SEARCH · Engineering Papers

Results for “experimental data error”

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.

SourceResearch connectionFrom yearThrough year

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

At least 1,063 records · Page 59

All sources NASA NTRS DOE OSTI

NASA NTRS2013

Spatial Statistical Data Fusion (SSDF)

As remote sensing for scientific purposes has transitioned from an experimental technology to an operational one, the selection of instruments has become more coordinated, so that the scientific community can exploit complementary measurements. However, tech nological and scientific heterogeneity across devices means that the statistical characteristics of the data they collect are different. The challenge addressed here is how to combine heterogeneous remote sensing data sets in a way that yields optimal statistical estimates of the underlying geophysical field, and provides rigorous uncertainty measures for those estimates. Different remote sensing data sets may have different spatial resolutions, different measurement error biases and variances, and other disparate characteristics. A state-of-the-art spatial statistical model was used to relate the true, but not directly observed, geophysical field to noisy, spatial aggregates observed by remote sensing instruments. The spatial covariances of the true field and the covariances of the true field with the observations were modeled. The observations are spatial averages of the true field values, over pixels, with different measurement noise superimposed. A kriging framework is used to infer optimal (minimum mean squared error and unbiased) estimates of the true field at point locations from pixel-level, noisy observations. A key feature of the spatial statistical model is the spatial mixed effects model that underlies it. The approach models the spatial covariance function of the underlying field using linear combinations of basis functions of fixed size. Approaches based on kriging require the inversion of very large spatial covariance matrices, and this is usually done by making simplifying assumptions about spatial covariance structure that simply do not hold for geophysical variables. In contrast, this method does not require these assumptions, and is also computationally much faster. This method is fundamentally different than other approaches to data fusion for remote sensing data because it is inferential rather than merely descriptive. All approaches combine data in a way that minimizes some specified loss function. Most of these are more or less ad hoc criteria based on what looks good to the eye, or some criteria that relate only to the data at hand.

Braverman, Amy J.↗

NASA NTRS2017

Retrievals of Aerosol Optical and Microphysical Properties from Imaging Polar Nephelometer Scattering Measurements

A method for the retrieval of aerosol optical and microphysical properties from in situ light-scattering measurements is presented and the results are compared with existing measurement techniques. The Generalized Retrieval of Aerosol and Surface Properties (GRASP) is applied to airborne and laboratory measurements made by a novel polar nephelometer. This instrument, the Polarized Imaging Nephelometer (PI-Neph), is capable of making high-accuracy field measurements of phase function and degree of linear polarization, at three visible wavelengths, over a wide angular range of 3 to 177°. The resulting retrieval produces particle size distributions (PSDs) that agree, within experimental error, with measurements made by commercial optical particle counters (OPCs). Additionally, the retrieved real part of the refractive index is generally found to be within the predicted error of 0.02 from the expected values for three species of humidified salt particles, with a refractive index that is well established. The airborne measurements used in this work were made aboard the NASA DC-8 aircraft during the Studies of Emissions and Atmospheric Composition, Clouds and Climate Coupling by Regional Surveys (SEAC4RS) field campaign, and the inversion of this data represents the first aerosol retrievals of airborne polar nephelometer data. The results provide confidence in the real refractive index product, as well as in the retrieval's ability to accurately determine PSD, without assumptions about refractive index that are required by the majority of OPCs.

Espinosa, W. Reed↗

NASA NTRS1983

Experimental comparison of icing cloud instruments

Icing cloud instruments were tested in the spray cloud Icing Research Tunnel (IRT) in order to determine their relative accuracy and their limitations over a broad range of conditions. It was found that the average of the readings from each of the liquid water content (LWC) instruments tested agreed closely with each other and with the IRT calibration; but all have a data scatter (+ or - one standard deviation) of about + or - 20 percent. The effect of this + or - 20 percent uncertainty is probably acceptable in aero-penalty and deicer experiments. Existing laser spectrometers proved to be too inaccurate for LWC measurements. The error due to water runoff was the same for all ice accretion LWC instruments. Any given laser spectrometer proved to be highly repeatable in its indications of volume median drop size (DVM), LWC and drop size distribution. However, there was a significant disagreement between different spectrometers of the same model, even after careful standard calibration and data analysis. The scatter about the mean of the DVM data from five Axial Scattering Spectrometer Probes was + or - 20 percent (+ or - one standard deviation) and the average was 20 percent higher than the old IRT calibration. The + or - 20 percent uncertainty in DVM can cause an unacceptable variation in the drag coefficient of an airfoil with ice; however, the variation in a deicer performance test may be acceptable.

