Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Boosting”

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 451 records · Page 25
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Effect of Phosphorus Modulation in Iron Single‐Atom Catalysts for Peroxidase Mimicking

Abstract Fe–N–C single‐atom catalysts (SACs) exhibit excellent peroxidase (POD)‐like catalytic activity, owing to their well‐defined isolated iron active sites on the carbon substrate, which effectively mimic the structure of natural peroxidase's active center. To further meet the requirements of diverse biosensing applications, SAC POD‐like activity still needs to be continuously enhanced. Herein, a phosphorus (P) heteroatom is introduced to boost the POD‐like activity of Fe–N–C SACs. A 1D carbon nanowire (FeNCP/NW) catalyst with enriched Fe–N 4 active sites is designed and synthesized, and P atoms are doped in the carbon matrix to affect the Fe center through long‐range interaction. The experimental results show that the P‐doping process can boost the POD‐like activity more than the non‐P‐doped one, with excellent selectivity and stability. The mechanism analysis results show that the introduction of P into SAC can greatly enhance POD‐like activity initially, but its effect becomes insignificant with increasing amount of P. As a proof of concept, FeNCP/NW is employed in an enzyme cascade platform for highly sensitive colorimetric detection of the neurotransmitter acetylcholine.

Ding, Shichao↗
DOE OSTI2023

Unveiling the Morphological and Physical Mechanism of Burn–in Loss Alleviation by Ternary Matrix Toward Stable and Efficient All–Polymer Solar Cells

All–polymer solar cells (All–PSCs) are considered the most promising candidate in achieving both efficient and stable organic photovoltaic devices, yet the field has rarely presented an in–depth understanding of corresponding device stability while efficiency is continuously boosted via the innovation of polymer acceptors. Herein, a ternary matrix is built for all–PSCs with optimized morphology, improved film ductility and importantly, boosted efficiency and better operational stability than its parental binary counterparts, as a platform to study the underlying mechanism. The target system PQM–Cl:PTQ10:PY–IT (0.8:0.2:1.2) exhibits an alleviated burn–in loss of morphology and efficiency under light soaking, which supports its promoted device lifetime. The comprehensive characterizations of fresh and light–soaked active layers lead to a clear illustration of opposite morphological and physical degradation direction of PQM–Cl and PTQ10, thus resulting in a delicate balance at the optimal ternary system. Specifically, the enlarging tendency of PQM–Cl and shrinking preference of PTQ10 in terms of phase separation leads to a stable morphology in their mixing phase; the hole transfer kinetics of PQM–Cl:PY–IT host is stabilized by incorporating PTQ10. Finally, this work succeeds in reaching a deep insight into all–PSC's stability promotion by a rational ternary design, which booms the prospect of gaining high–performance all–PSCs.

14 SOLAR ENERGY↗
DOE OSTI2023

Precise Tailoring of Lithium-Ion Transport for Ultralong-Cycling Dendrite-Free All-Solid-State Lithium Metal Batteries

All-solid-state lithium metal batteries can address crucial challenges regarding insufficient battery cycling life and energy density. The demonstration of long-cycling dendrite-free all-solid-state lithium metal batteries requires precise tailoring of lithium-ion transport of solid-state electrolytes (SSEs). Here, in this work, a proof of concept is reported for precise tailoring of lithium-ion transport of a halide SSE, Li 3 InCl 6 , including intragranular (within grains) but also intergranular (between grains) lithium-ion transport. Lithium-ion migration tailoring mechanism in crystals is developed by unexpected enhanced Li, In, and Cl vacancy populations and lower energy barrier for hopping. The lithium-ion transport tailoring mechanism between the grains is determined by the elimination of voids between grains and the formation of unexpected supersonic conducting grain boundaries, boosting the lithium dendrite suppression ability of SSE. Due to boosted lithium-ion conduction and dendrite-suppression ability, the all-solid-state lithium metal batteries coupled with Ni-rich LiNi 0.83 Co 0.12 Mn 0.05 O 2 cathodes and lithium metal anodes demonstrate breakthroughs in electrochemical performance by achieving extremely long cycling life at a high current density of 0.5 C (2000 cycles, 93.7% capacity retention). This concept of precise tailoring of lithium-ion transport provides a cost, time, and energy efficient solution to conquer the remaining challenges in all-solid-state lithium-metal batteries for fast developing electric vehicle markets.

