Search NASA⌕ Search

SEARCH · Search NASA

Results for “mean squared 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 883 records · Page 49

Bias-Variance Trade-Off in Physics-Informed Neural Networks with Randomized Smoothing for High-Dimensional PDEs

Physics-Informed Neural Networks (PINNs) have triggered a paradigm shift in scientific computing, leveraging mesh-free properties and robust approximation capabilities. While proving effective for low-dimensional partial differential equations (PDEs), the computational cost of PINNs remains a hurdle in high-dimensional scenarios. This is particularly pronounced when computing high-order and high-dimensional derivatives in the physics-informed loss. Randomized Smoothing PINN (RS-PINN) introduces Gaussian noise for stochastic smoothing of the original neural net model, enabling the use of Monte Carlo methods for derivative approximation, which eliminates the need for costly automatic differentiation. Despite its computational efficiency, especially in the approximation of high-dimensional derivatives, RS-PINN introduces biases in both loss and gradients, negatively impacting convergence, especially when coupled with stochastic gradient descent (SGD) algorithms. We present a comprehensive analysis of biases in RS-PINN, attributing them to the nonlinearity of the Mean Squared Error (MSE) loss as well as the intrinsic nonlinearity of the PDE itself. We propose tailored bias correction techniques, delineating their application based on the order of PDE nonlinearity. The derivation of an unbiased RS-PINN allows for a detailed examination of its advantages and disadvantages compared to the biased version. Specifically, the biased version has a lower variance and runs faster than the unbiased version, but it is less accurate due to the bias. To optimize the bias-variance trade-off, we combine the two approaches in a hybrid method that balances the rapid convergence of the biased version with the high accuracy of the unbiased version. In addition to methodological contributions, we present an enhanced implementation of RS-PINN. Extensive experiments on diverse high-dimensional PDEs, including Fokker-Planck, Hamilton-Jacobi-Bellman (HJB), viscous Burgers’, Allen-Cahn, and Sine-Gordon equations, illustrate the bias-variance trade-off and highlight the effectiveness of the hybrid RS-PINN. Empirical guidelines are provided for selecting biased, unbiased, or hybrid versions, depending on the dimensionality and nonlinearity of the specific PDE problem.

97 MATHEMATICS AND COMPUTING↗

Stand validation of lidar forest inventory modeling for a managed southern pine forest

We evaluated area-based approaches (ABAs) to light detection and ranging (lidar) predictions of plot- and stand-level forest attributes (tree count, height, basal area, volume, aboveground biomass, broadleaf/conifer, and diameter at breast height — “diameter”). ABA methods included post-stratification (PS), ordinary least squares (OLSs) regression, k nearest neighbors ( kNN), and random forest (RF). This study was conducted on the Savannah River Site in South Carolina, USA. Plot- and stand-level predictions were validated against fixed-radius 0.04 ha (0.1 acre) plots in 49 ≈2.0 ha (5 acre) stands. Our findings demonstrate that lidar can be incorporated operationally into forest inventory systems to provide stand-level inferences for a wide range of forest attributes. Volume predictions for specific diameter classes, however, often fared poorly (root mean squared error (RMSE) > 100%) for the methods we explored, especially for larger (less common) diameter trees. Stand-level results were consistently better than pixel-level results (10–200+ percentage points). kNN and RF performed similarly and better than OLS and PS, but RF was the most robust to model configurations, while kNN has practical advantages such as simultaneous predictions of many attributes.

Forestry↗

Machine Learning Assisted HPC Workload Trace Generation for Leadership Scale Storage Systems

