Search NASA⌕ Search

SEARCH · Search NASA

Results for “spline”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

BASS

SAND2026-17001O BASS implements Bayesian Adaptive Spline Surfaces in MATLAB and serves as a surrogate model for regression applications. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy's National Nuclear Security Administration under contract DE-NA0003525.

Tucker, J. Derek [Sandia National Lab. (SNL-CA), L↗
DOE OSTI2026

HITMAN

HITMAN (Hermite Interpolation of Trajectories and Measurement Synthesis for Analysis of Navigators) interpolates—or estimates the unknown values between known values—flight trajectories and generates synthetic inertial measurement unit (IMU) data using Hermite splines. This Python library provides modeling and simulation capabilities to synthesize inertial measurements from discrete trajectory points, enabling researchers to create exemplar datasets for evaluating navigation algorithms in various applications, including consumer devices like smartphones and vehicles. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Walker II, Michael [Sandia National Lab. (SNL-CA),↗
DOE OSTI2026

Disparities in the air quality monitoring stations and PM₂.₅ in Chicago’s air quality landscape

Fine particulate matter (PM₂.₅) poses significant public and environmental health risks in urban areas. Chicago’s dense industry and traffic create variable air quality, yet monitoring is unevenly distributed, resulting in undersampling of air quality data in some city areas. This study applied a hybrid approach using GIS-based kernel density mapping, interpolation modeling (IDW, Spline, Kriging) of USEPA monitoring data, multi-scale temporal trend analyses (hourly to annual), and ESDA. Accordingly, the density surface showed that monitors are concentrated in the affluent north, northwest, and southwest sides of Chicago (up to ~ 0.07 stations per sq mile), while the south and southeast regions, with predominantly minority communities, have virtually no coverage. Overall, citywide coverage is minimal (~ 4–5 monitors total; ~0.02 per sq mile; ≈1 per 600,000 residents). Temporal analyses showed that the city’s mean annual PM₂.₅ (~ 10.8 µg/m³) exceeds USEPA/WHO standards (9 µg/m³), with summer means (~ 17.1 µg/m³) significantly higher than other seasons. Diurnally, a clear pattern was observed, with PM₂.₅ concentrations peaking overnight (00:00–03:00) and during the morning rush hours, and dipping during midday to late afternoon. Spatial distribution of PM₂.₅ identified hotspots near O’Hare Airport, the downtown Loop area, and south-side neighborhoods, contrasting with lower concentrations on the north side, revealing Chicago’s socioeconomic divides and resulting environmental inequities. The findings underscore the need for expanded monitoring and targeted interventions in under-monitored, high-pollution communities to advance equitable community health.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Evaluating proxies for the drivers of natural gas productivity using machine-learning models

We report the extensive development of unconventional reservoirs using horizontal drilling and multistage hydraulic fracturing has generated large volumes of reservoir characterization and production data. The analysis of this abundant data using statistical methods and advanced machine-learning (ML) techniques can provide data-driven insights into well performance. Most predictive modeling studies have focused on the impact that different well completion and stimulation strategies have on well production but have not fully exploited the available in situ rock property data to determine its role in reservoir productivity. We have used machine-learning techniques to rank rock mechanical properties, microseismic attributes, and stimulation parameters in the order of their significance for predicting natural gas production from an unconventional reservoir. The data for this study came from a hydraulically fractured well in the Marcellus Shale in Monongalia County, West Virginia. The data classes included measurements aggregated by well completion stage that included (1) gas production, (2) well-log-derived measurements including bulk density, elastic moduli, shear impedance, compressional impedance, brittleness, and gamma measurements, (3) microseismic attributes, (4) long-period long-duration (LPLD) event counts, (5) fracture counts, and (6) stimulation parameters that included the fluid injection volume and average pumping pressure. To identify observable proxies for the drivers of gas production, we evaluated five commonly used ML approaches including multivariate adaptive regression spline, Gaussian mixture model, random forest, gradient boosting, and neural network. We selected five variables including LPLD event count, seismogenic b-value, hydraulic diffusivity, cumulative moment, and fluid volume as the features most likely to impact gas productivity at the stage level in the study area. The data-driven selection of these parameters for their importance in determining gas production can help reservoir engineers design more effective hydraulic-fracture treatments in the Marcellus Shale and other similar unconventional reservoirs. Plain language summary: We use machine-learning methods and data-driven selection of reservoir parameters to rank and better understand their importance in determining gas production, which can help reservoir engineers design more effective hydraulic-fracture treatments in the Marcellus Shale and other similar unconventional reservoirs.

