Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “forecast 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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Machine learning based algorithms for uncertainty quantification in numerical weather prediction models

Complex numerical weather prediction models incorporate a variety of physical processes, each described by multiple alternative physical schemes with specific parameters. The selection of the physical schemes and the choice of the corresponding physical parameters during model configuration can significantly impact the accuracy of model forecasts. There is no combination of physical schemes that works best for all times, at all locations, and under all conditions. It is therefore of considerable interest to understand the interplay between the choice of physics and the accuracy of the resulting forecasts under different conditions. This paper demonstrates the use of machine learning techniques to study the uncertainty in numerical weather prediction models due to the interaction of multiple physical processes. The first problem addressed herein is the estimation of systematic model errors in output quantities of interest at future times, and the use of this information to improve the model forecasts. The second problem considered is the identification of those specific physical processes that contribute most to the forecast uncertainty in the quantity of interest under specified meteorological conditions. In order to address these questions we employ two machine learning approaches, random forests and artificial neural networks. The discrepancies between model results and observations at past times are used to learn the relationships between the choice of physical processes and the resulting forecast errors. Numerical experiments are carried out with the Weather Research and Forecasting (WRF) model. The output quantity of interest is the model precipitation, a variable that is both extremely important and very challenging to forecast. The physical processes under consideration include various micro-physics schemes, cumulus parameterizations, short wave, and long wave radiation schemes. The experiments demonstrate the strong potential of machine learning approaches to aid the study of model errors.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Causes of Missing Snowmelt Following Drought

Abstract Water management in snowy mountainous regions hinges on forecasting snowmelt runoff. However, droughts are altering snowpack‐runoff relationships with ongoing debate about the driving mechanisms. For example, in 2021 in California, less than half of predicted streamflow arrived. Mechanisms proposed for this “missing” streamflow included changes in evapotranspiration ( ET ), rainfall, and subsurface moisture conditions. Here, we demonstrate that ET in drought years generates dry subsurface conditions that reduce runoff in subsequent years. A model including this legacy of depleted moisture storage reduced median error in 2021 forecasts from 60% to 20% at 15 minimally disturbed basins and from 18% to 2% at 6 water supply basins in the Sierra Nevada (basins range in area from 5 to 23,051 km 2 and mean annual precipitation from 814 to 1,549 mm). Our findings indicate that the relationship between snowpack and runoff will evolve as plant ecosystems respond to climate change and alter subsurface water storage dynamics.

Lapides, Dana A.↗
DOE OSTI2023

Improving the Representation of Hydropower in Production Cost Models

One of the challenges of a high-renewable, low-carbon system is that grid operators will no longer be able to count on fossil-fired generation should wind miss its forecast or modeling errors create shortage issues, and this change has operational and reliability implications that affect variable renewable energy integration. Hydropower can help in that it can provide many of the services that have been traditionally provided by fossil generation. However, getting the most from hydropower can be challenging in that its capabilities vary with time and are affected by other water users' needs, two complexities that are not well represented in most of today's production cost models (PCMs). This work is an early step in addressing these gaps and making the most of hydropower's capabilities.

cost model↗
DOE OSTI2024

Evidential Deep Learning for Probabilistic Modelling of Extreme Storm Events

Uncertainty quantification (UQ) methods play an important role in reducing errors in weather forecasting. Conventional approaches in UQ for weather forecasting rely on generating an ensemble of forecasts from physics-based simulations to estimate the uncertainty. However, it is computationally expensive to generate many forecasts to predict real-time extreme weather events. Evidential Deep Learning (EDL) is an uncertainty-aware deep learning approach designed to provide confidence about its predictions using only one forecast. It treats learning as an evidence acquisition process where more evidence is interpreted as increased predictive confidence. We apply EDL to storm forecasting using real-world weather datasets and compare its performance with traditional methods. Our findings indicate that EDL not only reduces computational overhead but also enhances predictive uncertainty. This method opens up novel opportunities in research areas such as climate risk assessment, where quantifying the uncertainty about future climate is crucial.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Uncertainty-Guided Prediction Horizon of Phase-Resolved Ocean Wave Forecasting Under Data Sparsity: Experimental and Numerical Evaluation

