Search NASA⌕ Search

SEARCH · Search NASA

Results for “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 217 records · Page 12

Machine learning for postprocessing ensemble streamflow forecasts

Skillful streamflow forecasts can inform decisions in various areas of water policy and management. We integrate numerical weather prediction ensembles, distributed hydrological model, and machine learning to generate ensemble streamflow forecasts at medium-range lead times (1–7 days). We demonstrate the application of machine learning as postprocessor for improving the quality of ensemble streamflow forecasts. Our results show that the machine learning postprocessor can improve streamflow forecasts relative to low-complexity forecasts (e.g., climatological and temporal persistence) as well as standalone hydrometeorological modeling and neural network. The relative gain in forecast skill from postprocessor is generally higher at medium-range timescales compared to shorter lead times; high flows compared to low–moderate flows, and the warm season compared to the cool ones. Overall, our results highlight the benefits of machine learning in many aspects for improving both the skill and reliability of streamflow forecasts.

54 ENVIRONMENTAL SCIENCES↗

Use of wind power forecasting in operational decisions.

The rapid expansion of wind power gives rise to a number of challenges for power system operators and electricity market participants. The key operational challenge is to efficiently handle the uncertainty and variability of wind power when balancing supply and demand in ths system. In this report, we analyze how wind power forecasting can serve as an efficient tool toward this end. We discuss the current status of wind power forecasting in U.S. electricity markets and develop several methodologies and modeling tools for the use of wind power forecasting in operational decisions, from the perspectives of the system operator as well as the wind power producer. In particular, we focus on the use of probabilistic forecasts in operational decisions. Driven by increasing prices for fossil fuels and concerns about greenhouse gas (GHG) emissions, wind power, as a renewable and clean source of energy, is rapidly being introduced into the existing electricity supply portfolio in many parts of the world. The U.S. Department of Energy (DOE) has analyzed a scenario in which wind power meets 20% of the U.S. electricity demand by 2030, which means that the U.S. wind power capacity would have to reach more than 300 gigawatts (GW). The European Union is pursuing a target of 20/20/20, which aims to reduce greenhouse gas (GHG) emissions by 20%, increase the amount of renewable energy to 20% of the energy supply, and improve energy efficiency by 20% by 2020 as compared to 1990. Meanwhile, China is the leading country in terms of installed wind capacity, and had 45 GW of installed wind power capacity out of about 200 GW on a global level at the end of 2010. The rapid increase in the penetration of wind power into power systems introduces more variability and uncertainty in the electricity generation portfolio, and these factors are the key challenges when it comes to integrating wind power into the electric power grid. Wind power forecasting (WPF) is an important tool to help efficiently address this challenge, and significant efforts have been invested in developing more accurate wind power forecasts. In this report, we document our work on the use of wind power forecasting in operational decisions.

17 WIND ENERGY↗

Analysis of Random Forest Modeling Strategies for Multi-Step Wind Speed Forecasting

Although the random forest (RF) model is a powerful machine learning tool that has been utilized in many wind speed/power forecasting studies, there has been no consensus on optimal RF modeling strategies. This study investigates three basic questions which aim to assist in the discernment and quantification of the effects of individual model properties, namely: (1) using a standalone RF model versus using RF as a correction mechanism for the persistence approach, (2) utilizing a recursive versus direct multi-step forecasting strategy, and (3) training data availability on model forecasting accuracy from one to six hours ahead. These questions are investigated utilizing data from the FINO1 offshore platform and Atmospheric Radiation Measurement (ARM) Southern Great Plains (SGP) C1 site, and testing results are compared to the persistence method. At FINO1, due to the presence of multiple wind farms and high inter-annual variability, RF is more effective as an error-correction mechanism for the persistence approach. The direct forecasting strategy is seen to slightly outperform the recursive strategy, specifically for forecasts three or more steps ahead. Finally, increased data availability (up to ~8 equivalent years of hourly training data) appears to continually improve forecasting accuracy, although changing environmental flow patterns have the potential to negate such improvement. We hope that the findings of this study will assist future researchers and industry professionals to construct accurate, reliable RF models for wind speed forecasting.