58 GEOSCIENCES↗
DOE OSTI2023

Supporting information for Few-Shot Learning Enables Population-Scale Analysis of Leaf Traits in Populus trichocarpa

In this work, we use few-shot learning to segment the body and vein architecture of P. trichocarpa leaves from high-resolution scans obtained in the UC Davis common garden. Leaf and vein segmentation are formulated as separate tasks, in which convolutional neural networks (CNNs) are used to iteratively expand partial segmentations until reaching stopping criteria. Our leaf and vein segmentation approaches use just 50 and 8 manually traced images for training, respectively, and are applied to a set of 2,634 top and bottom leaf scans. We show that both methods achieve high segmentation accuracy, in some cases exceeding even human-level segmentation. The leaf and vein segmentations are subsequently used to extract 68 morphological traits using traditional open-source image processing tools, which are validated using real-world physical measurements. For a biological perspective, we perform a genome-wide association study using the vein density trait to discover novel genetic architectures associated with multiple physiological processes relating to leaf development and function. In addition to sharing all of the few-shot learning code (see https://github.com/jlager/few-shot-leaf-segmentation), we are releasing all images, manual segmentations, model predictions, 68 extracted leaf phenotypes, and a new set of SNPs called against the v4 P. trichocarpa genome for 1,419 genotypes. The data folder includes all images, ground truth segmentations, predicted segmentations, and extracted leaf traits. All images encode the sample ID in the file name by indicating the treatment, block, row, position, and leaf side, respectively. For example, the file, C_1_1_2_bot.jpeg, indicates the control treatment, block 1, row 1, position 2, and the bottom side of the leaf. Tabulated results include position IDs as well as the corresponding genotype IDs. The images folder includes the 2,906 high-resolution leaf scans taken in the field. The leaf_masks folder includes 50 ground truth segmentations used for training the leaf tracing algorithm. The leaf_preds folder includes the 2,906 predicted segmentations from the leaf tracing algorithm. The vein_masks folder includes 8 ground truth segmentations used for training the vein growing algorithm. The vein_preds folder includes the 1,453 predicted segmentations from the vein growing algorithm. The vein_probs folder includes the 1,453 predicted probability maps from the vein growing algorithm before thresholding. The genomes folder includes the set of SNPs called against the v4 P. trichocarpa genome for 1,419 genotypes with a README file detailing the steps taken. The results folder includes: (i) raw values of the 68 predicted leaf traits in digital_traits.tsv, (ii) manually measured values of petiole length and width in manual_traits.tsv, (iii) thin plate spline (TPS) adjusted values of the vein density trait in vein_density_tps_adj.tsv, (iv) best linear unbiased prediction (BLUP) adjusted values of the vein density trait in vein_density_blups.tsv, and (v) GWAS results for the vein density trait, including chromosome positions and corresponding P values, in gwas_results.csv.

09 BIOMASS FUELS↗
DOE OSTI2024

Forward variable selection enables fast and accurate dynamic system identification with Karhunen-Loève decomposed Gaussian processes

A promising approach for scalable Gaussian processes (GPs) is the Karhunen-Loève (KL) decomposition, in which the GP kernel is represented by a set of basis functions which are the eigenfunctions of the kernel operator. Such decomposed kernels have the potential to be very fast, and do not depend on the selection of a reduced set of inducing points. However KL decompositions lead to high dimensionality, and variable selection thus becomes paramount. This paper reports a new method of forward variable selection, enabled by the ordered nature of the basis functions in the KL expansion of the Bayesian Smoothing Spline ANOVA kernel (BSS-ANOVA), coupled with fast Gibbs sampling in a fully Bayesian approach. It quickly and effectively limits the number of terms, yielding a method with competitive accuracies, training and inference times for tabular datasets of low feature set dimensionality. Theoretical computational complexities are O ( N P 2 ) in training and O ( P ) per point in inference, where N is the number of instances and P the number of expansion terms. The inference speed and accuracy makes the method especially useful for dynamic systems identification, by modeling the dynamics in the tangent space as a static problem, then integrating the learned dynamics using a high-order scheme. The methods are demonstrated on two dynamic datasets: a ‘Susceptible, Infected, Recovered’ (SIR) toy problem, along with the experimental ‘Cascaded Tanks’ benchmark dataset. Comparisons on the static prediction of time derivatives are made with a random forest (RF), a residual neural network (ResNet), and the Orthogonal Additive Kernel (OAK) inducing points scalable GP, while for the timeseries prediction comparisons are made with LSTM and GRU recurrent neural networks (RNNs) along with the SINDy package.

