SEARCH · Search NASA
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.
Weather forecasting is a tool in which the Savannah River Site relies on to complete daily tasks. The importance and integrity of forecasting systems and models is of the utmost importance to safety at SRS. By comparing and contrasting model bias, the meteorologists and employees of the Atmospheric Technologies Group will be equipped with bias data to create more accurate forecasts. Thus, furthering the safety of individuals at SRS.
Extreme weather events have significant consequences, dominating the impact of climate on society. While high-resolution weather models can forecast many types of extreme events on synoptic timescales, long-term climatological risk assessment is an altogether different problem. A once-in-a-century event takes, on average, 100 years of simulation time to appear just once, far beyond the typical integration length of a weather forecast model. Therefore, this task is left to cheaper, but less accurate, low-resolution or statistical models. But there is untapped potential in weather model output: despite being short in duration, weather forecast ensembles are produced multiple times a week. Integrations are launched with independent perturbations, causing them to spread apart over time and broadly sample phase space. Collectively, these integrations add up to thousands of years of data. We establish methods to extract climatological information from these short weather simulations. Using ensemble hindcasts by the European Center for Medium-range Weather Forecasting archived in the subseasonal-to-seasonal (S2S) database, we characterize sudden stratospheric warming (SSW) events with multi-centennial return times. Consistent results are found between alternative methods, including basic counting strategies and Markov state modeling. By carefully combining trajectories together, we obtain estimates of SSW frequencies and their seasonal distributions that are consistent with reanalysis-derived estimates for moderately rare events, but with much tighter uncertainty bounds, and which can be extended to events of unprecedented severity that have not yet been observed historically. These methods hold potential for assessing extreme events throughout the climate system, beyond this example of stratospheric extremes.
Global weather forecast models are vital tools with numerous applications, including public safety, agriculture, and transportation. Recent advancements in artificial intelligence (AI) and deep learning (DL) have shown the potential to enhance weather forecasting accuracy and speed. In this study, we developed a short-term hourly weather forecast framework with a wavelet transform function for data preprocessing and a spatiotemporal DL model, PredRNN, for predicting five surface atmospheric variables, including wind speed and direction, mean sea level pressure (MSLP), temperature, and precipitation. The framework demonstrated promising results. It produces global forecasts at 0.25° (∼25 km) with a 1-day lead time RMSE of 1.8 m/s for wind components, 180 Pa for MSLP, and 1.8 K for temperature. Although our model does not surpass state-of-the-art AI weather forecast models across all metrics, it outperforms these models in precipitation forecasting and wind prediction at short lead times and achieves comparable accuracy for MSLP. Its native hourly forecasting capability, together with training on widely accessible GPU hardware, contributes meaningfully to the advancement of accessible DL weather forecasting methods. Our work highlights the importance of integrating temporal components and data transformation techniques to improve the predictability and accuracy of weather forecasts.
Weather forecast uncertainty is unavoidable despite technological advancements. Accurately quantifying and modelling this uncertainty is essential for developing and comparing advanced building controllers. In this study, we present a structured approach using a first-order autoregressive model (AR(1)) to model uncertainty in ambient temperature and global solar irradiation (GHI) forecasts. We analyzed weather data from four cities and employed Jensen–Shannon divergence (JSD) to evaluate the similarity between synthetic and actual forecast errors. The average JSD values for temperature are 0.027 (Berkeley), 0.021 (Leuven), 0.018 (Berlin), and 0.008 (Oslo), and for GHI, the average JSD values are 0.016 (Berkeley), 0.058 (Leuven), and 0.013 (Berlin). The low JSD values indicate a high similarity between the synthetic and real forecast error distributions. Further, our approach successfully generates synthetic weather forecasts that mirror the statistical properties of actual forecasts. The implementation of our method for uncertain forecast generation is being added to the BOPTEST framework.
