Global Forecast System Accuracy at Cape Canaveral Space Force Station
Explore the source record for details and available documents.
Frank Leahy↗
SEARCH · Search NASA
Results for “forecast accuracy”
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.
Multi-Agency Ensemble Forecast of Wildfire Air Quality in the United States: Toward Community Consensus of Early Warning
Wildfires pose increasing risks to human health and properties in North America. Due to large uncertainties in fire emission, transport, and chemical transformation, it remains challenging to accurately predict air quality during wildfire events, hindering our collective capability to issue effective early warnings to protect public health and welfare. Here we present a new real-time Hazardous Air Quality Ensemble System (HAQES) by leveraging various wildfire smoke forecasts from three U.S. federal agencies (NOAA, NASA, and Navy). Compared to individual models, the HAQES ensemble forecast significantly enhances forecast accuracy. To further enhance forecasting performance, a weighted ensemble forecast approach was introduced and tested. Compared to the unweighted ensemble mean, the multilinear regression weighted ensemble reduced fractional bias by 34% in the major fire regions, false alarm rate by 72%, and increased hit rate by 17%. Finally, we improved the weighted ensemble using quantile regression and weighted regression methods to enhance the forecast of extreme air quality events. The advanced weighted ensemble increased the PM2.5 exceedance hit rate by 55% compared to the ensemble mean. Our findings provide insights into the development of advanced ensemble forecast methods for wildfire air quality, offering a practical way to enhance decision-making support to protect public health.
Yunyao Li↗
Use of Physics to Improve Solar Forecast: Physics-Informed Persistence Models for Simultaneously Forecasting GHI, DNI, and DHI
Observation-based statistical models have been widely used in forecasting solar energy; however, existing models often lack a clear relation to physics and are limited largely to global horizontal irradiance (GHI) forecasts over relatively short time horizons (< 1 hour). Incorporating physics into observation-based models, increasing forecast time horizons and developing a model system for forecasting not only GHI but also direct normal irradiance (DNI) and diffuse horizontal irradiance (DHI) remain challenging, especially under cloudy conditions because of complex cloud-radiation interactions. This work attempts to address these challenges by developing a hierarchy of four new physics-informed persistence models that can be used to simultaneously forecast GHI, DNI and DHI. The decade-long measurements (1998 to 2014) at the U.S. Department of Energy's Atmospheric Radiation Measurement (ARM)'s Southern Great Plains (SGP) Central Facility site are used to evaluate the performance of the new models. Overall, the results show that the new physics-informed forecast models generally outperform the simple and smart persistence models, and improve the forecast accuracy at lead times from 1.25 hours up to 6 hours. Further analysis reveals that the forecast error is highly related to the error and temporal variability of the assumed cloud predictor. The best model for forecasting different radiative components can be explained by the relationship between solar irradiances and cloud properties.
54 ENVIRONMENTAL SCIENCES↗
Some economic benefits of a synchronous earth observatory satellite
An analysis was made of the economic benefits which might be derived from reduced forecasting errors made possible by data obtained from a synchronous satellite system which can collect earth observation and meteorological data continuously and on demand. User costs directly associated with achieving benefits are included. In the analysis, benefits were evaluated which might be obtained as a result of improved thunderstorm forecasting, frost warning, and grain harvest forecasting capabilities. The anticipated system capabilities were used to arrive at realistic estimates of system performance on which to base the benefit analysis. Emphasis was placed on the benefits which result from system forecasting accuracies. Benefits from improved thunderstorm forecasts are indicated for the construction, air transportation, and agricultural industries. The effects of improved frost warning capability on the citrus crop are determined. The benefits from improved grain forecasting capability are evaluated in terms of both U.S. benefits resulting from domestic grain distribution and U.S. benefits from international grain distribution.