Accurate short-term wave forecasting is critical for the safe and efficient operation of marine structures that rely on real-time, phase-resolved ocean wave information for control and monitoring purposes (e.g., digital twins). These systems often depend on environmental sensors (e.g., waverider buoys, wave-sensing LIDAR). Challenges arise when upstream sensor data are missing, sparse, or phase-shifted due to drift. This study investigates the performance of two machine learning models, time-series dense encoder (TiDE) and long short-term memory (LSTM), for forecasting phase-resolved ocean surface elevations under varying degrees of data degradation. We introduce the τ-trimming algorithm, which adapts the prediction horizon based on uncertainty thresholds derived from historical forecasts. Numerical wave tank (NWT) and wave basin experiments are used to benchmark model performance under short- and long-term data masking, spatially coarse sensor grids, and upstream phase shifts. Results show under a 50% probability of upstream data loss, the τ-trimmed TiDE model achieves a 46% reduction in error at the most upstream target, compared to 22% for LSTM. Furthermore, phase misalignment in upstream data introduces a near-linear increase in forecast error. Under moderate model settings, a ±3 s misalignment increases the mean absolute error by approximately 0.5 m, while the same error is accumulated at ±4 s using the more conservative approach. These findings inform the design of resilient, uncertainty-aware wave forecasting systems suited for realistic offshore sensing environments.

42 ENGINEERING↗
DOE OSTI2021

Five-day track forecast skills of WRF model for the western North Pacific tropical cyclones

In this study, the characteristics of simulated tropical cyclones (TCs) over the western North Pacific by a regional model (the WRF Model) are verified. We utilize 12-km horizontal grid spacing, and simulations are integrated for 5 days from model initialization. A total of 125 forecasts are divided into five clusters through the k-means clustering method. The TCs in the cluster 1 and 2 (group 1), which includes many TCs moving northward in the subtropical region, generally have larger track errors than for TCs in cluster 3 and 4 (group 2). The optimal steering vector is used to examine the difference in the track forecast skill between these two groups. The bias in the steering vector between the model and analysis data is found to be more substantial for group 1 TCs than group 2 TCs. The larger steering vector difference for group 1 TCs indicates that environmental fields tend to be poorly simulated in group 1 TC cases. Furthermore, the residual terms, including the storm-scale process, asymmetric convection distribution, or beta-related effect, are also larger for group 1 TCs than group 2 TCs. Therefore, it is probable that the large track forecast error for group 1 TCs is a result of unreasonable simulations of environmental wind fields and residual processes in the midlatitudes.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Initialized Earth system prediction from subseasonal to decadal timescales

Initialized Earth system predictions are made by starting a numerical prediction model in a state as consistent as possible to observations, and running it forward in time for up to ten years. Skillful predictions at time slices from subseasonal to seasonal (S2S), seasonal to interannual (S2I) and seasonal to decadal (S2D) offer information useful for various stakeholders, from agriculture to water resource management, and human and infrastructure safety. In this Review, we examine the processes influencing predictability, and discuss estimates of skill across S2S, S2I and S2D timescales. There are encouraging signs that skillful predictions can be made: at S2S timescales, there has been some skill in predicting the Madden-Julian Oscillation and North Atlantic Oscillation; at S2I in predicting the El Niño-Southern Oscillation; and at S2D, in predicting variability in North Atlantic sea surface temperatures. However, challenges remain, and future work must prioritise reducing model error, more effectively communicating forecasts to users, and increasing process and mechanistic understanding that could increase predictive skill and, in turn, confidence. As numerical models progress towards Earth system models, initialized predictions are expanding to include prediction of sea-ice, air pollution, terrestrial and ocean biochemistry which can bring clear benefit to society and various stakeholders.