54 ENVIRONMENTAL SCIENCES↗

A Comparison of Infectious Disease Forecasting Methods across Locations, Diseases, and Time

Accurate infectious disease forecasting can inform efforts to prevent outbreaks and mitigate adverse impacts. This study compares the performance of statistical, machine learning (ML), and deep learning (DL) approaches in forecasting infectious disease incidences across different countries and time intervals. We forecasted three diverse diseases: campylobacteriosis, typhoid, and Q-fever, using a wide variety of features (n = 46) from public datasets, e.g., landscape, climate, and socioeconomic factors. We compared autoregressive statistical models to two tree-based ML models (extreme gradient boosted trees [XGB] and random forest [RF]) and two DL models (multi-layer perceptron and encoder–decoder model). The disease models were trained on data from seven different countries at the region-level between 2009–2017. Forecasting performance of all models was assessed using mean absolute error, root mean square error, and Poisson deviance across Australia, Israel, and the United States for the months of January through August of 2018. The overall model results were compared across diseases as well as various data splits, including country, regions with highest and lowest cases, and the forecasted months out (i.e., nowcasting, short-term, and long-term forecasting). Overall, the XGB models performed the best for all diseases and, in general, tree-based ML models performed the best when looking at data splits. There were a few instances where the statistical or DL models had minutely smaller error metrics for specific subsets of typhoid, which is a disease with very low case counts. Feature importance per disease was measured by using four tree-based ML models (i.e., XGB and RF with and without region name as a feature). The most important feature groups included previous case counts, region name, population counts and density, mortality causes of neonatal to under 5 years of age, sanitation factors, and elevation. This study demonstrates the power of ML approaches to incorporate a wide range of factors to forecast various diseases, regardless of location, more accurately than traditional statistical approaches.

59 BASIC BIOLOGICAL SCIENCES↗

Deep-Learning-Based Multi-Timescale Load Forecasting in Buildings: Opportunities and Challenges from Research to Deployment

Electricity load forecasting for buildings and campuses is becoming increasingly important as the penetration of distributed energy resources (DERs) grows. Efficient operation and dispatch of DERs require reasonably accurate predictions of future energy consumption in order to conduct near-real-time optimized dispatch of on-site generation and storage assets. Electric utilities have traditionally performed load forecasting for load pockets spanning large geographic areas, and therefore, forecasting has not been a common practice by buildings and campus operators. Given the growing trends of research and prototyping in the grid-interactive efficient buildings domain, characteristics beyond simple algorithm forecast accuracy are important in determining the algorithm's true utility for smart buildings. Other characteristics include the overall design of the deployed architecture and the operational efficiency of the forecasting system. In this work, we present a deep-learning-based load forecasting system that predicts the building load at 1-hour intervals for 18 hours in the future. We also discuss challenges associated with the real-time deployment of such systems as well as the research opportunities presented by a fully functional forecasting system that has been developed within the National Renewable Energy Laboratory's Intelligent Campus program.

building load forecasting↗

Distribution of Wind Power Forecast Errors from Operational Systems

Wind power forecasting is one important tool in the integration of large amounts of renewable generation into the electricity system. Wind power forecasts from operational systems are not perfect, and thus, an understanding of the forecast error distributions can be important in system operations. In this work, we examine the errors from operational wind power forecasting systems, both for asingle wind plant and for an entire interconnection. The resulting error distributions are compared with the normal distribution and the distribution obtained from the persistence forecasting model at multiple timescales. A model distribution is fit to the operational system forecast errors and the potential impact on system operations highlighted through the generation of forecast confidenceintervals.