25 ENERGY STORAGE↗
DOE OSTI2020

Reversible (De)Intercalation of Hydrated Zn 2+ in Mg 2+ -Stabilized V 2 O 5 Nanobelts with High Areal Capacity

The rechargeable aqueous zinc ion battery (ZIB) is regarded as one of the most promising candidates for large-scale energy storage applications due to its low-cost and eco-friendly properties. However, the development of a suitable cathode operating with high areal capacity and uncovering the relevant reaction mechanisms remain challenging. Herein, the application of Mg 0.26 V 2 O 5 ∙0.73H 2 O (MVO) nanobelts as a ZIB cathode is demonstrated. In situ FT-IR reveals the shift of OH stretching from 3350 cm -1 to 3200 cm -1 , corresponding to the hydration shell of Zn 2+ , while in situ Raman suggests the interlayer charges creening effect, which would boost the intercalation of hydrated Zn 2+ . Density function theory reveals that the hydrated Zn 2+ can lower the Coulombic repulsion at the electrode-electrolyte interface and circumvents the desolvation penalty of hydrated Zn 2+ during the (de)intercalation process. Additionally, excellent structure stability and large interlayer spacing guarantee the highly reversible (de)intercalation of hydrated Zn 2+ . Therefore, the MVO nanobelts exhibit a high areal capacity of 2.12 mAh cm -2 at 0.05 A g -1 , outstanding cycling stability of 2500 cycles at 10 A g -1 with a mass loading of 5 mg cm -2 . Finally, it is believed that the use of hydrated intercalation charge carriers will boost further studies in other multivalent rechargeable batteries.

25 ENERGY STORAGE↗
DOE OSTI2023

Unidirectional Sidechain Engineering to Construct Dual‐Asymmetric Acceptors for 19.23 % Efficiency Organic Solar Cells with Low Energy Loss and Efficient Charge Transfer

Abstract Achieving both high open‐circuit voltage ( V oc ) and short‐circuit current density ( J sc ) to boost power‐conversion efficiency (PCE) is a major challenge for organic solar cells (OSCs), wherein high energy loss ( E loss ) and inefficient charge transfer usually take place. Here, three new Y‐series acceptors of mono‐asymmetric asy‐YC11 and dual‐asymmetric bi‐asy‐YC9 and bi‐asy‐YC12 are developed. They share the same asymmetric D 1 AD 2 (D 1 =thieno[3,2‐ b ]thiophene and D 2 =selenopheno[3,2‐ b ]thiophene) fused‐core but have different unidirectional sidechain on D 1 side, allowing fine‐tuned molecular properties, such as intermolecular interaction, packing pattern, and crystallinity. Among the binary blends, the PM6 : bi‐asy‐YC12 one has better morphology with appropriate phase separation and higher order packing than the PM6 : asy‐YC9 and PM6 : bi‐asy‐YC11 ones. Therefore, the PM6 : bi‐asy‐YC12‐based OSCs offer a higher PCE of 17.16 % with both high V oc and J sc , due to the reduced E loss and efficient charge transfer properties. Inspired by the high V oc and strong NIR‐absorption, bi‐asy‐YC12 is introduced into efficient binary PM6 : L8‐BO to construct ternary OSCs. Thanks to the broadened absorption, optimized morphology, and furtherly minimized E loss , the PM6 : L8‐BO : bi‐asy‐YC12‐based OSCs achieve a champion PCE of 19.23 %, which is one of the highest efficiencies among these annealing‐free devices. Our developed unidirectional sidechain engineering for constructing bi‐asymmetric Y‐series acceptors provides an approach to boost PCE of OSCs.