climate prediction↗
DOE OSTI2022

The Simulation and Design of an On-Chip Superconducting Millimetre Filter-Bank Spectrometer

Abstract Superconducting on-chip filter banks provide a scalable, space saving solution to create imaging spectrometers at millimetre and submillimetre wavelengths. We present an easy to realise, lithographed superconducting filter design with a high tolerance to fabrication error. Using a capacitively coupled $$\lambda /2$$ λ / 2 microstrip resonator to define a narrow ( $$\lambda /\Delta \lambda = 300$$ λ / Δ λ = 300 ) spectral pass band, the filtered output of a given spectrometer channel directly connects to a lumped-element kinetic inductance detector. We show the tolerance analysis of our design, demonstrating $$<11\%$$ < 11 % change in filter quality factor to any one realistic fabrication error and a full filter-bank efficiency forecast to be 50% after accounting for fabrication errors and dielectric loss tangent.

Robson, G. (ORCID:0000000315279326)↗
DOE OSTI2024

Entropy-Infused Deep Learning Loss Function for Capturing Extreme Values in Wind Power Forecasting

Extreme scenarios in wind power generation occur with higher frequency and larger magnitude in the recent years due to the ever-increasing extreme meteorological factors. Accurate forecasting of the occurrence of extreme values in wind power generation is of great concern to ensure reliable power system operation. Recently, deep learning models have surged in popularity for wind power forecasting, with the mean squared error (MSE) loss function being commonly used. However, the MSE loss function, being sensitive to extreme values, disproportionately penalizes larger errors, cannot adequately capture the extreme values present in wind energy data, and novel loss functions have seldom been tailored for wind power forecasting. To this end, in this paper, we introduce a novel loss function specifically crafted to capture extreme values in wind power forecasting. The experimental results with four fundamental deep learning methods on open source wind power dataset validate that the new loss function is efficient and superior in all cases compared to MSE in capturing extreme values while maintaining forecasting performance.

17 WIND ENERGY↗
DOE OSTI2022

Physics-Informed Gaussian Process Regression for States Estimation and Forecasting in Power Grids

Real-time state estimation and forecasting are critical for the efficient operation of power grids. In this paper, a physics-informed Gaussian process regression (PhI-GPR) method is presented and used for forecasting and estimating the phase angle, angular speed, and wind mechanical power of a three-generator power grid system using sparse measurements. In standard data-driven Gaussian process regression (GPR), parameterized models for the prior statistics are fit by maximizing the marginal likelihood of observed data. In the PhI-GPR method, we propose to compute the prior statistics offline by solving stochastic differential equations (SDEs) governing the power grid dynamics. The short-term forecast of a power grid system dominated by wind generation is complicated by the stochastic nature of the wind and the resulting uncertainty in wind mechanical power. Here, we assume that the power grid dynamics are governed by swing equations, with the wind mechanical power fluctuating randomly in time. We solve these equations for the mean and covariances of the power grid states using the Monte Carlo simulation method. We demonstrate that the proposed PhI-GPR method can accurately forecast and estimate observed and unobserved states. For the considered problem, PhI-GPR has computational advantages over the ensemble Kalman filter (EnKF) method: In PhI-GPR, ensembles are computed offline and independently of the data acquisition process, whereas for EnFK, ensembles are computed online with data acquisition, rendering real-time forecast more challenging. We also demonstrate that the PhI-GPR forecast is more accurate than the EnKF forecast when the random mechanical wind power is non-Markovian. In contrast, the two methods produce similar forecasts for the Markovian mechanical wind power. For observed states, we show that PhI-GPR provides a forecast comparable to the standard data-driven GPR; both forecasts are significantly more accurate than the autoregressive integrated moving average (ARIMA) forecast. We also show that the ARIMA forecast is more sensitive to observation frequency and measurement errors than the PhI-GPR forecast.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

Non-autoregressive time-series methods for stable parametric reduced-order models