Battacharyya, R. K.↗
Routine High-Resolution Forecasts/Analyses for the Pacific Disaster Center: User Manual
Enclosed herein is our HWCMO user manual. This manual constitutes the final report for our NASA/PDC grant, NASA NAG5-8730, "Routine High Resolution Forecasts/Analysis for the Pacific Disaster Center". Since the beginning of the grant, we have routinely provided experimental high resolution forecasts from the RSM/MSM for the Hawaii Islands, while working to upgrade the system to include: (1) a more robust input of NCEP analyses directly from NCEP; (2) higher vertical resolution, with increased forecast accuracy; (3) faster delivery of forecast products and extension of initial 1-day forecasts to 2 days; (4) augmentation of our basic meteorological and simplified fireweather forecasts to firedanger and drought forecasts; (5) additional meteorological forecasts with an alternate mesoscale model (MM5); and (6) the feasibility of using our modeling system to work in higher-resolution domains and other regions. In this user manual, we provide a general overview of the operational system and the mesoscale models as well as more detailed descriptions of the models. A detailed description of daily operations and a cost analysis is also provided. Evaluations of the models are included although it should be noted that model evaluation is a continuing process and as potential problems are identified, these can be used as the basis for making model improvements. Finally, we include our previously submitted answers to particular PDC questions (Appendix V). All of our initially proposed objectives have basically been met. In fact, a number of useful applications (VOG, air pollution transport) are already utilizing our experimental output and we believe there are a number of other applications that could make use of our routine forecast/analysis products. Still, work still remains to be done to further develop this experimental weather, climate, fire danger and drought prediction system. In short, we would like to be a part of a future PDC team, if at all possible, to further develop and apply the system for the Hawaiian and other Pacific Islands as well as the entire Pacific Basin.
Roads, John↗
Short‐Term Hourly Weather Forecasting Using PredRNN With Image Preprocessing
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.
Tran, Hoang [Pacific Northwest National Laboratory↗
Atmospheric Composition Forecast Model Evaluation Using Ozone Measurements Collected by the Langley Mobile Ozone Lidar
The Langley Mobile Ozone Lidar (LMOL) is a mobile ground based lidar system based at NASA Langley in Hampton, Virginia. Between 2022 and 2024, LMOL collected over 2500 hours of ozone measurements for a range of different atmospheric conditions, including calm days, stratospheric intrusions, surface frontal passages, and long-range transported wildfire smoke plumes. Here, the data is used to evaluate the forecast accuracy of NASA’s Global GEOS Composition Forecasting (GEOS-CF) model. GEOS-CF makes daily three-dimensional forecasts of trace gases and aerosol species. Overall, for calm periods, the forecast model predicts lower tropospheric ozone at NASA Langley with reasonable accuracy (within 20%). The model best predicts the timing and extent of stratospheric intrusions but often vary in the magnitude of the ozone mixing ratio. Among the other types of atmospheric conditions, there is more variability in the model forecasts. Based on this analysis, model forecasts are utilized to determine future data acquisition opportunities with the goal of providing feedback to the modeling teams, thereby enabling them to better understand the model biases and improve the model forecasts of ozone during these different atmospheric conditions.
Daniel B Phoenix↗
Model Evaluation and Intercomparison Using Data Collected by the Langley Mobile Ozone Lidar in Hampton, Virginia
Throughout the year 2022, the Langley Mobile Ozone Lidar (LMOL) has been frequently collecting ozone and aerosol measurements in the lower troposphere. The lidar is located in the parking lot behind the Atmospheric Sciences building at NASA Langley in Hampton, Virginia, approximately 37.095 N, -76.389 W. The data was collected during a range of several distinct atmospheric conditions, including stratospheric intrusions, surface frontal passages, and long-range transported wildfire smoke plumes. We use this data to evaluate and intercompare the forecast accuracy of two atmospheric chemistry models: the GEOS Composition Forecasting model (GEOS-CF) and the Weather Research and Forecasting model with Chemistry (WRF-Chem). Both models make daily three-dimensional forecasts of many trace gases and species for the contiguous United States. Over a range of ten distinct collection events, each spanning 36 hours to nearly seven days, the forecast models predict tropospheric ozone at NASA Langley with reasonable accuracy. The models best predict the timing and shape of the observed stratospheric intrusions in the middle troposphere but often vary in the magnitude of the ozone mixing ratios. For other atmospheric conditions, there is more variability in the model accuracy. Here, we summarize the accuracy of the models for all events and investigate reasons for differences between the models and the lidar.