Chemistry↗
DOE OSTI2020

Super resolution for root imaging

Premise High‐resolution cameras are very helpful for plant phenotyping as their images enable tasks such as target vs. background discrimination and the measurement and analysis of fine above‐ground plant attributes. However, the acquisition of high‐resolution images of plant roots is more challenging than above‐ground data collection. An effective super‐resolution (SR) algorithm is therefore needed for overcoming the resolution limitations of sensors, reducing storage space requirements, and boosting the performance of subsequent analyses. Methods We propose an SR framework for enhancing images of plant roots using convolutional neural networks. We compare three alternatives for training the SR model: (i) training with non‐plant‐root images, (ii) training with plant‐root images, and (iii) pretraining the model with non‐plant‐root images and fine‐tuning with plant‐root images. The architectures of the SR models were based on two state‐of‐the‐art deep learning approaches: a fast SR convolutional neural network and an SR generative adversarial network. Results In our experiments, we observed that the SR models improved the quality of low‐resolution images of plant roots in an unseen data set in terms of the signal‐to‐noise ratio. We used a collection of publicly available data sets to demonstrate that the SR models outperform the basic bicubic interpolation, even when trained with non‐root data sets. Discussion The incorporation of a deep learning–based SR model in the imaging process enhances the quality of low‐resolution images of plant roots. We demonstrate that SR preprocessing boosts the performance of a machine learning system trained to separate plant roots from their background. Our segmentation experiments also show that high performance on this task can be achieved independently of the signal‐to‐noise ratio. We therefore conclude that the quality of the image enhancement depends on the desired application.

Ruiz‐Munoz, Jose F.↗
DOE OSTI2022

Direct Higgs-top CP-phase measurement with $t\overline{t}h$ at the 14 TeV LHC and 100 TeV FCC

The study of the Higgs boson’s properties is a cornerstone of the LHC and future collider programs. In this paper, we examine the potential to directly probe the Higgs-top interaction strength and CP-structure in the $t\overline{t}h$ channel with the Higgs boson decaying to bottom-quark pairs and top-quarks in the di-leptonic mode. We adopt the BDRS algorithm to tag the boosted Higgs and exploit the M 2 -assisted reconstruction to compute observables sensitive to the CP-phase at the $t\bar{t}$ rest frame, where the new physics sensitivity can be enhanced. Performing a side-band analysis at the LHC to control the continuum $t\bar{t}b\bar{b}$ background, we find that the Higgs-top strength and CP-phase can be probed up to δ κt ≲ 20% and |a| ≲ 36° at 95% CL, respectively. We also derive that a similar analysis at a 100 TeV future collider could further improve the precision to δ κt ≲ 1% and |a| ≲ 1.5° where the CP-odd observables play a crucial role, boosting the sensitivity on the CP-phase

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2024

Null Raychaudhuri: canonical structure and the dressing time

Abstract We initiate a study of gravity focusing on generic null hypersurfaces, non-perturbatively in the Newton coupling. We present an off-shell account of the extended phase space of the theory, which includes the expected spin-2 data as well as spin-0, spin-1 and arbitrary matter degrees of freedom. We construct the charges and the corresponding kinematic Poisson brackets, employing a Beltrami parameterization of the spin-2 modes. We explicitly show that the constraint algebra closes, the details of which depend on the non-perturbative mixing between spin-0 and spin-2 modes. Finally we show that the spin zero sector encodes a notion of a clock, called dressing time, which is dynamical and conjugate to the constraint. It is well-known that the null Raychaudhuri equation describes how the geometric data of a null hypersurface evolve in null time in response to gravitational radiation and external matter. Our analysis leads to three complementary viewpoints on this equation. First, it can be understood as a Carrollian stress tensor conservation equation. Second, we construct spin-0, spin-2 and matter stress tensors that act as generators of null time reparametrizations for each sector. This leads to the perspective that the null Raychaudhuri equation can be understood as imposing that the sum of CFT-like stress tensors vanishes. Third, we solve the Raychaudhuri constraint non-perturbatively. The solution relates the dressing time to the spin-2 and matter boost charge operators. Finally we establish that the corner charge corresponding to the boost operator in the dressing time frame is monotonic. These results show that the notion of an observer can be thought of as emerging from the gravitational degrees of freedom themselves. We briefly mention that the construction offers new insights into focusing conjectures.

