Search NASA⌕ Search

SEARCH · Search NASA

Results for “probabilistic forecasts”

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 199 records · Page 11

VRN3P: Variational Recurrent Neural Network Based Net-Load Prediction under High Solar Penetration

This is the final technical report for the SETO-funded VRN3P project (PNNL# 76914). The goal of this project, led by Pacific Northwest National Laboratory (PNNL), in collaboration with Lawrence Livermore National Laboratory (LLNL) and Portland General Electric (PGE), was to develop and validate a deep variational recurrent neural network-based net-load prediction (VRN3P) framework for probabilistic time-series forecasting of day-ahead net-load under high solar penetration scenarios. The project team reports successful design of a novel probabilistic net-load forecasting architecture, comprising of a variational autoencoder and a recurrent neural network, which demonstrates 30% improvement in forecast performance, 60% improvement in training time, and consumes 44% less memory, when compared with conventional baseline models. The team tested the VRN3P model performance on GridLAB-D test-cases representing varying BTM solar penetration levels of 20%, 30%, and 50%, with integrated time-series net-load profiles provided by the utility partner (PGE). The VRN3P model demonstrate <2% hourly MAPE (averaged over the year) for day- ahead net-load forecast on the test scenario with 20% BTM solar. Transfer learning extension of the VRN3P model has demonstrated 8.33× speed-up in training, while still achieving acceptable forecast performance of 2.24% hourly MAPE on the 30% BTM solar penetration test-scenario. A preliminary version of the VRN3P GridAPPS-D™has been developed, along with a web-based interactive user-interface (named ‘Forte’) which has made available on GitHub for public use.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Assessing probabilistic predictions of ENSO phase and intensity from the North American Multimodel Ensemble

Here we examine the skill of three, five, and seven-category monthly ENSO probability forecasts (1982–2015) from single and multi-model ensemble integrations of the North American Multimodel Ensemble (NMME) project. Three-category forecasts are typical and provide probabilities for the ENSO phase (El Niño, La Niña or neutral). Additional forecast categories indicate the likelihood of ENSO conditions being weak, moderate or strong. The level of skill observed for differing numbers of forecast categories can help to determine the appropriate degree of forecast precision. However, the dependence of the skill score itself on the number of forecast categories must be taken into account. For reliable forecasts with same quality, the ranked probability skill score (RPSS) is fairly insensitive to the number of categories, while the logarithmic skill score (LSS) is an information measure and increases as categories are added. The ignorance skill score decreases to zero as forecast categories are added, regardless of skill level. For all models, forecast formats and skill scores, the northern spring predictability barrier explains much of the dependence of skill on target month and forecast lead. RPSS values for monthly ENSO forecasts show little dependence on the number of categories. However, the LSS of multimodel ensemble forecasts with five and seven categories show statistically significant advantages over the three-category forecasts for the targets and leads that are least affected by the spring predictability barrier. These findings indicate that current prediction systems are capable of providing more detailed probabilistic forecasts of ENSO phase and amplitude than are typically provided.

54 ENVIRONMENTAL SCIENCES↗

Stochastic Optimization with Risk Aversion for Virtual Power Plant Operations: A Rolling Horizon Control

While the concept of aggregating and controlling renewable distributed energy resources (DERs) to provide grid services is not new, increasing policy support of DER market participation has driven research and development in algorithms to pool DERs for economically viable market participation. Sandia National Laboratories recently undertook a three-year research program to create the components of a real-world virtual power plant (VPP) that can simultaneously participate in multiple markets. Our research extends current state-of-the-art rolling horizon control through the application of stochastic programming with risk aversion at various time resolutions. Our rolling horizon control consists of (1) day-ahead optimization to produce an hourly aggregate schedule for the VPP operator and (2) sub-hourly optimization for real-time dispatch of each VPP subresource. Both optimization routines leverage a two-stage stochastic program (SP) with risk aversion, and integrate the most up-to-date forecasts to generate probabilistic scenarios in real operating time. Our results demonstrate the benefits to the VPP operator of constructing a stochastic solution regardless of the weather. In more extreme weather, applying risk optimization strategies can dramatically increase the financial viability of the VPP. As a result, the methodologies presented here can be further tailored for optimal control of any VPP asset fleet and its operational requirements.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Machine Learning Derived Dynamic Operating Reserve Requirements in High-Renewable Power Systems

