Accuracy of the Global Forecast System 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.
Enhancing Biomass Productivity by Forecast‐Informed Pond Operations
ABSTRACT Microalgal cultivation for biofuels and proteins holds significant promise but faces challenges in achieving economically viable biomass productivity under variable environmental conditions. This study introduces a forecast‐informed pond operation (FIPO) system that uses numerical weather prediction (NWP) ensemble forecasts and the biomass assessment tool (BAT) to optimize daily dilution rates for enhanced biomass production. In contrast to the current practice, where fixed dilution rates are based on operator experience, the FIPO system determines the optimal dilution rate based on future weather forecasts and biomass growth conditions. Our experiments validate the effectiveness of FIPO in both short‐ and long‐term growth scenarios. In short‐term experiments, FIPO increased biomass production by 21.3% compared to batch growth and 7.4% over fixed dilution (60% every 3 days) operations. The NWP forecast‐informed operations achieved biomass production nearly identical to that using perfect weather forecasts, highlighting the accuracy of current NWP forecasts for guiding pond operations. In long‐term experiments, FIPO resulted in biomass production increases of 13.3% and 17.8% compared to two fixed dilution rates (60% every 3 days and 20% daily). These findings underscore the viability of using NWP forecasts to optimize microalgal cultivation systems. By adjusting daily dilution rates in response to forecasted weather, operators can achieve higher biomass yields and mitigate risks associated with environmental variability. This study provides a foundation for future research and practical applications in commercial‐scale microalgal production.
Yan, Hongxiang [Energy and Environment Directorate↗
Aspects of clear air turbulence severity forecasting and detection
Factors influencing the accuracy of the forecasts of incidences of clear air turbulence (CAT) are discussed, along with techniques for improved verification. Descriptive ranking terms for the intensity of CAT events, ranging from light to extreme, are developed, and meteorological parameters used for predictions are reviewed, including jetstream core location, vertical and horizontal wind shears, stable layers, tropopause height, trough speed, 500-mb vorticity, surface fronts, pressure centers and cyclogenesis, and wind speeds near mountain ridges. Methods of remote detection of CAT, particularly by using radiometry sensitive to the IR water vapor band, are noted to have had some success in detecting actual CAT events and decreasing false alarms. Statistical aspects of CAT encounter severity are discussed, including the establishment of confidence intervals for thresholds of detection of CATs of varying intensities.
Ehernberger, L. J.↗
Comparative Analysis of Machine Learning Models for Day-Ahead Photovoltaic Power Production Forecasting
A main challenge for integrating the intermittent photovoltaic (PV) power generation remains the accuracy of day-ahead forecasts and the establishment of robust performing methods. The purpose of this work is to address these technological challenges by evaluating the day-ahead PV production forecasting performance of different machine learning models under different supervised learning regimes and minimal input features. Specifically, the day-ahead forecasting capability of Bayesian neural network (BNN), support vector regression (SVR), and regression tree (RT) models was investigated by employing the same dataset for training and performance verification, thus enabling a valid comparison. The training regime analysis demonstrated that the performance of the investigated models was strongly dependent on the timeframe of the train set, training data sequence, and application of irradiance condition filters. Furthermore, accurate results were obtained utilizing only the measured power output and other calculated parameters for training. Consequently, useful information is provided for establishing a robust day-ahead forecasting methodology that utilizes calculated input parameters and an optimal supervised learning approach. Finally, the obtained results demonstrated that the optimally constructed BNN outperformed all other machine learning models achieving forecasting accuracies lower than 5%.