Physics↗
DOE OSTI2024

Constrained HRT Surfaces and their Entropic Interpretation

Abstract Consider two boundary subregionsAandBthat lie in a common boundary Cauchy surface, and consider also the associated HRT surfaceγ B forB. In that context, the constrained HRT surfaceγ A:B can be defined as the codimension-2 bulk surface anchored toAthat is obtained by a maximin construction restricted to Cauchy slices containingγ B . As a result,γ A:B is the union of two pieces,$$ {\gamma}_{A:B}^B $$ γ A : B B and$$ {\gamma}_{A:B}^{\overline{B}} $$ γ A : B B ¯ lying respectively in the entanglement wedges ofBand its complement$$ \overline{B} $$ B ¯ . Unlike the area$$ \mathcal{A}\left({\gamma}_A\right) $$ A γ A of the HRT surfaceγ A , at least in the semiclassical limit, the area$$ \mathcal{A}\left({\gamma}_{A:B}\right) $$ A γ A : B ofγ A:B commutes with the area$$ \mathcal{A}\left({\gamma}_B\right) $$ A γ B ofγ B . To study the entropic interpretation of$$ \mathcal{A}\left({\gamma}_{A:B}\right) $$ A γ A : B , we analyze the Rényi entropies of subregionAin a fixed-area state of subregionB. We use the gravitational path integral to show that then ≈1 Rényi entropies are then computed by minimizing$$ \mathcal{A}\left({\gamma}_A\right) $$ A γ A over spacetimes defined by a boost angle conjugate to$$ \mathcal{A}\left({\gamma}_B\right) $$ A γ B . In the case where the pieces$$ {\gamma}_{A:B}^B $$ γ A : B B and$$ {\gamma}_{A:B}^{\overline{B}} $$ γ A : B B ¯ intersect at a constant boost angle, a geometric argument shows that then ≈1 Rényi entropy is then given by$$ \frac{\mathcal{A}\left({\gamma}_{A:B}\right)}{4G} $$ A γ A : B 4 G . We discuss how then ≈1 Rényi entropy differs from the von Neumann entropy due to a lack of commutativity of then→ 1 andG →0 limits. We also discuss how the behaviour changes as a function of the width of the fixed-area state. Our results are relevant to some of the issues associated with attempts to use standard random tensor networks to describe time dependent geometries.

Physics↗
DOE OSTI2021

Jet tagging in the Lund plane with graph networks

The identification of boosted heavy particles such as top quarks or vector bosons is one of the key problems arising in experimental studies at the Large Hadron Collider. In this article, we introduce LundNet, a novel jet tagging method which relies on graph neural networks and an efficient description of the radiation patterns within a jet to optimally disentangle signatures of boosted objects from background events. We apply this framework to a number of different benchmarks, showing significantly improved performance for top tagging compared to existing state-of-the-art algorithms. We study the robustness of the LundNet taggers to non-perturbative and detector effects, and show how kinematic cuts in the Lund plane can mitigate overfitting of the neural network to model-dependent contributions. Finally, we consider the computational complexity of this method and its scaling as a function of kinematic Lund plane cuts, showing an order of magnitude improvement in speed over previous graph-based taggers.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

A new spin on the Weak Gravity Conjecture

The mild form of the Weak Gravity Conjecture states that quantum or higher-derivative corrections should decrease the mass of large extremal charged black holes at fixed charge. This allows extremal black holes to decay, unless protected by a symmetry (such as supersymmetry). We reformulate this conjecture as an integrated condition on the effective stress tensor capturing the effect of quantum or higher-derivative corrections. In addition to charged black holes, we also consider rotating BTZ black holes and show that this condition is satisfied as a consequence of the $\textit{c}$-theorem, proving a spinning version of the Weak Gravity Conjecture. We also apply our results to a five-dimensional boosted black string with higher-derivative corrections. The boosted black string has a BTZ×$S^2$ near-horizon geometry and, after Kaluza-Klein reduction, describes a four-dimensional charged black hole. Combining the spinning and charged Weak Gravity Conjecture we obtain positivity bounds on the five-dimensional Wilson coefficients that are stronger than those obtained from charged black holes alone.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Implications of the XENON1T excess on the dark matter interpretation