Machine learning (ML) techniques have emerged as promising approaches to improve regional weather forecast accuracy and reliability through data-driven methods. We propose a novel ML-based weather forecasting model, the Multiperiod Embed Net (MPENet). A key distinguishing feature of MPENet is its explicit utilization of the inherent cyclic nature in weather dynamics, unlike the autoregressive strategies commonly used in other ML weather forecasting approaches. Critical cyclic structures are identified via Fourier analyses of dynamic time series. Cyclicity in the convolutional representation is achieved by transforming one-dimensional time series of meteorological variables into two-dimensional tensors based on identified periods. This approach enables the model to leverage intrinsic weather patterns, enhancing regional forecast performance. To demonstrate the effectiveness of MPENet, we conduct a comparative analysis with Nvidia’s FourCastNet. Both models are trained on High-Resolution Rapid Refresh (HRRR) data from 2015 to 2022, over a 192 km × 192 km region in Tennessee. The comparisons are performed locally at two specific locations known to have different weather dynamics due to orographic effects: Crossville, on the relatively flat Cumberland Plateau with fewer topographic airflow disruptions, and Oak Ridge, in the ridge-and-valley region, where airflow is heavily influenced by surrounding valleys and mountains. Our results indicate that FourCastNet achieves strong accuracy at very short lead times, while MPENet maintains competitive skill and shows advantages in capturing temporal evolution over longer periods. Cross-correlation analyses of MPENet and FourCastNet predictions with the HRRR data suggest that encoding critical cyclicity into the network architecture leads to improvements in the forecasting skill.
Abstract. Simulating low-likelihood high-impact extreme weather events in a warming world is a significant and challenging task for current ensemble forecasting systems. While these systems presently use up to 100 members, larger ensembles could enrich the sampling of internal variability. They may capture the long tails associated with climate hazards better than traditional ensemble sizes. Due to computational constraints, it is infeasible to generate huge ensembles (comprised of 1000–10 000 members) with traditional, physics-based numerical models. In this two-part paper, we replace traditional numerical simulations with machine learning (ML) to generate hindcasts of huge ensembles. In Part 1, we construct an ensemble weather forecasting system based on spherical Fourier neural operators (SFNOs), and we discuss important design decisions for constructing such an ensemble. The ensemble represents model uncertainty through perturbed-parameter techniques, and it represents initial condition uncertainty through bred vectors, which sample the fastest-growing modes of the forecast. Using the European Centre for Medium-Range Weather Forecasts Integrated Forecasting System (IFS) as a baseline, we develop an evaluation pipeline composed of mean, spectral, and extreme diagnostics. With large-scale, distributed SFNOs with 1.1 billion learned parameters, we achieve calibrated probabilistic forecasts. As the trajectories of the individual members diverge, the ML ensemble mean spectra degrade with lead time, consistent with physical expectations. However, the individual ensemble members' spectra stay constant with lead time. Therefore, these members simulate realistic weather states during the rollout, and the ML ensemble passes a crucial spectral test in the literature. The IFS and ML ensembles have similar extreme forecast indices, and we show that the ML extreme weather forecasts are reliable and discriminating. These diagnostics ensure that the ensemble can reliably simulate the time evolution of the atmosphere, including low-likelihood high-impact extremes. In Part 2, we generate a huge ensemble initialized each day in summer 2023, and we characterize the simulations of extremes.
Meteorological prediction is crucial for various sectors, including agriculture, navigation, daily life, disaster prevention, and scientific research. However, traditional numerical weather prediction (NWP) models are constrained by their high computational resource requirements, while the accuracy of deep learning models remains suboptimal. In response to these challenges, we propose a novel deep learning-based model, the Spatiotemporal Fusion Model (STFM), designed to enhance the accuracy of meteorological predictions. Our model leverages Fifth-Generation ECMWF Reanalysis (ERA5) data and introduces two key components: a spatiotemporal encoder module and a spatiotemporal fusion module. The spatiotemporal encoder integrates the strengths of convolutional neural networks (CNNs) and recurrent neural networks (RNNs), effectively capturing both spatial and temporal dependencies. Meanwhile, the spatiotemporal fusion module employs a dual attention mechanism, decomposing spatial attention into global static attention and channel dynamic attention. This approach ensures comprehensive extraction of spatial features from meteorological data. The combination of these modules significantly improves prediction performance. Experimental results demonstrate that STFM excels in extracting spatiotemporal features from reanalysis data, yielding predictions that closely align with observed values. In comparative studies, STFM outperformed other models, achieving a 7% improvement in ground and high-altitude temperature predictions, a 5% enhancement in the prediction of the u/v components of 10 m wind speed, and an increase in the accuracy of potential height and relative humidity predictions by 3% and 1%, respectively. This enhanced performance highlights STFM’s potential to advance the accuracy and reliability of meteorological forecasting.
