Search NASA⌕ Search

SEARCH · Search NASA

Results for “Model 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.

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

At least 1,657 records · Page 92

A Fusion of Geothermal and InSAR Data with Machine Learning for Enhanced Deformation Forecasting at the Geysers

The Geysers geothermal field in California is experiencing land subsidence due to the seismic and geothermal activities taking place. This poses a risk not only to the underlying infrastructure but also to the groundwater level which would reduce the water availability for the local community. Because of this, it is crucial to monitor and assess the surface deformation occurring and adjust geothermal operations accordingly. In this study, we examine the correlation between the geothermal injection and production rates as well as the seismic activity in the area, and we show the high correlation between the injection rate and the number of earthquakes. This motivates the use of this data in a machine learning model that would predict future deformation maps. First, we build a model that uses interferometric synthetic aperture radar (InSAR) images that have been processed and turned into a deformation time series using LiCSBAS, an open-source InSAR time series package, and evaluate the performance against a linear baseline model. The model includes both convolutional neural network (CNN) layers as well as long short-term memory (LSTM) layers and is able to improve upon the baseline model based on a mean squared error metric. Then, after getting preprocessed, we incorporate the geothermal data by adding them as additional inputs to the model. This new model was able to outperform both the baseline and the previous version of the model that uses only InSAR data, motivating the use of machine learning models as well as geothermal data in assessing and predicting future deformation at The Geysers as part of hazard mitigation models which would then be used as fundamental tools for informed decision making when it comes to adjusting geothermal operations.

Yazbeck, Joe (ORCID:0000000302235260)↗

Data-driven estimation of energy consumption for electric bus under real-world driving conditions

Reliable and accurate estimation of an electric bus’s instantaneous energy consumption is critical in evaluating energy impacts of planning and control of electric bus operations. In this study, we developed machine learning-based long short-term memory (LSTM) and artificial neural network (ANN) models to estimate 1 Hz energy consumption of electric buses based on continuous monitoring data of electric buses in Chattanooga, Tennessee, in 2019 and 2020. We propose a data-partitioning algorithm to separate energy charging and discharging modes before applying data-driven estimation models. Here, a K-fold cross-validation-based model selection process was conducted to identify the optimal model structure and input variables in terms of prediction accuracy. The estimation results show the predicted mean absolute percentage error rates of LSTM and ANN models were 3% and 5%, respectively. We compared the proposed models with existing models in the literature based on the same testing data to demonstrate the predictability of our models.

Artificial neural network↗

Integration, Validation, and Application of a PV Snow Coverage Model in SAM

Due to the increasing deployment of PV systems in snowy climates, there is significant interest in a method capable of estimating PV losses resulting from snow coverage that has been verified for a wide variety of system designs and locations. A scattering of independent snow coverage models have been developed over the last 15 years; however, there has been very little effort spent on verifying these models beyond the system design and location on which they were based. Moreover, none of the major PV modeling software products have incorporated any of these models into their workflow. In response to this deficiency, we have integrated the methodology of the snow model developed in the paper by Marion et al. [1] into the National Renewable Energy Laboratory's (NREL) System Advisor Model (SAM). In this work we describe how the snow model is implemented in SAM and discuss our demonstration of the model's effectiveness at reducing error in annual estimations for two PV arrays. Following this, we use this new functionality in conjunction with a long term historical dataset to estimate average snow losses across the United States for a typical PV system design. The open availability of the snow loss estimation capability in SAM to the PV modeling community, coupled with our results of the nation-wide study, will better equip the industry to accurately estimate PV energy production in areas affected by snowfall.