The dark matter interpretation for a recent observation of excessive electron recoil events at the XENON1T detector seems challenging because its velocity is not large enough to give rise to recoiling electrons of O(keV). Fast-moving or boosted dark matter scenarios are receiving attention as a remedy for this issue, rendering the dark matter interpretation a possibility to explain the anomaly. We investigate various scenarios where such dark matter of spin 0 and 1/2 interacts with electrons via an exchange of vector, axial-vector, pseudo-scalar, or scalar mediators. We find parameter values not only to reproduce the excess but to be consistent with existing bounds. Our study suggests that the scales of mass and coupling parameters preferred by the excess can be mostly affected by the type of mediator, and that significantly boosted dark matter can explain the excess depending on the mediator type and its mass choice. The method proposed in this work is general, and hence readily applicable to the interpretation of observed data in the dark matter direct detection experiment.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

Geometric entropies and their Hamiltonian flows

In holographic theories, the Hubeny-Rangamani-Takayanagi (HRT) area operator plays a key role in our understanding of the emergence of semiclassical Einstein-Hilbert gravity. When higher derivative corrections are included, the role of the area is instead played by a more general functional known as the geometric entropy. It is thus of interest to understand the flow generated by the geometric entropy on the classical phase space. In particular, the fact that the associated flow in Einstein-Hilbert or Jackiw-Teitelboim (JT) gravity induces a relative boost between the left and right entanglement wedges is deeply related to the fact that gravitational dressing promotes the von Neumann algebra of local fields in each wedge to type II. This relative boost is known as a boundary-condition-preserving (BCP) kink-transformation. In a general theory of gravity (with arbitrary higher-derivative terms), it is straightforward to show that the flow continues to take the above geometric form when acting on a spacetime where the HRT surface is the bifurcation surface of a Killing horizon. However, the form of the flow on other spacetimes is less clear. In this paper, we use the manifestly-covariant Peierls bracket to explore such flows in two-dimensional theories of JT gravity coupled to matter fields with higher derivative interactions. The results no longer take a purely geometric form and, instead, demonstrate new features that should be expected of such flows in general higher derivative theories. We also show how to obtain the above flows using Poisson brackets.

AdS-CFT correspondence↗
DOE OSTI2023

Evidence for the charge asymmetry in $pp$ → $t\bar{t}$ production at $\sqrt{s}$ = 13 TeV with the ATLAS detector

Inclusive and differential measurements of the top–antitop ($t\bar{t}$) charge asymmetry ${A}_{C}^{t\bar{t}}$ and the leptonic asymmetry ${A}_{C}^{\ell\bar{\ell}}$ are presented in proton–proton collisions at $\sqrt{s}$ = 13 TeV recorded by the ATLAS experiment at the CERN Large Hadron Collider. The measurement uses the complete Run 2 dataset, corresponding to an integrated luminosity of 139 fb –1 , combines data in the single-lepton and dilepton channels, and employs reconstruction techniques adapted to both the resolved and boosted topologies. A Bayesian unfolding procedure is performed to correct for detector resolution and acceptance effects. The combined inclusive $t\bar{t}$ charge asymmetry is measured to be ${A}_{C}^{t\bar{t}}$ = 0.0068 ± 0.0015, which differs from zero by 4.7 standard deviations. Differential measurements are performed as a function of the invariant mass, transverse momentum and longitudinal boost of the $t\bar{t}$ system. Both the inclusive and differential measurements are found to be compatible with the Standard Model predictions, at next-to-next-to-leading order in quantum chromodynamics perturbation theory with next-to-leading-order electroweak corrections. The measurements are interpreted in the framework of the Standard Model effective field theory, placing competitive bounds on several Wilson coefficients.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2020

Search for supersymmetry in proton-proton collisions at $\sqrt{s} =$ 13 TeV in events with high-momentum Z bosons and missing transverse momentum

A search for new physics in events with two highly Lorentz-boosted Z bosons and large missing transverse momentum is presented. The analyzed proton-proton collision data, corresponding to an integrated luminosity of 137 fb$^{−1}$, were recorded at $ \sqrt{s} $ = 13 TeV by the CMS experiment at the CERN LHC. The search utilizes the substructure of jets with large radius to identify quark pairs from Z boson decays. Backgrounds from standard model processes are suppressed by requirements on the jet mass and the missing transverse momentum. No significant excess in the event yield is observed beyond the number of background events expected from the standard model. For a simplified supersymmetric model in which the Z bosons arise from the decay of gluinos, an exclusion limit of 1920 GeV on the gluino mass is set at 95% confidence level. This is the first search for beyond-standard-model production of pairs of boosted Z bosons plus large missing transverse momentum.[graphic not available: see fulltext]

