Search NASA⌕ Search

SEARCH · Search NASA

Results for “Deep generative model”

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 775 records · Page 43

Modeling laser-driven ion acceleration with deep learning

Developments in machine learning promise to ameliorate some of the challenges of modeling complex physical systems through neural-network-based surrogate models. High-intensity, short-pulse lasers can be used to accelerate ions to mega-electronvolt energies, but to model such interactions requires computationally expensive techniques such as particle-in-cell simulations. Multilayer neural networks allow one to take a relatively sparse ensemble of simulations and generate a surrogate model that can be used to rapidly search the parameter space of interest. In this study, we created an ensemble of over 1,000 simulations modeling laser-driven ion acceleration and developed a surrogate to study the resulting parameter space. A neural-network-based approach allows for rapid feature discovery not possible for traditional parameter scans given the computational cost. A notable observation made during this study was the dependence of ion energy on the pre-plasma gradient length scale. While this methodology harbors great promise for ion acceleration, it has ready application to all topics in which large-scale parameter scans are restricted by significant computational cost or relatively large, but sparse, domains.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Machine Learning‐Assisted Microearthquake Location Workflow for Monitoring the Newberry Enhanced Geothermal System

Abstract Enhanced geothermal systems (EGS) offer a sustainable energy source but face challenges in accurately locating microearthquakes induced during reservoir stimulation. Locating these microearthquakes provides reliable feedback on the stimulation progress. Current deep learning methods for locating earthquakes require extensive data sets for training, which is problematic as detected microearthquakes are often limited. To address the scarcity of training data, we propose a practical workflow using probabilistic multilayer perceptron (PMLP) which predicts microearthquake locations from cross‐correlation time lags in waveforms. Utilizing a 3D velocity model of Newberry site derived from ambient noise interferometry, we generate numerous synthetic microearthquakes and 3D acoustic waveforms for PMLP training. Accurate synthetic tests prompt us to apply the trained network to the 2012 and 2014 stimulation field waveforms. To enhance the accuracy of source localization, we carefully handpick the P‐arrival times. Predictions on the 2012 stimulation data set show major microseismic activity at depths of 0.5–1.2 km, correlating with a known casing leakage scenario. In the 2014 data set, the majority of predictions concentrate at 2.0–2.9 km depths, consistent with results obtained from conventional physics‐based inversion, and align with the presence of natural fractures from 2.0 to 2.7 km. We validate our findings by comparing the synthetic and field picks, demonstrating a satisfactory match for the first arrivals. By combining the benefits of quick inference speeds and accurate location predictions, we demonstrate the feasibility of using realistic synthetic data set to locate microseismicity for EGS monitoring.

15 GEOTHERMAL ENERGY↗

Decarbonizing US passenger vehicle transport under electrification and automation uncertainty has a travel budget

Abstract The transportation sector is at the beginning of a transition represented by electrification, shared mobility, and automation, which could lead to either increases or decreases in total travel and energy use. Understanding the factors enabling deep decarbonization of the passenger vehicle sector is essential for planning the required infrastructure investments and technology adoption policies. We examine the requirements for meeting carbon reduction targets of 80% and higher for passenger vehicle transport in the United States (US) by midcentury under uncertainty. We model the changes needed in vehicle electrification, electricity carbon intensity, and travel demand. Since growth in fleet penetration of electric vehicles (EVs) is constrained by fleet stock turnover, we estimate the EV penetration rates needed to meet climate targets. We find for a base case level of passenger vehicle travel, midcentury deep decarbonization of US passenger transport is conditional on reducing the electricity generation carbon intensity to close to zero along with electrification of about 67% or 84% of vehicle travel to meet decarbonization targets of 80% or 90%, respectively. Higher electricity generation carbon intensity and degraded EV fuel economy due to automation would require higher levels of fleet electrification and/or further constrain the total vehicle travel allowable. Transportation deep decarbonization not only depends on electricity decarbonization, but also has a total travel budget, representing a maximum total vehicle travel threshold that still enables meeting a midcentury climate target. This makes encouraging ride sharing, reducing total vehicle travel, and increasing fuel economy in both human-driven and future automated vehicles increasingly important to deep decarbonization.

