Search NASA⌕ Search

SEARCH · Search NASA

Results for “prediction interval”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Short-Term Load Forecasting Considering EV Charging Loads with Prediction Interval Evaluation

Short-term load forecasting plays a critical role in power system planning and operation. Along with the electrification of various loads, electricity demands are becoming increasingly hard to predict. Notably, the recent rise in electric vehicles (EVs) has further contributed to this unpredictability. To address this issue, this paper proposes a probabilistic load forecasting strategy utilizing Gaussian process regression, structured in a day-ahead manner. While many works focus on deterministic prediction, probabilistic forecasting offers additional insights into variability and uncertainty, enabling more flexible and reliable operation for power systems. To enhance the accuracy of the load forecasting model, the inputs include features related to EV charging habits as well as commonly used weather information. The load forecasting results are evaluated using various metrics, including conventional ones that assess the accuracy of point forecasts, as well as additional metrics that test the reliability of prediction intervals. The proposed load forecasting method is finally tested on real residential power consumption data and EV charging data sampled from real-world sources. The results prove that the new features can greatly improve the performance of the load forecasting method.

electrical vehicle↗
DOE OSTI2022

PI3NN: Out-of-distribution-aware Prediction Intervals from Three Neural Networks

We propose a novel prediction interval (PI) method for uncertainty quantification, which addresses three major issues with the state-of-the-art PI methods. First, existing PI methods require retraining of neural networks (NNs) for every given confidence level and suffer from the crossing issue in calculating multiple PIs. Second, they usually rely on customized loss functions with extra sensitive hyperparameters for which fine tuning is required to achieve a well-calibrated PI. Third, they usually underestimate uncertainties of out-of-distribution (OOD) samples leading to over-confident PIs. Our PI3NN method calculates PIs from linear combinations of three NNs, each of which is independently trained using the standard mean squared error loss. The coefficients of the linear combinations are computed using root-finding algorithms to ensure tight PIs for a given confidence level. We theoretically prove that PI3NN can calculate PIs for a series of confidence levels without retraining NNs and it completely avoids the crossing issue. Additionally, PI3NN does not introduce any unusual hyperparameters resulting in a stable performance. Furthermore, we address OOD identification challenge by introducing an initialization scheme which provides reasonably larger PIs of the OOD samples than those of the in-distribution samples. Benchmark and real-world experiments show that our method outperforms several state-of-the-art approaches with respect to predictive uncertainty quality, robustness, and OOD samples identification.

Liu, Siyan↗
DOE OSTI2018

Nonparametric Prediction Intervals of Wind Power via Linear Programming

This letter proposes a machine learning-based linear programming model that quickly establishes the nonparametric prediction intervals of wind power by integrating extreme learning machine and quantile regression. The proportions of quantiles can be adaptively determined via sensitivity analysis. The proposed method has been proven to be significantly efficient and reliable, with a high application potential in power systems.

extreme learning machine↗
DOE OSTI2021

A prediction interval method for uncertainty quantification of regression models

This paper considers calculation of prediction intervals (PIs) by neural networks (NNs) for quantifying uncertainty in regression tasks, so as to provide fast, accurate and robust emulators to accelerate scientific simulations. We propose a novel method to learn lower and upper bounds of the PI using independent NNs without defining an exclusive loss. Our method requires no distributional assumption, does not introduce extra hyper-parameters, and can effectively identify out-of-distribution samples and quantify their uncertainty. We demonstrate advantages of our method using a benchmark problem and two real-world scientific applications.

Zhang, Pei↗
DOE OSTI2019

On the Effectiveness of Recurrent Neural Networks for Live Modeling of Cyber-Physical Systems

Attention to cyber security of cyber-physical systems (CPS) has led to the development of innovative cyber-resilient methodologies to ensure early detection and mitigation of cyber anomalies and threats. The concept of Digital Twin (DT) has recently emerged as one of the approaches to achieve the objective of resilience. In the approach using DT, a software-based live model of a target CPS is used to continuously monitor, surveil and verify the correctness of the target CPS operation. In this paper, we empirically study the effectiveness of Recurrent Neural Network (RNN)-based models as the basis of DT-based resilience. We uncover the important characteristics of an RNN-based solution with experimentation on a lab-scale Canal Lock CPS emulator with live validations and attack scenarios. For the first time, we demonstrate actual, real-time use of a RNN-based model as a DT for performing live analysis on an operational CPS. Based on the observed results, we highlight the importance of a DT model's training interval, prediction interval and CPS polling interval in the process of anomaly detection. We uncover the limitations in anomaly detection due to real-time synchronization needs of the RNN-based DT. We highlight this uncovered tug of war between synchronization and anomaly detection is inherent in any complex CPS that is monitored and synchronized by relying on the same sensor streams of ground truth for both synchronization as well as anomaly detection.