Hayes, Kyle↗
DOE OSTI2021

Watermarks in stream processing systems: semantics and comparative analysis of Apache Flink and Google cloud dataflow

Streaming data processing is an exercise in taming disorder: from oftentimes huge torrents of information, we hope to extract powerful and timely analyses. But when dealing with streaming data, the unbounded and temporally disordered nature of real-world streams introduces a critical challenge: how does one reason about the completeness of a stream that never ends? In this paper, we present a comprehensive definition and analysis of watermarks, a key tool for reasoning about temporal completeness in infinite streams.First, we describe what watermarks are and why they are important, highlighting how they address a suite of stream processing needs that are poorly served by eventually-consistent approaches:• Computing a single correct answer, as in notifications.• Reasoning about a lack of data, as in dip detection.• Performing non-incremental processing over temporal subsets of an infinite stream, as in statistical anomaly detection with cubic spline models.• Safely and punctually garbage collecting obsolete inputs and intermediate state.• Surfacing a reliable signal of overall pipeline health.Second, we describe, evaluate, and compare the semantically equivalent, but starkly different, watermark implementations in two modern stream processing engines: Apache Flink and Google Cloud Dataflow.

Akidau, Tyler↗
DOE OSTI2026

Beam loss modeling and mitigation due to intra-beam stripping

Intra-Beam Stripping (IBS) is a critical beam loss mechanism in high-intensity H- linacs and presents a significant limitation to increasing beam power. This work presents a computational framework to evaluate and mitigate IBS-induced beam loss along the Spallation Neutron Source (SNS) LINAC. Our calculation is based on an analytic theory and involves evaluation of a 9D integral using the Monte-Carlo technique. We first benchmarked our calculations against simplified, analytically solvable cases. We then applied our algorithm to Gaussian bunches with a known probability density function (PDF). We next expanded our algorithm to arbitrary bunch distributions using the Neural Spline Flow (NSF) models trained on PyORBIT tracking data. In the future, we plan to validate our algorithm experimentally and apply it to design IBS mitigation strategies.

Nln, Shivam [ORNL]↗
DOE OSTI2022

LaplaceInterpolation.jl: A Julia package for fast interpolation on a grid

We implement a linear-time algorithm for interpolation on a regular multidimensional grid in the Julia language. The algorithm is an approximate Laplace interpolation (Press, 1992) when no parameters are given; and when parameters m ∈ Z and ϵ > 0 are set, the interpolant approximates a Matérn kernel, of which radial basis functions and polyharmonic splines are a special case. We implement, in addition, Neumann, Dirichlet (trivial), and average boundary conditions with potentially different aspect ratios in the different dimensions. The interpolant functions in arbitrary dimensions.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Normalizing flows for high-dimensional detector simulations

Whenever invertible generative networks are needed for LHC physics, normalizing flows show excellent performance. In this work, we investigate their performance for fast calorimeter shower simulations with increasing phase space dimension. We use fast and expressive coupling spline transformations applied to the CaloChallenge datasets. In addition to the base flow architecture we also employ a VAE to compress the dimensionality and train a generative network in the latent space. We evaluate our networks on several metrics, including high-level features, classifiers, and generation timing. Our findings demonstrate that invertible neural networks have competitive performance when compared to autoregressive flows, while being substantially faster during generation.