17 WIND ENERGY↗

Short-Term Probabilistic Solar Forecasting via Reinforcement Learning over ECMWF

In this paper, we present an innovative reinforcement learning approach for short-term solar forecasting, leveraging data from the European Centre for Medium-Range Weather Forecasts (ECMWF). The methodology begins with the application of the System Advisor Model (SAM) to transform various ECMWF numerical weather prediction members into predictive photovoltaic power generation. To enhance the precision of deterministic forecasting, we introduce a dynamic model selection algorithm based on Q-learning. This algorithm dynamically identifies and utilizes the most accurate ensemble member for forecasting purposes. Furthermore, we employ a support vector regression surrogate model with a Gaussian distribution to generate probabilistic forecasts, providing a holistic view of solar energy generation uncertainty. To expedite the training process and make it more practical for real-world applications, we integrate a rolling update workflow. This innovative workflow reduces the training period from months to a mere 19 days, making our method highly efficient. Numerical results of the case study show that in comparison to benchmark models, the proposed method improves the deterministic and probabilistic solar forecasting accuracy by up to 40.84% and 48.42%, respectively.

ensemble forecasting↗

An analysis of the operational GFS simplified Arakawa Schubert parameterization within a WRF framework: A Hurricane Sandy (2012) long‐term track forecast perspective

Abstract Hurricane Sandy (2012) is known as an incredibly destructive storm and one defined meteorologically by its large size, and its significant forecast track spreads among various operational models roughly 1 week before landfall. While the operational European Centre for Medium‐Range Weather Forecasts model accurately depicted a northeastern United States landfall, the Global Forecasting System (GFS) model consistently forecast a track toward the North Atlantic Ocean. Using a Weather Research and Forecasting (WRF) model framework, Bassill ( ) suggested that these differences were primarily a function of differences between the two models' cumulus parameterization (CP). This study also uses a WRF model framework to examine the simplified Arakawa Schubert CP used in the GFS model. It is found that increasing the deep convective entrainment coefficient produces more realistic forecast tracks for forecasts initialized roughly 1 week before landfall. This occurs through a reorientation of the precipitation (and associated latent heating) around Sandy during a critical time period in which it was interacting with a series of upper troughs to its west and northwest. Reorienting the latent heating reshapes the upper tropospheric steering pattern toward the one that is more negatively tilted and consistent with observations.

Bassill, Nick P.↗

Predicting regional and pan-Arctic sea ice anomalies with kernel analog forecasting

Predicting Arctic sea ice extent is a notoriously difficult forecasting problem, even for lead times as short as one month. Motivated by Arctic intraannual variability phenomena such as reemergence of sea surface temperature and sea ice anomalies, we use a prediction approach for sea ice anomalies based on analog forecasting. Traditional analog forecasting relies on identifying a single analog in a historical record, usually by minimizing Euclidean distance, and forming a forecast from the analog’s historical trajectory. An ensemble of analogs is used to make forecasts, where the ensemble weights are determined by a dynamics-adapted similarity kernel, which takes into account the nonlinear geometry on the underlying data manifold. We apply this method for forecasting pan-Arctic and regional sea ice area and volume anomalies from multi-century climate model data, and in many cases find improvement over the benchmark damped persistence forecast. Examples of success include the 3–6 month lead time prediction of Arctic sea ice area, the winter sea ice area prediction of some marginal ice zone seas, and the 3–12 month lead time prediction of sea ice volume anomalies in many central Arctic basins. Finally, we discuss possible connections between KAF success and sea ice reemergence, and find KAF to be successful in regions and seasons exhibiting high interannual variability.

54 ENVIRONMENTAL SCIENCES↗

Time-Series Forecast Modeling on High-Bandwidth Network Measurements

With the increasing number of geographically distributed scientific collaborations and the growing sizes of scientific data, it has become challenging for users to achieve the best possible network performance on a shared network. In this paper, we have developed a model to forecast expected bandwidth utilization on high-bandwidth wide area networks. The forecast model can improve the efficiency of the resource utilization and scheduling of data movements on high-bandwidth networks to accommodate ever increasing data volume for large-scale scientific data applications. A univariate time-series forecast model is developed with the Seasonal decomposition of Time series by Loess (STL) and the AutoRegressive Integrated Moving Average (ARIMA) on Simple Network Management Protocol (SNMP) path utilization measurement data. Compared with the traditional approach such as Box-Jenkins methodology to train the ARIMA model, our forecast model reduces computation time up to 92.6 %. It also shows resilience against abrupt network usage changes. Finally, our forecast model conducts the large number of multi-step forecast, and the forecast errors are within the mean absolute deviation (MAD) of the monitored measurements.