14 SOLAR ENERGY↗

Integration, Validation, and Application of a PV Snow Coverage Model in SAM

Due to the increasing deployment of PV systems in snowy climates, there is significant interest in a method capable of estimating PV losses resulting from snow coverage that has been verified for a variety of system designs and locations. Many independent snow coverage models have been developed over the last 15 years; however, there has been very little effort verifying these models beyond the system designs and locations on which they were based. Moreover, major PV modeling software products have not yet incorporated any of these models into their workflows. In response to this deficiency, we have integrated the methodology of the snow model developed in the paper by Marion et al. (2013) into the National Renewable Energy Laboratory's (NREL) System Advisor Model (SAM). In this work, we describe how the snow model is implemented in SAM and we discuss our demonstration of the model's effectiveness at reducing error in annual estimations for three PV arrays. Next, we use this new functionality in conjunction with a long term historical data set to estimate average snow losses across the United States for two typical PV system designs. The open availability of the snow loss estimation capability in SAM to the PV modeling community, coupled with our results of the nationwide study, will better equip the industry to accurately estimate PV energy production in areas affected by snowfall.

14 SOLAR ENERGY↗

On the accuracy of the rate coefficients used in plasma fluid models for breakdown in air

The electrical breakdown of air depends on the balance between creation and loss of charged particles. In fluid models, datasets of the rate coefficients used are obtained either from fits to experimental data or by solutions of the Boltzmann equation. Here, we study the accuracy of the commonly used models for ionization and attachment frequencies and their impact on the prediction of the breakdown threshold for air. We show that large errors can occur depending on the model and propose the most accurate dataset available for modeling of air breakdown phenomena.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Assessing Alignment Between a Top-Down LCA Model and a Bottom-Up Supply Chain Model for Data Gap Identification and Prioritization

This work presents a method for evaluating the alignment between the results of bottom-up and top-down models and using the evaluation to enhance the bottom-up model and underlying data set. Disaggregation is used to enhance the embodied energy results of top-down models, which are then compared to bottom-up model results. Using the disaggregated top-down results makes it possible to identify specific data gaps and deficiencies within the bottom-up model and its data set. The top-down results will also provide information around which data gaps in the bottom-up model are contributing the most error to the results; in this way, data gaps can be identified as either critical or non-critical, and the effort needed to acquire and add data can be prioritized. Although the proposed method could be applied to any physical quantity or environmental impact that can be quantified with both bottom-up models (typically in physical units) and top-down models (typically in monetary units), embodied energy is the focus of this work. The disaggregated energy baseline is calculated from the throughput vector x, which gives the total economic activity required from each sector to provide a final demand. Using the direct requirements matrix, each element in x is disaggregated into a vector of inputs to the corresponding sector. Energy data from the interventions matrix B is then used to convert the monetary flows of the disaggregated x into physical energy flows. For each energy flow, the origin sector, the destination sector, and the energy carrier type will all be known. These energetic flows are analogous but not identical to direct energy inputs that would appear in a unit process used in life cycle analysis and other bottom-up methods, and thus can be used to evaluate the alignment between the top-down results and the results of a bottom-up model. To demonstrate and further develop the proposed method, embodied energy for chemicals assessed in the 2015 U.S. DOE bandwidth study on energy use within the chemical sector will be calculated using a top-down and a bottom-up model. The Materials Flows through Industry (MFI) modeling tool developed at the National Renewable Energy Laboratory is used as the bottom-up model, and the U.S. EEIO model, recently published by the U.S. Environmental Protection Agency, is used as the top-down model. U.S. EEIO and MFI results will be evaluated to determine how well the model results align. Where the two models are not in good alignment, the disaggregation method described above will be applied to the top-down model to generate a more detailed set of results that will aid in identifying data gaps in the MFI database. Using only MFI, data gaps can be identified in terms of which sectors have few or no unit processes in the database, but no information is available regarding the impact of the missing data on MFI results. The disaggregated top-down results will provide this information on which gaps in the MFI data are critical and have a significant impact on the results, and which are less important.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Solving Drift-flux Model Using High-Resolution Spatial Discretization Scheme