14 SOLAR ENERGY↗
Flight Departure Delay and Rerouting Under Uncertainty in En Route Convective Weather
Delays caused by uncertainty in weather forecasts can be reduced by improving traffic flow management decisions. This paper presents a methodology for traffic flow management under uncertainty in convective weather forecasts. An algorithm for assigning departure delays and reroutes to aircraft is presented. Departure delay and route assignment are executed at multiple stages, during which, updated weather forecasts and flight schedules are used. At each stage, weather forecasts up to a certain look-ahead time are treated as deterministic and flight scheduling is done to mitigate the impact of weather on four-dimensional flight trajectories. Uncertainty in weather forecasts during departure scheduling results in tactical airborne holding of flights. The amount of airborne holding depends on the accuracy of forecasts as well as the look-ahead time included in the departure scheduling. The weather forecast look-ahead time is varied systematically within the experiments performed in this paper to analyze its effect on flight delays. Based on the results, longer look-ahead times cause higher departure delays and additional flying time due to reroutes. However, the amount of airborne holding necessary to prevent weather incursions reduces when the forecast look-ahead times are higher. For the chosen day of traffic and weather, setting the look-ahead time to 90 minutes yields the lowest total delay cost.
Mukherjee, Avijit↗
The MST radar technique: Requirements for operational weather forecasting
There is a feeling that the accuracy of mesoscale forecasts for spatial scales of less than 1000 km and time scales of less than 12 hours can be improved significantly if resources are applied to the problem in an intensive effort over the next decade. Since the most dangerous and damaging types of weather occur at these scales, there are major advantages to be gained if such a program is successful. The interest in improving short term forecasting is evident. The technology at the present time is sufficiently developed, both in terms of new observing systems and the computing power to handle the observations, to warrant an intensive effort to improve stormscale forecasting. An assessment of the extent to which the so-called MST radar technique fulfills the requirements for an operational mesoscale observing network is reviewed and the extent to which improvements in various types of forecasting could be expected if such a network is put into operation are delineated.
Larsen, M. F.↗
Energy and Emission Prediction for Mixed-Vehicle Transit Fleets Using Multi-task and Inductive Transfer Learning
Public transit agencies are focused on making their fixed-line bus systems more energy efficient by introducing electric (EV) and hybrid (HV) vehicles to their fleets. However, because of the high upfront cost of these vehicles, most agencies are tasked with managing a mixed-fleet of internal combustion vehicles (ICEVs), EVs, and HVs. In managing mixed-fleets, agencies require accurate predictions of energy use for optimizing the assignment of vehicles to transit routes, scheduling charging, and ensuring that emission standards are met. The current state-of-the-art is to develop separate neural network models to predict energy consumption for each vehicle class. Although different vehicle classes’ energy consumption depends on a varied set of covariates, we hypothesize that there are broader generalizable patterns that govern energy consumption and emissions. In this paper, we seek to extract these patterns to aid learning to address two problems faced by transit agencies. First, in the case of a transit agency which operates many ICEVs, HVs, and EVs, we use multi-task learning (MTL) to improve accuracy of forecasting energy consumption. Second, in the case where there is a significant variation in vehicles in each category, we use inductive transfer learning (ITL) to improve predictive accuracy for vehicle class models with insufficient data. As this work is to be deployed by our partner agency, we also provide an online pipeline for joining the various sensor streams for fixed-line transit energy prediction. Here, we find that our approach outperforms vehicle-specific baselines in both the MTL and ITL settings.
97 MATHEMATICS AND COMPUTING↗
Assessing decadal variability of subseasonal forecasts of opportunity using explainable AI
Abstract Identifying predictable states of the climate system allows for enhanced prediction skill on the generally low-skill subseasonal timescale via forecasts with higher confidence and accuracy, known as forecasts of opportunity. This study takes a neural network approach to explore decadal variability of subseasonal predictability, particularly during forecasts of opportunity. Specifically, this work quantifies subseasonal prediction skill provided by the tropics within the Community Earth System Model Version 2 (CESM2) Large Ensemble and assesses how this skill evolves on decadal timescales. Utilizing the networks’ confidence and explainable artificial intelligence, physically meaningful sources of predictability associated with periods of enhanced skill are identified. Using these networks, we find that tropically-driven subseasonal predictability varies on decadal timescales during forecasts of opportunity. Further, we investigate the drivers of the low frequency modulation of the tropical-extratropical teleconnection and discuss the implications. Analysis is extended to ECMWF Reanalysis v5 data, revealing that the relationships learned within the CESM2-Large Ensemble holds in modern reanalysis data. These results indicate that the neural networks are capable of identifying predictable decadal states of the climate system within CESM2 that are useful for making confident, accurate subseasonal precipitation predictions in the real world.