SAND2025-14466O This repository contains code for developing, training, and evaluating machine learning models for weather and climate forecasting, including forecast skill assessment, feature importance analysis, and reproducible workflows for model comparison. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.
Given its location relative to the coast, seabreezes pass over the Savannah River Site (SRS) fairly often, usually overnight, with consequent effects on site meteorology. Similar to our previous work with fog, we have applied machine learning (ML) to the problem of forecasting seabreeze passage onsite, using as input i) meteorological observations and ii) weather model forecasts.The two ML techniques we applied both demonstrated skill, especially when compared to a simple forecast that uses the predicted land-sea temperature gradient as a predictor.
Meteorological modeling plays a pivotal role in operational safety and emergency response at the Savannah River Site (SRS). This study focuses on verifying the Regional Atmospheric Modelling System (RAMS) Version 4.3 through Mean Bias Error (MBE) and Root Mean Square Error (RMSE) analyses of temperature, dew point, and wind speed over a decade. Using observed data from SRS, we assessed RAMS' accuracy, revealing seasonal biases and error trends. Results indicate RAMS' strengths in mild weather conditions but challenges during seasonal extremes and wind speed predictions due to measurement disparities. Future research aims to expand verification to other models and parameters, advocating for enhanced forecasting accuracy crucial for safeguarding personnel and community well-being.
Explore the source record for details and available documents.
Weather forecasting has been a critical component to predict and control building energy consumption for better building energy management. Without accessibility to other data sources, the onsite observed temperatures or the airport temperatures are used in forecast models. In this paper, we present a novel approach by utilizing the crowdsourcing weather data from neighboring personal weather stations (PWS) to improve the weather forecast accuracy around buildings using a general spatial-temporal modeling framework. The final forecast is based on the ensemble of local forecasts for the target location using neighboring PWSs. Our approach is distinguished from existing literature in various aspects. First, we leverage the crowdsourcing weather data from PWS in addition to public data sources. In this way, the data is at much finer time resolution (e.g., at 5-minute frequency) and spatial resolution (e.g., arbitrary location vs grid). Second, our proposed model incorporates spatial-temporal correlation information of weather variables between the target building and a set of neighboring PWSs so that underlying correlations can be effectively captured to improve forecasting performance. Here, we demonstrate the performance of the proposed framework by comparing to the benchmark models on temperature forecasting for a building located at an arbitrary location at San Antonio, Texas, USA. In general, the proposed model framework equipped with machine learning technique such as Random Forest can improve forecasting by 50% compares with persistent model and has 90% chance to outperform airport forecast in short-term forecasting. In a real-time setting, the proposed model framework can provide more accurate temperature forecasting results compared with using airport temperature forecast for most forecast horizon. Moreover, we analyze the sensitivity of model parameters to gain insights on how crowdsourcing data from the neighboring personal weather stations impacts forecasting performance. Finally, we implement our model in other cities such as Syracuse and Chicago to test the model's performance in different landforms and climate types.
Abstract. In Part 1, we created an ensemble based on spherical Fourier neural operators. As initial condition perturbations, we used bred vectors, and as model perturbations, we used multiple checkpoints trained independently from scratch. Based on diagnostics that assess the ensemble's physical fidelity, our ensemble has comparable performance to operational weather forecasting systems. However, it requires orders-of-magnitude fewer computational resources. Here in Part 2, we generate a huge ensemble (HENS), with 7424 members initialized each day of summer 2023. We enumerate the technical requirements for running huge ensembles at this scale. HENS precisely samples the tails of the forecast distribution and presents a detailed sampling of internal variability. HENS has two primary applications: (1) as a large dataset with which to study the statistics and drivers of extreme weather and (2) as a weather forecasting system. For extreme climate statistics, HENS samples events 4σ away from the ensemble mean. At each grid cell, HENS increases the skill of the most accurate ensemble member and enhances coverage of possible future trajectories. As a weather forecasting model, HENS issues extreme weather forecasts with better uncertainty quantification. It also reduces the probability of outlier events, in which the verification value lies outside the ensemble forecast distribution.