Olsen, W.↗

DOE OSTI2021

Factors Governing Oxygen Vacancy Formation in Oxide Perovskites

The control of oxygen vacancy (V O ) formation is critical to advancing multiple metal-oxide-perovskite-based technologies. In this work, we report the construction of a compact linear model for the neutral V O formation energy in ABO 3 perovskites that reproduces, with reasonable fidelity, Hubbard-U-corrected density functional theory calculations based on the state-of-the-art, strongly constrained and appropriately normed exchange-correlation functional. We obtain a mean absolute error of 0.45 eV for perovskites stable at 298 K, an accuracy that holds across a large, electronically diverse set of ABO 3 perovskites. Our model considers perovskites containing alkaline-earth metals (Ca, Sr, and Ba) and lanthanides (La and Ce) on the A-site and 3d transition metals (Ti, V, Cr, Mn, Fe, Co, and Ni) on the B-site in six different crystal systems (cubic, tetragonal, orthorhombic, hexagonal, rhombohedral, and monoclinic) common to perovskites. Physically intuitive metrics easily extracted from existing experimental thermochemical data or via inexpensive quantum mechanical calculations, including crystal bond dissociation energies and (solid phase) reduction potentials, are key components of the model. Beyond validation of the model against known experimental trends in materials used in solid oxide fuel cells, the model yields new candidate perovskites not contained in our training data set, such as (Bi,Y)(Fe,Co)O 3 , which we predict may have favorable thermochemical water-splitting properties. The confluence of sufficient accuracy, efficiency, and interpretability afforded by our model not only facilitates high-throughput computational screening for any application that requires the precise control of V O concentrations but also provides a clear picture of the dominant physics governing V O formation in metal-oxide perovskites.

08 HYDROGEN↗

DOE OSTI2020

Prediction of Research/Motor Octane Number and Octane Sensitivity Using Artificial Neural Networks

Octane sensitivity (OS), dfined as the research octane number (RON) minus the motor octane number (MON) of a given fuel, has gained interest among researchers due to its apparent ffect on knocking conditions in internal combustion engines. Compounds with a high OS enable higher efficiencies, especially with respect to advanced compression ignition engines. RON/MON must be experimentally tested to determine OS; however, the experimental methods utilized require a substantial amount of time, a significant monetary investment, and specialized equipment. To this end, predictive computational models trained with existing experimental data and molecular properties would allow for the preemptive screening of compounds prior to performing these experiments. The present work proposes two methods for predicting the OS of a given compound: using artficial neural networks (ANNs) trained with quantitative structure-property relationship (QSPR) descriptors to predict RON and MON individually to compute OS from RON/MON predictions (derived octane sensitivity, dOS), and using an ANN trained with QSPR descriptors to directly predict OS. ANNs trained to predict RON and MON achieved test set root-mean-square errors (RMSEs) of 10.499 and 7.551 respectively. dOS calculations were found to have a test set RMSE of 6.432 while predicting OS directly resulted in a test set RMSE of 7.019, showing it is more bene cial to obtain OS from RON/MON predictions than predicting it directly. Furthermore, relationships between individual QSPR descriptors and RON/MON/OS are discussed, highlighting correlations between specfic molecular features and these properties.

09 BIOMASS FUELS↗

NASA NTRS1983

LANDSAT 4 band 6 data evaluation

Multiple altitude TM thermal infrared images were analyzed and the observed radiance values were computed. The data obtained represent an experimental relation between preceived radiance and altitude. A LOWTRAB approach was tested which incorporates a modification to the path radiance model. This modification assumes that the scattering out of the optical path is equal in magnitude and direction to the scattering into the path. The radiance observed at altitude by an aircraft sensor was used as input to the model. Expected radiance as a function of altitude was then computed down to the ground. The results were not very satisfactory because of somewhat large errors in temperature and because of the difference in the shape of the modeled and experimental curves.

