Search NASA⌕ Search

SEARCH · Search NASA

Results for “Data parking”

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 685 records · Page 38
All sourcesNASA NTRSDOE OSTI
NASA NTRS1998

Auroral Boundaries: Comparison Between UV Images, In Situ Precipitation, and Groundbased Optical Observations

The location of poleward and equatorward boundaries are used as diagnostics of substorm phase and energy storage in the magnetosphere. Boundaries are estimated from groundbased observations (all sky imagers, meridian scanning photometers, and magnetometers), from in situ particle observations, and from spacebased global auroral observations. Each observational technique has relative advantages. However, recent studies suggest caution when comparing boundaries derived from different methods. in the study, FUV auroral images from the POLAR Ultraviolet Imager are used to estimate auroral boundaries. These boundaries are then compared with similar boundaries derived from DMSP in situ particle precipitation observations and from groundbased meridian scanning photometers. The goal is to see how well the boundaries from these three dissimilar observations correlate, to estimate dependencies on instrumental capabilities, i.e. imager resolution, and to serve as a potential first step to derive an algorithm for finding oval boundaries from groundbased optical data.

Germany, G. A.↗
NASA NTRS2008

Kaguya Orbit Determination from JPL

Selene (re-named 'Kaguya' after launch) is an unmanned mission to the Moon navigated, in part, by JPL personnel. Launched by an H-IIA rocket on September 14, 2007 from Tanegashima Space Center, Kaguya entered a high, Earth-centered phasing orbit with apogee near the radius of the Moon's orbit. After 19 days and two orbits of Earth, Kaguya entered lunar orbit. Over the next 2 weeks the spacecraft decreased its apolune altitude until reaching a circular, 100 kilometer altitude orbit. This paper describes NASA/JPL's participation in the JAXA/Kaguya mission during that 5 week period, wherein JPL provided tracking data and orbit determination support for Kaguya.

lunar navigation↗
NASA NTRS2019

NtGCM User's Manual: 1.1 (High Pressure High Temperature Laser based) Nanotube Growth Chamber Monitor

This manual describes the installation and use of NtGCM software. NtGCM is software designed for monitoring the growth of nanotubes in a high temperature and high pressure chamber using a laser*. NtGCM software monitors a dozen dierent parameters that are important to understanding the growth of the nanomaterials including the laser input power, the temperature at eight separate locations inside and outside the growth chamber, as well as the pressure and ow rate of the gaseous media that control the environment in the chamber. The measurements are all made in real time. The program features a robust user account management layer and a rich data display manager that allows plotted data, displayed units and other parameters to be changed on the y for the operator's convenience.

Sauti, Godfrey↗
NASA NTRSDate not supplied

Fusing GeoNEX and VIIRS Surface BRDF Retrievals: Exploring a GEO-LEO Synergy

The Bidirectional Reflectance Distribution Function or BRDF, which describes the dependency of surface reflectance on the illumination-view geometries, are the foundation of many high-level satellite products for terrestrial and aquatic system monitoring. The latest geostationary sensors like GOES ABI provide high frequent (~10 minutes) observations of the Earth surface that feature continuously changing sun angles, allowing us to retrieve surface BRDF with dedicated atmospheric correction algorithms like MAIAC (Multi-Angle Implementation of Atmospheric Correction). For mid-latitude locations, because geostationary satellites have fixed view angles in the back-scattering directions, the angular sampling of surface BRDF by GEO sensors is not comprehensive. This study explores a GEO-LEO synergy to address this issue. We first extract concurrent GeoNEX and VIIRS BRDF data with the best quality (cloud-free and low aerosol loading) at chosen AERONET sites. We then compare the magnitude and the shape factors of the two set of BRDF parameters as well as their variations through the season. We calculate the “distances” between the GeoNEX and VIIRS BRDF by using them to cross-predict the top-of-atmosphere reflectance measured by their counterpart and evaluating the corresponding prediction errors. This metric allows us to derive a set of optimized BRDF parameters that minimize such distances or prediction errors, which are considered as the fused BRDF result. We validate the algorithm with reserved AERONET data and then apply it to generate the GEO-LEO BRDF synergy over CONUS. We expect the fused BRDF to have reduced uncertainties as compared to the source GeoNEX or VIIRS data and may find broadly application in deriving other high-level satellite products.