Accurately forecasting wind and solar power output poses challenges for deeply decarbonized electricity systems. Grid operators must commit resources to provide reserves to ensure reliable operations in the face of forecast errors, a process which can increase fuel consumption and emissions. We apply neural network-based machine learning to expand the usefulness of median point forecast data by creating probabilistic distributions of short-term uncertainty in demand, wind, and solar forecasts that adapt to prevailing grid conditions. Machine learning derived estimates of forecast errors compare favorably to estimates based on incumbent methods. Reserves derived from machine learning are usually smaller than values derived using incumbent methods, which enables fuel savings during most hours. Machine learning reserves are generally larger than incumbent reserves during times of higher forecast error, potentially improving system reliability. Performance is tested using multi-stage production simulation modeling of the California Independent System Operator (CAISO) system. Machine learning reserves provide production cost and greenhouse gas (GHG) emission reductions of approximately 0.3% relative to historical 2019 requirements. Savings in the 2030 timeframe are highly dependent on battery storage capacity. At lower levels of battery capacity, savings of 0.4% from machine learning reserves are shown. Significant quantities of battery storage are expected to be added to meet California's resource adequacy needs and GHG reduction targets. Addition of these batteries saturate reserve needs and results in minimal within-hour balancing costs in 2030.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Phase I Flow and Transport Model Document for Corrective Action Unit 97: Yucca Flat/Climax Mine, Nevada National Security Site, Nye County, Nevada, Revision 1 with ROTCs 1 and 2

The Underground Test Area (UGTA) Corrective Action Unit (CAU) 97, Yucca Flat/Climax Mine, in the northeast part of the Nevada National Security Site (NNSS) requires environmental corrective action activities to assess contamination resulting from underground nuclear testing. These activities are necessary to comply with the UGTA corrective action strategy (referred to as the UGTA strategy). The corrective action investigation phase of the UGTA strategy requires the development of groundwater flow and contaminant transport models whose purpose is to identify the lateral and vertical extent of contaminant migration over the next 1,000 years. In particular, the goal is to calculate the contaminant boundary, which is defined as a probabilistic model-forecast perimeter and a lower hydrostratigraphic unit (HSU) boundary that delineate the possible extent of radionuclide-contaminated groundwater from underground nuclear testing. Because of structural uncertainty in the contaminant boundary, a range of potential contaminant boundaries was forecast, resulting in an ensemble of contaminant boundaries. The contaminant boundary extent is determined by the volume of groundwater that has at least a 5 percent chance of exceeding the radiological standards of the Safe Drinking Water Act (SDWA) (CFR, 2012).

54 ENVIRONMENTAL SCIENCES↗

Applicability of land use models for the Houston area test site

Descriptions of land use models are presented which were considered for their applicability to the Houston Area Test Site. These models are representative both of the prevailing theories of land use dynamics and of basic approaches to simulation. The models considered are: a model of metropolis, land use simulation model, emperic land use forecasting model, a probabilistic model for residential growth, and the regional environmental management allocation process. Sources of environmental/resource information are listed.

Petersburg, R. K.↗

Application of Aviation Turbulence Information to Air-Traffic Management (ATM): Chapter - 24

Unexpected turbulence especially in the upper troposphere and lower stratosphere where cabin crews and passengers in cruising aircraft are likely to unbuckle causes in-flight injuries, structural damage, and flight delay. Therefore, turbulence information can be used to improve safety while pursuing efficiency in Air-Traffic Management (ATM). In this chapter, simple modeling of aircraft trajectories combined with wind and turbulence predictions can suggest the optimal solution of flight plans that minimizes both total flight time (e.g., fuel consumption) and potential encounters of turbulence from departure to arrival airports. Also, probabilistic ensemble turbulence forecasts are applied to suggest an optimal strategic and tactical ATM route planning in a given weather and turbulence condition in the United States which are evaluated against in situ Eddy Dissipation Rate observations from commercial aircraft. Finally, variations of long-haul trans-Oceanic flight routes and their turbulence potentials are investigated using a global reanalysis data to understand how the upper-level large-scale flow patterns can affect the long-term ATM planning through the changes of winds and turbulence conditions.

