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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
NASA NTRS2012

NASA Products to Enhance Energy Utility Load Forecasting

Existing energy load forecasting tools rely upon historical load and forecasted weather to predict load within energy company service areas. The shortcomings of load forecasts are often the result of weather forecasts that are not at a fine enough spatial or temporal resolution to capture local-scale weather events. This project aims to improve the performance of load forecasting tools through the integration of high-resolution, weather-related NASA Earth Science Data, such as temperature, relative humidity, and wind speed. Three companies are participating in operational testing one natural gas company, and two electric providers. Operational results comparing load forecasts with and without NASA weather forecasts have been generated since March 2010. We have worked with end users at the three companies to refine selection of weather forecast information and optimize load forecast model performance. The project will conclude in 2012 with transitioning documented improvements from the inclusion of NASA forecasts for sustained use by energy utilities nationwide in a variety of load forecasting tools. In addition, Battelle has consulted with energy companies nationwide to document their information needs for long-term planning, in light of climate change and regulatory impacts.

Lough, G.↗
NASA NTRS2006

Global Positioning System (GPS) Precipitable Water in Forecasting Lightning at Spaceport Canaveral

This paper evaluates the use of precipitable water (PW) from Global Positioning System (GPS) in lightning prediction. Additional independent verification of an earlier model is performed. This earlier model used binary logistic regression with the following four predictor variables optimally selected from a candidate list of 23 candidate predictors: the current precipitable water value for a given time of the day, the change in GPS-PW over the past 9 hours, the KIndex, and the electric field mill value. This earlier model was not optimized for any specific forecast interval, but showed promise for 6 hour and 1.5 hour forecasts. Two new models were developed and verified. These new models were optimized for two operationally significant forecast intervals. The first model was optimized for the 0.5 hour lightning advisories issued by the 45th Weather Squadron. An additional 1.5 hours was allowed for sensor dwell, communication, calculation, analysis, and advisory decision by the forecaster. Therefore the 0.5 hour advisory model became a 2 hour forecast model for lightning within the 45th Weather Squadron advisory areas. The second model was optimized for major ground processing operations supported by the 45th Weather Squadron, which can require lightning forecasts with a lead-time of up to 7.5 hours. Using the same 1.5 lag as in the other new model, this became a 9 hour forecast model for lightning within 37 km (20 NM)) of the 45th Weather Squadron advisory areas. The two new models were built using binary logistic regression from a list of 26 candidate predictor variables: the current GPS-PW value, the change of GPS-PW over 0.5 hour increments from 0.5 to 12 hours, and the K-index. The new 2 hour model found the following for predictors to be statistically significant, listed in decreasing order of contribution to the forecast: the 0.5 hour change in GPS-PW, the 7.5 hour change in GPS-PW, the current GPS-PW value, and the KIndex. The new 9 hour forecast model found the following five independent variables to be statistically significant, listed in decreasing order of contribution to the forecast: the current GPSPW value, the 8.5 hour change in GPS-PW, the 3.5 hour change in GPS-PW, the 12 hour change in GPS-PW, and the K-Index. In both models, the GPS-PW parameters had better correlation to the lightning forecast than the K-Index, a widely used thunderstorm index. Possible future improvements to this study are discussed.

Kehrer, Kristen C.↗
NASA NTRS2019

Evaluating Flood Forecasting System Performance in Cambodia During the 2019 Flood Season

Every year, Cambodia experiences both flash and prolonged riverine flooding as a result of monsoon rains and typhoons. Floods occur frequently in various parts of the region, and result in significant economic cost. Flood forecasting systems are designed to mitigate economic and social impacts, enabling people to prepare for extreme events. However, in order for forecasts to be used effectively, an assessment of the available forecasting systems is needed. In addition, following the onset of flooding, satellite imagery is used to generate flood maps to aid in response efforts. This study demonstrates the performance of regional and global flood forecasting systems over the 2019 flood season. To do this, we assess the flood forecast accuracy at different forecast lead times through a series of forecast verification metrics at gauge locations in Cambodia. We then compare the flood forecast performance to Sentinel 1 flood maps produced by the Hydrological Remote Sensing Analysis of Floods (HYDRAFloods) tool currently being co-developed by SERVIR-Mekong in collaboration with the Myanmar Department of Disaster Management. This assessment of the flood forecasting systems’ performance and comparison to generated flood maps helps provide context to forecasters and disaster managers as they make improvements to their models. Additionally, these results provide support to forecast users as they evaluate the strengths and weaknesses of different systems for taking action.