Yoginath, Srikanth↗
DOE OSTI2023

Uncertainty quantification of the virial black hole mass with conformal prediction

Precise measurements of the black hole mass are essential to gain insight on the black hole and host galaxy co-evolution. A direct measure of the black hole mass is often restricted to nearest galaxies and instead, an indirect method using the single-epoch virial black hole mass estimation is used for objects at high redshifts. However, this method is subjected to biases and uncertainties as it is reliant on the scaling relation from a small sample of local active galactic nuclei. In this study, we propose the application of conformalized quantile regression (CQR) to quantify the uncertainties of the black hole predictions in a machine learning setting. We compare CQR with various prediction interval techniques and demonstrated that CQR can provide a more useful prediction interval indicator. In contrast to baseline approaches for prediction interval estimation, we show that the CQR method provides prediction intervals that adjust to the black hole mass and its related properties. That is it yields a tighter constraint on the prediction interval (hence more certain) for a larger black hole mass, and accordingly, bright and broad spectral line width source. Using a combination of neural network model and CQR framework, the recovered virial black hole mass predictions and uncertainties are comparable to those measured from the Sloan Digital Sky Survey. The code is publicly available.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2015

Online adaptation and verification of VMAT

Purpose: This work presents a method for fast volumetric modulated arc therapy (VMAT) adaptation in response to interfraction anatomical variations. Additionally, plan parameters extracted from the adapted plans are used to verify the quality of these plans. The methods were tested as a prostate class solution and compared to replanning and to their current clinical practice. Methods: The proposed VMAT adaptation is an extension of their previous intensity modulated radiotherapy (IMRT) adaptation. It follows a direct (forward) planning approach: the multileaf collimator (MLC) apertures are corrected in the beam’s eye view (BEV) and the monitor units (MUs) are corrected using point dose calculations. All MLC and MU corrections are driven by the positions of four fiducial points only, without need for a full contour set. Quality assurance (QA) of the adapted plans is performed using plan parameters that can be calculated online and that have a relation to the delivered dose or the plan quality. Five potential parameters are studied for this purpose: the number of MU, the equivalent field size (EqFS), the modulation complexity score (MCS), and the components of the MCS: the aperture area variability (AAV) and the leaf sequence variability (LSV). The full adaptation and its separate steps were evaluated in simulation experiments involving a prostate phantom subjected to various interfraction transformations. The efficacy of the current VMAT adaptation was scored by target mean dose (CTV{sub mean}), conformity (CI{sub 95%}), tumor control probability (TCP), and normal tissue complication probability (NTCP). The impact of the adaptation on the plan parameters (QA) was assessed by comparison with prediction intervals (PI) derived from a statistical model of the typical variation of these parameters in a population of VMAT prostate plans (n = 63). These prediction intervals are the adaptation equivalent of the tolerance tables for couch shifts in the current clinical practice. Results: The proposed adaptation of a two-arc VMAT plan resulted in the intended CTV{sub mean} (Δ ≤ 3%) and TCP (ΔTCP ≤ 0.001). Moreover, the method assures the intended CI{sub 95%} (Δ ≤ 11%) resulting in lowered rectal NTCP for all cases. Compared to replanning, their adaptation is faster (13 s vs 10 min) and more intuitive. Compared to the current clinical practice, it has a better protection of the healthy tissue. Compared to IMRT, VMAT is more robust to anatomical variations, but it is also less sensitive to the different correction steps. The observed variations of the plan parameters in their database included a linear dependence on the date of treatment planning and on the target radius. The MCS is not retained as QA metric due to a contrasting behavior of its components (LSV and AAV). If three out of four plan parameters (MU, EqFS, AAV, and LSV) need to lie inside a 50% prediction interval (3/4—50%PI), all adapted plans will be accepted. In contrast, all replanned plans do not meet this loose criterion, mainly because they have no connection to the initially optimized and verified plan. Conclusions: A direct (forward) VMAT adaptation performs equally well as (inverse) replanning but is faster and can be extended to real-time adaptation. The prediction intervals for the machine parameters are equivalent to the tolerance tables for couch shifts in the current clinical practice. A 3/4—50%PI QA criterion accepts all the adapted plans but rejects all the replanned plans.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Uncertainty Quantification Enabled by Automatic Differentiation for Hydrodynamic Simulation of Shock‐to‐Detonation Transition in High Explosives

