Search NASA⌕ Search

SEARCH · Search NASA

Results for “Weatherization training”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 217 records · Page 12

Deep Learning Image Segmentation for Atmospheric Rivers

Abstract The identification of atmospheric rivers (ARs) is crucial for weather and climate predictions as they are often associated with severe storm systems and extreme precipitation, which can cause large impacts on society. This study presents a deep learning model, termed ARDetect, for image segmentation of ARs using ERA5 data from 1960 to 2020 with labels obtained from the TempestExtremes tracking algorithm. ARDetect is a convolutional neural network (CNN)-based U-Net model, with its structure having been optimized using automatic hyperparameter tuning. Inputs to ARDetect were selected to be the integrated water vapor transport (IVT) and total column water (TCW) fields, as well as the AR mask from TempestExtremes from the previous time step to the one being considered. ARDetect achieved a mean intersection-over-union (mIoU) rate of 89.04% for ARs, indicating its high accuracy in identifying these weather patterns and a superior performance than most deep learning–based models for AR detection. In addition, ARDetect can be executed faster than the TempestExtremes method (seconds vs minutes) for the same period. This provides a significant benefit for online AR detection, especially for high-resolution global models. An ensemble of 10 models, each trained on the same dataset but having different starting weights, was used to further improve on the performance produced by ARDetect, thus demonstrating the importance of model diversity in improving performance. ARDetect provides an effective and fast deep learning–based model for researchers and weather forecasters to better detect and understand ARs, which have significant impacts on weather-related events such as floods and droughts.

Galea, Daniel↗

Atmospheric Structure Prediction for Infrasound Propagation Modeling Using Deep Learning

Abstract Infrasound is generated by a variety of natural and anthropogenic sources. Infrasonic waves travel through the dynamic atmosphere, which can change on the order of minutes to hours. Infrasound propagation largely depends on the wind and temperature structure of the atmosphere. Numerical weather prediction models are available to provide atmospheric specifications, but uncertainties in these models exist and they are computationally expensive to run. Machine learning has proven useful in predicting tropospheric weather using Long Short‐Term Memory (LSTM) networks. An LSTM network is utilized to make atmospheric specification predictions up to ∼30 km for three different training and testing scenarios: (a) the model is trained and tested using only radiosonde data from the Albuquerque, NM, USA station, (b) the model is trained on radiosonde stations across the contiguous US, excluding the Albuquerque, NM, USA station, which was reserved for testing, and (c) the model is trained and tested on radiosonde stations across the contiguous US. Long Short‐Term Memory predictions are compared to a state‐of‐the‐art reanalysis model and show cases where the LSTM outperforms, performs equally as well, or underperforms in comparison to the state‐of‐the‐art. Regional and temporal trends in model performance across the US are also discussed. Results suggest that the LSTM model is a viable tool for predicting atmospheric specifications for infrasound propagation modeling.

54 ENVIRONMENTAL SCIENCES↗

Enriching the Twitter Stream Increasing Data Mining Yield and Quality Using Machine Learning

Social media data streams are important sources of real-time and historical global information for science applications. At the NASA Goddard Earth Sciences Data and Information Services Center (GES DISC), we are exploring the Twitter data stream for its potential in augmenting the validation program of NASA Earth science missions, specifically the Global Precipitation Measurement (GPM) mission. We have implemented a tweet processing infrastructure that outputs classified precipitation tweets. Inputs are "passive" tweets, along with a smaller number of tweets from "active" participants, i.e., those knowingly contributing to our effort. The "active" tweets, presumably of higher quality, enrich the Twitter stream. "Active" sources include data scraped from other social media (e.g., public Facebook posts) and data from existing crowdsourcing programs (e.g., mPING reports). In addition, there is likely relevant precipitation information in images and documents that are the end points of links often included in tweets. Information derived from these "active" sources could then be tweeted into the Twitter stream, thus enriching its quality. The objective of our current work is to mine these tweet­ linked images and documents, using neural networks, to increase the information content and quality related to precipitation. For images, we classified them as either precipitation-related or not. For training and validation, we used images obtained via the Google custom search API. We created two models: (1) by training a simple Convolutional Neural Network and (2) by using transfer learning principles to adapt a pre-trained object recognition model. For documents, both those linked to tweets and the tweet contents, we trained Hierarchical Attention Networks to determine precipitation occurrence, type, and intensity. For training and validation, we used a keyword-filtered tweet data set labelled with ground truth data from Dark Sky (an API to retrieve weather-related labels) and the National Severe Storms Laboratory's Multi­ Radar/Multi-Sensor (MRMS) system. Our results demonstrated the efficacy of our machine learning approaches for enriching the Twitter stream, to derive information potentially useful for validation of earth science satellite data.