Daniel B. Phoenix↗
Evaluating the Accuracy of Machine Learning Forecasts
To improve the accuracy of forecasting in machine learning, we must investigate multiple machine learning models and see how accurately they can predict values after training. We used seven machine learning models to try and get more accurate predictions. The models that were used were ARIMA, SES, MLP, CART, LightGBM, and XGBoost. We used a processed dataset from a Terminal at LAX that had the number of people traveling through terminal X every hour in March from 2015-2019. We trained our models with the dates March 6 - March 19 to predict the value for March 20th and the hours 6:00 am to 6:00 pm since those are the most popular traveling hours. By using the different models, we had varying results of accuracy when estimating the amount of people traveling through terminal X on March 20th. We know that machine learning models are helpful for forecasting and by seeing how accurately these models can predict, we can see how forecasting can be helpful for other issues. Using these methods, airports can use forecasting to predict the amount of people coming in and out and can use these predictions to prepare their resource management, operational efficiency, and overall passenger experience.
97 MATHEMATICS AND COMPUTING↗
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 ↗
The role of equatorial waves in triggering precipitation extremes in the Maritime Continent
This review offers a comprehensive analysis of convectively coupled equatorial waves (CCEWs) and their pivotal role in driving precipitation extremes across the Maritime Continent. It examines the current understanding of CCEWs, evaluates the performance of numerical models and forecasting techniques in predicting these phenomena, and pinpoints critical areas for improvement. The discussion centers on three key types of equatorial waves: equatorial Rossby waves, Kelvin waves, and mixed Rossby–gravity waves. By connecting scientific insights with practical forecasting applications, the review sheds light on the challenges of predicting these waves while identifying opportunities to advance both fundamental knowledge and forecasting accuracy. Designed as an educational resource, it targets operational forecasting centers, meteorologists, and researchers, aiming to enhance the prediction of extreme weather events in the region.
Maritime Continent↗
Evaluation of an open forecasting challenge to assess skill of West Nile virus neuroinvasive disease prediction
Abstract Background West Nile virus (WNV) is the leading cause of mosquito-borne illness in the continental USA. WNV occurrence has high spatiotemporal variation, and current approaches to targeted control of the virus are limited, making forecasting a public health priority. However, little research has been done to compare strengths and weaknesses of WNV disease forecasting approaches on the national scale. We used forecasts submitted to the 2020 WNV Forecasting Challenge, an open challenge organized by the Centers for Disease Control and Prevention, to assess the status of WNV neuroinvasive disease (WNND) prediction and identify avenues for improvement. Methods We performed a multi-model comparative assessment of probabilistic forecasts submitted by 15 teams for annual WNND cases in US counties for 2020 and assessed forecast accuracy, calibration, and discriminatory power. In the evaluation, we included forecasts produced by comparison models of varying complexity as benchmarks of forecast performance. We also used regression analysis to identify modeling approaches and contextual factors that were associated with forecast skill. Results Simple models based on historical WNND cases generally scored better than more complex models and combined higher discriminatory power with better calibration of uncertainty. Forecast skill improved across updated forecast submissions submitted during the 2020 season. Among models using additional data, inclusion of climate or human demographic data was associated with higher skill, while inclusion of mosquito or land use data was associated with lower skill. We also identified population size, extreme minimum winter temperature, and interannual variation in WNND cases as county-level characteristics associated with variation in forecast skill. Conclusions Historical WNND cases were strong predictors of future cases with minimal increase in skill achieved by models that included other factors. Although opportunities might exist to specifically improve predictions for areas with large populations and low or high winter temperatures, areas with high case-count variability are intrinsically more difficult to predict. Also, the prediction of outbreaks, which are outliers relative to typical case numbers, remains difficult. Further improvements to prediction could be obtained with improved calibration of forecast uncertainty and access to real-time data streams (e.g. current weather and preliminary human cases). Graphical Abstract
54 ENVIRONMENTAL SCIENCES↗
A general spatial-temporal framework for short-term building temperature forecasting at arbitrary locations with crowdsourcing weather data
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.