Quantifying the effects of uncertainty in a reactive burn model on the run-to-detonation time in high explosives (HEs) provides a robust methodology for assessing the probability of an HE failing the IHE qualification standard. Moreover, uncertainty quantification helps evaluate whether the model calibration accurately represents data outside the calibration set. This study uses a specialized hydrodynamic simulation code for modeling detonation to determine the run-to-detonation time of the HE PBX 9502 for various impact velocities. To quickly approximate uncertainties in the model, a surrogate was constructed using a Taylor series expansion centered at the mean of the input parameters. To obtain the sensitivities required for constructing the Taylor series, HYP-percomplex Automatic Differentiation (HYPAD) was implemented. HYPAD is a methodology for infusing existing codes with automatic differentiation capabilities by augmenting variables with one or more imaginary units to compute step-size independent partial derivatives. These derivatives are accurate to machine precision with respect to the implemented numerical algorithm, meaning their accuracy reflects that of the underlying method (e.g., integration or discretization schemes). Using reduced order modeling techniques, the mean and standard deviation of the run-to-detonation time of a shock within PBX 9502 were computed for a number of initial impact velocities. A weighted least squares regression was then performed to obtain a best fit curve and prediction interval for the computed statistics. Historical data points from explosively driven wedge tests were utilized to validate the prediction interval, ensuring its reliability in predicting future outcomes. With this prediction interval and a known safety constraint curve, the most probable point of failure and the probability of failure for the HE PBX 9502 were determined.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

A comparison of material flow strength models using Bayesian cross-validation

Predicting material flow strength over a range of conditions, such as temperature and strain rate, is necessary for many engineering applications. In this paper, we consider how to compare the predictiveness of several different strength models using a statistical technique called Bayesian cross-validation. Given a dataset of flow strength measurements obtained from mechanictesting experiments, the procedure consists of performing a Bayesian calibration of each strength model on a subset of the data and evaluating how well the trained models predict the remaining data. The predictiveness of a calibrated strength model is quantifiable probabilistically, which provides an interpretable metric for comparing the different models. As an illustrative example, we compare the Johnson-Cook (JC), Zerilli-Armstrong (ZA), Preston-Tonks-Wallace (PTW), and Mechanical Threshold Stress (MTS) flow strength models for the tantalum stress-strain curve data from Chen and Gray (1996). We show that prediction intervals for the four strength models cover the held-out data at most experimental conditions, but also that prediction interval coverage and prediction uncertainty varies by model and experimental condition. Finally, the analysis further allows us to identify experimental regimes for which one of the strength models predicts better than the other three.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Conformalized-KANs: Uncertainty Quantification with Coverage Guarantees for Kolmogorov-Arnold Networks (KANs) in Scientific Machine Learning

This paper explores uncertainty quantification (UQ) methods in the context of Kolmogorov–Arnold Networks (KANs). We apply an ensemble approach to KANs to obtain a heuristic measure of UQ, enhancing interpretability and robustness in modeling complex functions. Building on this, we introduce Conformalized-KANs, which integrate conformal prediction, a distribution-free UQ technique, with KAN ensembles to generate calibrated prediction intervals with guaranteed coverage.} Extensive numerical experiments are conducted to evaluate the effectiveness of these methods, focusing particularly on the robustness and accuracy of the prediction intervals under various hyperparameter settings. We show that the conformal KAN predictions can be applied to recent extensions of KANs, including Finite Basis KANs (FBKANs) and multifideilty KANs (MFKANs). The results demonstrate the potential of our approaches to significantly improve the reliability and applicability of KANs in scientific machine learning.

• Artificial intelligence (AI) / machine learning ↗
DOE OSTI2014

Uncertainty Reduction in Power Generation Forecast Using Coupled Wavelet-ARIMA

In this paper, we introduce a new approach without implying normal distributions and stationarity of power generation forecast errors. In addition, it is desired to more accurately quantify the forecast uncertainty by reducing prediction intervals of forecasts. We use automatically coupled wavelet transform and autoregressive integrated moving-average (ARIMA) forecasting to reflect multi-scale variability of forecast errors. The proposed analysis reveals slow-changing “quasi-deterministic” components of forecast errors. This helps improve forecasts produced by other means, e.g., using weather-based models, and reduce forecast errors prediction intervals.

Power system planning, uncertainty reduction, fore↗
DOE OSTI2015

Forecasting of municipal solid waste quantity in a developing country using multivariate grey models

Highlights: • Grey model can be used to forecast MSW quantity accurately with the limited data. • Prediction interval overcomes the uncertainty of MSW forecast effectively. • A multivariate model gives accuracy associated with factors affecting MSW quantity. • Population, urbanization, employment and household size play role for MSW quantity. - Abstract: In order to plan, manage and use municipal solid waste (MSW) in a sustainable way, accurate forecasting of MSW generation and composition plays a key role. It is difficult to carry out the reliable estimates using the existing models due to the limited data available in the developing countries. This study aims to forecast MSW collected in Thailand with prediction interval in long term period by using the optimized multivariate grey model which is the mathematical approach. For multivariate models, the representative factors of residential and commercial sectors affecting waste collected are identified, classified and quantified based on statistics and mathematics of grey system theory. Results show that GMC (1, 5), the grey model with convolution integral, is the most accurate with the least error of 1.16% MAPE. MSW collected would increase 1.40% per year from 43,435–44,994 tonnes per day in 2013 to 55,177–56,735 tonnes per day in 2030. This model also illustrates that population density is the most important factor affecting MSW collected, followed by urbanization, proportion employment and household size, respectively. These mean that the representative factors of commercial sector may affect more MSW collected than that of residential sector. Results can help decision makers to develop the measures and policies of waste management in long term period.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2024