54 ENVIRONMENTAL SCIENCES↗
Time Relevance of Convective Weather Forecast for Air Traffic Automation
The Federal Aviation Administration (FAA) is handling nearly 120,000 flights a day through its Air Traffic Management (ATM) system and air traffic congestion is expected to increse substantially over the next 20 years. Weather-induced impacts to throughput and efficiency are the leading cause of flight delays accounting for 70% of all delays with convective weather accounting for 60% of all weather related delays. To support the Next Generation Air Traffic System goal of operating at 3X current capacity in the NAS, ATC decision support tools are being developed to create advisories to assist controllers in all weather constraints. Initial development of these decision support tools did not integrate information regarding weather constraints such as thunderstorms and relied on an additional system to provide that information. Future Decision Support Tools should move towards an integrated system where weather constraints are factored into the advisory of a Decision Support Tool (DST). Several groups such at NASA-Ames, Lincoln Laboratories, and MITRE are integrating convective weather data with DSTs. A survey of current convective weather forecast and observation data show they span a wide range of temporal and spatial resolutions. Short range convective observations can be obtained every 5 mins with longer range forecasts out to several days updated every 6 hrs. Today, the short range forecasts of less than 2 hours have a temporal resolution of 5 mins. Beyond 2 hours, forecasts have much lower temporal. resolution of typically 1 hour. Spatial resolutions vary from 1km for short range to 40km for longer range forecasts. Improving the accuracy of long range convective forecasts is a major challenge. A report published by the National Research Council states improvements for convective forecasts for the 2 to 6 hour time frame will only be achieved for a limited set of convective phenomena in the next 5 to 10 years. Improved longer range forecasts will be probabilistic as opposed to the deterministic shorter range forecasts. Despite the known low level of confidence with respect to long range convective forecasts, these data are still useful to a DST routing algorithm. It is better to develop an aircraft route using the best information available than no information. The temporally coarse long range forecast data needs to be interpolated to be useful to a DST. A DST uses aircraft trajectory predictions that need to be evaluated for impacts by convective storms. Each time-step of a trajectory prediction n&s to be checked against weather data. For the case of coarse temporal data, there needs to be a method fill in weather data where there is none. Simply using the coarse weather data without any interpolation can result in DST routes that are impacted by regions of strong convection. Increasing the temporal resolution of these data can be achieved but result in a large dataset that may prove to be an operational challenge in transmission and loading by a DST. Currently, it takes about 7mins retrieve a 7mb RUC2 forecast file from NOAA at NASA-Ames Research Center. A prototype NCWF6 1 hour forecast is about 3mb in size. A Six hour NCWFG forecast with a 1hr forecast time-step will be about l8mb (6 x 3mb). A 6 hour NCWF6 forecast with a l5min forecast time-step will be about 7mb (24 x 3mb). Based on the time it takes to retrieve a 7mb RUC2 forecast, it will take approximately 70mins to retrieve a 6 hour NCWF forecast with 15min time steps. Until those issues are addressed, there is a need to develop an algorithm that interpolates between these temporally coarse long range forecasts. This paper describes a method of how to use low temporal resolution probabilistic weather forecasts in a DST. The beginning of this paper is a description of some convective weather forecast and observation products followed by an example of how weather data are used by a DST. The subsequent sections will describe probabilistic forecasts followed by a descrtion of a method to use low temporal resolution probabilistic weather forecasts by providing a relevance value to these data outside of their valid times.