Accurate modeling and simulation of the two-phase flow phenomena are critical to the system and safety analysis of light water reactors. Compared to the more complex two-fluid model, the drift-flux model treats the two phases as a mixture, and thus the models are formulated to consider the conservation laws of the mixture. The relative motion between the two phases is realized by constitutive correlations. Although the drift flux models have limitations in certain applications, they are widely used in many applications due to their simplicity and applicability to a wide range of two-phase flow problems. First-order numerical schemes are widely used in existing codes, which introduces excessive numerical diffusions. The objective of this work is to investigate a high-resolution spatial scheme in the application to solve drift-flux two-phase flow problems. In this study, a high-resolution spatial discretization scheme has been investigated in the application of solving drift-flux two-phase flow problem. The scheme is validated using existing experimental results. Compared to the first order scheme, it demonstrated excellent capability in reducing numerical error. Extended work will focus on the comparison of numerical errors from discretization schemes and model uncertainties. (authors)

42 ENGINEERING↗

Graph-Based Approaches for Predicting Solvation Energy in Multiple Solvents: Open Datasets and Machine Learning Models

The solvation properties of molecules, often estimated using quantum chemical simulations, are important in the synthesis of energy storage materials, drugs, and industrial chemicals. Here, we develop machine learning models of solvation energies to replace expensive quantum chemistry calculations with inexpensive-to-compute message-passing neural network models that require only the molecular graph as inputs. Our models are trained on a new database of solvation energies for 130,258 molecules taken from the QM9 dataset computed in five solvents (acetone, ethanol, acetonitrile, dimethyl sulfoxide, and water) via an implicit solvent model. Our best model achieves a mean absolute error of 0.5 kcal/mol for molecules with nine or fewer non-hydrogen atoms and 1 kcal/mol for molecules with between 10 and 14 non-hydrogen atoms. We make the entire dataset of 651,290 computed entries openly available and provide simple web and programmatic interfaces to enable others to run our solvation energy model on new molecules. This model calculates the solvation energies for molecules using only the SMILES string and also provides an estimate of whether each molecule is within the domain of applicability of our model. We envision that the dataset and models will provide the functionality needed for the rapid screening of large chemical spaces to discover improved molecules for many applications.

25 ENERGY STORAGE↗

Quantifying prediction fidelity in multiscale multiphysics simulations.

Multiscale multiphysics problems arise in a host of application areas of significant relevance to DOE, including electrical storage systems (membranes and electrodes in fuel cells, batteries, and ultracapacitors), water surety, chemical analysis and detection systems, and surface catalysis. Multiscale methods aim to provide detailed physical insight into these complex systems by incorporating coupled effects of relevant phenomena on all scales. However, many sources of uncertainty and modeling inaccuracies hamper the predictive fidelity of multiscale multiphysics simulations. These include parametric and model uncertainties in the models on all scales, and errors associated with coupling, or information transfer, across scales/physics. This presentation introduces our work on the development of uncertainty quantification methods for spatially decomposed atomistic-to-continuum (A2C) multiscale simulations. The key thrusts of this research effort are: inference of uncertain parameters or observables from experimental or simulation data; propagation of uncertainty through particle models; propagation of uncertainty through continuum models; propagation of information and uncertainty across model/scale interfaces; and numerical and computational analysis and control. To enable the bidirectional coupling between the atomistic and continuum simulations, a general formulation has been developed for the characterization of sampling noise due to intrinsic variability in particle simulations, and for the propagation of both this sampling noise and parametric uncertainties through coupled A2C multiscale simulations. Simplified tests of noise quantification in particle computations are conducted through Bayesian inference of diffusion rates in an idealized isothermal binary material system. A proof of concept is finally presented based on application of the present formulation to the propagation of uncertainties in a model plane Couette flow, where the near wall region is handled with molecular dynamics while the bulk region is handled with continuum methods.