Nauman, Claire M.↗
NASA NTRS2023

Interpretation of Probabilistic Surface Ozone Forecasts: A Case Study for Philadelphia

The use of probabilistic forecasting has been growing in a variety of disciplines because of its potential to emphasize the degree of uncertainty inherent in a prediction. Interpretation of probabilistic forecasts, however, is oftentimes difficult, deterring users who may benefit from such forecasts. To encourage broader use of probabilistic forecasts in the field of air quality, a process for interpreting forecasts from a statistical probabilistic air quality surface ozone model [the Regression in Self Organizing Map (REGiS)] is demonstrated. Four procedures to convert probabilistic to deterministic forecasts are explored for the Philadelphia, Pennsylvania, metropolitan area. These procedures calibrate the predicted probability of daily maximum 8-h-average ozone exceeding a standard value by 1) estimating climatological relative frequency, 2) establishing a probability of an exceedance threshold as 50%, 3) maximizing the threat score, and 4) determining the unit bias ratio. REGiS is trained using 2000–11 ozone-season (1 May–30 September) data, calibrated using 2012–14 data, and evaluated using 2015–18 data. Assessment of the calibration data with the Pierce skill score suggests an exceedance threshold based on climatological relative frequency for the conversion from probabilistic to deterministic forecasts. Calibrated REGiS generally compares well to predictions from the U.S. national air quality model and operational “expert” forecasts over the evaluation period. For other probabilistic models and situations, different procedures of converting probabilistic to deterministic forecasts may be more beneficial. The methods presented in this paper represent an approach for operational air quality forecasters seeking to use probabilistic model output to support forecasts designed to protect public health.

Nikolay Balashov↗
NASA NTRS2020

Evaluation of adjoint-based observation impacts as a function of forecast length using an Observing System Simulation Experiment

Adjoints of numerical weather prediction models may be employed for Forecast Sensitivity to Observation (FSO) in order to monitor the contribution of ingested observation data on short-term forecast skill. However, the calculation of short-term forecast error is difficult due to the lack of a truly independent dataset for verification. In an Observing System Simulation Experiment framework, the Nature Run is able to provide a true and complete verification dataset and allows accurate evaluation of short term forecast errors. In this work, an OSSE developed at the National Aeronautics and Space Administration Global Modeling and Assimilation Office is used to explore the impact of observational data on forecasts in the 6 to 48 hour range. An adjoint of the Global Earth Observing System model is employed to compare the observation impacts estimated using both self-analysis verification and the true Nature Run verification. Self-analysis verification is found to inflate the estimated forecast error growth during the early forecast period, resulting in overestimations of observation impacts, particularly in the 6-12 hour forecast range. By 48 hours, the self-analysis verification estimates of forecast error and observation impacts more closely match the true values. The fraction of beneficial observations is also overinflated at short forecast times when self-analysis verification is used. The progression of impacts of an individual observation or data type depends on the character of the growth of the initial condition error that each observation affects.

numerical weather prediction↗
DOE OSTI2025

Novel Deep Learning Transformer Model for Short to Sub‐Seasonal Streamflow Forecast

Accurate short-to-subseasonal streamflow forecasts are becoming crucial for effective water management in an increasingly variable climate. However, streamflow forecast remains challenging over extended lead times, uncertainty in meteorological inputs, and increased frequency and variability in extreme weather and climate events. We implemented a Future Time Series Transformer (FutureTST) model for streamflow forecasting that separately integrates past meteorological and streamflow data while incorporating future weather conditions. FutureTST achieves a mean Nash-Sutcliffe Efficiency (NSE) of 0.82 to 0.67 for 1- to 30-day streamflow forecasts. Incorporating upstream streamflow information improved forecast accuracy by up to 10%. During real-time forecast, FutureTST maintains higher forecast skills of 9.03 for 1-day and 5.74 for 14-day forecasts. In contrast, calibrated process-based hydrological model forecasts become unreliable beyond a 4-day lead time. Our findings demonstrate the potential of FutureTST as a reliable streamflow forecasting tool that offers a valuable addition to operational flood monitoring systems and climate-resilient decision-making.