Ernst, Florian↗
DOE OSTI2021

IBM Open Science Price - SWAP Gate Challenge

On November 30, 2020, IBM announced an open science price competition aimed at improving the fidelity of a SWAP gate on their 7 qubit Quantum system named ”Casablanca”. The details of the SWAP gate problem was outlined in a Jupyter notebook, which utilizes the IBM developed open source package Qiskit. The participants were allowed to work in teams with up to five people and restricted to only use open source software in solving the problem. Their results were due on April 16, 2021. Our approach to solving the SWAP gate challenge is based on the quantum optimal control techniques implemented in our open source packages Juqbox.jl and Quandary. The results from the optimal control approach is only as good as the accuracy in the description of the quantum system dynamics, characterized by a Hamiltonian model that was provided by IBM. Based on the calibrated control pulses IBM provide for the standard gate set, we developed a reverse engineering approach to calibrate our computational model. Techniques were developed to translate between Qiskit’s pulse representation and the B-spline formulation used in Juqbox and Quandary. The fidelity of the optimized pulse sequences were estimated using Qiskit’s randomized bench marking techniques.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2026

Enabling the Broader Use of MOOSE for Nuclear Energy and Other Simulation

This Final Scientific and Technical Report summarizes work performed under the Phase IIA SBIR project “Enabling the Broader Use of MOOSE for Nuclear Energy and Other Simulation” (DE-SC0020906) from August 2023 through August 2025. The objective of the Phase IIA effort was to mature and harden capabilities developed during Phase II, with the goal of enabling practical interoperability between Coreform’s isogeometric analysis (IGA) technologies and the Multiphysics Object-Oriented Simulation Environment (MOOSE), while improving robustness, performance, and scalability for complex, nuclear-relevant geometries. Over the course of Phase IIA, the project established and validated an extraction-based interoperability pathway between Coreform tools and MOOSE. A combined mesh and matrix format was defined collaboratively with MOOSE developers and integrated into the solver, enabling standard MOOSE workflows to operate on data exported from Coreform’s IGA and Flex Representation Method (FRM) pipelines. Early demonstrations validated architectural compatibility using linear solid mechanics problems, while later efforts focused on benchmark testing and external use. By the end of the project period, engineers at BWXT were able to independently set up and execute a simulation using the Coreform–MOOSE workflow and provide direct feedback that informed further refinement. In parallel, substantial effort was devoted to improving the robustness of trimmed U-spline construction for complex CAD geometries. A growing test suite of nuclear-relevant models was compiled through collaboration with multiple stakeholders and used to drive extensive bug fixing and reliability improvements. These efforts resulted in improved robustness and performance, including the addition of fallback capabilities that enhance reliability when the underlying commercial CAD kernel fails. Performance-oriented work progressed later in the project, with the development and demonstration of methods to decompose complex geometries into structured subregions and updated data representations to support more efficient solver processing. Additionally, extensive enhancements to threadsafe parallel data structures and trimming operations established a foundation for scalable processing of large assemblies. Collaboration with Sandia National Laboratories on the SGM geometric modeling kernel advanced to a functioning interface test case, positioning the workflow for future kernel integration. Overall, the Phase IIA effort successfully transitioned the project from architectural proof-of-concept to externally exercised, solver-integrated capability, while clarifying remaining technical challenges related to standardization, performance optimization, and kernel integration.

42 ENGINEERING↗
DOE OSTI2023

Predictor-corrector models for lightweight massive machine-type communications in Industry 4.0

Future Industry 4.0 scenarios are characterized by seamless integration between computational and physical processes. To achieve this objective, dense platforms made of small sensing nodes and other resource constraint devices are ubiquitously deployed. All these devices have a limited number of computational resources, just enough to perform the simple operation they are in charge of. The remaining operations are delegated to powerful gateways that manage sensing nodes, but resources are never unlimited, and as more and more devices are deployed on Industry 4.0 platforms, gateways present more problems to handle massive machine-type communications. Although the problems are diverse, those related to security are especially critical. To enable sensing nodes to establish secure communications, several semiconductor companies are currently promoting a new generation of devices based on Physical Unclonable Functions, whose usage grows every year in many real industrial scenarios. Those hardware devices do not consume any computational resource but force the gateway to keep large key-value catalogues for each individual node. In this context, memory usage is not scalable and processing delays increase exponentially with each new node on the platform. In this paper, we address this challenge through predictor-corrector models, representing the key-value catalogues. Models are mathematically complex, but we argue that they consume less computational resources than current approaches. The lightweight models are based on complex functions managed as Laurent series, cubic spline interpolations, and Boolean functions also developed as series. Unknown parameters in these models are predicted, and eventually corrected to calculate the output value for each given key. The initial parameters are based on the Kane Yee formula. An experimental analysis and a performance evaluation are provided in the experimental section, showing that the proposed approach causes a significant reduction in the resource consumption.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Monte Carlo Simulation and Reconstruction: Assessment of Myocardial Perfusion Imaging of Tracer Dynamics With Cardiac Motion Due to Deformation and Respiration Using Gamma Camera With Continuous Acquisition