Monitoring and analyzing a wide range of I/O activities in an HPC cluster is important in maintaining mission-critical performance in a large-scale, multi-user, parallel storage system. Center-wide I/O traces can provide high-level information and fine-grained activities per application or per user running in the system. Studying such large-scale traces can provide helpful insights into the system. It can be used to develop predictive methods for making predictive decisions, adjusting scheduling policies, or providing decisions for the design of next-generation systems. However, sharing real-world I/O traces to expedite such research efforts leaves a few concerns; i) the cost of sharing the large traces is expensive due to this large size, and ii) privacy concern is an issue.We address such issues by building an end-to-end machine learn- ing (ML) workflow that can generate I/O traces for large-scale HPC applications. We leverage ML based feature selection and gener- ative models for I/O trace generation. The generative models are trained on I/O traces collected by the darshan I/O characterization tool over a period of one year. We present a two-step generation process consisting of two deep-learning models, called the feature generator and the trace generator. The combination of two-step generative models provides robustness by reducing the bias of the model and accounting for the stochastic nature of the I/O traces across different runs of an application. We evaluate the performance of the generative models and show that the two-step model can generate time-series I/O traces with less than 20% root mean square error.

Paul, Arnab↗

Red-QAOA: Efficient Variational Optimization through Circuit Reduction

The Quantum Approximate Optimization Algorithm (QAOA) provides a quantum solution for combinatorial optimization problems. However, the optimal parameter searching process of QAOA is greatly affected by noise, leading to non-optimal solutions. This paper introduces a novel approach to optimize QAOA by exploiting the energy landscape concentration of similar instances via graph reduction, thus addressing the effect of noise. We formalize the notion of similar instances in QAOA and develop a Simulated Annealing-based graph reduction algorithm, called Red-QAOA, to identify the most similar subgraph for efficient parameter optimization. Red-QAOA outperforms state-of-the-art Graph Neural Network (GNN) based graph pooling techniques in performance and demonstrates effectiveness on a diverse set of real-world optimization problems encompassing 3200 graphs. Red-QAOA reduced the node counts and edge counts by 28% and 37%, respectively, while maintaining a low mean square error of 2%. These enable the identification of an optimal parameter set that is closer to the ideal true optimal solution in the presence of noise. By substantially streamlining the search for QAOA parameters, our approach sets the stage for the practical application of quantum algorithms in solving complex optimization problems.

Wang, Meng↗

Non-Invasive Electrode Impedance Estimation for Optimized Charge Profile Parameterization of Lithium-Ion Batteries

This work presents a non-invasive method for parameterizing a physically motivated equivalent circuit model of lithium-ion batteries using operando electrochemical impedance spectroscopy and time-domain data. The proposed model consists exclusively of linear circuit elements, enabling computationally efficient simulation and real-time implementation on battery management system chips. By integrating frequency- and time-domain measurements, the model accurately estimates internal states such as the negative electrode potential, achieving a root mean square error of 12.3 mV during fast charging validation. Parameterization requires only rate tests with sinusoidal perturbations at three different ambient temperatures, making the approach experimentally accessible. The model reveals key insights into battery behavior, including rate-dependent overpotentials primarily governed by charge transfer kinetics at the positive electrode, and temperature-dependent impedance contributions from both charge transfer and solid-state diffusion processes. Validation using reference electrodes confirms the model’s ability to detect lithium plating onset and reproduce impedance behavior across a wide range of operating conditions. The approach enables in situ optimization of fast charging profiles and lays the foundation for future extensions incorporating aging effects and plating dynamics.

25 ENERGY STORAGE↗

GPU-Accelerated Denoising in 3D (GD3D)

The raw computational power GPU Accelerators enables fast denoising of 3D MR images using bilateral filtering, anisotropic diffusion, and non-local means. This software addresses two facets of this promising application: what tuning is necessary to achieve optimal performance on a modern GPU? And what parameters yield the best denoising results in practice? To answer the first question, the software performs an autotuning step to empirically determine optimal memory blocking on the GPU. To answer the second, it performs a sweep of algorithm parameters to determine the combination that best reduces the mean squared error relative to a noiseless reference image.