Albayrak, Arif↗

Evaluating Meteorological Dust Events and Machine-Learning Based Dust Identification in Geostationary Satellite Imagery

NASA scientists in the Short-term Prediction Research and Transition Center (SPoRT) developed a physically-based machine learning approach to identify dust in satellite imagery with a focus on night-time dust detection (Berndt et al. 201; DustTracker-AI). NASA/NOAA Geostationary Environmental Operational Satellite-16 (GOES-16) imagery was used for training and model inputs. The training, testing and validation data set consists of 28 events in the Southwest United States, capturing dust and null events in the region from 2018-2020.With 83 distinct images and millions of pixels a random forest model was trained and validated, correctly labeling 85% of dust pixels.For the first time, the model was run in near-real time production during the spring of 2022 and dust probability visualizations were made available to NOAA National Weather Service (NWS) forecasters to assess its utility for dust forecasting. Results indicated the model helped increase the confidence in the presence of dust and enabled dust tracking for a longer period of time into the night-time hours. Forecaster assessment and running the model in near real-time allowed for the team to determine the types of events missed, captured, and false alarms. To gain additional context on model performance,the SPoRT team sought to gather more detailed information on the training database(e.g., meteorological characteristics and drivers). The goal of this project was to identify the meteorological drivers for the dust events and create a database which synthesized information from observations, forecaster discussions, and analyses pertaining to the dust events to understand the types of events currently used to train the model. A more detailed meteorological synopsis was created for each dust event in the training, testing, and validation datasets. Following the completion of the database and documentation, the classification details revealed that 88% of the dust events were synoptically driven while mesoscale events were less prevalent in model datasets. Meteorological conditions found such as mixing layer depth and wind velocity had mean values of 645mb and 21kt respectively.With conditions of deep mixed layers and moderate to strong surface winds a mesoscale thunderstorm outflow event was considered and subsequently added to the model training data set to test the impact of additional mesoscale training data. The model was retrained and then qualitatively tested on a sample thunderstorm outflow case that the original model was unable to identify. Preliminary results showed potential that the addition of more mesoscale events included in the training data could help to better identify indistinct and localized dust events.

Connor Welch↗

Convolutional Neural Networks for Hydrometeor Classification using Dual Polarization Doppler Radars

Traditional fuzzy logic hydrometeor classification algorithm is a common way to classify precipitation type from dual polarization doppler radar. We propose a deep learning-based method to estimate hydrometeors efficiently using observed radar variables such as horizontal reflectivity (Z H ), differential reflectivity (Z DR ), correlation coefficient (ρ HV ) and specific differential phase (K DP ) from National Weather Service NEXRAD collected at Vance AFB facility at the first elevation angle from January 1st, 2015 to July 31th, 2019. We stack matrices of values from these four polarimetric variables as one 3D array. Samples are preprocessed and divided into training, validation and test set with four target hydrometeor categories (Ice Crystals (IC), Dry Snow (DS), Light and/or Moderate Rain (RA) and Big Drops (rain) (BD)). We developed and optimized five Convolutional Neural Networks (CNNs) architectures and achieved an accuracy of 87.23% and 93.736% respectively using modified ResNet with two different input data selection strategies for hydrometeor classification. Training data selection strategies were important to ensure use of available samples in training for robust performance evaluated by applying the models to novel time period beyond what was use to train the model. Seasonal variation in atmospheric conditions lead to seasonal patterns of liquid vs solid forms of precipitation, that poses challenge for classifier and offer insights into domain specific approaches required for problem of hydrometeor identification. Computationally efficient and scalable approach for classification of hydrometeors offer opportunties to effectively use the large volumes of rich time series of radar observations that are becoming increasingly available.