Chan, William N.↗
Forecasting the Solar Drivers of Solar Energetic Particle Events
Large flares and fast CMEs are the drivers of the most severe space weather including Solar Energetic Particle Events (SEP Events). Large flares and their co-produced CMEs are powered by the explosive release of free magnetic energy stored in non-potential magnetic fields of sunspot active regions. The free energy is stored in and released from the low-beta regime of the active region's magnetic field above the photosphere, in the chromosphere and low corona. From our work over the past decade and from similar work of several other groups, it is now well established that (1) a proxy of the free magnetic energy stored above the photosphere can be measured from photospheric magnetograms, maps of the measured field in the photosphere, and (2) an active region's rate of production of major CME/flare eruptions in the coming day or so is strongly correlated with its present measured value of the free-energy proxy. These results have led us to use the large database of SOHO/MDI full-disk magnetograms spanning Solar Cycle 23 to obtain empirical forecasting curves that from an active region's present measured value of the free-energy proxy give the active region's expected rates of production of major flares, CMEs, fast CMEs, and SEP Events in the coming day or so (Falconer et al 2011, Space Weather, 9, S04003). We will present these forecasting curves and demonstrate the accuracy of their forecasts. In addition, we will show that the forecasts for major flares and fast CMEs can be made significantly more accurate by taking into account not only the value of the free energy proxy but also the active region's recent productivity of major flares; specifically, whether the active region has produced a major flare (GOES class M or X) during the past 24 hours before the time of the measured magnetogram.
Falconer, David A.↗
Forecasting the Solar Drivers of Severe Space Weather from Active-Region Magnetograms
Large flares and fast CMEs are the drivers of the most severe space weather including Solar Energetic Particle Events (SEP Events). Large flares and their co-produced CMEs are powered by the explosive release of free magnetic energy stored in non-potential magnetic fields of sunspot active regions. The free energy is stored in and released from the low-beta regime of the active region s magnetic field above the photosphere, in the chromosphere and low corona. From our work over the past decade and from similar work of several other groups, it is now well established that (1) a proxy of the free magnetic energy stored above the photosphere can be measured from photospheric magnetograms, and (2) an active region s rate of production of major CME/flare eruptions in the coming day or so is strongly correlated with its present measured value of the free-energy proxy. These results have led us to use the large database of SOHO/MDI full-disk magnetograms spanning Solar Cycle 23 to obtain empirical forecasting curves that from an active region s present measured value of the free-energy proxy give the active region s expected rates of production of major flares, CMEs, fast CMEs, and SEP Events in the coming day or so (Falconer et al 2011, Space Weather, 9, S04003). We will present these forecasting curves and demonstrate the accuracy of their forecasts. In addition, we will show that the forecasts for major flares and fast CMEs can be made significantly more accurate by taking into account not only the value of the free energy proxy but also the active region s recent productivity of major flares; specifically, whether the active region has produced a major flare (GOES class M or X) during the past 24 hours before the time of the measured magnetogram. By empirically determining the conversion of the value of free-energy proxy measured from a GONG or HMI magnetogram to that which would be measured from an MDI magnetogram, we have made GONG and HMI magnetograms useable with our MDI-based forecasting curves to forecast event rates.