Purpose: Myocardial perfusion imaging (MPI) with single photon emission computed tomography (SPECT) is routinely used for stress testing in nuclear medicine. Recently, our group extended its potential going from 3D visual qualitative image analysis to 4D spatiotemporal reconstruction of dynamically acquired data to capture the time variation of the radiotracer concentration and the estimated myocardial blood flow (MBF) and coronary flow reserve (CFR). However, the quality of reconstructed image is compromised due to cardiac deformation and respiration. The work presented here develops an algorithm that reconstructs the dynamic sequence of separate respiratory and cardiac phases and evaluates the algorithm with data simulated with a Monte Carlo simulation for the continuous image acquisition and processing with a slowly rotating SPECT camera. Methods: A clinically realistic Monte Carlo (MC) simulation is developed using the 4D Extended Cardiac Torso (XCAT) digital phantom with respiratory and cardiac motion to model continuous data acquisition of dynamic cardiac SPECT with slowly rotating gamma cameras by incorporating deformation and displacement of the myocardium due to cardiac and respiratory motion. We extended our previously developed 4D maximum-likelihood expectation-maximization (MLEM) reconstruction algorithm for a data set binned from a continuous list mode (LM) simulation with cardiac and respiratory information. Our spatiotemporal image reconstruction uses splines to explicitly model the temporal change of the tracer for each cardiac and respiratory gate that delineates the myocardial spatial position as the tracer washes in and out. Unlike in a fully list-mode data acquisition and reconstruction the accumulated photons are binned over a specific but very short time interval corresponding to each cardiac and respiratory gate. Reconstruction results are presented showing the dynamics of the tracer in the myocardium as it continuously deforms. These results are then compared with the conventional 4D spatiotemporal reconstruction method that models only the temporal changes of the tracer activity. Mean Stabilized Activity (MSA), signal to noise ratio (SNR) and Bias for the myocardium activities for three different target-to-background ratios (TBRs) are evaluated. Dynamic quantitative indices such as wash-in (K1) and wash-out (k2) rates at each gate were also estimated. Results: The MSA and SNR are higher with higher TBRs while biases were improved with higher TBRs to less than 10%. The correlation between exhalation-inhalation sequence with the ground truth during respiratory cycle was excellent. Our reconstruction method showed better resolved myocardial walls during diastole to systole as compared to the ungated 4D image. Estimated values of K1 and k2 were also consistent with the ground truth. Conclusion: The continuous image acquisition for dynamic scan using conventional two-head gamma cameras can provide valuable information for MPI. Our study demonstrated the viability of using a continuous image acquisition method on a widely used clinical two-head SPECT system. Our reconstruction method showed better resolved myocardial walls during diastole to systole as compared to the ungated 4D image. Precise implementation of reconstruction algorithms, better segmentation techniques by generating images of different tissue types and background activity would improve the feasibility of the method in real clinical environment.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

Characterization of Plasma Protein Alterations in Pregnant and Postpartum Individuals Living With HIV to Support Physiologically-Based Pharmacokinetic Model Development