Alarfaj, Abdullah F. (ORCID:0000000157360662)↗

Triggering of the largest Deccan eruptions by the Chicxulub impact

New constraints on the timing of the Cretaceous- Paleogene mass extinction and the Chicxulub impact, together with a particularly voluminous and apparently brief eruptive pulse toward the end of the "main-stage" eruptions of the Deccan continental flood basalt province suggest that these three events may have occurred within less than about a hundred thousand years of each other. Partial melting induced by the Chicxulub event does not provide an energetically plausible explanation for this coincidence, and both geochronologic and magnetic-polarity data show that Deccan volcanism was under way well before Chicxulub/Cretaceous-Paleogene time. However, historical data document that eruptions from existing volcanic systems can be triggered by earthquakes. Seismic modeling of the ground motion due to the Chicxulub impact suggests that the impact could have generated seismic energy densities of order 0.1-1.0 J/m 3 throughout the upper ~200 km of Earth's mantle, sufficient to trigger volcanic eruptions worldwide based upon comparison with historical examples. Triggering may have been caused by a transient increase in the effective permeability of the existing deep magmatic system beneath the Deccan province, or mantle plume "head." It is therefore reasonable to hypothesize that the Chicxulub impact might have triggered the enormous Poladpur, Ambenali, and Mahabaleshwar (Wai Subgroup) lava flows, which together may account for >70% of the Deccan Traps main-stage eruptions. This hypothesis here is consistent with independent stratigraphic, geochronologic, geochemical, and tectonic constraints, which combine to indicate that at approximately Chicxulub/Cretaceous- Paleogene time, a huge pulse of mantle plume-derived magma passed through the crust with little interaction and erupted to form the most extensive and voluminous lava flows known on Earth. High-precision radioisotopic dating of the main-phase Deccan flood basalt formations may be able either to confirm or reject this hypothesis, which in turn might help to determine whether this singular outburst within the Deccan Traps (and possibly volcanic eruptions worldwide) contributed significantly to the Cretaceous-Paleogene extinction.

58 GEOSCIENCES↗

NASA’s first ground-based Galactic Cosmic Ray Simulator: Enabling a new era in space radiobiology research

With exciting new NASA plans for a sustainable return to the moon, astronauts will once again leave Earth’s protective magnetosphere only to endure higher levels of radiation from galactic cosmic radiation (GCR) and the possibility of a large solar particle event (SPE). Gateway, lunar landers, and surface habitats will be designed to protect crew against SPEs with vehicle optimization, storm shelter concepts, and/or active dosimetry; however, the ever penetrating GCR will continue to pose the most significant health risks especially as lunar missions increase in duration and as NASA sets its aspirations on Mars. The primary risks of concern include carcinogenesis, central nervous system (CNS) effects resulting in potential in-mission cognitive or behavioral impairment and/or late neurological disorders, degenerative tissue effects including circulatory and heart disease, as well as potential immune system decrements impacting multiple aspects of crew health. Characterization and mitigation of these risks requires a significant reduction in the large biological uncertainties of chronic (low-dose rate) heavy-ion exposures and the validation of countermeasures in a relevant space environment. Historically, most research on understanding space radiation-induced health risks has been performed using acute exposures of monoenergetic single-ion beams. However, the space radiation environment consists of a wide variety of ion species over a broad energy range. Using the fast beam switching and controls systems technology recently developed at the NASA Space Radiation Laboratory (NSRL) at Brookhaven National Laboratory, a new era in radiobiological research is possible. NASA has developed the “GCR Simulator” to generate a spectrum of ion beams that approximates the primary and secondary GCR field experienced at human organ locations within a deep-space vehicle. The majority of the dose is delivered from protons (approximately 65%–75%) and helium ions (approximately 10%–20%) with heavier ions (Z ≥ 3) contributing the remainder. The GCR simulator exposes state-of-the art cellular and animal model systems to 33 sequential beams including 4 proton energies plus degrader, 4 helium energies plus degrader, and the 5 heavy ions of C, O, Si, Ti, and Fe. A polyethylene degrader system is used with the 100 MeV/n H and He beams to provide a nearly continuous distribution of low-energy particles. A 500 mGy exposure, delivering doses from each of the 33 beams, requires approximately 75 minutes. To more closely simulate the low-dose rates found in space, sequential field exposures can be divided into daily fractions over 2 to 6 weeks, with individual beam fractions as low as 0.1 to 0.2 mGy. In the large beam configuration (60 × 60 cm 2 ), 54 special housing cages can accommodate 2 to 3 mice each for an approximately 75 min duration or 15 individually housed rats. On June 15, 2018, the NSRL made a significant achievement by completing the first operational run using the new GCR simulator. This paper discusses NASA’s innovative technology solution for a ground-based GCR simulator at the NSRL to accelerate our understanding and mitigation of health risks faced by astronauts. Ultimately, the GCR simulator will require validation across multiple radiogenic risks, endpoints, doses, and dose rates.