Geostationary satellite↗
NASA NTRSDate not supplied

Effects of Low Dose Radiation and Radiation Countermeasures on Infection By Spaceflight Analogue Cultured Salmonella Using 3-D Biomimetic Human Tissue Models

While both microgravity and radiation are major biological stressors associated with the spaceflight environment, their cumulative impact on host-pathogen interactions and infectious disease risks are rarely considered. This is critical to address, since the cumulative effects of these stressors during spaceflight may result in unexpected negative impacts on crew health and performance that neither condition alone would predict, thus limiting the ability to develop effective countermeasures. Previously, we showed that both spaceflight and spaceflight analogue culture increased the virulence and pathogenesis-related characteristics of the foodborne pathogen, Salmonella Typhimurium (S. Typhimurium), which is responsible for disqualification of food destined for the International Space Station and Salmonella spp. have been found aboard NASA spacecraft. Recently, we demonstrated that spaceflight-analogue culture of S. Typhimurium increased its ability to infect 3-D biomimetic human intestinal tissue models. In a separate study, we showed low dose radiation damaged our 3-D intestinal models. The primary objective of this proposal is to evaluate the possibility that low dose radiation will exacerbate the already increased bacterial pathogenicity of S. Typhimurium observed following spaceflight analogue culture. In addition, we will determine the impact of a radiation countermeasure to provide protection against both radiation and pathogen-induced tissue damage and inflammation. Hypothesis: The already enhanced infection potential of spaceflight analogue cultured S. Typhimurium will be further exacerbated when used to infect host cells exposed to low dose radiation and this enhanced pathogenicity can be mitigated by a radioprotective compound. Aims: 1.Characterize the impact of spaceflight-analogue culture on the ability of S. Typhimurium to infect 3-D biomimetic intestinal tissue models before and after exposure to low dose radiation. 2. Evaluate the ability of the radioprotective compound, EC-18, to protect 3-D intestinal models from low dose radiation, S. Typhimurium infection, and the cumulative impact of these stressors. Significance: Current infectious disease risk assessments for spaceflight do not consider the potential for increased susceptibility to infection and disease resulting from exposure to low dose radiation, which is a critical consideration. This study will provide key evidence to determine if exposure to low dose radiation may be a factor in astronaut susceptibility to infection during long duration exploration missions and the impact of selected countermeasures to mitigate that risk to crew health. We have completed infection studies of the 3-D biomimetic intestinal tissue models and are currently analyzing the data.

Jennifer Barrila↗
NASA NTRSDate not supplied

Effects of Low Dose Radiation and Radiation Countermeasures on Infection by Spaceflight Analogue Cultured Salmonella Using 3-D Biomimetic Human Tissue Models

While both microgravity and radiation are major biological stressors associated with the spaceflight environment, their cumulative impact on host-pathogen interactions and infectious disease risks are rarely considered. This is critical to address, since the cumulative effects of these stressors during spaceflight may result in unexpected negative impacts on crew health and performance that neither condition alone would predict, thus limiting the ability to develop effective countermeasures. Previously, we showed that both spaceflight and spaceflight analogue culture increased the virulence and pathogenesis-related characteristics of the foodborne pathogen, Salmonella Typhimurium (S. Typhimurium), which is responsible for disqualification of food destined for the International Space Station and Salmonella spp. have been found aboard NASA spacecraft. Recently, we demonstrated that spaceflight-analogue culture of S. Typhimurium increased its ability to infect 3-D biomimetic human intestinal tissue models. In a separate study, we showed low dose radiation damaged our 3-D intestinal models. The primary objective of this proposal is to evaluate the possibility that low dose radiation will exacerbate the already increased bacterial pathogenicity of S. Typhimurium observed following spaceflight analogue culture. In addition, we will determine the impact of a radiation countermeasure to provide protection against both radiation and pathogen-induced tissue damage and inflammation. Hypothesis: The already enhanced infection potential of spaceflight analogue cultured S. Typhimurium will be further exacerbated when used to infect host cells exposed to low dose radiation and this enhanced pathogenicity can be mitigated by a radioprotective compound. Aims: 1.Characterize the impact of spaceflight-analogue culture on the ability of S. Typhimurium to infect 3-D biomimetic intestinal tissue models before and after exposure to low dose radiation. 2. Evaluate the ability of the radioprotective compound, EC-18, to protect 3-D intestinal models from low dose radiation, S. Typhimurium infection, and the cumulative impact of these stressors. Significance: Current infectious disease risk assessments for spaceflight do not consider the potential for increased susceptibility to infection and disease resulting from exposure to low dose radiation, which is a critical consideration. This study will provide key evidence to determine if exposure to low dose radiation may be a factor in astronaut susceptibility to infection during long duration exploration missions and the impact of selected countermeasures to mitigate that risk to crew health. We have completed infection studies of the 3-D biomimetic intestinal tissue models and are currently analyzing the data.

