being BD candidates. No optical counterpart could be detected for just one source, which makes this source a good BD candidate. We conclude that we found in total four good BD candidates.

79 ASTRONOMY AND ASTROPHYSICS↗

A SYSTEMATIC SEARCH FOR PERIODICALLY VARYING QUASARS IN PAN-STARRS1: AN EXTENDED BASELINE TEST IN MEDIUM DEEP SURVEY FIELD MD09

We present a systematic search for periodically varying quasars and supermassive black hole binary (SMBHB) candidates in the Pan-STARRS1 (PS1) Medium Deep Survey’s MD09 field. From a color-selected sample of 670 quasars extracted from a multi-band deep-stack catalog of point sources, we locally select variable quasars and look for coherent periods with the Lomb–Scargle periodogram. Three candidates from our sample demonstrate strong variability for more than ∼3 cycles, and their PS1 light curves are well fitted to sinusoidal functions. We test the persistence of the candidates’ apparent periodic variations detected during the 4.2 years of the PS1 survey with archival photometric data from the SDSS Stripe 82 survey or new monitoring with the Large Monolithic Imager at the Discovery Channel Telescope. None of the three periodic candidates (including PSO J334.2028+1.4075) remain persistent over the extended baseline of 7–14 years, corresponding to a detection rate of <1 in 670 quasars in a search area of ≈5 deg{sup 2}. Even though SMBHBs should be a common product of the hierarchal growth of galaxies, and periodic variability in SMBHBs has been theoretically predicted, a systematic search for such signatures in a large optical survey is strongly limited by its temporal baseline and the “red noise” associated with normal quasar variability. We show that follow-up long-term monitoring (≳5 cycles) is crucial to our search for these systems.

79 ASTRONOMY AND ASTROPHYSICS↗

The metal abundances across cosmic time (MACT) Survey. I. Optical spectroscopy in the subaru deep field

Deep rest-frame optical spectroscopy is critical for characterizing and understanding the physical conditions and properties of the ionized gas in galaxies. Here, we present a new spectroscopic survey called “Metal Abundances across Cosmic Time” or MACT, which will obtain rest-frame optical spectra for ∼3000 emission-line galaxies. This paper describes the optical spectroscopy that has been conducted with MMT/Hectospec and Keck/DEIMOS for ≈1900 z = 0.1–1 emission-line galaxies selected from our narrowband and intermediate-band imaging in the Subaru Deep Field. In addition, we present a sample of 164 galaxies for which we have measured the weak [O iii]λ4363 line (66 with at least 3σ detections and 98 with significant upper limits). This nebular emission line determines the gas-phase metallicity by measuring the electron temperature of the ionized gas. This paper presents the optical spectra, emission-line measurements, interstellar properties (e.g., metallicity, gas density), and stellar properties (e.g., star formation rates, stellar mass). Paper II of the MACT survey (Ly et al.) presents the first results on the stellar mass–gas metallicity relation at z ≲ 1 using the sample with [O iii]λ4363 measurements.

79 ASTRONOMY AND ASTROPHYSICS↗

DEEP CFHT Y-BAND IMAGING OF VVDS-F22 FIELD. I. DATA PRODUCTS AND PHOTOMETRIC REDSHIFTS

We present our deep Y-band imaging data of a 2 square degree field within the F22 region of the VIMOS VLT Deep Survey. The observations were conducted using the WIRCam instrument mounted at the Canada–France–Hawaii Telescope (CFHT). The total on-sky time was 9 hr, distributed uniformly over 18 tiles. The scientific goals of the project are to select faint quasar candidates at redshift z>2.2 and constrain the photometric redshifts for quasars and galaxies. In this paper, we present the observation and the image reduction, as well as the photometric redshifts that we derived by combining our Y-band data with the CFHTLenS u{sup ∗}g{sup ′}r{sup ′}i{sup ′}z{sup ′} optical data and UKIDSS DXS JHK near-infrared data. With the J-band image as a reference, a total of ∼80,000 galaxies are detected in the final mosaic down to a Y-band 5σ point-source limiting depth of 22.86 mag. Compared with the ∼3500 spectroscopic redshifts, our photometric redshifts for galaxies with z<1.5 and i{sup ′}≲24.0 mag have a small systematic offset of |Δz|≲0.2, 1σ scatter 0.03<σ{sub Δz}<0.06, and less than 4.0% of catastrophic failures. We also compare with the CFHTLenS photometric redshifts and find that ours are more reliable at z≳0.6 because of the inclusion of the near-infrared bands. In particular, including the Y-band data can improve the accuracy at z∼1.0--2.0 because the location of the 4000 Å break is better constrained. The Y-band images, the multiband photometry catalog, and the photometric redshifts are released at http://astro.pku.edu.cn/astro/data/DYI.html.

79 ASTRONOMY AND ASTROPHYSICS↗

Deep Generative Modeling of Periodic Variable Stars Using Physical Parameters

The ability to generate physically plausible ensembles of variable sources is critical to the optimization of time domain survey cadences and the training of classification models on data sets with few to no labels. Traditional data augmentation techniques expand training sets by reenvisioning observed exemplars, seeking to simulate observations of specific training sources under different (exogenous) conditions. Unlike fully theory-driven models, these approaches do not typically allow principled interpolation nor extrapolation. Moreover, the principal drawback of theory-driven models lies in the prohibitive computational cost of simulating source observables from ab initio parameters. In this work, we propose a computationally tractable machine learning approach to generate realistic light curves of periodic variables capable of integrating physical parameters and variability classes as inputs. Our deep generative model, inspired by the transparent latent space generative adversarial networks, uses a variational autoencoder (VAE) architecture with temporal convolutional network layers, trained using the OGLE-III optical light curves and physical characteristics (e.g., effective temperature and absolute magnitude) from Gaia DR2. A test using the temperature–shape relationship of RR Lyrae demonstrates the efficacy of our generative “physics-enhanced latent space VAE” (PELS-VAE) model. Such deep generative models, serving as nonlinear nonparametric emulators, present a novel tool for astronomers to create synthetic time series over arbitrary cadences.

79 ASTRONOMY AND ASTROPHYSICS↗