59 BASIC BIOLOGICAL SCIENCES↗

Deep learning-assisted modeling for χ (2) nonlinear optics

Modeling second-order (χ(2)) nonlinear optical processes remains computationally expensive due to the need to resolve fast field oscillations and simulate wave propagation using methods such as the split-step Fourier method (SSFM). This can become a bottleneck in real-time applications, such as high-repetition-rate laser systems requiring rapid feedback and control. We present a long short-term memory-based surrogate model trained on SSFM simulations generated from a start-to-end model of the photocathode drive laser at SLAC National Accelerator Laboratory’s Linac Coherent Light Source II. The model achieves over 250× speedup while maintaining high fidelity, enabling future real-time optimization and laying the foundation for data-integrated modeling frameworks and digital twins of laser systems.

Accelerator Physics (physics.acc-ph)↗

Modeling the value of integrated U.S. and Canadian power sector expansion

The U.S.-Canadian power system has evolved into a highly integrated grid. Cross-border transmission and coordination of system operations create an interconnected power system with combined imports and exports of electricity of greater than 77 TWh per year. Currently, more than 5 GW of new international transmission lines are in various stages of permitting and development. These transmission lines may enable even greater integration and coordination of the U.S. and Canadian systems, which can in turn increase the reliability and flexibility of North America's electricity grid and help address challenges associated with integrating high levels of variable renewables. Using a version of the National Renewable Energy Laboratory's Regional Energy Deployment System (ReEDS) model that incorporates Canada, this analysis quantifies the differences in the evolution of the power system under scenarios in which cross-border transmission capacity is restricted to today's levels, and scenarios in which new transmission is less restricted. These impacts are analyzed under a 'business-as-usual' reference scenario and a scenario in which deep cuts in power sector carbon dioxide emissions levels are achieved. A set of key impact metrics is analyzed, including 1) the composition of generating capacity by technology, 2) system costs, 3) wholesale electricity prices, 4) international electricity exports and imports, 5) transmission capacity, and 6) carbon dioxide emission levels. When new cross-border transmission is not allowed, the United States needs additional capacity (primarily natural gas and renewable energy) to meet domestic needs, while total Canadian capacity is lower because less capacity is needed to export to the United States. This effect is amplified under the carbon cap scenario. Impacts vary on a regional basis, largely due to the different relative sizes of the generation portfolio between countries and regions and the relative impact from cross-border electricity trade. The total impact from restricting cross-border trade on carbon emissions and average wholesale electricity prices is limited, due to the relative size of the domestic power systems and the cross-border trade volume. Lastly, cross-border transmission capacity is projected to more than double under the unrestricted transmission capacity scenarios, which exceeds the rate of projected domestic transmission capacity additions in each country.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Understanding and Leveraging the I/O Patterns of Emerging Machine Learning Analytics

The scientific community is currently experiencing unprecedented amounts of data generated by cutting-edge science facilities. Soon facilities will be producing up to 1 PB/s which will force scientist to use more autonomous techniques to learn from the data. The adoption of machine learning methods, like deep learning techniques, in large-scale workflows comes with a shift in the workflow’s computational and I/O patterns. These changes often include iterative processes and model architecture searches, in which datasets are analyzed multiple times in different formats with different model configurations in order to find accurate, reliable and efficient learning models. This shift in behavior brings changes in I/O patterns at the application level as well at the system level. These changes also bring new challenges for the HPC I/O teams, since these patterns contain more complex I/O workloads. In this paper we discuss the I/O patterns experienced by emerging analytical codes that rely on machine learning algorithms and highlight the challenges in designing efficient I/O transfers for such workflows. We comment on how to leverage the data access patterns in order to fetch in a more efficient way the required input data in the format and order given by the needs of the application and how to optimize the data path between collaborative processes. We will motivate our work and show performance gains with a study case of medical applications.