Source record↗

NASA NTRS1991

Frequency domain identification for robust large space structure control design

A methodology is demonstrated for frequency domain identification of large space structures which systematically transforms experimental raw data into a form required for synthesizing H(infinity) controllers using modern robust control design software (e.g., Matlab Toolboxes). A unique feature of this approach is that the additive uncertainty is characterized to a specified statistic confidence rather than with hard bounds. In this study, the difference in robust performance is minimal between the two levels of confidence. In general cases, the present methodology provides a tool for performance/confidence level tradeoff studies. For simplicity, the additive uncertainty on a frequency grid is considered and the interpolation error in between grid points is neglected.

Yam, Y.↗

NASA NTRSDate not supplied

Hybrid Modeling of Unmanned Aerial Vehicle Electric Powertrain for Fault Detection and Diagnostics

This paper shows the application of hybrid physics-informed machine learning to a representative electric powertrain for unmanned aerial vehicles. The model is composed of physics-derived principles and empirical equations, as well as fully connected networks that are strategically placed within the model to substitute equations that are subject to large uncertainty. Polynomial fit driven by heuristics or empirical observations can be substituted by more flexible networks that can minimize the error between model predictions and observations without being restricted to a predefined functional form. This modeling strategy allows training of networks deep inside the model and unknown parameters in a single learning stage. It has already been applied to Li-ion batteries in the past, and in this work, we extend the applications to other components of an electric powertrain, namely electronic speed controller with pulse-width modulation, and brushless DC motor with connected propeller. Training and testing of the model is carried out using experimental data from Li-ion battery discharge and powertrain testing in a laboratory environment.

Physics-Informed Machine Learning↗

DOE OSTI2025

AI‐Driven Robot Enables Synthesis‐Property Relation Prediction for Metal Halide Perovskites in Humid Atmosphere

Materials Acceleration Platforms (MAPs) – also known as self-driving laboratories– present a new paradigm for materials science and promise an order of magnitude accelerated materials discovery compared to the traditional trial-and-error approach. Metal halide perovskites (MHPs) are an emerging class of materials for optoelectronic applications but are plagued by irreproducible optoelectronic quality, particularly for films fabricated in a humid atmosphere. Here, in this work, a machine learning (ML)-guided closed-loop platform is developed with a multimodal data fusion approach to predict synthesis–property relations for the optical quality of MHP thin films in relative humidities (RHs) ranging from 5–55%. The efficiency of this approach is confirmed by the fast-dropping learning rate to 2% after experimentally sampling less than 1% of the possible 5,000+ combinations. The prediction of synthesis–property relations is done by optical and imaging characterizations. In situ photoluminescence characterization revealed the origin of thin film quality variation at different RH. These insights provide an avenue for controlling the MHP crystallization by fine-tuning the synthesis parameters and RH for a given chemistry, thus lifting the need for stringent atmosphere control. The MAP enables an accelerated screening and understanding of the synthesis design space, facilitating rational synthesis recipe choice for a wide range of materials.

AI-driven robot↗

DOE OSTI2022

Accurate determination of solvation free energies of neutral organic compounds from first principles

The main goal of molecular simulation is to accurately predict experimental observables of molecular systems. Another long-standing goal is to devise models for arbitrary neutral organic molecules with little or no reliance on experimental data. While separately these goals have been met to various degrees, for an arbitrary system of molecules they have not been achieved simultaneously. For biophysical ensembles that exist at room temperature and pressure, and where the entropic contributions are on par with interaction strengths, it is the free energies that are both most important and most difficult to predict. We compute the free energies of solvation for a diverse set of neutral organic compounds using a polarizable force field fitted entirely to ab initio calculations. The mean absolute errors (MAE) of hydration, cyclohexane solvation, and corresponding partition coefficients are 0.2 kcal/mol, 0.3 kcal/mol and 0.22 log units, i.e. within chemical accuracy. The model (ARROW FF) is multipolar, polarizable, and its accompanying simulation stack includes nuclear quantum effects (NQE). The simulation tools’ computational efficiency is on a par with current state-of-the-art packages. The construction of a wide-coverage molecular modelling toolset from first principles, together with its excellent predictive ability in the liquid phase is a major advance in biomolecular simulation.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2022