Howison, Mark↗

Fusion RF Modeling Machine Learning (FusionML_RF) v1.0

FusionML_RF consists of multiple codes and trained machine learning (ML) models that perform low-cost output modeling from the Genray-CQL3D. Three machine learning techniques (multilayer perceptron, random forest, and Gaussian process) provide fast surrogate models for lower hybrid current drive (LHCD) simulations. For example, completing a single GENRAY/CQL3D simulation without radial diffusion of fast electrons requires several minutes of wall-clock time. On the other hand, these ML models achieve ~ms of inference time with high accuracy across the input parameter space. This software collection consists of multiple components. (1) codes that use ML methods and precomputed Genray-CQL3D simulation output to build regression models that enable approximate computations of Genray-CLQ3D outputs from arbitrary but physically meaningful input parameters (surrogate modeling); (2) three trained models created by the team, using a database of 16,000+ GENRAY/CQL3D simulations, to study the performance of ML models for surrogate modeling; (3) codes that load the trained models and simulation data, and then compute mean squared error between the models' predictions and the ground truth of simulation output data. This collection is being made available in conjunction with a scientific publication about the work to promote reusability and provide an artifact of the scientific work.

Bai, Zhe↗

Deep machine learning-assisted multiphoton microscopy to reduce light exposure and expedite imaging

Two-photon excitation fluorescence (2PEF) allows imaging of tissue up to about one millimeter in thickness. Typically, reducing fluorescence excitation exposure reduces the quality of the image. However, using deep learning super resolution techniques, these low-resolution images can be converted to high-resolution images. This work explores improving human tissue imaging by applying deep learning to maximize image quality while reducing fluorescence excitation exposure. We analyze two methods: a method based on U-Net, and a patch-based regression method. Both methods are evaluated on a skin dataset and an eye dataset. The eye dataset includes 1200 paired high power and low power images of retinal organoids. The skin dataset contains multiple frames of each sample of human skin. High-resolution images were formed by averaging 70 frames for each sample and low-resolution images were formed by averaging the first 7 and 15 frames for each sample. The skin dataset includes 550 images for each of the resolution levels. We track two measures of performance for the two methods: mean squared error (MSE) and structural similarity index measure (SSIM). For the eye dataset, the patches method achieves an average MSE of 27,611 compared to 146,855 for the U-Net method, and an average SSIM of 0.636 compared to 0.607 for the U-Net method. For the skin dataset, the patches method achieves an average MSE of 3.768 compared to 4.032 for the U-Net method, and an average SSIM of 0.824 compared to 0.783 for the U-Net method. Despite better performance on image quality, the patches method is worse than the U-Net method when comparing the speed of prediction, taking 303 seconds to predict one image compared to less than one second for the U-Net method.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

The Wind Forecast Improvement Project (WFIP): A Public–Private Partnership Addressing Wind Energy Forecast Needs

The Wind Forecast Improvement Project (WFIP) is a public–private research program, the goal of which is to improve the accuracy of short-term (0–6 h) wind power forecasts for the wind energy industry. WFIP was sponsored by the U.S. Department of Energy (DOE), with partners that included the National Oceanic and Atmospheric Administration (NOAA), private forecasting companies (WindLogics and AWS Truepower), DOE national laboratories, grid operators, and universities. WFIP employed two avenues for improving wind power forecasts: first, through the collection of special observations to be assimilated into forecast models and, second, by upgrading NWP forecast models and ensembles. The new observations were collected during concurrent year-long field campaigns in two high wind energy resource areas of the United States (the upper Great Plains and Texas) and included 12 wind profiling radars, 12 sodars, several lidars and surface flux stations, 184 instrumented tall towers, and over 400 nacelle anemometers. Results demonstrate that a substantial reduction (12%–5% for forecast hours 1–12) in power RMSE was achieved from the combination of improved numerical weather prediction models and assimilation of new observations, equivalent to the previous decade’s worth of improvements found for low-level winds in NOAA/National Weather Service (NWS) operational weather forecast models. Data-denial experiments run over select periods of time demonstrate that up to a 6% improvement came from the new observations. Ensemble forecasts developed by the private sector partners also produced significant improvements in power production and ramp prediction. Based on the success of WFIP, DOE is planning follow-on field programs.