Gainaru, Ana↗

Machine learning for seismic low-frequency extrapolation

The cycle-skipping problem that plagues full waveform inversion (FWI) can be at least partially mitigated if low frequencies (which encode the kinematics of wave propagation in seismic data) are recorded. However, seismic sources and receivers are band-limited, so seismic data does not generally include signals down to 0 Hz. To improve our ability to solve the seismic inverse problem, one can synthesize this missing low-frequency (LF) content from the recorded high-frequency (HF) data using machine learning (ML) models. Deep learning models such as convolutional neural networks (CNNs) demonstrate impressive ability to perform low frequency extrapolation. However, such models require powerful hardware (GPU machines) and careful training. We assess the extrapolation capabilities of three different ML models that do not require GPU machines, namely, random forest, Gaussian process regression and gradient boosting, on both synthetic and real data. Experimental results on two synthetic data sets (generated from a low velocity lens embedded in a homogeneous medium, and the Marmousi model) demonstrate that FWI applied to the extrapolated data consistently improves inversion accuracy relative to FWI applied to the original data sets that do not contain low frequencies. Application of low-frequency extrapolation to real data from the Northwest Shelf of Australia demonstrates that tree-based ML models such as gradient boosting can outperform CNNs in terms of both accuracy and computational cost on non-GPU architectures.

58 GEOSCIENCES↗

The expressivity of classical and quantum neural networks on entanglement entropy

Abstract Analytically continuing the von Neumann entropy from Rényi entropies is a challenging task in quantum field theory. While then-th Rényi entropy can be computed using the replica method in the path integral representation of quantum field theory, the analytic continuation can only be achieved for some simple systems on a case-by-case basis. In this work, we propose a general framework to tackle this problem using classical and quantum neural networks with supervised learning. We begin by studying several examples with known von Neumann entropy, where the input data is generated by representing$${\text {Tr}}\rho _A^n$$ Tr ρ A n with a generating function. We adopt KerasTuner to determine the optimal network architecture and hyperparameters with limited data. In addition, we frame a similar problem in terms of quantum machine learning models, where the expressivity of the quantum models for the entanglement entropy as a partial Fourier series is established. Our proposed methods can accurately predict the von Neumann and Rényi entropies numerically, highlighting the potential of deep learning techniques for solving problems in quantum information theory.

Physics↗

MIDA: A Multimodal Imaging-Based Detailed Anatomical Model of the Human Head and Neck

Computational modeling and simulations are increasingly being used to complement experimental testing for analysis of safety and efficacy of medical devices. Multiple voxel- and surface-based whole- and partial-body models have been proposed in the literature, typically with spatial resolution in the range of 1–2 mm and with 10–50 different tissue types resolved. We have developed a multimodal imaging-based detailed anatomical model of the human head and neck, named “MIDA”. The model was obtained by integrating three different magnetic resonance imaging (MRI) modalities, the parameters of which were tailored to enhance the signals of specific tissues: i) structural T1- and T2-weighted MRIs; a specific heavily T2-weighted MRI slab with high nerve contrast optimized to enhance the structures of the ear and eye; ii) magnetic resonance angiography (MRA) data to image the vasculature, and iii) diffusion tensor imaging (DTI) to obtain information on anisotropy and fiber orientation. The unique multimodal high-resolution approach allowed resolving 153 structures, including several distinct muscles, bones and skull layers, arteries and veins, nerves, as well as salivary glands. The model offers also a detailed characterization of eyes, ears, and deep brain structures. A special automatic atlas-based segmentation procedure was adopted to include a detailed map of the nuclei of the thalamus and midbrain into the head model. The suitability of the model to simulations involving different numerical methods, discretization approaches, as well as DTI-based tensorial electrical conductivity, was examined in a case-study, in which the electric field was generated by transcranial alternating current stimulation. The voxel- and the surface-based versions of the models are freely available to the scientific community.