Classical Simulation of Boson Sampling Based on Graph Structure

Boson sampling is a fundamentally and practically important task that can be used to demonstrate quantum supremacy using noisy intermediate-scale quantum devices. In this Letter, we present classical sampling algorithms for single-photon and Gaussian input states that take advantage of a graph structure of a linear-optical circuit. The algorithms’ complexity grows as so-called treewidth, which is closely related to the connectivity of a given linear-optical circuit. Using the algorithms, we study approximated simulations for local Haar-random linear-optical circuits. For equally spaced initial sources, we show that, when the circuit depth is less than the quadratic in the lattice spacing, the efficient simulation is possible with an exponentially small error. Notably, right after this depth, photons start to interfere each other and the algorithms’ complexity becomes subexponential in the number of sources, implying that there is a sharp transition of its complexity. Finally, when a circuit is sufficiently deep enough for photons to typically propagate to all modes, the complexity becomes exponential as generic sampling algorithms. We numerically implement a likelihood test with a recent Gaussian boson sampling experiment and show that the treewidth-based algorithm with a limited treewidth renders a larger likelihood than the experimental data.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

NASA NTRS1984

A flight test evaluation of the pilot interface with a digital advanced avionics system

A flight study was conducted to study pilot workload and the pilot interface with high levels of avionics capability and automation. The study was done in the context of general aviation, single-pilot IFR operations and utilized an experimental, digital, integrated avionics system. Results indicate that such advanced systems can provide improved information to the pilot and increased functional capability. The results also indicate that additional research is needed to increase the knowledge base required to design the pilot interfaces with highly capable systems. A CRT-based moving map display format tested provided excellent navigational situational awareness but was inferior to an HSI for manual path tracking. The complexity of navigation data management, autopilot management, and maintaining awareness of system status contributed to pilot workload and errors. Suggested guidelines for the design of the pilot/avionics interface for advanced avionics systems are given.

Hinton, D. A.↗

NASA NTRS2001

Enabling Advanced Automation in Spacecraft Operations with the Spacecraft Emergency Response System

True autonomy is the Holy Grail of spacecraft mission operations. The goal of launching a satellite and letting it manage itself throughout its useful life is a worthy one. With true autonomy, the cost of mission operations would be reduced to a negligible amount. Under full autonomy, any problems (no matter the severity or type) that may arise with the spacecraft would be handled without any human intervention via some combination of smart sensors, on-board intelligence, and/or smart automated ground system. Until the day that complete autonomy is practical and affordable to deploy, incremental steps of deploying ever-increasing levels of automation (computerization of once manual tasks) on the ground and on the spacecraft are gradually decreasing the cost of mission operations. For example, NASA's Goddard Space Flight Center (NASA-GSFC) has been flying spacecraft with low cost operations for several years. NASA-GSFC's SMEX (Small Explorer) and MIDEX (Middle Explorer) missions have effectively deployed significant amounts of automation to enable the missions to fly predominately in 'light-out' mode. Under light-out operations the ground system is run without human intervention. Various tools perform many of the tasks previously performed by the human operators. One of the major issues in reducing human staff in favor of automation is the perceived increased in risk of losing data, or even losing a spacecraft, because of anomalous conditions that may occur when there is no one in the control center. When things go wrong, missions deploying advanced automation need to be sure that anomalous conditions are detected and that key personal are notified in a timely manner so that on-call team members can react to those conditions. To ensure the health and safety of its lights-out missions, NASA-GSFC's Advanced Automation and Autonomy branch (Code 588) developed the Spacecraft Emergency Response System (SERS). The SERS is a Web-based collaborative environment that enables secure distributed fault and resource management. The SERS incorporates the use of intelligent agents, threaded discussions, workflow, database connectivity, and links to a variety of communications devices (e.g., two-way paging, PDA's, and Internet phones) via commercial gateways. When the SERS detects a problem, it notifies on-call team members, who then can remotely take any necessary actions to resolve the anomalies.The SERS goes well beyond a simple '911' system that sends out an error code to everyone with a pager. Instead, SERS' software agents send detailed data (i.e., notifications) to the most appropriate team members based on the type and severity of the anomaly and the skills of the on-call team members. The SERS also allows the team members to respond to the notifications from their wireless devices. This unique capability ensures rapid response since the team members no longer have to go to a PC or the control center for every anomalous event. Most importantly, the SERS enables safe experimentation with various techniques for increasing levels of automation, leading to robust autonomy. For the MIDEX missions at NASA GSFC, the SERS is used to provide 'human-in-the-loop' automation. During lights-out operations, as greater control is given to the MIDEX automated systems, the SERS can be configured to page remote personnel and keep them informed regarding actions taking place in the control center. Remote off-duty operators can even be given the option of enabling or inhibiting a specific automated response in near real time via their two-way pagers. The SERS facilitates insertion of new technology to increase automation, while maintaining the safety and security of mission resources. This paper will focus on SERS' overall functionality and how SERS has been designed to handle the monitoring and emergency response for missions with varying levels of automation. The paper will also convey some of the key lessons learned from SERS' deployment across of variety of missions, highlighting this incremental approach to achieving 'robust autonomy'.