Alterations in plasma protein concentrations in pregnant and postpartum individuals can influence antiretroviral (ARV) pharmacokinetics. Physiologically-based pharmacokinetic (PBPK) models can serve to inform drug dosing decisions in understudied populations. However, development of such models requires quantitative physiological information (e.g., changes in plasma protein concentration) from the population of interest. Objective: To quantitatively describe the time-course of albumin and α1-acid glycoprotein (AAG) concentrations in pregnant and postpartum women living with HIV. Serum and plasma protein concentrations procured from the International Maternal Pediatric Adolescent AIDS Clinical Trial Protocol 1026s (P1026s) were analyzed using a generalized additive modeling approach. Separate non-parametric smoothing splines were fit to albumin and AAG concentrations as functions of gestational age or postpartum duration. The analysis included 871 and 757 serum albumin concentrations collected from 380 pregnant (~20 to 42 wks gestation) and 354 postpartum (0 to 46 wks postpartum) women, respectively. Thirty-six and 32 plasma AAG concentrations from 31 pregnant (~24 to 38 wks gestation) and 30 postpartum women (~2–13 wks postpartum), respectively, were available for analysis. Estimated mean albumin concentrations remained stable from 20 wks gestation to term (33.4 to 34.3 g/L); whereas, concentrations rapidly increased postpartum until stabilizing at ~42.3 g/L 15 wk after delivery. Estimated AAG concentrations slightly decreased from 24 wks gestation to term (53.6 and 44.9 mg/dL) while postpartum levels were elevated at two wks after delivery (126.1 mg/dL) and subsequently declined thereafter. Computational functions were developed to quantitatively communicate study results in a form that can be readily utilized for PBPK model development. By characterizing the trajectory of plasma protein concentrations in pregnant and postpartum women living with HIV, our analysis can increase confidence in PBPK model predictions for HIV antiretrovirals and better inform drug dosing decisions in this understudied population.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

Machine Learning Driven Contouring of High-Frequency Four-Dimensional Cardiac Ultrasound Data

Automatic boundary detection of 4D ultrasound (4DUS) cardiac data is a promising yet challenging application at the intersection of machine learning and medicine. Using recently developed murine 4DUS cardiac imaging data, we demonstrate here a set of three machine learning models that predict left ventricular wall kinematics along both the endo- and epi-cardial boundaries. Each model is fundamentally built on three key features: (1) the projection of raw US data to a lower dimensional subspace, (2) a smoothing spline basis across time, and (3) a strategic parameterization of the left ventricular boundaries. Model 1 is constructed such that boundary predictions are based on individual short-axis images, regardless of their relative position in the ventricle. Model 2 simultaneously incorporates parallel short-axis image data into their predictions. Model 3 builds on the multi-slice approach of model 2, but assists predictions with a single ground-truth position at end-diastole. To assess the performance of each model, Monte Carlo cross validation was used to assess the performance of each model on unseen data. For predicting the radial distance of the endocardium, models 1, 2, and 3 yielded average R2 values of 0.41, 0.49, and 0.71, respectively. Monte Carlo simulations of the endocardial wall showed significantly closer predictions when using model 2 versus model 1 at a rate of 48.67%, and using model 3 versus model 2 at a rate of 83.50%. These finding suggest that a machine learning approach where multi-slice data are simultaneously used as input and predictions are aided by a single user input yields the most robust performance. Subsequently, we explore the how metrics of cardiac kinematics compare between ground-truth contours and predicted boundaries. We observed negligible deviations from ground-truth when using predicted boundaries alone, except in the case of early diastolic strain rate, providing confidence for the use of such machine learning models for rapid and reliable assessments of murine cardiac function. To our knowledge, this is the first application of machine learning to murine left ventricular 4DUS data. Future work will be needed to strengthen both model performance and applicability to different cardiac disease models.

4D ultrasound↗
DOE OSTI2022

Generation of Data-Driven Expected Energy Models for Photovoltaic Systems

Although unique expected energy models can be generated for a given photovoltaic (PV) site, a standardized model is also needed to facilitate performance comparisons across fleets. Current standardized expected energy models for PV work well with sparse data, but they have demonstrated significant over-estimations, which impacts accurate diagnoses of field operations and maintenance issues. This research addresses this issue by using machine learning to develop a data-driven expected energy model that can more accurately generate inferences for energy production of PV systems. Irradiance and system capacity information was used from 172 sites across the United States to train a series of models using Lasso linear regression. The trained models generally perform better than the commonly used expected energy model from international standard (IEC 61724-1), with the two highest performing models ranging in model complexity from a third-order polynomial with 10 parameters (Radj2 = 0.994) to a simpler, second-order polynomial with 4 parameters (Radj2=0.993), the latter of which is subject to further evaluation. Subsequently, the trained models provide a more robust basis for identifying potential energy anomalies for operations and maintenance activities as well as informing planning-related financial assessments. We conclude with directions for future research, such as using splines to improve model continuity and better capture systems with low (≤1000 kW DC) capacity.

14 SOLAR ENERGY↗