Falconer, David A.↗
Forecasting Space Weather from Magnetograms
Large flares and fast CMEs are the drivers of the most severe space weather including Solar Energetic Particle Events (SEP Events). Large flares and their co-produced CMEs are powered by the explosive release of free magnetic energy stored in non-potential magnetic fields of sunspot active regions. The free energy is stored in and released from the low-beta regime of the active region s magnetic field above the photosphere, in the chromosphere and low corona. From our work over the past decade and from similar work of several other groups, it is now well established that (1) a proxy of the free magnetic energy stored above the photosphere can be measured from photospheric magnetograms, maps of the measured field in the photosphere, and (2) an active region s rate of production of major CME/flare eruptions in the coming day or so is strongly correlated with its present measured value of the free-energy proxy. These results have led us to use the large database of SOHO/MDI full-disk magnetograms spanning Solar Cycle 23 to obtain empirical forecasting curves that from an active region s present measured value of the free-energy proxy give the active region s expected rates of production of major flares, CMEs, fast CMEs, and SEP Events in the coming day or so (Falconer et al 2011, Space Weather, 9, S04003). For each type of event, the expected rate is readily converted to the chance that the active region will produce such an event in any given forward time window of a day or so. If the chance is small enough (e.g. <5%), the forecast is All Clear for that type of event. We will present these forecasting curves and demonstrate the accuracy of their forecasts. In addition, we will show that the forecasts for major flares and fast CMEs can be made significantly more accurate by taking into account not only the value of the free energy proxy but also the active region s recent productivity of major flares; specifically, whether the active region has produced a major flare (GOES class M or X) during the past 24 hours before the time of the measured magnetogram.
Falconer, David A.↗
Forecasting the Solar Drivers of Severe Space Weather from Active-Region Magnetograms
Large flares and fast CMEs are the drivers of the most severe space weather including Solar Energetic Particle Events (SEP Events). Large flares and their co-produced CMEs are powered by the explosive release of free magnetic energy stored in non-potential magnetic fields of sunspot active regions. The free energy is stored in and released from the low-beta regime of the active region s magnetic field above the photosphere, in the chromosphere and low corona. From our work over the past decade and from similar work of several other groups, it is now well established that (1) a proxy of the free magnetic energy stored above the photosphere can be measured from photospheric magnetograms, and (2) an active region s rate of production of major CME/flare eruptions in the coming day or so is strongly correlated with its present measured value of the free-energy proxy. These results have led us to use the large database of SOHO/MDI full-disk magnetograms spanning Solar Cycle 23 to obtain empirical forecasting curves that from an active region s present measured value of the free-energy proxy give the active region s expected rates of production of major flares, CMEs, fast CMEs, and SEP Events in the coming day or so (Falconer et al 2011, Space Weather, 9, S04003). We will present these forecasting curves and demonstrate the accuracy of their forecasts. In addition, we will show that the forecasts for major flares and fast CMEs can be made significantly more accurate by taking into account not only the value of the free energy proxy but also the active region s recent productivity of major flares; specifically, whether the active region has produced a major flare (GOES class M or X) during the past 24 hours before the time of the measured magnetogram. By empirically determining the conversion of the value of free-energy proxy measured from a GONG or HMI magnetogram to that which would be measured from an MDI magnetogram, we have made GONG and HMI magnetograms useable with our MDI-based forecasting curves to forecast event rates.
Falconer, David A.↗
Deep Learning Provides Substantial Improvements to County‐Level Fire Weather Forecasting Over the Western United States
Abstract The recent wildfires in the western United States during 2018 and 2020 caused record‐breaking fire damage and casualties. Despite remarkable advances in fire modeling and weather forecasting, it remains challenging to anticipate catastrophic wildfire events and associated damage. One key missing component is a fire weather prediction system with sufficiently long lead time capable of providing useful regional details. Here, we develop a hybrid prediction model of wildfire danger called CFS with super resolution (CFS‐SR) as a proof of concept to fill that void. The CFS‐SR model is constructed by integrating the Climate Forecast System version 2 with a deep learning (DL) technique from Single Image Super Resolution, a method widely used in enhancing image resolution. We show that for the 2018–2019 fire season, the CFS‐SR model significantly improves accuracy in forecasting fire weather at lead times of up to 7 days with an enhanced spatial resolution up to 4 km. This level of high resolution provides county‐level fire weather forecast, making it more practical for allocating resources to mitigate wildfire danger. Our study demonstrates that a proper combination of ensemble climate predictions with DL techniques can boost predictability at finer spatial scales, increasing the utility of fire weather forecasts for practical applications.