Breed, Julie↗

NASA NTRS2001

The Behavior of TCP and Its Extensions in Space

The performance of Transmission Control Protocol (TCP) in space has been examined from the observations of simulation and experimental tests for several years at National Aeronautics and Space Administration (NASA), Department of Defense (DoD) and universities. At New Mexico State University (NMSU), we have been concentrating on studying the performance of two protocol suites: the file transfer protocol (ftp) running over Transmission Control Protocol/Internet Protocol (TCP/IP) stack and the file protocol (fp) running over the Space Communications Protocol Standards (SCPS)-Transport Protocol (TP) developed under the Consultative Committee for Space Data Systems (CCSDS) standards process. SCPS-TP is considered to be TCP's extensions for space communications. This dissertation experimentally studies the behavior of TCP and SCPS-TP by running the protocol suites over both the Space-to-Ground Link Simulator (SGLS) test-bed and realistic satellite link. The study concentrates on comparing protocol behavior by plotting the averaged file transfer times for different experimental configurations and analyzing them using Statistical Analysis System (SAS) based procedures. The effects of different link delays and various Bit-Error-Rates (BERS) on each protocol performance are also studied and linear regression models are built for experiments over SGLS test-bed to reflect the relationships between the file transfer time and various transmission conditions.

Wang, Ruhai↗

DOE OSTI2023

Experimental Assessment of Mammalian Lipidome Complexity Using Multimodal 21 T FTICR Mass Spectrometry Imaging

Herein, we assess the complementarity and complexity of data that can be detected within mammalian lipidome mass spectrometry imaging (MSI) via matrix-assisted laser desorption ionization (MALDI) and nanospray desorption electrospray ionization (nano-DESI). We do so by employing 21 T Fourier transform ion cyclotron resonance mass spectrometry (FTICR-MS) with absorption mode FT processing in both cases, allowing unmatched mass resolving power per unit time (≥613k at m/z 760, 1.536 s transients). While our results demonstrated that molecular coverage and dynamic range capabilities were greater in MALDI analysis, nano-DESI provided superior mass error, and all annotations for both modes had sub-ppm error. Taken together, these experiments highlight the coverage of 1676 lipids and serve as a functional guide for expected lipidome complexity within nano-DESI-MSI and MALDI-MSI. To further assess the lipidome complexity, mass splits (i.e., the difference in mass between neighboring peaks) within single pixels were collated across all pixels from each respective MSI experiment. The spatial localization of these mass splits was powerful in informing whether the observed mass splits were biological or artificial (e.g., matrix related). Mass splits down to 2.4 mDa were observed (i.e., sodium adduct ambiguity) in each experiment, and both modalities highlighted comparable degrees of lipidome complexity. Further, we highlight the persistence of certain mass splits (e.g., 8.9 mDa; double bond ambiguity) independent of ionization biases. Here, we also evaluate the need for ultrahigh mass resolving power for mass splits ≤4.6 mDa (potassium adduct ambiguity) at m/z > 1000, which may only be resolved by advanced FTICR-MS instrumentation.

21T-FTICR-MS↗

DOE OSTI2022

Physics-informed graph neural networks for predicting cetane number with systematic data quality analysis