Wind Optimal↗

Convective Weather Forecast Quality Metrics for Air Traffic Management Decision-Making

Since numerical weather prediction models are unable to accurately forecast the severity and the location of the storm cells several hours into the future when compared with observation data, there has been a growing interest in probabilistic description of convective weather. The classical approach for generating uncertainty bounds consists of integrating the state equations and covariance propagation equations forward in time. This step is readily recognized as the process update step of the Kalman Filter algorithm. The second well known method, known as the Monte Carlo method, consists of generating output samples by driving the forecast algorithm with input samples selected from distributions. The statistical properties of the distributions of the output samples are then used for defining the uncertainty bounds of the output variables. This method is computationally expensive for a complex model compared to the covariance propagation method. The main advantage of the Monte Carlo method is that a complex non-linear model can be easily handled. Recently, a few different methods for probabilistic forecasting have appeared in the literature. A method for computing probability of convection in a region using forecast data is described in Ref. 5. Probability at a grid location is computed as the fraction of grid points, within a box of specified dimensions around the grid location, with forecast convection precipitation exceeding a specified threshold. The main limitation of this method is that the results are dependent on the chosen dimensions of the box. The examples presented Ref. 5 show that this process is equivalent to low-pass filtering of the forecast data with a finite support spatial filter. References 6 and 7 describe the technique for computing percentage coverage within a 92 x 92 square-kilometer box and assigning the value to the center 4 x 4 square-kilometer box. This technique is same as that described in Ref. 5. Characterizing the forecast, following the process described in Refs. 5 through 7, in terms of percentage coverage or confidence level is notionally sound compared to characterizing in terms of probabilities because the probability of the forecast being correct can only be determined using actual observations. References 5 through 7 only use the forecast data and not the observations. The method for computing the probability of detection, false alarm ratio and several forecast quality metrics (Skill Scores) using both the forecast and observation data are given in Ref. 2. This paper extends the statistical verification method in Ref. 2 to determine co-occurrence probabilities. The method consists of computing the probability that a severe weather cell (grid location) is detected in the observation data in the neighborhood of the severe weather cell in the forecast data. Probabilities of occurrence at the grid location and in its neighborhood with higher severity, and with lower severity in the observation data compared to that in the forecast data are examined. The method proposed in Refs. 5 through 7 is used for computing the probability that a certain number of cells in the neighborhood of severe weather cells in the forecast data are seen as severe weather cells in the observation data. Finally, the probability of existence of gaps in the observation data in the neighborhood of severe weather cells in forecast data is computed. Gaps are defined as openings between severe weather cells through which an aircraft can safely fly to its intended destination. The rest of the paper is organized as follows. Section II summarizes the statistical verification method described in Ref. 2. The extension of this method for computing the co-occurrence probabilities in discussed in Section HI. Numerical examples using NCWF forecast data and NCWD observation data are presented in Section III to elucidate the characteristics of the co-occurrence probabilities. This section also discusses the procedure for computing throbabilities that the severity of convection in the observation data will be higher or lower in the neighborhood of grid locations compared to that indicated at the grid locations in the forecast data. The probability of coverage of neighborhood grid cells is also described via examples in this section. Section IV discusses the gap detection algorithm and presents a numerical example to illustrate the method. The locations of the detected gaps in the observation data are used along with the locations of convective weather cells in the forecast data to determine the probability of existence of gaps in the neighborhood of these cells. Finally, the paper is concluded in Section V.

Chatterji, Gano B.↗

Generating wind power scenarios for probabilistic ramp event prediction using multivariate statistical post-processing

Wind power forecasting is gaining international significance as more regions promote policies to increase the use of renewable energy. Wind ramps, large variations in wind power production during a period of minutes to hours, challenge utilities and electrical balancing authorities. A sudden decrease in wind-energy production must be balanced by other power generators to meet energy demands, while a sharp increase in unexpected production results in excess power that may not be used in the power grid, leading to a loss of potential profits. In this study, we compare different methods to generate probabilistic ramp forecasts from the High Resolution Rapid Refresh (HRRR) numerical weather prediction model with up to 12h of lead time at two tall-tower locations in the United States. We validate model performance using 21 months of 80m wind speed observations from towers in Boulder, Colorado, and near the Columbia River gorge in eastern Oregon. We employ four statistical post-processing methods, three of which are not currently used in the literature for wind forecasting. These procedures correct biases in the model and generate short-term wind speed scenarios which are then converted to power scenarios. This probabilistic enhancement of HRRR point forecasts provides valuable uncertainty information of ramp events and improves the skill of predicting ramp events over the raw forecasts. We compute Brier skill scores for each method with regard to predicting up- and down-ramps to determine which method provides the best prediction. We find that the Standard Schaake shuffle method yields the highest skill at predicting ramp events for these datasets, especially for up-ramp events at the Oregon site. Increased skill for ramp prediction is limited at the Boulder, CO, site using any of the multivariate methods because of the poor initial forecasts in this area of complex terrain. These statistical methods can be implemented by wind farm operators to generate a range of possible wind speed and power scenarios to aid and optimize decisions before ramp events occur.