Advection-dominated dynamical systems, characterized by partial differential equations, are found in applications ranging from weather forecasting to engineering design where accuracy and robustness are crucial. There has been significant interest in the use of techniques borrowed from machine learning to reduce the computational expense and/or improve the accuracy of predictions for these systems. These rely on the identification of a basis that reduces the dimensionality of the problem and the subsequent use of time series and sequential learning methods to forecast the evolution of the reduced state. Often, however, machine-learned predictions after reduced-basis projection are plagued by issues of stability stemming from incomplete capture of multiscale processes as well as due to error growth for long forecast durations. To address these issues, we have developed a non-autoregressive time series approach for predicting linear reduced-basis time histories of forward models. In particular, we demonstrate that non-autoregressive counterparts of sequential learning methods such as long short-term memory (LSTM) considerably improve the stability of machine-learned reduced-order models. Further, we evaluate our approach on the inviscid shallow water equations and show that a non-autoregressive variant of the standard LSTM approach that is bidirectional in the principal component directions obtains the best accuracy for recreating the nonlinear dynamics of partial observations. Moreover-and critical for many applications of these surrogates-inference times are reduced by three orders of magnitude using our approach, compared with both the equation-based Galerkin projection method and the standard LSTM approach.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Dynamic Line Rating Models and Their Potential for a Cost‐Effective Transition to Carbon‐Neutral Power Systems

Most transmission system operators (TSOs) currently use seasonally steady-state models considering limiting weather conditions that serve as reference to compute the transmission capacity of overhead power lines. The use of dynamic line rating (DLR) models can avoid the construction of new lines, market splitting, false congestions, and the degradation of lines in a cost-effective way. DLR can also be used in the long run in grid extension and new power capacity planning. In the short run, it should be used to help operate power systems with congested lines. The operation of the power systems is planned to have the market trading into account; thus, it computes transactions hours ahead of real-time operation, using power flow forecasts affected by large errors. In the near future, within a “smart grid” environment, in real-time operation conditions, TSOs should be able to rapidly compute the capacity rating of overhead lines using DLR models and the most reliable weather information, forecasts, and line measurements, avoiding the current steady-state approach that, in many circumstances, assumes ampacities above the thermal limits of the lines. Here, this work presents a review of the line rating methodologies in several European countries and the United States. Furthermore, it presents the results of pilot projects and studies considering the application of DLR in overhead power lines, obtaining significant reductions in the congestion of internal networks and cross-border transmission lines.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2025

Effects of Atmosphere and Ocean Horizontal Model Resolution on Tropical Cyclone and Upper-Ocean Response Forecasts in Four Major Hurricanes

A coupled atmosphere–ocean model is necessary for tropical cyclone (TC) prediction to accurately characterize ocean feedback on atmospheric processes within the TC environment. Here, the ECMWF coupled global model is run at horizontal resolutions from 9 to 1.4 km in the atmosphere, as well as 25 and 8 km in the ocean, to identify how resolution impacts forecast accuracy of four observed major TCs in the Atlantic: Irma, Florence, Teddy, and Ida. Most of the resolutions used here are unprecedented for global models. GOES-16 and synthetic aperture radar (SAR) satellite images and best track data are used for atmospheric validation. Salinity and temperature observations from Air-Launched Autonomous Micro-Observer (ALAMO) floats are used to validate modeled upper-ocean response, including mixed layer deepening, sea surface cooling, and near-inertial waves in the wakes of TCs. Increasing atmospheric resolution leads to more realistic TC structure and stronger winds, significantly improving TC intensity forecasts and modestly improving track errors. Ocean resolution impacts the upper-ocean response but does not influence atmospheric forecasts for the fast-moving TCs considered here. Stronger mixing, sea surface cooling, and near-inertial oscillations are found for both higher atmosphere and ocean resolutions, provided the initial upper-ocean state is the same for the two ocean resolutions. Whether this agrees better with the ALAMO observations also depends on the realism of the initial upper-ocean state in the model, emphasizing the importance of ocean initialization for the accurate upper-ocean response. Overall, the model at all resolutions correctly predicts stronger mixing, surface cooling, and near-inertial oscillation amplitudes to the right of a TC center, as observed by ALAMO floats.