54 ENVIRONMENTAL SCIENCES↗
Predictive performance of multi-model ensemble forecasts of COVID-19 across European nations
Background: Short-term forecasts of infectious disease burden can contribute to situational awareness and aid capacity planning. Based on best practice in other fields and recent insights in infectious disease epidemiology, one can maximise the predictive performance of such forecasts if multiple models are combined into an ensemble. Here, we report on the performance of ensembles in predicting COVID-19 cases and deaths across Europe between 08 March 2021 and 07 March 2022. Methods: We used open-source tools to develop a public European COVID-19 Forecast Hub. We invited groups globally to contribute weekly forecasts for COVID-19 cases and deaths reported by a standardised source for 32 countries over the next 1–4 weeks. Teams submitted forecasts from March 2021 using standardised quantiles of the predictive distribution. Each week we created an ensemble forecast, where each predictive quantile was calculated as the equally-weighted average (initially the mean and then from 26th July the median) of all individual models’ predictive quantiles. We measured the performance of each model using the relative Weighted Interval Score (WIS), comparing models’ forecast accuracy relative to all other models. We retrospectively explored alternative methods for ensemble forecasts, including weighted averages based on models’ past predictive performance. Results: Over 52 weeks, we collected forecasts from 48 unique models. We evaluated 29 models’ forecast scores in comparison to the ensemble model. We found a weekly ensemble had a consistently strong performance across countries over time. Across all horizons and locations, the ensemble performed better on relative WIS than 83% of participating models’ forecasts of incident cases (with a total N=886 predictions from 23 unique models), and 91% of participating models’ forecasts of deaths (N=763 predictions from 20 models). Across a 1–4 week time horizon, ensemble performance declined with longer forecast periods when forecasting cases, but remained stable over 4 weeks for incident death forecasts. In every forecast across 32 countries, the ensemble outperformed most contributing models when forecasting either cases or deaths, frequently outperforming all of its individual component models. Among several choices of ensemble methods we found that the most influential and best choice was to use a median average of models instead of using the mean, regardless of methods of weighting component forecast models. Conclusions: Our results support the use of combining forecasts from individual models into an ensemble in order to improve predictive performance across epidemiological targets and populations during infectious disease epidemics. Our findings further suggest that median ensemble methods yield better predictive performance more than ones based on means. Our findings also highlight that forecast consumers should place more weight on incident death forecasts than incident case forecasts at forecast horizons greater than 2 weeks. Funding: AA, BH, BL, LWa, MMa, PP, SV funded by National Institutes of Health (NIH) Grant 1R01GM109718, NSF BIG DATA Grant IIS-1633028, NSF Grant No.: OAC-1916805, NSF Expeditions in Computing Grant CCF-1918656, CCF-1917819, NSF RAPID CNS-2028004, NSF RAPID OAC-2027541, US Centers for Disease Control and Prevention 75D30119C05935, a grant from Google, University of Virginia Strategic Investment Fund award number SIF160, Defense Threat Reduction Agency (DTRA) under Contract No. HDTRA1-19-D-0007, and respectively Virginia Dept of Health Grant VDH-21-501-0141, VDH-21-501-0143, VDH-21-501-0147, VDH-21-501-0145, VDH-21-501-0146, VDH-21-501-0142, VDH-21-501-0148. AF, AMa, GL funded by SMIGE - Modelli statistici inferenziali per governare l'epidemia, FISR 2020-Covid-19 I Fase, FISR2020IP-00156, Codice Progetto: PRJ-0695. AM, BK, FD, FR, JK, JN, JZ, KN, MG, MR, MS, RB funded by Ministry of Science and Higher Education of Poland with grant 28/WFSN/2021 to the University of Warsaw. BRe, CPe, JLAz funded by Ministerio de Sanidad/ISCIII. BT, PG funded by PERISCOPE European H2020 project, contract number 101016233. CP, DL, EA, MC, SA funded by European Commission - Directorate-General for Communications Networks, Content and Technology through the contract LC-01485746, and Ministerio de Ciencia, Innovacion y Universidades and FEDER, with the project PGC2018-095456-B-I00. DE., MGu funded by Spanish Ministry of Health / REACT-UE (FEDER). DO, GF, IMi, LC funded by Laboratory Directed Research and Development program of Los Alamos National Laboratory (LANL) under project number 20200700ER. DS, ELR, GG, NGR, NW, YW funded by National Institutes of General Medical Sciences (R35GM119582; the content is solely the responsibility of the authors and does not necessarily represent the official views of NIGMS or the National Institutes of Health). FB, FP funded by InPresa, Lombardy Region, Italy. HG, KS funded by European Centre for Disease Prevention and Control. IV funded by Agencia de Qualitat i Avaluacio Sanitaries de Catalunya (AQuAS) through contract 2021-021OE. JDe, SMo, VP funded by Netzwerk Universitatsmedizin (NUM) project egePan (01KX2021). JPB, SH, TH funded by Federal Ministry of Education and Research (BMBF; grant 05M18SIA). KH, MSc, YKh funded by Project SaxoCOV, funded by the German Free State of Saxony. Presentation of data, model results and simulations also funded by the NFDI4Health Task Force COVID-19 ( https://www.nfdi4health.de/task-force-covid-19-2 ) within the framework of a DFG-project (LO-342/17-1). LP, VE funded by Mathematical and Statistical modelling project (MUNI/A/1615/2020), Online platform for real-time monitoring, analysis and management of epidemic situations (MUNI/11/02202001/2020); VE also supported by RECETOX research infrastructure (Ministry of Education, Youth and Sports of the Czech Republic: LM2018121), the CETOCOEN EXCELLENCE (CZ.02.1.01/0.0/0.0/17-043/0009632), RECETOX RI project (CZ.02.1.01/0.0/0.0/16-013/0001761). NIB funded by Health Protection Research Unit (grant code NIHR200908). SAb, SF funded by Wellcome Trust (210758/Z/18/Z).