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

Fuel Property Effects on Knock Propensity and Thermal Efficiency in a Direct-Injection Spark-Ignition Engine

Engine knock remains one of the major barriers to further improvement in thermal efficiency of Direct-Injection Spark-Ignition (DISI) engines. While Research Octane Number and Motor Octane Number are often used as standard rating methods for knock resistance of fuels, the impacts of other fuel properties on knock propensity in modern engines such as heat of vaporization (HoV) and laminar flame speed (LFS) require better understanding in order to co-optimize fuels and engine designs to achieve higher thermal efficiency and lower CO2 emission. In the present study, computational fluid dynamics (CFD) is used to model a boosted DISI engine with a focus on knock prediction and fuel property effects. A level-set G-equation model is employed to capture turbulent premixed combustion, and is coupled with a transported Livengood-Wu (L-W) integral approach to predict autoignition in the unburnt region. A criterion associated with the L-W integral is developed to accurately predict knock onset and knock-limited spark-advance. This model is then applied to a sensitivity analysis of HoV and LFS on knock tendency and thermal efficiency. The pressure-temperature trajectory framework is applied and extended to study the fuel effects on auto-ignition process in the engine. An existing efficiency-based merit function, which is derived from experiments for boosted SI engines, is evaluated and improved based on the current CFD results.

DISI↗
DOE OSTI2020

A novel improved model for building energy consumption prediction based on model integration

Building energy consumption prediction plays an irreplaceable role in energy planning, management, and conservation. Constantly improving the performance of prediction models is the key to ensuring the efficient operation of energy systems. Moreover, accuracy is no longer the only factor in revealing model performance, it is more important to evaluate the model from multiple perspectives, considering the characteristics of engineering applications. Based on the idea of model integration, this paper proposes a novel improved integration model (stacking model) that can be used to forecast building energy consumption. The stacking model combines advantages of various base prediction algorithms and forms them into “meta-features” to ensure that the final model can observe datasets from different spatial and structural angles. Two cases are used to demonstrate practical engineering applications of the stacking model. A comparative analysis is performed to evaluate the prediction performance of the stacking model in contrast with existing well-known prediction models including Random Forest, Gradient Boosted Decision Tree, Extreme Gradient Boosting, Support Vector Machine, and K-Nearest Neighbor. The results indicate that the stacking method achieves better performance than other models, regarding accuracy (improvement of 9.5%–31.6% for Case A and 16.2%–49.4% for Case B), generalization (improvement of 6.7%–29.5% for Case A and 7.1%-34.6% for Case B), and robustness (improvement of 1.5%–34.1% for Case A and 1.8%–19.3% for Case B). The proposed model enriches the diversity of algorithm libraries of empirical models.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2021

A novel machine learning based identification of potential adopter of rooftop solar photovoltaics

With the proliferation of rooftop solar photovoltaic installations, there is a need to proactively predict consumer potential for solar photovoltaic adoption, for improved electric utility planning and operation. Traditional analytical modeling approaches are limited to a few survey features and a larger part of the survey would remain untouched by the decision model. This article presents a novel, data-driven modeling approach that strategically prunes a large set of consumer profile features using a machine learning framework to train a model for predicting potential solar adoption. The approach utilizes the Gradient Boosting Decision Tree model through a Light Gradient Boosting framework that improves significantly over the poor prediction accuracy of the existing approaches. Model training using focal-loss based supervision is used to overcome the difficulty in identifying the potential adopters that is inherent in conventional data-driven models. In addition, to overcome possible data sparsity in a limited survey sample, a Generative Adversarial Network is presented to create synthetic user samples and its effectiveness on model performance is assessed. A Bayesian optimization approach is used to systematically arrive at the hyperparameters of the proposed model. Validation of the presented approach on a survey data collected by the National Rural Electric Cooperative Association in Virginia in 2018 demonstrates the excellent predictive capability of the machine learning based approach to modeling solar adoption reliably.

14 SOLAR ENERGY↗