Atmosphere-ocean interaction↗
DOE OSTI2020

A Novel Modeling Framework for Computationally Efficient and Accurate Real-Time Ensemble Flood Forecasting With Uncertainty Quantification

A novel modeling framework that simultaneously improves accuracy, predictability, and computational efficiency is presented. It embraces the benefits of three modeling techniques integrated together for the first time: surrogate modeling, parameter inference, and data assimilation. The use of polynomial chaos expansion (PCE) surrogates significantly decreases computational time. Parameter inference allows for model faster convergence, reduced uncertainty, and superior accuracy of simulated results. Ensemble Kalman filters assimilate errors that occur during forecasting. To examine the applicability and effectiveness of the integrated framework, we developed 18 approaches according to how surrogate models are constructed, what type of parameter distributions are used as model inputs, and whether model parameters are updated during the data assimilation procedure. We conclude that (1) PCE must be built over various forcing and flow conditions, and in contrast to previous studies, it does not need to be rebuilt at each time step; (2) model parameter specification that relies on constrained, posterior information of parameters (so-called Selected specification) can significantly improve forecasting performance and reduce uncertainty bounds compared to Random specification using prior information of parameters; and (3) no substantial differences in results exist between single and dual ensemble Kalman filters, but the latter better simulates flood peaks. The use of PCE effectively compensates for the computational load added by the parameter inference and data assimilation (up to ~80 times faster). Therefore, the presented approach contributes to a shift in modeling paradigm arguing that complex, high-fidelity hydrologic and hydraulic models should be increasingly adopted for real-time and ensemble flood forecasting.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Modeling injection-induced fault slip using long short-term memory networks

Stress changes due to changes in fluid pressure and temperature in a faulted formation may lead to the opening/shearing of the fault. This can be due to subsurface (geo)engineering activities such as fluid injections and geologic disposal of nuclear waste. Such activities are expected to rise in the future making it necessary to assess their short- and long-term safety. Here, a new machine learning (ML) approach to model pore pressure and fault displacements in response to high-pressure fluid injection cycles is developed. The focus is on fault behavior near the injection borehole. To capture the temporal dependencies in the data, long short-term memory (LSTM) networks are utilized. To prevent error accumulation within the forecast window, four critical measures to train a robust LSTM model for predicting fault response are highlighted: (i) setting an appropriate value of LSTM lag, (ii) calibrating the LSTM cell dimension, (iii) learning rate reduction during weight optimization, and (iv) not adopting an independent injection cycle as a validation set. Several numerical experiments were conducted, which demonstrated that the ML model can capture peaks in pressure and associated fault displacement that accompany an increase in fluid injection. The model also captured the decay in pressure and displacement during the injection shut-in period. Further, the ability of an ML model to highlight key changes in fault hydromechanical activation processes was investigated, which shows that ML can be used to monitor risk of fault activation and leakage during high pressure fluid injections.

58 GEOSCIENCES↗
DOE OSTI2020

A Study on Modeled Wind Speed Errors Using the U.S. Department of Energy Buoys

Pacific Northwest National Laboratory (PNNL) operates two AXYS WindSentinel lidar buoys for the U.S. Department of Energy’s Wind Energy Technologies Office. The purpose of these buoys is to collect hub-height winds and supporting meteorological and oceanographic information to facilitate the development of wind energy in the U.S. waters. The first deployment for one buoy was off the coast of Virginia from December 2014 to May 2016, and the first deployment for the other buoy was off the coast of New Jersey from November 2015 until February 2017. This report describes recent analysis of data collected during these first two deployments. Specifically, we compare hub-height wind speed estimates using Monin-Obukhov Similarity Theory (MOST) to the lidar measurements, and examine how those errors are affected by wind direction, atmospheric stability, wind-wave direction differences, and various measures of the wave-state. The comparisons are done using standard similarity functions based on MOST; including the Businger - Dyer, the Beljaars & Holtslag and the Vickers & Mahrt similarity functions. All models produce large errors over the range of atmospheric stabilities that were observed, with the largest errors occurring for stable flows. The Vickers & Mahrt function resulted in the largest overall bias and standard deviation, while Beljaars & Holtslag function gave the smallest bias and standard deviation due to its better performance under stable conditions. The models perform best under unstable conditions, but even in this regime there is a consistent overestimation of the wind speed of between roughly 0 to 1 ms -1 compared to the lidar measurements. We identify specific metocean conditions (i.e. stability and wind and wave directions) at each of the deployment locations that lead to large errors in MOST predictions. Finally, a coupled ocean-atmosphere model framework was investigated to simulate large errors in weather research forecasting (WRF).