Designing alternative fuels for advanced compression ignition engines necessitates a predictive model for cetane number (CN). In this study, the physics-informed graph neural networks are introduced for a reliable CN prediction by considering molecular features pertinent to the physical properties of molecules that affect CN. The reliability of measured data is another key factor to consider for improving the predictive model. Various experimental instruments for measuring CN exist, including standard and non-standard methods. In this regard, a systematic data quality analysis was carried out for the total 630 CNs collected from literature and new measurements in this study using Advanced Fuel Ignition Delay Analyzer (AFIDA). The results from this data curation process were reflected in the model by imposing lower sample weights on the data coming from less reliable measurement techniques. This approach effectively maximized the prediction accuracy while incorporating data from all available sources. Using the sample weights decreased the mean absolute error (MAE) up to 0.8 CN units. The accuracy was also improved by introducing the CN-related physical properties (the number of hydrogen bond donors and acceptors); the test set MAE is 5.74 and 7.01 for the model with and without such properties, respectively. Investigating molecular structural effects on CN was also carried out to gain chemical insights into factors used to design new fuel candidates. The dimensionality reduction analysis of feature vectors showed a clear clustering in terms of functional groups and CN and the structural effect derived from the model was consistent with the physicochemical insights. Finally, this physics-informed model and data curation would be helpful for accurate CN prediction and inform rational fuel design.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Reduced order modeling for flow and transport problems with Barlow Twins self-supervised learning

Abstract We propose a unified data-driven reduced order model (ROM) that bridges the performance gap between linear and nonlinear manifold approaches. Deep learning ROM (DL-ROM) using deep-convolutional autoencoders (DC–AE) has been shown to capture nonlinear solution manifolds but fails to perform adequately when linear subspace approaches such as proper orthogonal decomposition (POD) would be optimal. Besides, most DL-ROM models rely on convolutional layers, which might limit its application to only a structured mesh. The proposed framework in this study relies on the combination of an autoencoder (AE) and Barlow Twins (BT) self-supervised learning, where BT maximizes the information content of the embedding with the latent space through a joint embedding architecture. Through a series of benchmark problems of natural convection in porous media, BT–AE performs better than the previous DL-ROM framework by providing comparable results to POD-based approaches for problems where the solution lies within a linear subspace as well as DL-ROM autoencoder-based techniques where the solution lies on a nonlinear manifold; consequently, bridges the gap between linear and nonlinear reduced manifolds. We illustrate that a proficient construction of the latent space is key to achieving these results, enabling us to map these latent spaces using regression models. The proposed framework achieves a relative error of 2% on average and 12% in the worst-case scenario (i.e., the training data is small, but the parameter space is large.). We also show that our framework provides a speed-up of $$7 \times 10^{6}$$ 7 × 10 6 times, in the best case, and $$7 \times 10^{3}$$ 7 × 10 3 times on average compared to a finite element solver. Furthermore, this BT–AE framework can operate on unstructured meshes, which provides flexibility in its application to standard numerical solvers, on-site measurements, experimental data, or a combination of these sources.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Using spatio-temporal graph neural networks to estimate fleet-wide photovoltaic performance degradation patterns

Accurate estimation of photovoltaic (PV) system performance is crucial for determining its feasibility as a power generation technology and financial asset. PV-based energy solutions offer a viable alternative to traditional energy resources due to their superior Levelized Cost of Energy (LCOE). A significant challenge in assessing the LCOE of PV systems lies in understanding the Performance Loss Rate (PLR) for large fleets of PV systems. Estimating the PLR of PV systems becomes increasingly important in the rapidly growing PV industry. Precise PLR estimation benefits PV users by providing real-time monitoring of PV module performance, while explainable PLR estimation assists PV manufacturers in studying and enhancing the performance of their products. However, traditional PLR estimation methods based on statistical models have notable drawbacks. Firstly, they require user knowledge and decision-making. Secondly, they fail to leverage spatial coherence for fleet-level analysis. Additionally, these methods inherently assume the linearity of degradation, which is not representative of real world degradation. To overcome these challenges, we propose a novel graph deep learning-based decomposition method called the Spatio-Temporal Graph Neural Network for fleet-level PLR estimation (PV-stGNN-PLR). PV-stGNN-PLR decomposes the power timeseries data into aging and fluctuation components, utilizing the aging component to estimate PLR. PV-stGNN-PLR exploits spatial and temporal coherence to derive PLR estimation for all systems in a fleet and imposes flatness and smoothness regularization in loss function to ensure the successful disentanglement between aging and fluctuation. We have evaluated PV-stGNN-PLR on three simulated PV datasets consisting of 100 inverters from 5 sites. Experimental results show that PV-stGNN-PLR obtains a reduction of 33.9% and 35.1% on average in Mean Absolute Percent Error (MAPE) and Euclidean Distance (ED) in PLR degradation pattern estimation compared to the state-of-the-art PLR estimation methods.

14 SOLAR ENERGY↗