Jennifer Barrila↗
DOE OSTI2025

Machine learning model inputs, outputs, and scripts associated with “Artificial intelligence-guided iterations between observations and modeling significantly improve environmental predictions”

NOTE: The manuscript associated with this data package is currently in review. The data may be revised based on reviewer feedback. Upon manuscript acceptance, this data package will be updated with the final dataset and additional metadata. This data package is associated with the manuscript “Artificial intelligence-guided iterations between observations and modeling significantly improve environmental predictions” (Malhotra et al., in prep). This effort was designed following ICON (integrated, coordinated, open, and networked) principles to facilitate a model-experiment (ModEx) iteration approach, leveraging crowdsourced sampling across the contiguous United States (CONUS). New machine learning models were created every month to guide sampling locations. Data from the resulting samples were used to test and rebuild the machine learning models for the next round of sampling guidance. Associated sediment and water geochemistry and in situ sensor data can be found at https://data.ess-dive.lbl.gov/datasets/doi:10.15485/1923689, https://data.ess-dive.lbl.gov/datasets/doi:10.15485/1729719, and https://data.ess-dive.lbl.gov/datasets/doi:10.15485/1603775. This data package is associated with two GitHub repositories found at https://github.com/parallelworks/dynamic-learning-rivers and https://github.com/WHONDRS-Hub/ICON-ModEx_Open_Manuscript. In addition to this readme, this data package also includes two file-level metadata (FLMD) files that describes each file and two data dictionaries (DD) that describe all column/row headers and variable definitions. This data package consists of two main folders (1) dynamic-learning-rivers and (2) ICON-ModEx_Open_Manuscript which contain snapshots of the associated GitHub repositories. The input data, output data, and machine learning models used to guide sampling locations are within dynamic-learning-rivers. The folder is organized into five top-level directories: (1) “input_data” holds the training data for the ML models; (2) “ml_models” holds machine learning (ML) models trained on the data in “input_data”; (3) “examples” contains files for direct experimentation with the machine learning model, including scripts for setting up “hindcast” run; (4) “scripts” contains data preprocessing and postprocessing scripts and intermediate results specific to this data set that bookend the ML workflow; and (5) “output_data” holds the overall results of the ML model on that branch. Each trained ML model resides on its own branch in the repository; this means that inputs and outputs can be different branch-to-branch. There is also one hidden directory “.github/workflows”. This hidden directory contains information for how to run the ML workflow as an end-to-end automated GitHub Action but it is not needed for reusing the ML models archived here. Please see the top-level README.md in the GitHub repository for more details on the automation. The scripts and data used to create figures in the manuscript are within ICON-ModEx_Open_Manuscript. The folder is organized into four folders which contain the scripts, data, and pdf for each figure. Within the “fig-model-score-evolution” folder, there is a folder called “intermediate_branch_data” which contains some intermediate files pulled from dynamic-learning-rivers and reorganized to easily integrate into the workflows. NOTE: THIS FOLDER INCLUDES THE FILES AT THE POINT OF PAPER SUBMISSION. IT WILL BE UPDATED ONCE THE PAPER IS ACCEPTED WITH ANY REVISIONS AND WILL INCLUDE A DD/FLMD AT THAT POINT. We thank the United States Forest Service, Washington Department of Fish and Wildlife, Washington Department of Natural Resources, Cowiche Canyon Conservatory, Washington State Parks and Recreation Commission (Scientific Research Permit #210901), and the Confederated Tribes and Bands of the Yakama Nation for access to field locations where the samples labeled “SSS” were collected. We also thank the Yakama Nation Tribal Council and Yakama Nation Fisheries for working with us to facilitate sample collection and optimization of data usage according to their values and worldview. WHONDRS consortium members were asked to provide any acknowledgments for the collection of samples labeled “CM” and the following is a list of acknowledgments that were submitted with their corresponding Site IDs: (MART) Research activities were conducted in part on the Wind River Experimental Forest within the Gifford Pinchot National Forest; (MP- 100379) Philadelphia is part of Lenapehoking, the ancestral homelands of the Lenape peoples; (MP-102398) Land surveyed is the ancestral homelands of the Nookhose'iinenno (Arapaho), Tsis tsis'tas (Cheyenne), and Nuuchu (Ute); (MP-100749 and MP- 100747) Georgia Coastal Ecosystem LTER, OCE-1832178; (SP-70 and SP-72) Eastern Shoshone, Shoshone-Bannock; (MP- 102944) Funded by Oregon Watershed Enhancement Board. On the traditional lands of the Confederated Tribes of the Siletz, Confederated Tribes of the Grand Rhonde, and the Clatsop-Nehalem Confederated Tribe; (MP- 100607) Holiday Creek is located on the traditional territory of the Monacan Indian Nation; (SP-45) Lafayette Blue Springs State Park; (MP-102420) NSF DEB-2016749; (MP-100019) New Hampshire Agriculture Experiment Station; (SP-35) Rayonier (land owner; https://www.rayonier.com/); (MP- 101276) US Department of Energy, Office of Science, Biological and Environmental Research, Subsurface Biogeochemical Research, Watershed Dynamics and Evolution SFA at ORNL; (MP- 103224) Watershed Dynamics and Evolution SFA at ORNL; (MP- 101584) Traditional lands of the Oceti Sakowin (Dakota, Lakota, Nakoda) and Anishinaabe Peoples.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Citizen science coupled with machine learning to quantify green-blue infrastructure cooling potential in Maricopa County, Arizona