Ambika, Anukesh Krishnankutty [Oak Ridge National ↗
NASA NTRS1984

The impact of satellite temperature soundings on the forecasts of a small national meteorological service

The impact of introducing satellite temperature sounding data on a numerical weather prediction model of a national weather service is evaluated. A dry five level, primitive equation model which covers most of the Northern Hemisphere, is used for these experiments. Series of parallel forecast runs out to 48 hours are made with three different sets of initial conditions: (1) NOSAT runs, only conventional surface and upper air observations are used; (2) SAT runs, satellite soundings are added to the conventional data over oceanic regions and North Africa; and (3) ALLSAT runs, the conventional upper air observations are replaced by satellite soundings over the entire model domain. The impact on the forecasts is evaluated by three verification methods: the RMS errors in sea level pressure forecasts, systematic errors in sea level pressure forecasts, and errors in subjective forecasts of significant weather elements for a selected portion of the model domain. For the relatively short range of the present forecasts, the major beneficial impacts on the sea level pressure forecasts are found precisely in those areas where the satellite sounding are inserted and where conventional upper air observations are sparse. The RMS and systematic errors are reduced in these regions. The subjective forecasts of significant weather elements are improved with the use of the satellite data. It is found that the ALLSAT forecasts are of a quality comparable to the SAR forecasts.

Wolfson, N.↗
NASA NTRS2011

Evaluating the Impact of Atmospheric Infrared Sounder (AIRS) Data On Convective Forecasts

The Short-term Prediction Research and Transition Center (SPoRT) is a collaborative partnership between NASA and operational forecasting partners, including a number of National Weather Service (NWS) offices. SPoRT provides real-time NASA products and capabilities to its partners to address specific operational forecast challenges. The mission of SPoRT is to transition observations and research capabilities into operations to help improve short-term weather forecasts on a regional scale. Two areas of focus are data assimilation and modeling, which can to help accomplish SPoRT's programmatic goals of transitioning NASA data to operational users. Forecasting convective weather is one challenge that faces operational forecasters. Current numerical weather prediction (NWP) models that operational forecasters use struggle to properly forecast location, timing, intensity and/or mode of convection. Given the proper atmospheric conditions, convection can lead to severe weather. SPoRT's partners in the National Oceanic and Atmospheric Administration (NOAA) have a mission to protect the life and property of American citizens. This mission has been tested as recently as this 2011 severe weather season, which has seen more than 300 fatalities and injuries and total damages exceeding $10 billion. In fact, during the three day period from 25-27 April, 1,265 storms reports (362 tornado reports) were collected making this three day period one of most active in American history. To address the forecast challenge of convective weather, SPoRT produces a real-time NWP model called the SPoRT Weather Research and Forecasting (SPoRT-WRF), which incorporates unique NASA data sets. One of the NASA assets used in this unique model configuration is retrieved profiles from the Atmospheric Infrared Sounder (AIRS).The goal of this project is to determine the impact that these AIRS profiles have on the SPoRT-WRF forecasts by comparing to a current operational model and a control SPoRT-WRF model that does not contain AIRS profiles.