17 WIND ENERGY↗

Evaluation of Various Methods for Estimating Global Solar Radiation in the Southeastern United States

Global solar radiation Rg is an important input for crop models to simulate crop responses. Because the scarcity of long and continuous records of Rg is a serious limitation in many countries, Rg is estimated using models. For crop-model application, empirical Rg models that use commonly measured meteorological variables, such as temperature and precipitation, are generally preferred. Although a large number of models of this kind exist, few have been evaluated for conditions in the United States. This study evaluated the performances of 16 empirical, temperature- and/or precipitation-based Rg models for the southeastern United States. By taking into account spatial distribution and data availability, 30 locations in the region were selected and their daily weather data spanning eight years obtained. One-half of the data was used for calibrating the models, and the other half was used for evaluation. For each model, location-specific parameter values were estimated through regressions. Models were evaluated for each location using the root-mean-square error and the modeling efficiency as goodness-of-fit measures. Among the models that use temperature or precipitation as the input variable, the Mavromatis model showed the best performance. The piecewise linear regression based Wu et al. model (WP) performed best not only among the models that use both temperature and precipitation but also among the 16 models evaluated, mainly because it has separate relationships for low and high radiation levels. The modeling efficiency of WP was from ~5% to more than 100% greater than those of the other models, depending on models and locations.

Irradiance, Model evaluation/performance, Agricult↗

Estimating Fine-Resolution Shortwave Broadband Albedo of Croplands from Harmonized Landsat and Sentinel-2 Data

Altered surface albedo due to land-cover conversions and management is a significant driver of global climate change. Albedo can be directly measured at ground stations, and remote sensing data can be used to scale-up albedo values to regional and global levels. Some previous studies have retrieved fine-resolution (10–30 m) instantaneous albedo and coarse-resolution (500–1000 m) daily mean albedo from remote sensing data, but they all required the input of Moderate Resolution Imaging Spectroradiometer (MODIS) albedo information at 500-m resolution, and none have assembled both instantaneous and daily albedo based exclusively on fine-resolution satellite data. Here, to address this issue, we compiled 387 instantaneous and 346 daily albedo records using field net radiometer measurements from the bioenergy croplands at the W. K. Kellogg Biological Station in southwest Michigan. We then connected these albedo records with a suite of variables derived from harmonized Landsat and Sentinel-2 data through two machine learning algorithms (random forest regression and extreme gradient boosting) to retrieve clear-sky instantaneous and daily shortwave broadband albedo. The performance statistics indicate reasonable accuracy of model results [root-mean-square error (RMSE)] around or below 0.03 except for snow-covered surfaces), suggesting that the retrieval of both instantaneous and daily albedo based exclusively on fine-resolution satellite data is promising. To facilitate the use of fine-resolution albedo products at the global level, future efforts need to include more albedo records of diverse surface cover types, as well as to accurately model daily albedo for cloudy days to address the “clear-sky bias.”

Harmonized Landsat and Sentinel-2↗

Corrigendum

In Schiemann et al. (2017), a mistake occurred in Fig. 11 in how the area-weighted cor-relation and root-mean-square error (RMSE) were calculated. The corrected figure appears below. This has no impact on the interpretation of the figure and on the conclusions of the paper. Any future quantitative comparisons will need to refer to the corrected version of the figure. We regret any inconvenience this may cause.

99 GENERAL AND MISCELLANEOUS↗

Representation of U.S. Warm Temperature Extremes in Global Climate Model Ensembles

Extreme temperature events can have considerable negative impacts on sectors such as health, agriculture, and transportation. Observational evidence indicates the severity and frequency of warm extremes are increasing over much of the United States, but there are sizeable challenges both in estimating extreme temperature changes and in quantifying the relevant associated uncertainties. This study provides a simple statistical framework using a block maxima approach to analyze the representation of warm temperature extremes in several recent global climate model ensembles. Uncertainties due to structural model differences, grid resolution, and internal variability are characterized and discussed. Results show that models and ensembles differ greatly in the representation of extreme temperature over the United States, and variability in tail events is dependent on time and anthropogenic warming, which can influence estimates of return periods and distribution parameter estimates using generalized extreme value (GEV) distributions. These effects can considerably influence the uncertainty of model hindcasts and projections of extremes. Several idealized regional applications are highlighted for evaluating ensemble skill and trends, based on quantile analysis and root-mean-square errors in the overall sample and the upper tail. The results are relevant to regional climate assessments that use global model outputs and that are sensitive to extreme warm temperature. Accompanying this manuscript is a simple toolkit using the R statistical programming language for characterizing extreme events in gridded datasets.