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.
Modern data-driven surrogate models for weather forecasting provide accurate short-term predictions but inaccurate and nonphysical long-term forecasts. This paper investigates online weather prediction using machine learning surrogates supplemented with partial and noisy observations. We empirically demonstrate and theoretically justify that, despite the long-time instability of the surrogates and the sparsity of the observations, filtering estimates can remain accurate in the long-time horizon. As a case study, we integrate the Fourier Forecasting Neural Network (FourCastNet), a weather surrogate model, within a variational data assimilation framework using partial, noisy ERA5 global reanalysis data from the European Centre for Medium-Range Weather Forecasts (ECMWF). Here, our results show that filtering estimates remain accurate over a year-long assimilation window and provide effective initial conditions for forecasting tasks, including extreme event prediction.
Recent wildfires in Colorado raise the question of whether rising global temperatures have increased fire weather occurrences in Colorado. The U.S. National Weather Service defines fire weather as when “forecast weather conditions will result in a significant threat for the ignition and/or spread of wildfires.” We use two datasets to address the question: “How has the occurrence of fire weather changed in Colorado?” Using 22 years of observed weather conditions from a meteorological tower at the National Renewable Energy Laboratory and 67 years of ERA5 reanalysis data, we assess changing trends in Colorado fire weather as defined by hot, dry, and windy conditions. Additionally, we explore if the difference in recorded wind speeds between observational data and reanalysis data can be explained by differences in spatial and temporal resolution and what are the implications in the context of quantifying fire weather occurrences. The observational data are limited in temporal extent and spatial representativeness, but they capture exact real-world conditions at a location in complex terrain. The reanalysis data are available for an extended period of time and for the entire state, but the data are of relatively coarse spatial and temporal resolution and may fail to capture extremes. To quantify fire risk, we calculate the hot–dry–windy index (HDWI), which relies on wind speed and vapor pressure deficit. No statistically significant trend in the HDWI appears in the observational dataset. However, according to the reanalysis data, strong increasing trends in HDWI values emerge across all of Colorado. This apparent conflict between observational and reanalysis data suggests that reanalysis data may not be representative. Further, more long-term observational datasets are required to assess fire risk.
Distribution system resilience enhancement is an important topic to ensure customers have access to power supply during extreme events. In fact, certain weather-related extreme events can be predicted ahead of time. Therefore, it is important to investigate how to predict grid outages using extreme weather forecasts, and how outage predictions can be incorporated into distribution system resilience enhancement. In this paper, a preventative scheduling model for distribution systems is proposed. The model targets at allocating resources, especially mobile responsive resources such as mobile backup generators and mobile energy storage systems, to prepare for an extreme event in the day-ahead context. To achieve efficient resource allocation and scheduling, a machine learning-based outage prediction module is developed to predict vulnerable or risky segments of the distribution system based on historical operating records and extreme weather event forecast. By integrating the outage prediction results into the scheduling model, optimal resource allocation can be derived to help distribution systems prepare for an upcoming event and improve resilience performance. A real distribution feeder in North Carolina, U.S. is used in the case study to validate the proposed approach.
Compute-optimal scaling laws are relatively well studied for NLP and CV, where objectives are typically single-step and targets are comparatively homogeneous. Weather forecasting is harder to characterize in the same framework: autoregressive rollouts compound errors over long horizons, outputs couple many physical channels with disparate scales and predictability, and globally pooled test metrics can disagree sharply with per-channel, late-lead behavior implied by short-horizon training. We extend neural scaling analysis for autoregressive weather forecasting from single-step training loss to long rollouts and per-channel metrics. We quantify (1) how prediction error is distributed across channels and how its growth rate evolves with forecast horizon, (2) if power law scaling holds for test error, relative to rollout length when error is pooled globally, and (3) how that fit varies jointly with horizon and channel for parameter, data, and compute-based scaling axes. We find strong cross-channel and cross-horizon heterogeneity: pooled scaling can look favorable while many channels degrade at late leads. We discuss implications for weighted objectives, horizon-aware curricula, and resource allocation across outputs.