17 WIND ENERGY↗
DOE OSTI2022

Improving Seasonal Forecast Using Probabilistic Deep Learning

The path toward realizing the potential of seasonal forecasting and its socioeconomic benefits relies on improving general circulation model (GCM) based dynamical forecast systems. To improve dynamical seasonal forecasts, it is crucial to set up forecast benchmarks, and clarify forecast limitations posed by model initialization errors, formulation deficiencies, and internal climate variability. With huge costs in generating large forecast ensembles, and limited observations for forecast verification, the seasonal forecast benchmarking and diagnosing task proves challenging. Here, we develop a probabilistic deep learning-based statistical forecast methodology, drawing on a wealth of climate simulations to enhance seasonal forecast capability and forecast diagnosis. By explicitly modeling the internal climate variability and GCM formulation differences, the proposed Conditional Generative Forecasting (CGF) methodology enables bypassing crucial barriers in dynamical forecast, and offers a top-down viewpoint to examine how complicated GCMs encode the seasonal predictability information. We apply the CGF methodology for global seasonal forecast of precipitation and 2 m air temperature, based on a unique data set consisting 52,201 years of climate simulation. Results show that the CGF methodology can faithfully represent the seasonal predictability information encoded in GCMs. We successfully apply this learned relationship in real-world seasonal forecast, achieving competitive performance compared to dynamical forecasts. Using this CGF as benchmark, we reveal the impact of insufficient forecast spread sampling that limits the skill of the considered dynamical forecast system. Finally, we introduce different strategies for composing ensembles using the CGF methodology, highlighting the potential for leveraging the strengths of multiple GCMs to achieve advantgeous seasonal forecast.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Synthetic method of analogues for emerging infectious disease forecasting

The Method of Analogues (MOA) has gained popularity in the past decade for infectious disease forecasting due to its non-parametric nature. In MOA, the local behavior observed in a time series is matched to the local behaviors of several historical time series. The known values that directly follow the historical time series that best match the observed time series are used to calculate a forecast. This non-parametric approach leverages historical trends to produce forecasts without extensive parameterization, making it highly adaptable. However, MOA is limited in scenarios where historical data is sparse. This limitation was particularly evident during the early stages of the COVID-19 pandemic, where the emerging global epidemic had little-to-no historical data. In this work, we propose a new method inspired by MOA, called the Synthetic Method of Analogues (sMOA). sMOA replaces historical disease data with a library of synthetic data that describe a broad range of possible disease trends. This model circumvents the need to estimate explicit parameter values by instead matching segments of ongoing time series data to a comprehensive library of synthetically generated segments of time series data. We demonstrate that sMOA has competitive performance with state-of-the-art infectious disease forecasting models, out-performing 78% of models from the COVID-19 Forecasting Hub in terms of averaged Mean Absolute Error and 76% of models from the COVID-19 Forecasting Hub in terms of averaged Weighted Interval Score. Additionally, we introduce a novel uncertainty quantification methodology designed for the onset of emerging epidemics. Developing versatile approaches that do not rely on historical data and can maintain high accuracy in the face of novel pandemics is critical for enhancing public health decision-making and strengthening preparedness for future outbreaks.

97 MATHEMATICS AND COMPUTING↗