54 ENVIRONMENTAL SCIENCES↗

Understanding the Biases in Global Monsoon Simulations from the Perspective of Atmospheric Energy Transport

Understanding global monsoon (GM) variability and projecting its future changes rely heavily on climate models. However, climate models generally show pronounced biases in GM simulations, and the reasons for this remain unclear. Here, in this study, we evaluate the performance of 20 pairs of climate models that participated in both phase 5 of the Coupled Model Intercomparison Project (CMIP5) and phase 6 of CMIP (CMIP6) and identify the sources of their GM simulation biases from an energy transport perspective. The multimodel mean improvement in CMIP6 compared to CMIP5 is demonstrated by the increasing skill scores for various GM metrics from 0.20–0.79 to 0.48–0.83. More specifically, the dry biases in the Northern Hemisphere Summer Monsoon (NHSM) precipitation in CMIP5 [root-mean-square error (RMSE): 1.85 mm day −1 ] are reduced in CMIP6 (RMSE: 1.66 mm day −1 ). This higher simulation skill is associated with higher skill in simulating the precipitation-solstitial mode, monsoon intensity, and monsoon domains. The improvement in the NHSM precipitation simulation results from that in the meridional transport of atmospheric energy. Atmospheric energy budget analysis shows that the negative biases in downward surface longwave radiation and northward energy transport are smaller in CMIP6 than in CMIP5 in the boreal summer, resulting in a more realistic interhemispheric thermal contrast and meridional gradient of moist static energy. However, a major weakness of the CMIP6 models is found in the Southern Hemisphere Summer Monsoon precipitation simulation due to the positive bias in the top-of-the-atmosphere downward longwave radiation. This study shows that reasonably reproducing the meridional global atmospheric energy transportation is necessary for skillful GM simulation.

54 ENVIRONMENTAL SCIENCES↗

PERSIANN-CNN: Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks–Convolutional Neural Networks

Abstract Accurate and timely precipitation estimates are critical for monitoring and forecasting natural disasters such as floods. Despite having high-resolution satellite information, precipitation estimation from remotely sensed data still suffers from methodological limitations. State-of-the-art deep learning algorithms, renowned for their skill in learning accurate patterns within large and complex datasets, appear well suited to the task of precipitation estimation, given the ample amount of high-resolution satellite data. In this study, the effectiveness of applying convolutional neural networks (CNNs) together with the infrared (IR) and water vapor (WV) channels from geostationary satellites for estimating precipitation rate is explored. The proposed model performances are evaluated during summer 2012 and 2013 over central CONUS at the spatial resolution of 0.08° and at an hourly time scale. Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks (PERSIANN)–Cloud Classification System (CCS), which is an operational satellite-based product, and PERSIANN–Stacked Denoising Autoencoder (PERSIANN-SDAE) are employed as baseline models. Results demonstrate that the proposed model (PERSIANN-CNN) provides more accurate rainfall estimates compared to the baseline models at various temporal and spatial scales. Specifically, PERSIANN-CNN outperforms PERSIANN-CCS (and PERSIANN-SDAE) by 54% (and 23%) in the critical success index (CSI), demonstrating the detection skills of the model. Furthermore, the root-mean-square error (RMSE) of the rainfall estimates with respect to the National Centers for Environmental Prediction (NCEP) Stage IV gauge–radar data, for PERSIANN-CNN was lower than that of PERSIANN-CCS (PERSIANN-SDAE) by 37% (14%), showing the estimation accuracy of the proposed model.