Lu, Yuping↗

Mapping tree canopy cover and canopy height with L-band SAR using LiDAR data and Random Forests

Light detection and ranging (LiDAR) data can provide direct measurements of vegetation structures but are limited by the sparse spatial coverage. Polarimetric synthetic aperture radar (SAR) can perform large-scale high-resolution mapping without weather constraints but the information about vegetation and ground subsurface are mixed in the backscatter data. In this paper, we adopted the Random Forests algorithm to train an upscaling function using tree canopy cover (TCC) and canopy height model (CHM) derived from Goddard’s LiDAR, Hyperspectral and Thermal Imager (G-LiHT) data. The regression model is then applied to the L-band Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) data acquired during the 2017 Arctic-Boreal Vulnerability Experiment (ABoVE) airborne campaign to map the TCC and CHM over the Delta Junction area in interior Alaska.

Moghaddam, Mahta↗

An innovative heterogeneous transfer learning framework to enhance the scalability of deep reinforcement learning controllers in buildings with integrated energy systems

Deep Reinforcement Learning (DRL)-based control shows enhanced performance in the management of integrated energy systems when compared with Rule-Based Controllers (RBCs), but it still lacks scalability and generalisation due to the necessity of using tailored models for the training process. Transfer Learning (TL) is a potential solution to address this limitation. However, existing TL applications in building control have been mostly tested among buildings with similar features, not addressing the need to scale up advanced control in real-world scenarios with diverse energy systems. This paper assesses the performance of an online heterogeneous TL strategy, comparing it with RBC and offline and online DRL controllers in a simulation setup using EnergyPlus and Python. The study tests the transfer in both transductive and inductive settings of a DRL policy designed to manage a chiller coupled with a Thermal Energy Storage (TES). The control policy is pre-trained on a source building and transferred to various target buildings characterised by an integrated energy system including photovoltaic and battery energy storage systems, different building envelope features, occupancy schedule and boundary conditions (e.g., weather and price signal). The TL approach incorporates model slicing, imitation learning and fine-tuning to handle diverse state spaces and reward functions between source and target buildings. Results show that the proposed methodology leads to a reduction of 10% in electricity cost and between 10% and 40% in the mean value of the daily average temperature violation rate compared to RBC and online DRL controllers. Moreover, online TL maximises self-sufficiency and self-consumption by 9% and 11% with respect to RBC. Conversely, online TL achieves worse performance compared to offline DRL in either transductive or inductive settings. However, offline Deep Reinforcement Learning (DRL) agents should be trained at least for 15 episodes to reach the same level of performance as the online TL. Therefore, the proposed online TL methodology is effective, completely model-free and it can be directly implemented in real buildings with satisfying performance.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Weathering the Worst Solar Storms

When the last really big solar storm hit in 1921, Earth’s magnetic field funneled a wave of electrically charged particles toward the ground, where they induced a current along telegraph lines and railroad tracks, setting to telegraph offices and train stations—and the fledgling electric grid went dark. Almost a century later, today’s grid is bigger, more interconnected, and even more susceptible to a solar storm disaster. Los Alamos National Laboratory is developing a scientific analysis about how frequently a major geomagnetic storm might strike, which regions of the country are most vulnerable, and how bad it might be. This analysis is part of a plan to support electric utility companies and government regulators in taking the necessary steps to spare us all from the nightmare of days, weeks, or even months without power.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Deep Learning Parameterization of Vertical Wind Velocity Variability via Constrained Adversarial Training