Here, this study investigates the spatiotemporal cooling performance of green and blue infrastructure (GBI) in the Dobson Ranch urban neighborhood in Phoenix, Arizona. We leveraged citizen science near-surface (2 m) air temperature (Tair) measurements to train a highly accurate Tair predicting LightGBM machine learning model (R 2 : 0.986, MAE: 0.251 °C, RMSE: 0.585 °C). On June 16, 2024, the park area exhibited approximately 1 °C cooling effect (relative to the neighborhood mean) during both day and night. In contrast, the nearby artificial lake exhibited a stronger cooling effect of 2.4 °C during the day but a slight warming of 0.3 °C at night. At 00:00, locations 50 m downwind of the park were 0.3 °C warmer than the park, while locations 50 m upwind were 0.8 °C warmer. At 11:00, we observed that the downwind area is 0.8 °C cooler and the upwind area is 0.6 °C warmer—at the same 50 m distances relative to the park. We also observed 1 °C cooler and warmer effects respectively at the same 50 m downwind and upwind locations at 19:00 on June 17, 2024. Our data-driven analysis highlights potential limitations of car-traverse measurements, showing that failure to account for temporal variations during the traverse can lead to overestimation of Tair at night and underestimation during the day. Our analysis also showed only a weak correlation (coefficient: 0.48) between Landsat-derived land surface temperature (LST) and model predicted Tair at the time of the local Landsat overpass (∼11.00). This highlights the potential error of relying solely on LST for human thermal exposure analysis—particularly within the heterogenous built-environment.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Commercial Vehicle Driver Behaviors and Decision Making: Lessons Learned from Urban Ridealongs

As e-commerce and urban deliveries spike, cities grapple with managing urban freight more actively. In order to effectively manage urban deliveries, city planners and policy makers need to better understand driver behaviors and the challenges they experience in performing deliveries. In this study, we collected data on commercial vehicle (CV) driver behaviors by performing ridealongs with various logistics carriers. Ridealongs were performed in Seattle, Washington, covering a range of vehicles (cars, vans, and trucks), goods (parcels, mail, beverages, and printed materials), and customer types (residential, office, large and small retail). Observers collected qualitative observations and quantitative data on trip and dwell times, while also tracking vehicles through GPS devices. The results showed that, on average, urban CVs spent 80 percent of their daily operating time parked. The study also found that, unlike the common belief, drivers (especially those operating heavier vehicles) parked in authorized parking locations, with only less than 5 percent of stops occurring in the travel lane. Dwell times associated with authorized parking locations were significantly longer than those of other parking locations, and mail and heavy goods deliveries generally had longer dwell times. We also identified three main criteria CV drivers used for choosing a parking location: avoiding unsafe maneuvers, minimizing conflicts with other users of the road, and coopetition with other commercial drivers. Here, the results provide estimates for trip times, dwell times, and parking choice types, as well as insights into why those decisions are made and the factors affecting driver choices.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2022