54 ENVIRONMENTAL SCIENCES↗

The Impact of Nonzenith Elevation Angles on Ground-Based Infrared Thermodynamic Retrievals

Observing thermodynamic profiles within the planetary boundary layer is essential to understanding and predicting atmospheric phenomena because of the significant exchange of sensible and latent heat between the land and atmosphere within that layer. The Atmospheric Emitted Radiance Interferometer (AERI) is a ground-based infrared spectrometer used to obtain the vertical profiles of temperature and water vapor mixing ratio. Most AERIs are only capable of zenith views, although the Marine AERI (M-AERI) has a design that allows it to view various elevation angles. In this study, we quantify the improvement in the information content and accuracy of the retrieved profiles when nonzenith angles are included, as is common with microwave radiometer profilers. The impacts of the additional scan angles are quantified through both a synthetic study and with M-AERI observations from the ARM Cloud Aerosol Precipitation Experiment (ACAPEX) campaign. Furthermore, the simulation study shows that low elevation angles contain more information content for temperature whereas high elevation angles have more information content for water vapor. Outside of very humid environments, the addition of low elevation angles also results in lower root-mean-square errors when compared with high angles for both temperature and water vapor mixing ratio, although this is primarily a result of averaging multiple observations together to reduce instrument noise. Real-world results from the ACAPEX dataset indicate similar results as were found for the simulation study, although not all predicted benefits are realized because of the small sample size and observational uncertainties.

54 ENVIRONMENTAL SCIENCES↗

Assimilation of a Coordinated Fleet of Uncrewed Aircraft System Observations in Complex Terrain: EnKF System Design and Preliminary Assessment

Abstract Uncrewed aircraft system (UAS) observations collected during the 2018 Lower Atmospheric Process Studies at Elevation—a Remotely Piloted Aircraft Team Experiment (LAPSE-RATE) field campaign were assimilated into a high-resolution configuration of the Weather Research and Forecasting Model using an ensemble Kalman filter. The benefit of UAS observations was assessed for a terrain-driven (drainage and upvalley) flow event that occurred within Colorado’s San Luis Valley (SLV) using independent observations. The analysis and prediction of the strength, depth, and horizontal extent of drainage flow from the Saguache Canyon and the subsequent transition to upvalley and up-canyon flow were improved relative to that obtained both without data assimilation (benchmark) and when only surface observations were assimilated. Assimilation of UAS observations greatly improved the analyses of vertical variations in temperature, relative humidity, and winds at multiple locations in the northern portion of the SLV, with reductions in both bias and the root-mean-square error of roughly 40% for each variable relative to the benchmark run. Despite these noted improvements, some biases remain that were tied to measurement error and/or the impact of the boundary layer parameterization on vertically spreading the observations, both of which require further exploration. The results presented here highlight how observations obtained with a fleet of profiling UAS improve limited-area, high-resolution analyses and short-term forecasts in complex terrain.

54 ENVIRONMENTAL SCIENCES↗

Laser-Induced Breakdown Spectroscopy (LIBS) Measurement of Uranium in Molten Salt

In this current study, the molten salt aerosol–laser-induced breakdown spectroscopy (LIBS) system was used to measure the uranium (U) content in a ternary UCl 3 –LiCl–KCl salt to investigate and assess a near real-time analytical approach for material safeguards and accountability. Experiments were conducted using five different U concentrations to determine the analytical figures of merit for the system with respect to U. In the analysis, three U lines were used to develop univariate calibration curves at the 367.01 nm, 385.96 nm, and 387.10 nm lines. The 367.01 nm line had the lowest limit of detection (LOD) of 0.065 wt% U. The 385.96 nm line had the best root mean square error of cross-validation (RMSECV) of 0.20 wt% U. In addition to the univariate calibration approach, a multivariate partial least squares (PLS) model was developed to further analyze the data. Using partial least squares (PLS) modeling, an RMSECV of 0.085 wt% U was determined. The RMSECV from the multivariate approach was significantly better than the univariate case and the PLS model is recommended for future LIBS analysis. Overall, the aerosol-LIBS system performed well in monitoring the U concentration and it is expected that the system could be used to quantitatively determine the U compositions within the normal operational concentrations of U in pyroprocessing molten salts.

Williams, Ammon↗