97 MATHEMATICS AND COMPUTING↗

Multiscale influenza forecasting

Abstract Influenza forecasting in the United States (US) is complex and challenging due to spatial and temporal variability, nested geographic scales of interest, and heterogeneous surveillance participation. Here we present Dante, a multiscale influenza forecasting model that learns rather than prescribes spatial, temporal, and surveillance data structure and generates coherent forecasts across state, regional, and national scales. We retrospectively compare Dante’s short-term and seasonal forecasts for previous flu seasons to the Dynamic Bayesian Model (DBM), a leading competitor. Dante outperformed DBM for nearly all spatial units, flu seasons, geographic scales, and forecasting targets. Dante’s sharper and more accurate forecasts also suggest greater public health utility. Dante placed 1st in the Centers for Disease Control and Prevention’s prospective 2018/19 FluSight challenge in both the national and regional competition and the state competition. The methodology underpinning Dante can be used in other seasonal disease forecasting contexts having nested geographic scales of interest.

59 BASIC BIOLOGICAL SCIENCES↗

Evaluation of FluSight influenza forecasting in the 2021–22 and 2022–23 seasons with a new target laboratory-confirmed influenza hospitalizations

Accurate forecasts can enable more effective public health responses during seasonal influenza epidemics. For the 2021–22 and 2022–23 influenza seasons, 26 forecasting teams provided national and jurisdiction-specific probabilistic predictions of weekly confirmed influenza hospital admissions for one-to-four weeks ahead. Forecast skill is evaluated using the Weighted Interval Score (WIS), relative WIS, and coverage. Six out of 23 models outperform the baseline model across forecast weeks and locations in 2021–22 and 12 out of 18 models in 2022–23. Averaging across all forecast targets, the FluSight ensemble is the 2nd most accurate model measured by WIS in 2021–22 and the 5th most accurate in the 2022–23 season. Forecast skill and 95% coverage for the FluSight ensemble and most component models degrade over longer forecast horizons. In this work we demonstrate that while the FluSight ensemble was a robust predictor, even ensembles face challenges during periods of rapid change.

59 BASIC BIOLOGICAL SCIENCES↗

Learning from Dynamic User Interaction Graphs to Forecast Diverse Social Behavior

Most of the existing graph analytics for understanding social be- havior focuses on learning from static rather than dynamic graphs using hand-crafted network features or recently emerged graph embeddings learned independently from a downstream predictive task, and solving predictive (e.g., link prediction) rather than fore- casting tasks directly. To address these limitations, we propose (1) a novel task – forecasting user interactions over dynamic social graphs, and (2) a novel deep learning, multi-task, node-aware at- tention model that focuses on forecasting social interactions, going beyond recently emerged approaches for learning dynamic graph embeddings. Our model relies on graph convolutions and recurrent layers to forecast future social behavior and interaction patterns in dynamic social graphs. We evaluate our model on the ability to forecast the number of retweets and mentions of a specific news source on Twitter (focusing on deceptive and credible news sources) with R2 of 0.79 for retweets and 0.81 for mentions. An additional evaluation includes model forecasts of user-repository interactions on GitHub and comments to a specific video on YouTube with a mean absolute error close to 2% and R2 exceeding 0.69. Our results demonstrate that learning from connectivity information over time in combination with node embeddings yields better forecasting results than when we incorporate the state-of-the-art graph em- beddings e.g., Node2Vec and DeepWalk into our model. Finally, we perform in-depth analyses to examine factors that influence model performance across tasks and different graph types e.g., the influence of training and forecasting windows as well as graph topological properties.

Shrestha, Prasha↗

Accuracy of real-time multi-model ensemble forecasts for seasonal influenza in the U.S.