Atmospheric models with typical resolution in the tenths of kilometers cannot resolve the dynamics of air parcel ascent, which varies on scales ranging from tens to hundreds of meters. Small-scale wind fluctuations are thus characterized by a subgrid distribution of vertical wind velocity W with standard deviation σ W . The parameterization of σ W is fundamental to the representation of aerosol–cloud interactions, yet it is poorly constrained. Using a novel deep learning technique, this work develops a new parameterization for σ W merging data from global storm-resolving model simulations, high-frequency retrievals of W , and climate reanalysis products. The parameterization reproduces the observed statistics of σ W and leverages learned physical relations from the model simulations to guide extrapolation beyond the observed domain. Incorporating observational data during the training phase was found to be critical for its performance. The parameterization can be applied online within large-scale atmospheric models, or offline using output from weather forecasting and reanalysis products.

54 ENVIRONMENTAL SCIENCES↗

This is NASA

The organization, operations, functions, and objectives of NASA are outlined. Data include manned space flights, satellite weather observations, orbiting radio relays, and new views of the earth and beyond the earth as observed by satellites. Details of NASA's work in international programs, educational training programs, and adopting space technology to earth uses are also given.

Source record↗

Hazard Detection Analysis for a Forward-Looking Interferometer

The Forward-Looking Interferometer (FLI) is a new instrument concept for obtaining the measurements required to alert flight crews to potential weather hazards to safe flight. To meet the needs of the commercial fleet, such a sensor should address multiple hazards to warrant the costs of development, certification, installation, training, and maintenance. The FLI concept is based on high-resolution Infrared Fourier Transform Spectrometry (FTS) technologies that have been developed for satellite remote sensing. These technologies have also been applied to the detection of aerosols and gases for other purposes. The FLI concept is being evaluated for its potential to address multiple hazards including clear air turbulence (CAT), volcanic ash, wake vortices, low slant range visibility, dry wind shear, and icing during all phases of flight (takeoff, cruise, and landing). The research accomplished in this second phase of the FLI project was in three major areas: further sensitivity studies to better understand the potential capabilities and requirements for an airborne FLI instrument, field measurements that were conducted in an effort to provide empirical demonstrations of radiometric hazard detection, and theoretical work to support the development of algorithms to determine the severity of detected hazards

West, Leanne↗

How Generalizable is a Machine-Learning Approach for Modeling Hub-Height Turbulence Intensity?

Hub-height turbulence intensity is essential for a variety of wind energy applications. However, simulating it is a challenging task. Simple analytical models have been proposed in the literature, but they all come with significant limitations. Even state-of-the-art numerical weather prediction models, such as the Weather Research and Forecasting model, currently struggle to predict hub-height turbulence intensity. Here, we propose a machine-learning-based approach to predict hub-height turbulence intensity from other hub-height and ground-level atmospheric measurements, using observations from the Perdigao field campaign and the Southern Great Plains atmospheric observatory. We consider a random forest regression model, which we validate first at the site used for training and then under a more robust round-robin approach, and compare its performance to a multivariate linear regression. The random forest successfully outperforms the linear regression in modeling hub-height turbulence intensity, with a normalized root-mean-square error as low as 0.014 when using 30-minute average data. In order to achieve such low root-mean-square error values, the knowledge of hub-height turbulence kinetic energy (which can instead be modeled in the Weather Research and Forecasting model) is needed. Interestingly, we find that the performance of the random forest generalizes well when considering a round-robin validation (i.e., when the algorithm is trained at one site such as Perdigao or Southern Great Plains) and then applied to model hub-height turbulence intensity at the other location.

17 WIND ENERGY↗

Satellite Proving Ground for the GOES-R Geostationary Lightning Mapper (GLM)