30 DIRECT ENERGY CONVERSION↗

Statistical and Neural Network for Real Sensor-Data-Driven Anomaly Detection in Nuclear Applications

Anomaly detection (AD) in sensor data is critical to ensure uninterrupted functionality of nuclear power plants (NPPs). Consequently, AD model validation through real-world sensor data is important for applications in nuclear facilities. In this paper, we propose an Autoencoder (AE)—a multi-layered neural network, for AD in sensor data from an operational NPP testbed. Since the dataset lacks labels for irregularities, we introduce random noise and label them to effectively train our model. The proposed AE model assigns a higher reconstruction error to the abnormal samples that deviate from those encountered during the training phase and uses the reconstruction loss to detect anomalies in a representative imbalanced dataset. We also introduce an analytical solution—seasonal trend decomposition (STD)—as another AD scheme for identifying irregularities withinthe same time-series dataset. In contrast to the AE model which relies on reconstruction loss, the STD scheme decomposes the entire dataset into its trend, seasonality, and residual components to pinpoint irregularities. Our findings indicate that the proposed AE and STD models individually achieve recall scores of 97% and 92%, respectively. We validate the performance of the two models on both balanced and imbalanced data. We further solidify the results by picking the combined selected anomalies of the two solutions with an "AND" operator for more reliable predictions.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Statistical and Neural Network for Real Sensor-Data-Driven Anomaly Detection in Nuclear Applications

Anomaly detection (AD) in sensor data is critical to ensure uninterrupted functionality of nuclear power plants (NPPs). Consequently, validation of AD models through real-world sensor data is important for their application in nuclear facilities. In this paper, we propose an Autoencoder (AE)— a multi-layered neural network, for AD in sensor data from an operational NPP testbed. Since the dataset lacks labels for irregularities, we introduce random noise and label them to effectively train our model. The proposed AE model assigns a higher reconstruction error to the abnormal samples that deviate from those encountered during the training phase and uses the reconstruction loss to detect anomalies in a representative imbalanced dataset. We also introduce an analytical solution—seasonal trend decomposition (STD) — as another AD scheme for identifying irregularities within the same time-series dataset. In contrast to the AE model which relies on reconstruction loss, the STD scheme decomposes the entire dataset into its trend, seasonality, and residual components to pinpoint irregularities. Our findings indicate that the proposed AE and STD models individually achieve recall scores of 97% and 92%, respectively. We also validate the performance of the two models on both balanced and imbalanced data. We further solidify the results by picking the combined selected anomalies of the two solutions with an "AND" operator for more reliable predictions.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Issue Resolution During the Development of the Performance Assessment for the Savannah River Site Saltstone Disposal Facility - 20125

In 2019, Savannah River Remediation developed a revision to the performance assessment (PA) on behalf of the U.S. Department of Energy (DOE) Savannah River Operations Office (SR) for the near-surface disposal of low-level waste at the Savannah River Site (SRS) Saltstone Disposal Facility (SDF). Soluble waste from SRS Tank Farms undergoes salt processing to remove cesium and other high-activity constituents. The low-activity decontaminated salt solution (DSS) is then immobilized by mixing it into a cementitious waste form known as saltstone. After mixing, the saltstone is poured into leak-tight concrete vaults, known as saltstone disposal units (SDUs), where the waste form cures. By the time of facility closure, the SDF is expected to consist of 15 SDUs with a combined capacity of 1.06 E+09 L (280 Mgal) of cured saltstone. The facility operates under a Disposal Authorization Statement from DOE and a permit from the South Carolina Department of Health and Environmental Control (SCDHEC). Since the start of operations in 1990, the SDF has received almost 6.7 E+07 L (18 Mgal) of DSS, resulting in the safe disposal of 2.7 E+16 Bq (7.3 E+05 Ci) of activity. Due to the radioactive decay of short-lived contaminants, the total remaining activity in the disposed waste is estimated to be approximately 1.4 E+16 Bq (3.9 E+05 Ci), as of September 2018. The Disposal Authorization Statement requires a demonstration that the system of engineered and natural features of the disposal facility will limit releases from the facility and be protective of human health and the environment for at least the next 1,000 years. The long-term performance of the facility was evaluated under the requirements of the DoE's Radioactive Waste Management Manual (US DOE Manual 435.1-1). Simulations were performed to demonstrate that the disposal facility would meet performance objectives specified in the manual. The evaluation was based on numerical models that simulate the releases of contaminants from the saltstone waste form. Contaminants were transported through groundwater and air pathways to points of assessment to evaluate compliance (i.e., 100 m from the SDUs). In addition, the potential consequences of an inadvertent human intrusion (IHI) were also evaluated. A number of issues were overcome during the development of these simulations. These issues were identified as part of internal technical reviews. Simulations are developed by people and people make mistakes, so the internal technical review process is a vital step in PA development. Specific examples of resolved issues include a unit-conversion error, an inappropriate definition for a model boundary condition, a model time-stepping issue, and an error in the calculation for the buildup of contaminants in soil. Actions taken to address these issues resulted in an improved product with a better supported technical basis and more defensible results. The identification and correction of these issues are discussed. By understanding these issues, model developers and technical reviewers working on PAs in the future may avoid repeating these types of mistakes. Transparency with respect to these mistakes builds trust between waste management sites, regulators, and stakeholders. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Toward equitable environmental exposure modeling through convergence of data, open, and citizen sciences: an example of air pollution exposure modeling amidst increasing wildfire smoke