60 APPLIED LIFE SCIENCES↗
Deep learning for time series forecasting: a survey of recent advances
Time series forecasting plays a critical role in numerous real-world applications, such as finance, healthcare, transportation, and scientific computing. In recent years, deep learning has become a powerful tool for modeling complex temporal patterns and improving forecasting accuracy. This survey provides an overview of recent deep learning approaches for time series forecasting, involving various architectures including RNNs, CNNs, GNNs, transformers, large language models, MLP-based models, and diffusion models. We first identify key challenges in the field, such as temporal dependency, efficiency, and cross-variable dependency, which drive the development of forecasting techniques. Then, the general advantages and limitations of each architecture are discussed to contextualize their adaptation in time series forecasting. Furthermore, we highlight promising design trends like multi-scale modeling, decomposition, and frequency-domain techniques, which are shaping the future of the field. This paper serves as a compact reference for researchers and practitioners seeking to understand the current landscape and future trajectory of deep learning in time series forecasting.
97 MATHEMATICS AND COMPUTING↗
Use of EOS Data in AWIPS for Weather Forecasting
Operational weather forecasting relies heavily on real time data and modeling products for forecast preparation and dissemination of significant weather information to the public. The synthesis of this information (observations and model products) by the meteorologist is facilitated by a decision support system to display and integrate the information in a useful fashion. For the NWS this system is called Advanced Weather Interactive Processing System (AWIPS). Over the last few years NASA has launched a series of new Earth Observation Satellites (EOS) for climate monitoring that include several instruments that provide high-resolution measurements of atmospheric and surface features important for weather forecasting and analysis. The key to the utilization of these unique new measurements by the NWS is the real time integration of the EOS data into the AWIPS system. This is currently being done in the Huntsville and Birmingham NWS Forecast Offices under the NASA Short-term Prediction Research and Transition (SPORT) Program. This paper describes the use of near real time MODIS and AIRS data in AWIPS to improve the detection of clouds, moisture variations, atmospheric stability, and thermal signatures that can lead to significant weather development. The paper and the conference presentation will focus on several examples where MODIS and AIRS data have made a positive impact on forecast accuracy. The results of an assessment of the utility of these products for weather forecast improvement made at the Huntsville NWS Forecast Office will be presented.
Jedlovec, Gary J.↗
Enhancing Short-Range Weather Forecasts through Temporal Variation Encoding: A Multiperiod Embedding Approach
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.
Artificial intelligence↗
Robust Deep Gaussian Process-Based Probabilistic Electrical Load Forecasting Against Anomalous Events
The abnormal events, such as the unprecedented COVID-19 pandemic, can significantly change the load behaviors, leading to huge challenges for traditional short-term forecasting methods. This article proposes a robust deep Gaussian processes (DGP)-based probabilistic load forecasting method using a limited number of data. Since the proposed method only requires a limited number of training samples for load forecasting, it allows us to deal with extreme scenarios that cause short-term load behavior changes. In particular, the load forecasting at the beginning of abnormal event is cast as a regression problem with limited training samples and solved by double stochastic variational inference DGP. The mobility data are also utilized to deal with the uncertainties and pattern changes and enhance the flexibility of the forecasting model. The proposed method can quantify the uncertainties of load forecasting outcomes, which would be essential under uncertain inputs. Extensive comparison results with other state-of-the-art point and probabilistic forecasting methods show that our proposed approach can achieve high forecasting accuracies with only a limited number of data while maintaining the excellent performance of capturing the forecasting uncertainties.
anomalous events↗