Canopy spectra, Feb2017, PA-SLZ: Panama

Canopy spectra of sunlit canopy of Guarea kunthiana, Brosimum utile, Terminalia amazonia (TERMAM), Vochysia ferruginea (VOCHFE), Miconia borealis (MICOBO) and Guatteria dumetorum (GUATDU) species from the Smithsonian Tropical Research Institute (STRI) canopy crane site in the San Lorenzo National Park, Republic of Panama (PA-SLZ: Bosque Protector San Lorenzo). Canopy spectra were measured at 1:20 – 2 pm on 22 February 2017, using a SVC spectroradiometer. This data package includes the raw SVC data (*.sig), processed data of individual spectra, and processed spectra averaged over the canopy of each of the six trees measured (*.csv). The package also includes photographs of the canopy spectral targets, metadata and the instrument manual. This data was collected as part of the 2017 Brookhaven National Laboratory – Smithsonian Tropical Research Institute leaf traits by age campaign.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS1978

Air turbulence measurements in and below cumulus congestus over mountainous terrain

Consideration is given to the definition and application to air turbulence measurements over mountainous terrain of the ensemble averaging operator in the second-order turbulent transfer model of moist, precipitating mesoscale systems developed by Manton and Cotton (1977) as a first step in the formulation of a unified mesoscale turbulence theory. The use of running means to smooth out point-to-point data variability is proposed as a means of avoiding certain of the problems associated with ensemble averaging, and is applied to airborne velocity measurements in cumulus congestus over South Park, Colorado. It is found that, in general, vertical transport of any cloud parameter will be primarily eddy transport in the mesoscale modeling of cloud processes.

Cotton, W. R.↗
NASA NTRS1988

Mars Exploration: Mission and System Analysis of the Split Sprint Mission

The information presented in this report provides detailed mission and system analysis of the Split Sprint Mission to Mars. These data were generated from September 1987 through July 1988 and involved numerous individuals within Program Development. This mission derives its name from the fact that the total mission payload is split between two vehicles, a cargo vehicle, and a piloted vehicle. The cargo vehicle carries the Mars lander and propellant for the piloted vehicle return to Earth. Then approximately 1 1/2 years later, the piloted vehicle carries the crew on a higher energy "sprint” trajectory to Mars. The advantages of the Split Sprint Mission is that the payload for the piloted vehicle is minimized and the crew would be in space for only 14 months. Mission and system data are presented for a Sprint Mission in the year 2004. Many important aspects of the mission were studied in detail. These include orbital lighting and lifetime analysis, Mars parking orbit selection, Earth departure window analysis, lander descent and ascent performance, vehicle aerobraking requirements, mission orbital maneuvers, and many other analyses listed in the Table of Contents. Emphasis was placed on vehicle performance analysis which ranged from recovery of the Earth departure stages to aerocapture of the Earth Return Capsule. There is also a section describing the computer programs that were used for this study. These programs provide many useful tools for future studies of manned planetary missions. This introductory section will give an overall view of the Split Sprint Mission and describe the orbital operations and vehicles that were studied.

Mars Architecture Team↗
DOE OSTI2026

Interpretable Machine Learning for Characterizing Electric Vehicle Charging Behavior: Insights from Real-World Data

As electric vehicle (EV) adoption rises globally, concerns about the impact on aging electrical grids grow, particularly regarding the charging behavior of EV drivers. This study analyzes real-world driving and charging data from Ford battery electric vehicles (BEVs) collected between 2018 and 2019 to develop interpretable models that characterize charging behavior and quantify influencing factors. Prior research has relied on assumptions regarding driver behavior, often overlooking actual charging patterns. By employing generalized linear mixed models (GLMMs), this work offers insights into how various elements, such as next trip distance and state of charge (SOC), influence charging decisions. The dataset comprises over three million park-trip pairs from 1,997 vehicles, revealing that features related to driving behavior significantly dictate charging behavior, while infrastructure and regional factors have lesser impacts. The findings suggest that existing simulation models may oversimplify EV charging behavior assumptions. This work utilizes real-world EV driving and charging data to train interpretable models that describe charging behavior and quantify the factors most associated with how drivers use charging infrastructure. This research underscores the need for interpretable, data-driven methodologies to inform future EV infrastructure planning and grid management.