17 WIND ENERGY↗

A pre-registered short-term forecasting study of COVID-19 in Germany and Poland during the second wave

Disease modelling has had considerable policy impact during the ongoing COVID-19 pandemic, and it is increasingly acknowledged that combining multiple models can improve the reliability of outputs. Here we report insights from ten weeks of collaborative short-term forecasting of COVID-19 in Germany and Poland (12 October–19 December 2020). The study period covers the onset of the second wave in both countries, with tightening non-pharmaceutical interventions (NPIs) and subsequently a decay (Poland) or plateau and renewed increase (Germany) in reported cases. Thirteen independent teams provided probabilistic real-time forecasts of COVID-19 cases and deaths. These were reported for lead times of one to four weeks, with evaluation focused on one- and two-week horizons, which are less affected by changing NPIs. Heterogeneity between forecasts was considerable both in terms of point predictions and forecast spread. Ensemble forecasts showed good relative performance, in particular in terms of coverage, but did not clearly dominate single-model predictions. The study was preregistered and will be followed up in future phases of the pandemic.

60 APPLIED LIFE SCIENCES↗

Probabilistic Prediction of Geomagnetic Storms and the K p index

Geomagnetic activity is often described using summary indices to summarize the likelihood of space weather impacts, as well as when parameterizing space weather models. The geomagnetic index K p in particular, is widely used for these purposes. Current state-of-the-art forecast models provide deterministic K p predictions using a variety of methods – including empirically-derived functions, physics-based models, and neural networks – but do not provide uncertainty estimates associated with the forecast. This paper provides a sample methodology to generate a 3-hour-ahead K p prediction with uncertainty bounds and from this provide a probabilistic geomagnetic storm forecast. Specifically, we have used a two-layered architecture to separately predict storm (K p ≥ 5 – ) and non-storm cases. As solar wind-driven models are limited in their ability to predict the onset of transient-driven activity we also introduce a model variant using solar X-ray flux to assess whether simple models including proxies for solar activity can improve the predictions of geomagnetic storm activity with lead times longer than the L1-to-Earth propagation time. By comparing the performance of these models we show that including operationally-available information about solar irradiance enhances the ability of predictive models to capture the onset of geomagnetic storms and that this can be achieved while also enabling probabilistic forecasts.

79 ASTRONOMY AND ASTROPHYSICS↗

Forte: An Interactive Visual Analytic Tool for Trust-Augmented Net-Load Forecasting

Accurate net-load forecasting is vital for energy planning, aiding decisions on trade and load distribution. However, assessing the performance of forecasting models across diverse input variables, like temperature and humidity, remains challenging, particularly for eliciting a high degree of trust in the model outcomes. In this context, there is a growing need for data-driven technological interventions to aid scientists in comprehending how models react to both noisy and clean input variables, thus shedding light on complex behaviors and fostering confidence in the outcomes. In this paper, we present Forte, a visual analytics-based application to explore deep probabilistic net-load forecasting models across various input variables and understand the error rates for different scenarios. With carefully designed visual interventions, this web-based interface empowers scientists to derive insights about model performance by simulating diverse scenarios, facilitating an informed decision-making process. We discuss observations made using Forte and demonstrate the effectiveness of visualization techniques to provide valuable insights into the correlation between weather inputs and net-load forecasts, ultimately advancing grid capabilities by improving trust in forecasting models.

Bhattacharjee, Kaustav↗

AI/ML-Enhanced Wind Forecasts for Reducing Uncertainty in Prescribed Fire Planning

Prescribed fire is a vital tool for ecosystem management and wildfire risk reduction but its escalation is constrained by overly conservative burn windows because of uncertainties, for instance, in wind forecasts. This review describes the state of the art in weather product use by fire/smoke models and identifies three priority research gaps that artificial intelligence/machine learning (AI/ML) is well positioned to address: (1) spatial and temporal downscaling to meter-scale, sub-hourly wind fields; (2) bias correction for systematic model errors in complex terrain; and (3) robust uncertainty quantification to inform ensemble-based simulations. Emerging AI/ML techniques offer promising frameworks to address all three challenges. By providing high-resolution, bias-corrected, and probabilistic wind fields, AI/ML-enhanced forecasts will allow for expanded burn windows, improved ignition strategy design and a reduced reliance on expert intuition, especially when a prescribed fire is introduced into new areas.