Exposure modeling is critical in environmental epidemiology and human health but may face challenges (e.g., skewed data, unequal error, context-insensitive validation, and computational demands). Modeling decisions reflect the intended use of the models and the values that modelers prioritize. We aimed to provide a conceptual framework and machine learning (ML) modeling protocols that address these issues. With 500m-gridded hourly PM 2.5 and O 3 levels in Illinois before, during, and after the 2023 Canadian wildfire season as a motivating example, we conducted modeling experiments to evaluate modeling methods, guided by three domains we propose based on theories of science: 1) Data Diversity, leveraging open and citizen science data to enhance inclusivity, parsimony, and representativeness; 2) Equitable Accuracy, ensuring fairly distributed uncertainties across subpopulations; and 3) Sustainable Modeling, balancing accuracy with reducing computational demands to promote accessibility for under-resourced researchers. Here, we found that ML with publicly available data can achieve high accuracy. Depending on methods, performance may vary substantially, even with identical input data. Large but skewed data may reduce performance. Misuse of cross-validation protocols can underestimate prediction error; although we observed R 2 s of ∼98 %, the modeled estimates varied significantly, indicating the need for careful model validation. By using new modeling protocols including representativeness-considered training and validation data and a new loss function, we achieved high agreement between estimates and ground-based measurements (e.g., R 2 = ∼90 % for PM 2.5 ; ∼80 % for O 3 ), equally distributed errors across sociodemographic strata and urban–rural divides, and reduction in computation time—from several weeks or months to a few days.

Exposure assessment↗

An anomaly detection framework for dynamic systems using a Bayesian hierarchical framework

Complex systems are susceptible to many types of anomalies, faults, and abnormal behavior caused by a variety of off-nominal conditions that may ultimately result in major failures or catastrophic events. Early and accurate detection of these anomalies using system inputs and outputs collected from sensors and smart devices has become a challenging problem and an active area of research in many application domains. In this article, we present a new Bayesian hierarchical framework that is able to model the relationship between system inputs (sensor measurements) and outputs (response variables) without imposing strong distributional/parametric assumptions while using only a subset of training samples and sensor attributes. Then, an optimal cost-sensitive anomaly detection framework is proposed to determine whether a sample is an anomalous one taking into consideration the trade-off between misclassification errors and detection rates. The model can be used for both supervised and unsupervised settings depending on the availability of data regarding the behavior of the system under anomaly conditions. The unsupervised model is particularly useful when it is prohibitive to identify in advance the anomalies that a system may present and where no data are available regarding the behavior of the system under anomaly conditions. A Bayesian hierarchical setting is used to structure the proposed framework and help with accommodating uncertainty, imposing interpretability, and controlling the sparsity and complexity of the proposed anomaly detection framework. A Markov chain Monte Carlo algorithm is also developed for model training using past data. Furthermore, the numerical experiments conducted using a simulated data set and a wind turbine data set demonstrate the successful application of the proposed work for system response modeling and anomaly detection.