54 ENVIRONMENTAL SCIENCES↗
Evaluating Flood Forecasting System Performance in Cambodia
Every year, Cambodia experiences flooding as a result of monsoon rains and typhoons. Flood forecasting systems are designed to enable people to mitigate economic and social impacts from these events. However, in order for forecasts to be used effectively, an assessment of their accuracy is needed. 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 and gauge locations in Cambodia. We then compare the flood forecast performance to satellite-based 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 flood extents helps (1) provide valuable information to forecasters and disaster managers as they make improvements to their models, and (2) provides support to forecast users as they evaluate the strengths and weaknesses of different systems for taking action.
Nauman, Claire↗
Improved Air Quality Forecasts using NASA’s Pandora and GEOS CF at International and Domestic Sites for SNWG Stakeholders
Air pollution prediction is complex due to the dynamic nature of atmospheric processes and the variability in data resolutions and availability. This project addresses these challenges by integrating and analyzing high-resolution ground-based measurements with global air quality models. Through this integration, we have gained a deeper understanding of how these processes interact under various conditions, which we then use to model and enhance the accuracy of forecasts.
Noussair Lazrak↗
Intercomparison of Deep Learning Model Architectures for Atmospheric River Prediction
With a rapid surge in the application of machine learning (ML) for a diverse range of tasks in climate science, the present study addresses a challenge for climate scientists when selecting the optimal ML or deep learning (DL) architecture for a given application. In particular, a DL intercomparison study was performed with a focus on forecasting the position of atmospheric rivers (ARs) on short-range time scales (up to 5-day lead times). AR predictions from multiple DL architectures, including various types of convolutional autoencoders and a vision transformer (ViT), were compared against ECMWF ERA5 reanalysis and hindcasts from a global climate model. DL models with similar trainable parameters were trained on ERA5 reanalysis data and AR positions derived from a thresholding algorithm to ensure a fair comparison among the DL models. Each model’s performance and accuracy in forecasting AR location and key input fields within a 5-day window were assessed using metrics of root-mean-square error, anomaly correlation, and mean intersection over union. The ViT architecture outperformed other autoencoder models in most of the metrics. Incorporating additional meteorological fields only yielded slight improvements in forecasting certain fields at longer lead times. The results also suggest that a smaller number of input time steps or smaller number of autoregressive steps can achieve better prediction skills, while also improving the overall computational efficiency. This research offers valuable insights into the strengths and weaknesses of different DL techniques for AR forecasting, hopefully guiding the development of improved models for forecasting this phenomenon.
54 ENVIRONMENTAL SCIENCES↗
Attention-based functional-group coarse-graining: a deep learning framework for molecular prediction and design
Machine learning (ML) offers considerable promise for the design of new molecules and materials. In real-world applications, the design problem is often domain-specific, and suffers from insufficient data, particularly labeled data, for ML training. In this study, we report a data-efficient, deep-learning framework for molecular discovery that integrates a coarse-grained functional-group representation with a self-attention mechanism to capture intricate chemical interactions. Our approach exploits group-contribution concepts to create a graph-based intermediate representation of molecules, serving as a low-dimensional embedding that substantially reduces the data demands typically required for training. Using a self-attention mechanism to learn the subtle but highly relevant chemical context of functional groups, the method proposed here consistently outperforms existing approaches for predictions of multiple thermophysical properties. In a case study focused on adhesive polymer monomers, we train on a limited dataset comprising only 6,000 unlabeled and 600 labeled monomers. The resulting chemistry prediction model achieves over 92% accuracy in forecasting properties directly from SMILES strings, exceeding the performance of current state-of-the-art techniques. Furthermore, the latent molecular embedding is invertible, enabling the design pipeline to automatically generate new monomers from the learned chemical subspace. We illustrate this functionality by targeting several properties, including high and low glass transition temperatures (Tg), and demonstrate that our model can identify new candidates with values that surpass those in the training set. The ease with which the proposed framework navigates both chemical diversity and data scarcity offers a promising route to accelerate and broaden the search for functional materials.
Han, Ming [Univ. of Chicago, IL (United States)]↗