Kozlowski, Danielle↗
NASA NTRS2017

Skillful Spring Forecasts of September Arctic Sea Ice Extent Using Passive Microwave Data

In this study, we demonstrate skillful spring forecasts of detrended September Arctic sea ice extent using passive microwave observations of sea ice concentration (SIC) and melt onset (MO). We compare these to forecasts produced using data from a sophisticated melt pond model, and find similar to higher skill values, where the forecast skill is calculated relative to linear trend persistence. The MO forecasts shows the highest skill in March-May, while the SIC forecasts produce the highest skill in June-August, especially when the forecasts are evaluated over recent years (since 2008). The high MO forecast skill in early spring appears to be driven primarily by the presence and timing of open water anomalies, while the high SIC forecast skill appears to be driven by both open water and surface melt processes. Spatial maps of detrended anomalies highlight the drivers of the different forecasts, and enable us to understand regions of predictive importance. Correctly capturing sea ice state anomalies, along with changes in open water coverage appear to be key processes in skillfully forecasting summer Arctic sea ice.

melt onset↗
NASA NTRS2019

Impact of Satellite Sea Surface Salinity Observations on ENSO Predictions from the GMAO Seasonal Forecast System

El Nino/Southern Oscillation (ENSO) has far reaching global climatic impacts and so extending useful ENSO forecasts would be of great benefit for society. However, one key variable that has yet to be fully exploited within coupled forecast systems is accurate estimation of near-surface ocean density. Satellite sea surface salinity (SSS), combined with temperature, help to identify ocean density changes and associated mixing near the ocean surface. We assess the impact of satellite SSS observations for improving near-surface dynamics within ocean analyses and how these impact dynamical ENSO forecasts using the NASA GMAO (Global Modeling and Assimilation Office) Sub-seasonal to Seasonal (S2S_v2.1) coupled forecast system (Molod et al. 2018 - i.e. NASA's contribution to the NMME (North American Multi-Model Ensemble) project). For all initialization experiments, all available along-track absolute dynamic topography and in situ observations are assimilated using the LETKF (Local Ensemble Transform Kalman Filter) scheme similar to Penny et al., 2013. A separate reanalysis additionally assimilates Aquarius V5 (September 2011 to June 2015) and SMAP (Soil Moisture Active Passive satellite) V4.1 (March 2015 to present) along-track data.We highlight the impact of satellite SSS on ocean reanalyses by comparing validation statistics of experiments that assimilate SSS versus our current prediction system that withholds SSS. We find that near-surface validation versus observed statistics for salinity are slightly degraded when assimilating SSS. This is an expected result due to known biases between SSS (measured by satellite at approximately 1-centimeter depth) and in situ measurements (typically measured by Argo floats at 3-meters depth). On the other hand, a very encouraging result is that both temperature, absolute dynamic topography, and mixed layer statistics are improved with SSS assimilation. Previous work has shown that correcting near-surface density structure via gridded SSS assimilation can improve coupled forecasts. Here we present results of coupled forecasts that are initialized from GMAO S2S spring reanalyses that assimilate/withhold along-track (L2) SSS. In particular, we contrast forecasts of the big 2015 El Nino, the 2017 La Nina and the 2018 weak El Nino. For each of these ENSO scenarios, assimilation of satellite SSS improves the forecast validation. Improved SSS and density upgrade the mixed layer depth leading to more accurate coupled air/sea interaction. From March to June 2015, the availability of two overlapping satellite SSS instruments, Aquarius and SMAP, allows a unique opportunity to compare and contrast forecasts initialized with the benefit of these two satellite SSS observation types. We assess the impact of gridded satellite sea surface salinity observations on dynamical ENSO forecasts for the big 2015 El Nino.

Hackert, E.↗
NASA NTRS2019

Seasonal Forecasting of the Quasi-Biennial Oscillation

The ability to seasonally forecast the Quasi-Biennial Oscillation (QBO) was examined using NASA S2S (Sub-seasonal to Seasonal), 9-month, retrospective forecasts. Validation of these forecasts showed that the S2S retrospective QBO forecasts improved skill in predicting the QBO amplitude and phase over a simple QBO phase propagation model at forecast lead times of 1 to 3 months. Results from an initial assessment of whether more accurate QBO forecasts can improve Northern Hemisphere winter sea level pressure forecasts showed no significant forecast improvement at a 1-month lead time, indicating the need for improved stratosphere-troposphere QBO coupling metrics and pathway identification. Overall, these results suggest that future improvements in representing the QBO in global models can increase the ensemble fraction of valid 1 to 3 month QBO forecasts and potentially extend useful QBO forecasts beyond 3 months.