59 BASIC BIOLOGICAL SCIENCES↗

Assessing and benchmarking the fidelity of posterior inference methods for astrophysics data analysis

In this era of large and complex astronomical survey data, interpreting, validating, and comparing inference techniques becomes increasingly difficult. This is particularly critical for emerging inference methods like Simulation-Based Inference (SBI), which offer significant speedup potential and posterior modeling flexibility, especially when deep learning is incorporated. We present a study to assess and compare the performance and uncertainty prediction capability of Bayesian inference algorithms – from traditional MCMC sampling of analytic functions to deep learning-enabled SBI. We focus on testing the capacity of hierarchical inference modeling in those scenarios. Before we extend this study to cosmology, we first use astrophysical simulation data to ensure interpretability. We demonstrate a probabilistic programming implementation of hierarchical and non-hierarchical Bayesian inference using simulations derived from the DeepBench software library, a benchmarking tool developed by our group that generates simple and controllable astrophysical objects from first principles. This study will enable astronomers and physicists to harness the inference potential of these methods with confidence.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Power Production, Inter- and Intra-Array Wake Losses from the U.S. East Coast Offshore Wind Energy Lease Areas

There is an urgent need to develop accurate predictions of power production, wake losses and array–array interactions from multi-GW offshore wind farms in order to enable developments that maximize power benefits, minimize levelized cost of energy and reduce investment uncertainty. New, climatologically representative simulations with the Weather Research and Forecasting (WRF) model are presented and analyzed to address these research needs with a specific focus on offshore wind energy lease areas along the U.S. east coast. These, uniquely detailed, simulations are designed to quantify important sources of wake-loss projection uncertainty. They sample across different wind turbine deployment scenarios and thus span the range of plausible installed capacity densities (ICDs) and also include two wind farm parameterizations (WFPs; Fitch and explicit wake parameterization (EWP)) and consider the precise WRF model release used. System-wide mean capacity factors for ICDs of 3.5 to 6.0 MWkm−2 range from 39 to 45% based on output from Fitch and 50 to 55% from EWP. Wake losses are 27–37% (Fitch) and 11–19% (EWP). The discrepancy in CF and wake losses from the two WFPs derives from two linked effects. First, EWP generates a weaker ‘deep array effect’ within the largest wind farm cluster (area of 3675 km2), though both parameterizations indicate substantial within-array wake losses. If 15 MW wind turbines are deployed at an ICD of 6 MWkm−2 the most heavily waked wind turbines generate an average of only 32–35% of the power of those that experience the freestream (undisturbed) flow. Nevertheless, there is no evidence for saturation of the resource. The wind power density (electrical power generation per unit of surface area) increases with ICD and lies between 2 and 3 Wm−2. Second, EWP also systematically generates smaller whole wind farm wakes. Sampling across all offshore wind energy lease areas and the range of ICD considered, the whole wind farm wake extent for a velocity deficit of 5% is 1.18 to 1.38 times larger in simulations with Fitch. Over three-quarters of the variability in normalized wake extents is attributable to variations in freestream wind speeds, turbulent kinetic energy and boundary layer depth. These dependencies on meteorological parameters allow for the development of computationally efficient emulators of wake extents from Fitch and EWP.

17 WIND ENERGY↗

Informed Feature Selection for Data Clustering of CSP Plant Production

To make concentrating solar power (CSP) more cost competitive, rigourous optimizations must be run to improve plant design and operations. However, these optimizaitons rely on time consuming annual simulations that solve an electricity dispatch scheduling problem to maximize plant revenue. To reduce the runtime of annual dispatch simulations of CSP plants, a data clustering approach is utilized. This approach assumes that like days of revenue and electricity generation can be identified using weather and price data. Although weather and price are important factors for electricity production, this work investigates how thermal energy storage (TES) inventory at the beginning of a day, denoted as Si, can be used as a supplemental feature to group like days. A framework for creating and training a deep neural network to predict Si is proposed. This model is validated and assessed using eleven sets of testing data that were not used during training. Then, the data clustering approach is performed three seperate times with features of weather and price along with either Si from the neural network, Si from the full annual simulation, or no Si. Ultimately, the results suggest that using Si as an additional clustering feature improves the data clustering simulation accuracy by 1.4%.

Tuman, Matthew J. (ORCID:000900038772051X)↗

DeepCwind Consortium Research Program: January 15, 2010 - March 31, 2013 (Final Technical Report)