Challenges of COVID-19 Case Forecasting in the US, 2020–2021

During the COVID-19 pandemic, forecasting COVID-19 trends to support planning and response was a priority for scientists and decision makers alike. In the United States, COVID-19 forecasting was coordinated by a large group of universities, companies, and government entities led by the Centers for Disease Control and Prevention and the US COVID-19 Forecast Hub ( https://covid19forecasthub.org ). We evaluated approximately 9.7 million forecasts of weekly state-level COVID-19 cases for predictions 1–4 weeks into the future submitted by 24 teams from August 2020 to December 2021. We assessed coverage of central prediction intervals and weighted interval scores (WIS), adjusting for missing forecasts relative to a baseline forecast, and used a Gaussian generalized estimating equation (GEE) model to evaluate differences in skill across epidemic phases that were defined by the effective reproduction number. Overall, we found high variation in skill across individual models, with ensemble-based forecasts outperforming other approaches. Forecast skill relative to the baseline was generally higher for larger jurisdictions (e.g., states compared to counties). Over time, forecasts generally performed worst in periods of rapid changes in reported cases (either in increasing or decreasing epidemic phases) with 95% prediction interval coverage dropping below 50% during the growth phases of the winter 2020, Delta, and Omicron waves. Ideally, case forecasts could serve as a leading indicator of changes in transmission dynamics. However, while most COVID-19 case forecasts outperformed a naïve baseline model, even the most accurate case forecasts were unreliable in key phases. Further research could improve forecasts of leading indicators, like COVID-19 cases, by leveraging additional real-time data, addressing performance across phases, improving the characterization of forecast confidence, and ensuring that forecasts were coherent across spatial scales. In the meantime, it is critical for forecast users to appreciate current limitations and use a broad set of indicators to inform pandemic-related decision making.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Advanced surrogate model for electron-scale turbulence in tokamak pedestals

We derive an advanced surrogate model for predicting turbulent transport at the edge of tokamaks driven by electron temperature gradient (ETG) modes. Our derivation is based on a recently developed sensitivity-driven sparse grid interpolation approach for uncertainty quantification and sensitivity analysis at scale, which informs the set of parameters that define the surrogate model as a scaling law. Our model reveals that ETG-driven electron heat flux is influenced by the safety factor q, electron beta β e and normalized electron Debye length λ D , in addition to well-established parameters such as the electron temperature and density gradients. To assess the trustworthiness of our model's predictions beyond training, we compute prediction intervals using bootstrapping. The surrogate model's predictive power is tested across a wide range of parameter values, including within-distribution testing parameters (to verify our model) as well as out-of-bounds and out-of-distribution testing (to validate the proposed model). Overall, validation efforts show that our model competes well with, or can even outperform, existing scaling laws in predicting ETG-driven transport.

fusion plasma↗
DOE OSTI2023

Uncertainty quantification of machine learning models to improve streamflow prediction under changing climate and environmental conditions

Machine learning (ML) models, and Long Short-Term Memory (LSTM) networks in particular, have demonstrated remarkable performance in streamflow prediction and are increasingly being used by the hydrological research community. However, most of these applications do not include uncertainty quantification (UQ). ML models are data driven and can suffer from large extrapolation errors when applied to changing climate/environmental conditions. UQ is required to quantify the influence of data noises on model predictions and avoid overconfident projections in extrapolation. In this work, we integrate a novel UQ method, called PI3NN, with LSTM networks for streamflow prediction. PI3NN calculates Prediction Intervals by training 3 Neural Networks. It can precisely quantify the predictive uncertainty caused by the data noise and identify out-of-distribution (OOD) data in a non-stationary condition to avoid overconfident predictions. We apply the PI3NN-LSTM method in the snow-dominant East River Watershed in the western US and in the rain-driven Walker Branch Watershed in the southeastern US. Results indicate that for the prediction data which have similar features as the training data, PI3NN precisely quantifies the predictive uncertainty with the desired confidence level; and for the OOD data where the LSTM network fails to make accurate predictions, PI3NN produces a reasonably large uncertainty indicating that the results are not trustworthy and should avoid overconfidence. PI3NN is computationally efficient, robust in performance, and generalizable to various network structures and data with no distributional assumptions. It can be broadly applied in ML-based hydrological simulations for credible prediction.

54 ENVIRONMENTAL SCIENCES↗