17 WIND ENERGY↗

Reconstructing Richtmyer–Meshkov instabilities from noisy radiographs using low dimensional features and attention-based neural networks

We develop an ML-based approach for density reconstruction based on transformer neural networks. This approach is demonstrated in the setting of ICF-like double shell hydrodynamic simulations wherein the parameters related to material properties and initial conditions are varied. The new method can robustly recover the complex topologies given by the Richtmyer-Meshkoff instability (RMI) from a sequence of hydrodynamic features derived from radiographic images corrupted with blur, scatter, and noise. A noise model is developed to characterize errors in extracting features from synthetic radiographs of the simulated density field. The key component of the network is a transformer encoder that acts on a sequence of features extracted from noisy radiographs. This encoder includes numerous self-attention layers that act to learn temporal dependencies in the input sequences and increase the expressiveness of the model. This approach is shown to exhibit an excellent ability to accurately recover the RMI growth rates, despite the gas-metal interface being greatly obscured by radiographic noise. Our approach can be applied in a broad array of fields involving shock physics and material science.

47 OTHER INSTRUMENTATION↗

Dark Energy Survey Year 3 Results: Constraints on cosmological parameters and galaxy bias models from galaxy clustering and galaxy-galaxy lensing using the redMaGiC sample

We constrain cosmological parameters and galaxy-bias parameters using the combination of galaxy clustering and galaxy-galaxy lensing measurements from the Dark Energy Survey Year-3 data. We describe our modeling framework and choice of scales analyzed, validating their robustness to theoretical uncertainties in small-scale clustering by analyzing simulated data. Using a linear galaxy bias model and redMaGiC galaxy sample, we obtain constraints on the matter content of the universe to be $\Omega_{\rm m} = 0.325^{+0.033}_{-0.034}$. We also implement a non-linear galaxy bias model to probe smaller scales that includes parameterizations based on hybrid perturbation theory, and find that it leads to a 17% gain in cosmological constraining power. Using the redMaGiC galaxy sample as foreground lens galaxies, we find the galaxy clustering and galaxy-galaxy lensing measurements to exhibit significant signals akin to decorrelation between galaxies and mass on large scales, which is not expected in any current models. This likely systematic measurement error biases our constraints on galaxy bias and the $S_8$ parameter. We find that a scale-, redshift- and sky-area-independent phenomenological decorrelation parameter can effectively capture this inconsistency between the galaxy clustering and galaxy-galaxy lensing. We perform robustness tests of our methodology pipeline and demonstrate stability of the constraints to changes in the theory model. After accounting for this decorrelation, we infer the constraints on the mean host halo mass of the redMaGiC galaxies from the large-scale bias constraints, finding the galaxies occupy halos of mass approximately $1.5 \times 10^{13} M_{\odot}/h$.

79 ASTRONOMY AND ASTROPHYSICS↗

Machine-Learned Linear Structural Dynamics

The tension between accuracy and computational cost is a common thread throughout computational simulation. One such example arises in the modeling of mechanical joints. Joints are typically confined to a physically small domain and yet are computationally expensive to model with a high-resolution finite element representation. A common approach is to substitute reduced-order models that can capture important aspects of the joint response and enable the use of more computationally efficient techniques overall. Unfortunately, such reduced-order models are often difficult to use, error prone, and have a narrow range of application. In contrast, we propose a new type of reduced-order model, leveraging machine learning, that would be both user-friendly and extensible to a wide range of applications.

97 MATHEMATICS AND COMPUTING↗