Seasonal influenza results in substantial annual morbidity and mortality in the United States and worldwide. Accurate forecasts of key features of influenza epidemics, such as the timing and severity of the peak incidence in a given season, can inform public health response to outbreaks. As part of ongoing efforts to incorporate data and advanced analytical methods into public health decision-making, the United States Centers for Disease Control and Prevention (CDC) has organized seasonal influenza forecasting challenges since the 2013/2014 season. In the 2017/2018 season, 22 teams participated. A subset of four teams created a research consortium called the FluSight Network in early 2017. During the 2017/2018 season they worked together to produce a collaborative multi-model ensemble that combined 21 separate component models into a single model using a machine learning technique called stacking. This approach creates a weighted average of predictive densities where the weight for each component is determined by maximizing overall ensemble accuracy over past seasons. In the 2017/2018 influenza season, one of the largest seasonal outbreaks in the last 15 years, this multi-model ensemble performed better on average than all individual component models and placed second overall in the CDC challenge. It also outperformed the baseline multi-model ensemble created by the CDC that took a simple average of all models submitted to the forecasting challenge. This project shows that collaborative efforts between research teams to develop ensemble forecasting approaches can bring measurable improvements in forecast accuracy and important reductions in the variability of performance from year to year. Efforts such as this, that emphasize real-time testing and evaluation of forecasting models and facilitate the close collaboration between public health officials and modeling researchers, are essential to improving our understanding of how best to use forecasts to improve public health response to seasonal and emerging epidemic threats.

59 BASIC BIOLOGICAL SCIENCES↗

Conditioning multi-model ensembles for disease forecasting

In this study we investigate how an ensemble of disease models can be conditioned to observational data, in a bid to improve its predictive skill. We use the ensemble of influenza forecasting models gathered by the US Centers for Disease Control and Prevention (CDC) as the exemplar. This ensemble is used every year to forecast the annual influenza outbreak in the United States. The models constituting this ensemble draw on very different modeling assumptions and approximations and are a diverse collection of methods to approximate epidemiological dynamics. Currently, each models' predictions are accorded the same importance, or weight, when compiling the ensemble's forecast. We consider this equally-weighted ensemble as the baseline case which has to be improved upon. In this study, we explore whether an ensemble forecast can be improved by "conditioning" the ensemble to whatever observational data is available from the ongoing outbreak. "Conditioning" can imply according the ensemble's members different weights which evolve over time, or simply perform the forecast using the top k (equally-weighted) models. In the latter case, the composition of the "top-k-see of models evolves over time. This is called "model averaging" in statistics. We explore four methods to perform model-averaging, three of which are new. We find that the CDC ensemble responds best to the "top-k-models" approach to model-averaging. All the new MA methods perform better than the baseline equally-weighted ensemble. The four model-averaging methods treat the models as black-boxes and simply use their forecasts as inputs i.e., one does not need access to the models at all, but rather only their forecasts. The model-averaging approaches reviewed in this report thus form a general framework for model-averaging any model ensemble.

59 BASIC BIOLOGICAL SCIENCES↗

Advanced Solar and Load Forecasting Incorporating HD Sky Imaging (Phase III)

