Search NASA⌕ Search

SEARCH · Search NASA

Results for “hyperspectral imagery”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
NASA NTRS2016

The Matsu Wheel: A Cloud-Based Framework for Efficient Analysis and Reanalysis of Earth Satellite Imagery

Project Matsu is a collaboration between the Open Commons Consortium and NASA focused on developing open source technology for cloud-based processing of Earth satellite imagery with practical applications to aid in natural disaster detection and relief. Project Matsu has developed an open source cloud-based infrastructure to process, analyze, and reanalyze large collections of hyperspectral satellite image data using OpenStack, Hadoop, MapReduce and related technologies. We describe a framework for efficient analysis of large amounts of data called the Matsu "Wheel." The Matsu Wheel is currently used to process incoming hyperspectral satellite data produced daily by NASA's Earth Observing-1 (EO-1) satellite. The framework allows batches of analytics, scanning for new data, to be applied to data as it flows in. In the Matsu Wheel, the data only need to be accessed and preprocessed once, regardless of the number or types of analytics, which can easily be slotted into the existing framework. The Matsu Wheel system provides a significantly more efficient use of computational resources over alternative methods when the data are large, have high-volume throughput, may require heavy preprocessing, and are typically used for many types of analysis. We also describe our preliminary Wheel analytics, including an anomaly detector for rare spectral signatures or thermal anomalies in hyperspectral data and a land cover classifier that can be used for water and flood detection. Each of these analytics can generate visual reports accessible via the web for the public and interested decision makers. The result products of the analytics are also made accessible through an Open Geospatial Compliant (OGC)-compliant Web Map Service (WMS) for further distribution. The Matsu Wheel allows many shared data services to be performed together to efficiently use resources for processing hyperspectral satellite image data and other, e.g., large environmental datasets that may be analyzed for many purposes.

0↗
NASA NTRS2015

Development and Application of Hyperspectral Infrared Ozone Retrieval Products for Operational Meteorology

Cyclogenesis is a key forecast challenge at operational forecasting centers such as WPC and OPC, so these centers have a particular interest in unique products that can identify key storm features. In some cases, explosively developing extratropical cyclones can produce hurricane force, non-convective winds along the East Coast and north Atlantic as well as the Pacific Ocean, with the potential to cause significant damage to life and property. Therefore, anticipating cyclogenesis for these types of storms is crucial for furthering the NOAA goal of a "Weather Ready Nation". Over the last few years, multispectral imagery (i.e. RGB) products have gained popularity among forecasters. The GOES-R satellite champion at WPC/OPC has regularly evaluated the Air Mass RGB products from GOES Sounder, MODIS, and SEVIRI to aid in forecasting cyclogenesis as part of ongoing collaborations with SPoRT within the framework of the GOES-R Proving Ground. WPC/OPC has used these products to identify regions of stratospheric air associated with tropopause folds that can lead to cyclogenesis and hurricane force winds. RGB products combine multiple channels or channel differences into multi-color imagery in which different colors represent a particular cloud or air mass type. Initial interaction and feedback from forecasters evaluating the legacy Air Mass RGBs revealed some uncertainty regarding what physical processes the qualitative RGB products represent and color interpretation. To enhance forecaster confidence and interpretation of the Air Mass RGB, NASA SPoRT has transitioned a total column ozone product from AIRS retrievals to the WPC/OPC. The use of legacy AIRS demonstrates future JPSS capabilities possible with CrIS or OMPS. Since stratospheric air can be identified by anomalous potential vorticity and warm, dry, ozone-rich air, hyperspectral infrared sounder ozone products can be used in conjunction with the Air Mass RGB for identifying the role of stratospheric air in explosive cyclogenesis and hurricane force wind events. Currently, forecasters at WPC/OPC are evaluating the Air Mass RGB imagery in conjunction with the AIRS total column ozone to aid forecasting cyclogenesis and high wind forecasts. One of the limitations of the total ozone product is that it is difficult for forecasters to determine whether elevated ozone concentrations are related to stratospheric air or climatologically high values of ozone in certain regions. To address this limitation, SPoRT created an AIRS ozone anomaly product which calculates the percent of normal ozone based on a global stratospheric ozone mean climatology. With the knowledge that ozone values 125 percent of normal and greater typically represent stratospheric air; the anomaly product can be used with the total column ozone product to confirm regions of stratospheric air on the Air Mass RGB. This presentation describes the generation of these products along with forecaster feedback concerning the use of the AIRS ozone products in conjunction with the Air Mass RGB product for the unique forecast challenges WPC/OPC face. Additionally examples of CrIS ozone and anomaly products will be shown to further demonstrate the utility and capability of JPSS in forecasting unique events.