The key mission of the Satellite Proving Ground is to demonstrate new satellite observing data, products and capabilities in the operational environment to be ready on Day 1 to use the GOES-R suite of measurements. Algorithms, tools, and techniques must be tested, validated, and assessed by end users for their utility before they are finalized and incorporated into forecast operations. The GOES-R Proving Ground for the Geostationary Lightning Mapper (GLM) focuses on evaluating how the infusion of the new technology, algorithms, decision aids, or tailored products integrate with other available tools (weather radar and ground strike networks; nowcasting systems, mesoscale analysis, and numerical weather prediction models) in the hands of the forecaster responsible for issuing forecasts and warning products. Additionally, the testing concept fosters operation and development staff interactions which will improve training materials and support documentation development. Real-time proxy total lightning data from regional VHF lightning mapping arrays (LMA) in Northern Alabama, Central Oklahoma, Cape Canaveral Florida, and the Washington, DC Greater Metropolitan Area are the cornerstone for the GLM Proving Ground. The proxy data will simulate the 8 km Event, Group and Flash data that will be generated by GLM. Tailored products such as total flash density at 1-2 minute intervals will be provided for display in AWIPS-2 to select NWS forecast offices and national centers such as the Storm Prediction Center. Additional temporal / spatial combinations are being investigated in coordination with operational needs and case-study proxy data and prototype visualizations may also be generated from the NASA heritage Lightning Imaging Sensor and Optical Transient Detector data. End users will provide feedback on the utility of products in their operational environment, identify use cases and spatial/temporal scales of interest, and provide feedback to the developers for adjusted or new products.

Goodman, Steven J.↗

Meta-modeling strategy for data-driven forecasting

Accurately forecasting the weather is a key requirement for climate change mitigation. Data-driven methods offer the ability to make more accurate forecasts, but lack interpretability and can be expensive to train and deploy if models are not carefully developed. Here, we make use of two historical climate data sets and tools from machine learning, to accurately predict temperature fields. Furthermore, we are able to use low fidelity models that are cheap to train and evaluate, to selectively avoid expensive high fidelity function evaluations, as well as uncover seasonal variations in predictive power. This allows for an adaptive training strategy for computationally efficient geophysical emulation.

Skinner, Dominic J↗

Applying Geospatial Technologies for International Development and Public Health: The USAID/NASA SERVIR Program

Background: SERVIR -- the Regional Visualization and Monitoring System -- helps people use Earth observations and predictive models based on data from orbiting satellites to make timely decisions that benefit society. SERVIR operates through a network of regional hubs in Mesoamerica, East Africa, and the Hindu Kush-Himalayas. USAID and NASA support SERVIR, with the long-term goal of transferring SERVIR capabilities to the host countries. Objective/Purpose: The purpose of this presentation is to describe how the SERVIR system helps the SERVIR regions cope with eight areas of societal benefit identified by the Group on Earth Observations (GEO): health, disasters, ecosystems, biodiversity, weather, water, climate, and agriculture. This presentation will describe environmental health applications of data in the SERVIR system, as well as ongoing and future efforts to incorporate additional health applications into the SERVIR system. Methods: This presentation will discuss how the SERVIR Program makes environmental data available for use in environmental health applications. SERVIR accomplishes its mission by providing member nations with access to geospatial data and predictive models, information visualization, training and capacity building, and partnership development. SERVIR conducts needs assessments in partner regions, develops custom applications of Earth observation data, and makes NASA and partner data available through an online geospatial data portal at SERVIRglobal.net. Results: Decision makers use SERVIR to improve their ability to monitor air quality, extreme weather, biodiversity, and changes in land cover. In past several years, the system has been used over 50 times to respond to environmental threats such as wildfires, floods, landslides, and harmful algal blooms. Given that the SERVIR regions are experiencing increased stress under larger climate variability than historic observations, SERVIR provides information to support the development of adaptation strategies for nations affected by climate change. Conclusions: SERVIR is a platform for collaboration and cross-agency coordination, international partnerships, and delivery of web-based geospatial information services and applications. SERVIR makes a variety of geospatial data available for use in studies of environmental health outcomes.