Coy, Lawrence↗
NASA NTRS2021

Impacts of the Eruption of Mount Pinatubo on Surface Temperatures and Precipitation Forecasts With the NASA GEOS Subseasonal-to-Seasonal System

A contemporary seasonal forecasting system is used to study the impacts of a volcanic sulfate injection into the stratosphere on the seasonal forecasts for surface temperatures, the El Niño Southern Oscillation (ENSO), and precipitation. The focus is a case study of the June 1991 eruption of Mt. Pinatubo, Philippines and the period from July 1991 to February 1992. Version 2 of the Goddard Earth Observing System (GEOS) subseasonal-to-seasonal (S2S) forecasting system is used in this study. GEOS-S2S includes the GOddard Chemistry, Aerosols, Radiation and Transport (GOCART) aerosol module, which allows to prognostically simulate aerosol distributions. GOCART is coupled to the radiation and cloud modules to include the impact of the eruption on forecasted radiation and precipitation. The coupled GEOS-S2S system was initialized in May 1991 with fields based on observations to produce ten-member 9-month forecasts with and without the volcanic sulfur injection. The results of these ensemble experiments demonstrate that including Mt. Pinatubo in seasonal forecasts would improve the forecasts of the 1991–1992 global mean temperature and precipitation but worsen the forecast of ENSO by strengthening of El Niño beyond what showed in observations. Most significant changes in the forecasts of temperatures and precipitation are limited to the tropics. The only land area where the inclusion of Pinatubo significantly lowered the forecasted precipitation is tropical Africa.

Mt. Pinatubo↗
NASA NTRS2021

Investigating the potential of a global precipitation forecast to inform landslide prediction

Extreme rainfall events within landslide-prone areas can be catastrophic, resulting in loss of property, infrastructure, and life. A global Landslide Hazard Assessment for Situational Awareness (LHASA) model provides routine near-real time estimates of landslide hazard using Integrated Multi-Satellite Precipitation Retrievals for the Global Precipitation Mission (IMERG). However, it does not provide information on potential landslide hazard in the future. Forecasting potential landslide events at a global scale presents an area of open research. This study compares a global precipitation forecast provided by NASA's Goddard Earth Observing System (GEOS) with near-real time satellite precipitation estimates. The Multi-Radar Multi-Sensor gauge corrected (MRMS-GC) reference is used to assess the performance of both satellite and model-based precipitation products over the contiguous United States (CONUS). The forecast lead time of 24hrs is considered, with a focus on extreme precipitation events. The performance of IMERG and GEOS-Forecast products is assessed in terms of the probability of detection, success ratio, critical success index and hit bias as well as continuous statistics. The results show that seasonality influences the performance of both satellite and model-based precipitation products. Comparison of IMERG and GEOS-Forecast globally as well as in several event case studies (Colombia, southeast Asia, and Tajikistan) reveals that GEOS-Forecast detects extreme rainfall more frequently relative to IMERG for these specific analyses. For recent landslide points across the globe, the 24hr accumulated precipitation forecast >100 mm corresponds well with near-real time daily accumulated IMERG precipitation estimates. GEOS-Forecast and IMERG precipitation match more closely for tropical cyclones than for other types of storms. The main intention of this study is to assess the viability of using a global forecast for landslide predictions and understand the extent of the variability between these products to inform where we would expect the landslide modeling results to most prominently diverge. Results of this study will be used to inform how forecasted precipitation estimates can be incorporated into the LHASA model to provide the first global predictive view of landslide hazards.