Berndt, Emily↗
NASA NTRS2022

Quantifying Mangrove Canopy Regrowth and Recovery After Hurricane Irma With Large-Scale Repeat Airborne Lidar in the Florida Everglades

Hurricane Irma caused significant damages to mangrove forested wetlands in south Florida, including defoliation, tree snapping, and uprooting. Previous studies have used optical satellite imagery to estimate large-scale forest disturbance and resilience patterns. However, satellite images alone cannot provide measurements of vertical mangrove structure. In this study, we used dense point cloud data collected by NASA Goddard’s LiDAR, Hyperspectral, and Thermal (G-LiHT) airborne imager before (March 2017) and after (December 2017 and March 2020) Hurricane Irma to quantify the recovery, or lack thereof, of the three-dimensional (3D) mangrove forest structure. Recent resilience and vulnerability models developed from Landsat time series following the storm were used to group the lidar data into distinct disturbance-recovery classes. We then analyzed lidar-based forest canopy within each of the recovery classes to test a suite of forest structural characteristics. Our results indicate that 77.0 % of the survey area experienced canopy height loss three months after Hurricane Irma, whereby the majority of canopy height loss occurred in areas with the tallest mangrove forests (i.e., 15–25 m tall). Our analysis shows that the mangrove canopy height in South Florida increased by an average 0.26 m from December 2017 to March 2020, with most of the forest (84.7 % of the survey area) experiencing canopy height regrowth. However, only 38.1 % of the survey area has recovered to pre-storm canopy height. The distribution of canopy height was significantly altered by Hurricane Irma in the low and intermediate resilience classes, but were not significantly different 2.5 years later. Indeed, in areas of low resilience, little to no vertical change has occurred suggesting the absence of canopy regrowth and natural regeneration. Conversely, mangroves in high resilience class, which are dominated by shorter canopies (<5 m), were not heavily damaged by the storm and have maintained the same structural attributes as those before Hurricane Irma. Our findings highlight that hurricane disturbances significantly alter mangrove forest canopy structure, but recovery of vertical structure varies by resilience classes, species composition, and canopy height.

Lidar↗
NASA NTRS2001

EO-1/Hyperion Hyperspectral Imager Design, Development, Characterization, and Calibration

The Hyperion Imaging Spectrometer is one of three principal instruments aboard the EO-1 spacecraft. Its mission as a technology demonstrator is to evaluate on-orbit issues for imaging spectroscopy and to assess the capabilities of a spacebased imaging spectrometer for earth science and earth observation missions. The instrument provides earth imagery at 30 meter spatial resolution, 7.5 km swath width in 220 contiguous spectral bands at 10 nm spectral resolution. Spectral range is from 0.4 gm to 2.5 gm. The instrument includes internal and solar calibration sub-systems. This paper will review the design, construction and calibration of the Hyperion instrument. The on-orbit plans and operations will be presented along with updated calibration and characterization measurements.

Folkman, Mark↗
NASA NTRS2012

EO-1/Hyperion: Nearing Twelve Years of Successful Mission Science Operation and Future Plans

The Earth Observing One (EO-1) satellite is a technology demonstration mission that was launched in November 2000, and by July 2012 will have successfully completed almost 12 years of high spatial resolution (30 m) imaging operations from a low Earth orbit. EO-1 has two unique instruments, the Hyperion and the Advanced Land Imager (ALI). Both instruments have served as prototypes for NASA's newer satellite missions, including the forthcoming (in early 2013) Landsat-8 and the future Hyperspectral Infrared Imager (HyspIRI). As well, EO-1 is a heritage platform for the upcoming German satellite, EnMAP (2015). Here, we provide an overview of the mission, and highlight the capabilities of the Hyperion for support of science investigations, and present prototype products developed with Hyperion imagery for the HyspIRI and other space-borne spectrometers.

Middleton, Elizabeth M.↗
NASA NTRS2012

Operational Use of the AIRS Total Column Ozone Retrievals Along with the RGB Air Mass Product as Part of the GOES-R Proving Ground

The National Oceanic and Atmospheric Administration (NOAA) National Centers for Environmental Prediction (NCEP) Hydrometeorological Prediction Center (HPC) and Ocean Prediction Center (OPC) provide short-term and medium-range forecast guidance of heavy precipitation, strong winds, and other features often associated with mid-latitude cyclones over both land and ocean. As a result, detection of factors that lead to rapid cyclogenesis and high wind events is key to improving forecast skill. One phenomenon that has been identified with these events is the stratospheric intrusion that occurs near tropopause folds. This allows for deep mixing near the top of the atmosphere where dry air high in ozone concentrations and potential vorticity descends (sometimes rapidly) deep into the mid-troposphere. Observations from satellites can aid in detection of these stratospheric air intrusions (SAI) regions. Specifically, multispectral composite imagery assign a variety of satellite spectral bands to the red, green, and blue (RGB) color components of imagery pixels and result in color combinations that can assist in the detection of dry stratospheric air associated with PV advection, which in turn may alert forecasters to the possibility of a rapidly strengthening storm system. Single channel or RGB satellite imagery lacks quantitative information about atmospheric moisture unless the sampled brightness temperatures or other data are converted to estimates of moisture via a retrieval process. Thus, complementary satellite observations are needed to capture a complete picture of a developing storm system. Here, total column ozone retrievals derived from a hyperspectral sounder are used to confirm the extent and magnitude of SAIs. Total ozone is a good proxy for defining locations and intensity of SAIs and has been used in studies evaluating that phenomenon (e.g. Tian et al. 2007, Knox and Schmidt 2005). Steep gradients in values of total ozone seen by satellites have been linked to stratosphere-troposphere exchange (WMO, 1985).