Due to rapidly changing sky conditions, the available solar irradiance for energy generation is subject to wide swings in amplitude. As the market penetration of solar energy continues to increase rapidly, these variations in solar power generation are beginning to have an impact on grid stability and increased wear on power switches. Solar power forecasting plays a critical role in operations for Independent System Operators (ISOs) and utilities. Accurate forecasts help maintain grid reliability, optimize generation from renewables, and reduce operating costs. Of particular interest to the ISOs and utilities are sudden changes in solar irradiance, termed “ramp events,” due to the movement of clouds. One significant impact of ramp events on the grid is additional ancillary service requirements necessary to manage such variability. Ramp events can also cause voltage fluctuations in the distribution grids and trigger actions of automated line equipment (e.g., tap changers), leading to additional maintenance costs. In high penetration solar regions, forecasts must be made for both transmission-connected and distribution-connected resources – either behind the meter or in front of it. Particularly for distributed solar energy resources, forecasting can be a challenge due to the lack of visibility of the energy resource. Brookhaven National Laboratory (BNL) has been working towards nowcasting Global Horizontal Irradiance (GHI) using low-cost technologies for several years now. The Solar NowCasting technology being developed by BNL is a 0 – 30 min solar “nowcasting” technology applicable to a scale covering both large generating facilities and residential, distributed solar installations that relies on a network of ground-based high-definition (HD) cameras and surface pyranometers. GHI forecasts are being produced for both regions using 8 ground-based HD cameras and at least 2 surface pyranometers. When stitched together, the camera images can be used to forecast the impact of clouds on available solar irradiance over a domain of ~50 km 2 . Phase I of the project was the engineering scale up conceptual design stage. Phase II was the initial field test and demonstration, in which the technology was scaled up by a factor of 20 times and successfully demonstrated in eastern Long Island. In Phase III, an additional forecasting network was added in upstate NY and both networks are currently being operated until at least a full year of data is gathered by the Albany network to allow for the collection of sufficient data to evaluate performance against the persistence and smart persistence models using the Solar Arbiter.

14 SOLAR ENERGY↗

Solar and Wind Forecast Error Reserve Sharing in a Multi-Utility Region

As electricity systems transition to higher levels of solar and wind generation, electric system operators will likely need to hold additional reserves to manage the forecast error associated with these resources. Because wind and solar forecast errors tend to be poorly correlated across space, system operators can reduce their reserve requirements by sharing reserves. This paper examines the value of forecast error reserve sharing among balancing areas in the Southeast United States. It finds that forecast error reserve requirements increase linearly with growth in solar and wind generation capacity but that reserve sharing can significantly reduce physical (MW) reserve requirements (from 25%-26% to 18%-19% of average load in high solar scenarios). It finds that the value of forecast error reserve sharing declines with higher levels of solar and wind generation, due to lower wholesale energy and reserve prices. Even with declines in wholesale prices, forecast error reserve sharing can still provide substantial value (as much as $\$$400 million per year in a high solar scenario), though with higher levels of solar, wind, and electricity storage, this value is increasingly tied to avoiding scarcity prices. The results suggest the importance of coordinated capacity expansion planning for forecast error reserve sharing.

14 SOLAR ENERGY↗

Evaluation of GloFAS-Seasonal Forecasts for Cascade Reservoir Impoundment Operation in the Upper Yangtze River

Standard impoundment operation rules (SIOR) are pre-defined guidelines for refilling reservoirs before the end of the wet season. The advancement and availability of the seasonal flow forecasts provide the opportunity for reservoir operators to use flexible and early impoundment operation rules (EIOR). These flexible impoundment rules can significantly improve water conservation, particularly during dry years. In this study, we investigate the potential application of seasonal streamflow forecasts for employing EIOR in the upper Yangtze River basin. We first define thresholds to determine the streamflow condition in September, which is an important period for decision-making in the basin, and then select the most suitable impoundment operation rules accordingly. The thresholds are used in a simulation–optimization model to evaluate different scenarios for EIOR and SIOR by multiple objectives. We measure the skill of the GloFAS-Seasonal forecast, an operational global seasonal river flow forecasting system, to predict streamflow condition according to the selected thresholds. The results show that: (1) the 20th and 30th percentiles of the historical September flow are suitable thresholds for evaluating the possibility of employing EIOR; (2) compared to climatological forecasts, GloFAS-Seasonal forecasts are skillful for predicting the streamflow condition according to the selected 20th and 30th percentile thresholds; and (3) during dry years, EIOR could improve the fullness storage rate by 5.63% and the annual average hydropower generation by 4.02%, without increasing the risk of flooding. GloFAS-Seasonal forecasts and early reservoir impoundment have the potential to enhance hydropower generation and water utilization.

54 ENVIRONMENTAL SCIENCES↗