S. Khan↗
NASA NTRS2021

Investigating the Potential of A Global Precipitation Forecast to Inform Landslide Prediction

Extreme rainfall events within landslide-prone areas can be catastrophic, resulting in loss of property, infra-structure, and life. A global Landslide Hazard Assessment for Situational Awareness (LHASA) model provides routine near-real time estimates of landslide hazard using Integrated Multi-Satellite Precipitation Retrievals for the Global Precipitation Mission (IMERG). However, it does not provide information on potential landslide hazard in the future. Forecasting potential landslide events at a global scale presents an area of open research. This study compares a global precipitation forecast provided by NASA’s Goddard Earth Observing System (GEOS) with near-real time satellite precipitation estimates. The Multi-Radar Multi-Sensor gauge corrected (MRMS-GC) reference is used to assess the performance of both satellite and model-based precipitation products over the contiguous United States (CONUS). The forecast lead time of 24hrs is considered, with a focus on extreme precipitation events. The performance of IMERG and GEOS-Forecast products is assessed in terms of the probability of detection, success ratio, critical success index and hit bias as well as continuous statistics. The results show that seasonality influences the performance of both satellite and model-based precipitation products. Comparison of IMERG and GEOS-Forecast globally as well as in several event case studies (Colombia, southeast Asia, and Tajikistan) reveals that GEOS-Forecast detects extreme rainfall more frequently relative to IMERG for these specific analyses. For recent landslide points across the globe, the 24hr accumulated precipitation forecast >100 mm corresponds well with near-real time daily accumulated IMERG precipitation estimates. GEOS-Forecast and IMERG precipitation match more closely for tropical cyclones than for other types of storms. The main intention of this study is to assess the viability of using a global forecast for landslide predictions and understand the extent of the variability between these products to inform where we would expect the landslide modeling results to most prominently diverge. Results of this study will be used to inform how forecasted precipitation estimates can be incorporated into the LHASA model to provide the first global predictive view of landslide hazards.

S. Khan↗
NASA NTRS2023

A Community Convention for Ecological Forecasting: Output Files and Metadata Version 1.0

This paper summarizes the open community conventions developed by the Ecological Forecasting Initiative (EFI) for the common formatting and archiving of ecological forecasts and the metadata associated with these forecasts. Such open standards are intended to promote interoperability and facilitate forecast communication, distribution, validation, and synthesis. For output files, we first describe the convention conceptually in terms of global attributes, forecast dimensions, forecasted variables, and ancillary indicator variables. We then illustrate the application of this convention to the two file formats that are currently preferred by the EFI, netCDF (network common data form), and comma-separated values (CSV), but note that the convention is extensible to future formats. For metadata, EFI's convention identifies a subset of conventional metadata variables that are required (e.g., temporal resolution and output variables) but focuses on developing a framework for storing information about forecast uncertainty propagation, data assimilation, and model complexity, which aims to facilitate cross-forecast synthesis. The initial application of this convention expands upon the Ecological Metadata Language (EML), a commonly used metadata standard in ecology. To facilitate community adoption, we also provide a Github repository containing a metadata validator tool and several vignettes in R and Python on how to both write and read in the EFI standard. Lastly, we provide guidance on forecast archiving, making an important distinction between short-term dissemination and long-term forecast archiving, while also touching on the archiving of code and workflows. Overall, the EFI convention is a living document that can continue to evolve over time through an open community process.

Michael C. Dietze↗
DOE OSTI2025

Day-Ahead Probabilistic Forecasting of Net-Load and Demand Response Potentials with High Penetration of Behind-the-Meter Solar-plus-Storage

The goal of this project is to develop advanced methods for day-ahead net-load forecasting, by leveraging the state-of-the-art machine learning techniques. The developed models produce both point and probabilistic forecasts for a variety of use cases, and are versatile to work with different types of data sets. The innovation lies in the novel design of the architectures, leveraging the most recent advances in machine learning that have not been explored in power systems, accompanied by techniques in the broader artificial intelligence fields such as fuzzy systems. This project has achieved the following accomplishments: (1) preprocessing of over 10 data sets covering varying geographical regions, time horizons, and system levels, which form a robust foundation for training and evaluating forecasting models across a wide range of realistic grid scenarios; (2) development of an interactive web app that enables exploratory analysis of load and generation data, and supports better understanding of data trends, anomalies, and correlations, facilitating model development and stakeholder engagement; (3) implementation of over 10 benchmark models for point and probabilistic forecasting, which include a mix of conventional machine learning methods and state-of-the-art deep learning approaches, providing a comprehensive baseline for performance comparison and validation of the proposed models; (4) development of a fuzzy system based gradient boosting model, tailored for small (less than 3 years) data sets, which achieves a mean absolute percentage error (MAPE) of 4% for point forecasting and a 20% improvement in average pinball loss for probabilistic forecasting; (5) development of a Transformer (a state-of-the-art deep learning architecture) based neural network model, tailored for large (3 years or more) data sets, which achieves a MAPE of 2% for point forecasting and a 20% improvement in average pinball loss for probabilistic forecasting; (6) development of a methodology for quantifying DR potential, and extensions of the previous models for multi-target forecasting of net load and DR potential, which achieve a MAPE of 10% for DR potential.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2012