54 ENVIRONMENTAL SCIENCES↗

The WRF-Solar Ensemble Prediction System: Development, Test, and Validation

Providing reliable probabilistic solar radiation information is needed to improve management of the uncertainty and variability of solar generation. Thus, guidance on how to develop skillful and accurate ensemble forecasts is essential and it will ultimately contribute to integration of high amounts of solar energy on the grid. A team from the National Renewable Energy Laboratory and the National Center for Atmospheric Research had been collaborating to develop the WRF-Solar ensemble prediction system (WRF-Solar EPS) in the past three years to produce probabilistic solar irradiance forecasts and better predict solar energy by quantifying forecast uncertainty. The WRF-Solar EPS basically generates ensemble members for solar irradiance based on stochastic perturbations to provide intraday and day-ahead probabilistic forecasts. This study will present main research steps in developing the WRF-Solar EPS including: (a) tangent linear analysis for identifying key input variables of six WRF-Solar modules significantly related to predicting of cloud and solar irradiance, (b) combining stochastic perturbation technique with the WRF-Solar model, and (c) ensemble calibration method to decrease error and uncertainty of ensemble-based solar forecasts. The capability of WRF-Solar EPS is now updated to the most recent version of standard WRF model. This presentation will summarize comprehensive results from the evaluation of forecasts against the National Solar Radiation Data Base as well as ground-measured observations. Moreover, we will introduce the user's guide for WRF-Solar EPS (e.g., parameters to configure stochastic perturbations) and future extension of this research.

day-ahead forecast↗

Stochastic Predictions of Cell Kill During Stereotactic Ablative Radiation Therapy: Do Hypoxia and Reoxygenation Really Matter?

Purpose: To simulate stereotactic ablative radiation therapy on hypoxic and well-oxygenated in silico tumors, incorporating probabilistic parameter distributions and linear-quadratic versus linear-quadratic-cubic methodology and the evaluation of optimal fractionation schemes using biological effective dose (BED{sub α/β=10} {sub or} {sub 3}) comparisons. Methods and Materials: A temporal tumor growth and radiation therapy algorithm simulated high-dose external beam radiation therapy using stochastic methods. Realistic biological proliferative cellular hierarchy and pO{sub 2} histograms were incorporated into the 10{sup 8}-cell tumor model, with randomized radiation therapy applied during continual cell proliferation and volume-based gradual tumor reoxygenation. Dose fractions ranged from 6-35 Gy, with predictive outcomes presented in terms of the total doses (converted to BED) required to eliminate all cells that could potentially regenerate the tumor. Results: Well-oxygenated tumor control BED{sub 10} outcomes were not significantly different for high-dose versus conventional radiation therapy (BED{sub 10}: 79-84 Gy; Equivalent Dose in 2 Gy fractions with α/β of 10: 66-70 Gy); however, total treatment times decreased from 7 down to 1-3 weeks. For hypoxic tumors, an additional 28 Gy (51 Gy BED{sub 10}) was required, with BED{sub 10} increasing with dose per fraction due to wasted dose in the final fraction. Fractions of 9 Gy compromised well for total treatment time and BED, with BED{sub 10}:BED{sub 3} of 84:176 Gy for oxic and 132:278 Gy for non-reoxygenating hypoxic tumors. Initial doses of 12 Gy followed by 6 Gy further increased the therapeutic ratio. When delivering ≥9 Gy per fraction, applying reoxygenation and/or linear-quadratic-cubic cell survival both affected tumor control doses by a significant 1-2 fractions. Conclusions: The complex temporal dynamics of tumor oxygenation combined with probabilistic cell kinetics in the modeling of radiation therapy requires sophisticated stochastic modeling to predict tumor cell kill. For stereotactic ablative radiation therapy, high doses in the first week followed by doses that are more moderate may be beneficial because a high percentage of hypoxic cells could be eradicated early while keeping the required BED{sub 10} relatively low and BED{sub 3} toxicity to tolerable levels.

62 RADIOLOGY AND NUCLEAR MEDICINE↗