This is the final technical report for the U.S. Department of Energy-funded program, DE-0002981: DeepCwind Consortium Research Program. The project objective was the partial validation of coupled models and optimization of materials for offshore wind structures. The United States has a great opportunity to harness an indigenous abundant renewable energy resource: offshore wind. In 2010, the National Renewable Energy Laboratory (NREL) estimated there to be over 4,000 GW of potential offshore wind energy found within 50 nautical miles of the US coastlines (Musial and Ram, 2010). The US Energy Information Administration reported the total annual US electric energy generation in 2010 was 4,120 billion kilowatt-hours (equivalent to 470 GW) (US EIA, 2011), slightly more than 10% of the potential offshore wind resource. In addition, deep water offshore wind is the dominant US ocean energy resource available comprising 75% of the total assessed ocean energy resource as compared to wave and tidal resources (Musial, 2008). Through these assessments it is clear offshore wind can be a major contributor to US energy supplies. The caveat to capturing offshore wind along many parts of the US coast is deep water. Nearly 60%, or 2,450 GW, of the estimated US offshore wind resource is located in water depths of 60 m or more (Musial and Ram, 2010). At water depths over 60 m building fixed offshore wind turbine foundations, such as those found in Europe, is likely economically infeasible (Musial et al., 2006). Therefore floating wind turbine technology is seen as the best option for extracting a majority of the US offshore wind energy resource. Volume 1 - Test Site; Volume 2 - Coupled Models; and Volume 3 - Composite Materials.

17 WIND ENERGY↗

Using Ultrasound Image Augmentation and Ensemble Predictions to Prevent Machine-Learning Model Overfitting

Deep learning predictive models have the potential to simplify and automate medical imaging diagnostics by lowering the skill threshold for image interpretation. However, this requires predictive models that are generalized to handle subject variability as seen clinically. Here, we highlight methods to improve test accuracy of an image classifier model for shrapnel identification using tissue phantom image sets. Using a previously developed image classifier neural network—termed ShrapML—blind test accuracy was less than 70% and was variable depending on the training/test data setup, as determined by a leave one subject out (LOSO) holdout methodology. Introduction of affine transformations for image augmentation or MixUp methodologies to generate additional training sets improved model performance and overall accuracy improved to 75%. Further improvements were made by aggregating predictions across five LOSO holdouts. This was done by bagging confidences or predictions from all LOSOs or the top-3 LOSO confidence models for each image prediction. Top-3 LOSO confidence bagging performed best, with test accuracy improved to greater than 85% accuracy for two different blind tissue phantoms. This was confirmed by gradient-weighted class activation mapping to highlight that the image classifier was tracking shrapnel in the image sets. Overall, data augmentation and ensemble prediction approaches were suitable for creating more generalized predictive models for ultrasound image analysis, a critical step for real-time diagnostic deployment.

60 APPLIED LIFE SCIENCES↗

Evolution of linear perturbations in Lemaítre-Tolman-Bondi void models

We study the evolution of linear perturbations in a Lemaítre-Tolman-Bondi (LTB) void model with realistic cosmological initial conditions. Linear perturbation theory in LTB models is substantially more complicated than in standard Friedmann universes as the inhomogeneous background causes gauge-invariant perturbations couple at first order. As shown by Clarkson et al. (2009) [1], the evolution is constrained by a system of linear partial differential equations which need to be integrated numerically. We present a new numerical scheme using finite element methods to solve this equation system and generate scalar initial conditions based on Gaussian random fields with an underlying power spectrum for the Bardeen potential. After spherical harmonic decomposition, the initial fluctuations are propagated in time and estimates of angular power spectra of each gauge invariant variable are computed as functions of redshift. This allows to analyse the coupling strength in a statistical way. We find significant couplings up to 25% for large and deep voids of Gpc scale as required to fit the distance redshift relations of SNe.

79 ASTRONOMY AND ASTROPHYSICS↗

QuGAN: A Quantum State Fidelity based Generative Adversarial Network

In the recent years, Generative Adversarial Networks (GANs) have been arguably one of the largest strides forward in Deep Learning. Many papers illustrate the use of GANs to accomplish extremely impressive goals, such as text-to-image or image augmentation. Specifically, GANs have seen this success in the computer vision domain. However, GANs are not without their own set of problems. GANs are computationally expensive, sometimes computationally prohibitive, and can suffer a multitude of convergence problems. As research on classical GANs continues to push the topic further, a branch of GANs, namely Quantum GANs, has seen research interest in the past years. In this work, we intend to push this research further with an illustration of a Quantum GAN architecture that provide stable convergence of the model and is extended onto real data sets. Furthermore, unlike many other Quantum GANs out there, our model's GAN architecture runs the discriminator and the generator primarily on Quantum hardware through the use of a Quantum-based similarity metric. When compared to the very few other Quantum GAN papers, our architecture leads to significantly better results in almost all aspects.

Stein, Samuel A.↗