Advancing Data Assimilation in Operational Hydrologic Forecasting: Progresses, Challenges, and Emerging Opportunities

Data assimilation (DA) holds considerable potential for improving hydrologic predictions as demonstrated in numerous research studies. However, advances in hydrologic DA research have not been adequately or timely implemented in operational forecast systems to improve the skill of forecasts for better informed real-world decision making. This is due in part to a lack of mechanisms to properly quantify the uncertainty in observations and forecast models in real-time forecasting situations and to conduct the merging of data and models in a way that is adequately efficient and transparent to operational forecasters. The need for effective DA of useful hydrologic data into the forecast process has become increasingly recognized in recent years. This motivated a hydrologic DA workshop in Delft, the Netherlands in November 2010, which focused on advancing DA in operational hydrologic forecasting and water resources management. As an outcome of the workshop, this paper reviews, in relevant detail, the current status of DA applications in both hydrologic research and operational practices, and discusses the existing or potential hurdles and challenges in transitioning hydrologic DA research into cost-effective operational forecasting tools, as well as the potential pathways and newly emerging opportunities for overcoming these challenges. Several related aspects are discussed, including (1) theoretical or mathematical aspects in DA algorithms, (2) the estimation of different types of uncertainty, (3) new observations and their objective use in hydrologic DA, (4) the use of DA for real-time control of water resources systems, and (5) the development of community-based, generic DA tools for hydrologic applications. It is recommended that cost-effective transition of hydrologic DA from research to operations should be helped by developing community-based, generic modeling and DA tools or frameworks, and through fostering collaborative efforts among hydrologic modellers, DA developers, and operational forecasters.

forecasting↗
DOE OSTI2025

A cross-dimensional analysis of data-driven short-term load forecasting methods with large-scale smart meter data

Electricity load forecasting is essential to utility operation and power grid stability. A wide spectrum of data-driven methods, ranging from linear regression models to more recent deep learning models have been adopted to forecast electric load over the years. However, there still lacks a holistic evaluation of the applicability of conventional statistical and machine learning based algorithms with respect to different temporal and spatial scopes, computational requirements, and sensitivity of model-tuning. Enabled by a large-scale electricity load profile dataset of over 40,000 residential customers in a utility region, we conducted a cross-dimensional analysis of data-driven load forecasting methods. Three regression-based and seven deep learning algorithms with different model configurations were evaluated in terms of their overall and peak load prediction accuracy, and training burdens, across spatial aggregation levels ranging from the transformer, feeder, substation, to neighborhood. We found, first, the load forecasting accuracy is constrained by a predictability boundary, influenced by the forecasting horizon and spatial aggregation level. Specifically, RandomForest, XGBoost, TFT, TSMixer, and TiDE models achieved less than 10 % prediction error for up to 96-h ahead forecasting for district, substation, and feeder levels, while other models struggle at long-horizon predictions; Second, for winter and summer peak load dates, most models were able to predict the peak demand timing within ± 1 h, but the prediction percentage error varied by models, with TFT and TiDE models being the top performers; Third, models with similar prediction accuracy can differ in training burden by an order of magnitude. Therefore, choosing model configurations that balance prediction performance and computational resource is an important practical consideration for large-scale deployment of the machine learning based load forecasting. The outcome of this study can guide researchers and practitioners to choose the proper load forecasting algorithms based on their problem scope, required accuracy, and available resources. The predictability boundary can serve as a benchmark for electricity load forecasting problems with new algorithms and datasets.

Li, Han↗