Hemmings, Sarah↗

Impact of Lake Okeechobee Sea Surface Temperatures on Numerical Predictions of Summertime Convective Systems over South Florida

The NASA Short-term Prediction Research and Transition (SPoRT) Center, the Florida Institute of Technology, and the NOAA/NWS Weather Forecast Office at Miami, FL (MFL) are collaborating on a project to investigate the impact of using high-resolution, 2-km Moderate Resolution Imaging Spectroradiometer (MODIS) sea surface temperature (SST) composites within the Weather Research and Forecasting (WRF) prediction system. The NWS MFL is currently running WRF in real-time to support daily forecast operations, using the National Centers for Environmental Prediction Nonhydrostatic Mesoscale Model dynamical core within the NWS Science and Training Resource Center's Environmental Modeling System (EMS) software. Twenty-seven hour forecasts are run daily initialized at 0300, 0900, 1500, and 2100 UTC on a domain with 4-km grid spacing covering the southern half of Florida and adjacent waters of the Gulf of Mexico and Atlantic Ocean. The SSTs are initialized with the NCEP Real-Time Global (RTG) analyses at 1/12deg resolution. The project objective is to determine whether more accurate specification of the lower-boundary forcing over water using the MODIS SST composites within the 4-km WRF runs will result in improved sea fluxes and hence, more accurate e\~olutiono f coastal mesoscale circulations and the associated sensible weather elements. SPoRT conducted parallel WRF EMS runs from February to August 2007 identical to the operational runs at NWS MFL except for the use of MODIS SST composites in place of the RTG product as the initial and boundary conditions over water. During the course of this evaluation, an intriguing case was examined from 6 May 2007, in which lake breezes and convection around Lake Okeechobee evolved quite differently when using the high-resolution SPoRT MODIS SST composites versus the lower-resolution RTG SSTs. This paper will analyze the differences in the 6 May simulations, as well as examine other cases from the summer 2007 in which the WRF-simulated Lake Okeechobee breezes evolved differently due to the SST initialization. The effects on wind fields and precipitation systems will be emphasized, including validation against surface mesonet observations and Stage IV precipitation grids.

Case, Jonathan L.↗

Agent Architecture for Aviation Data Integration System

This paper describes the proposed agent-based architecture of the Aviation Data Integration System (ADIS). ADIS is a software system that provides integrated heterogeneous data to support aviation problem-solving activities. Examples of aviation problem-solving activities include engineering troubleshooting, incident and accident investigation, routine flight operations monitoring, safety assessment, maintenance procedure debugging, and training assessment. A wide variety of information is typically referenced when engaging in these activities. Some of this information includes flight recorder data, Automatic Terminal Information Service (ATIS) reports, Jeppesen charts, weather data, air traffic control information, safety reports, and runway visual range data. Such wide-ranging information cannot be found in any single unified information source. Therefore, this information must be actively collected, assembled, and presented in a manner that supports the users problem-solving activities. This information integration task is non-trivial and presents a variety of technical challenges. ADIS has been developed to do this task and it permits integration of weather, RVR, radar data, and Jeppesen charts with flight data. ADIS has been implemented and used by several airlines FOQA teams. The initial feedback from airlines is that such a system is very useful in FOQA analysis. Based on the feedback from the initial deployment, we are developing a new version of the system that would make further progress in achieving following goals of our project.

Kulkarni, Deepak↗

Future Changes in Midwest Extreme Precipitation Depend on Storm Type

Midwestern U.S. extreme precipitation is associated with multiple storm types including mesoscale convective systems (MCSs) and/or training thunderstorms, tropical cyclone (TC) remnants, and winter storms. Anthropogenic warming is expected to increase climatological precipitation globally, however, there may be little correspondence with regional storm-based changes. Furthermore, uncertainty remains in precipitation-temperature scaling due to use of convective parameterization in most global models. In this study, we investigated historically impactful extreme precipitation events from multiple types of Midwest storms using the Weather Research and Forecasting model at convection-permitting resolution. We simulated five-member ensembles of historical hindcasts and experiments representing the storms in the future using the pseudo-global warming method. We found that future precipitation changes depend on storm type, with increases near Clausius-Clapeyron (CC) for winter storms, no consensus for MCSs and/or training thunderstorms, and sub-CC increases for TC remnants. This research highlights the importance of considering storm type in future extreme precipitation projections.

54 ENVIRONMENTAL SCIENCES↗