29 - ENERGY PLANNING, POLICY AND ECONOMY↗
DOE OSTI2026

2005 Tahoe Regional Household Travel Survey

The 2005 Tahoe Regional Household Travel Survey is a comprehensive survey of the travel patterns of households in the Tahoe Basin region of California and Nevada. The survey was conducted for the Tahoe Regional Planning Agency over a four-month period, from June through September 2005. This collection contains two sets of travel data: 1) a survey of 1,220 permanent households within the Tahoe Basin region and 2) a subset survey of 125 seasonal households within the same area. The permanent resident dataset contains information about 2,732 household members, 2,471 vehicles, and 11,048 trips made during a 24-hour period. The seasonal resident subset features 726 trip observations and information about 229 household members and 185 vehicles. The survey relied on the willingness of study area residents to 1) provide demographic information about their household, its members, and its vehicles and 2) document all travel for each household member, regardless of age, over an assigned 24-hour period. During the recruitment phase, respondents were asked to provide detailed household information, including permanent or seasonal resident status, number of household occupants, type of dwelling unit, number of vehicles available to household members, as well as the year, body type, and fuel type of each vehicle. Survey participants received mailed travel logs to aid in documenting travel information for the 24-hour assessment period. Respondents were instructed to record their mode of transportation, trip purpose, number of passengers, departure and arrival times, activities at each trip destination, ride fare, and parking costs. Demographic information for this study includes age, gender, income, education, and employment status.

1Hz data↗
DOE OSTI2021

A Framework for International Collaboration on ITER Using Large-Scale Data Transfer to Enable Near-Real-Time Analysis

The global nature of the ITER project along with its projected ~ petabyte per day data generation presents a unique challenge, but also an opportunity for the fusion community to rethink, optimize, and enhance our scientific discovery process. Recognizing this, collaborative research with computational scientists was undertaken over the past several years to create a framework for large-scale data movement across wide-area networks (WANs), to enable global near-real time analysis of fusion data. This would broaden the available computational resources for analysis/simulation, and increase the number of researchers actively participating in experiments. An official demonstration of this framework for fast, large data transfer and real-time analysis was carried out between the KSTAR tokamak in Daejeon, Korea and PPPL in Princeton, USA. Streaming large data transfer, with near real-time movie creation and analysis of the KSTAR Electron Cyclotron Emission imaging (ECEI) data, was performed using the I/O framework ADIOS, and comparisons made at PPPL with simulation results from the XGC1 code. These demonstrations were made possible utilizing an optimized network configuration at PPPL, which achieved over 8.8 Gbps (88% utilization) in throughput tests from NFRI to PPPL. This demonstration showed the feasibility for large-scale data analysis of KSTAR data, and provides a nascent framework to enable use of globally distributed computational and personnel resources in pursuit of scientific knowledge from the ITER experiment.

43 PARTICLE ACCELERATORS↗
DOE OSTI2025

OpenCRUMS USA: An Open Machine Learning Framework for Characterizing Variability in Aerosol Reanalysis Data

Advances in artificial intelligence (AI) have called for exploring how these techniques can be used for exploring patterns in large climate datasets. To that regard, the U.S. Department of Energy AI for Earth System Predictability (AI4ESP) supported a pilot initiative called the Open Classification of Regimes in the Southeast USA (OpenCRUMS USA) project to explore how AI can be used to characterize modes of spatial variability in large climate datasets. For this study, we focus on comparing two methods for characterizing the modes of spatial variability of surface aerosol concentration over the Houston region: empirical orthogonal functions (EOFs) and layerwise relevance propagation (LRP) applied to a convolutional neural network (CNN) classifier. We show that EOF analysis typically attributes spatial variability modes that span all of southeast Texas, prohibiting the attribution of spatial variability to localized regions. However, using LRP on the CNN classifier resolves the explanatory parameters at a finer spatial resolution than EOFs. This allows for the attribution of the spatial variability of surface aerosols to local regions of organic carbon which was not possible using EOFs. In addition, the LRP analysis also suggests that synoptic-scale transport of dust is most prevalent during anticyclonic and pretrough synoptic conditions as categorized by self-organizing maps.

54 ENVIRONMENTAL SCIENCES↗