Folmer, Michael↗
NASA NTRS2022

Evaluating Approaches Relating Ecosystem Productivity with Desis Spectral Information

Data from the DLR Earth Sensing Imaging Spectrometer (DESIS), mounted on the International Space Station (ISS), were used to develop and test algorithms for remotely retrieving ecosystem productivity. Twenty DESIS images were used from three widely separated forested study sites representing deciduous and conifer forests. Gross primary production (GPP) values from eddy covariance flux towers at the sites were matched with DESIS spectral reflectances collected on the same days. Multiple algorithms were successful relating spectral reflectance with GPP, including: spectral vegetation indices (SVI) sensitive to chlorophyll content, SVI used in a photosynthetic light-use efficiency model framework, spectral shape characteristics through spectral derivatives and absorption feature analysis, and statistical models leading to multiband hyperspectral indices from partial least squares regression. Successful algorithms were able to achieve R2 better than 0.7 using a diverse set of observations combining data from different sites from multiple years and at multiple times during the year. The demonstrated robustness of the algorithms provides some confidence in using DESIS imagery to map spatial patterns of GPP.

K F Huemmrich↗
NASA NTRS2001

Development of Ground Reference GIS for Assessing Land Cover Maps of Northeast Yellowstone National Park

GIS technology and ground reference data often play vital roles in assessing land cover maps derived from remotely sensed data. This poster illustrates these roles, using results from a study done in Northeast Yellowstone National Park. This area holds many forest, range, and wetland cover types of interest to park managers. Several recent studies have focused on this locale, including the NASA Earth Observations Commercial Applications Program (EOCAP) hyperspectral project performed by Yellowstone Ecosystems Studies (YES) on riparian and in-stream habitat mapping. This poster regards a spin-off to the EOCAP project in which YES and NASA's Earth Science Applications Directorate explored the potential for synergistic use of hyperspecral, synthetic aperture radar, and multiband thermal imagery in mapping land cover types. The project included development of a ground reference GIS for site-specific data needed to evaluate maps from remotely sensed imagery. Field survey data included reflectance of plant communities, native and exotic plant species, and forest health conditions. Researchers also collected GPS points, annotated aerial photographs, and took hand held photographs of reference sites. The use of ESRI, ERDAS, and ENVI software enabled reference data entry into a GIS for comparision to georeferenced imagery and thematic maps. The GIS-based ground reference data layers supported development and assessment of multiple maps from remotely sensed data sets acquired over the study area.

Spruce, Joe↗
NASA NTRS2020

NASA Next-Generation Sensing Technologies for Earth & Planetary Science

Dr. Ved Chirayath's seminar will highlight new sensing technologies and airborne platforms he is developing for Earth & Space Science as director of the NASA Silicon Valley Laboratory for Advanced Sensing. His talk will feature recent work on Fluid Lensing, the first remote sensing technology capable of imaging through ocean waves in 3D at sub-cm resolutions, MiDAR, a next-generation active hyperspectral remote sensing and optical communications instrument, airborne gas sensing of multipollutant combustion sources, and a plasma actuated unmanned aerial vehicle (UAV) that utilized high-voltage dielectric discharge devices to achieve the first plasma controlled flight in history.Fluid Lensing and the NASA FluidCam instrument have been used extensively to provide distortion-free 3D multispectral imagery from UAVs of shallow marine systems around the world. MiDAR is being deployed on aircraft and underwater remotely operated vehicles (ROVs) as a new method to remotely sense living and nonliving structures in extreme environments as an analog for future Ocean Worlds robotic exploration missions. Finally, Chirayath will present preliminary results from NeMO-Net, a supercomputer-based neural network that uses a citizen science video game for global multimodal coral reef benthic habitat mapping, fusing remote sensing data from Fluid Lensing, MiDAR, NASA's Earth Observing System, and commercial satellites, to better understand the present and past dynamics of shallow marine systems. Together, these maturing technologies present promising new ways in which to explore terrestrial, marine, and aerial systems on Earth, and, ultimately, aid in the search for extraterrestrial life within our solar system and beyond.

Chirayath, Ved↗
NASA NTRSDate not supplied

Machine-Learning-Based Adaptive Thinning of CrIS Radiances to Improve Global Tropical Cyclone Analysis and Forecasts

This work is focused on optimizing the assimilation of hyperspectral infrared (IR) radiances from the Cross-track Infrared Sounder (CrIS) with the goal of improving the representation of tropical cyclones (TCs) in global analyses and forecasts. Current operational assimilation systems rely on subsampling IR radiances on a regular thinning grid. A new and improved adaptive methodology based on machine learning (ML) recognizes TCs from geostationary satellite imagery and is implemented in the Goddard Earth Observing System (GEOS) model and data assimilation framework. The ML methodology is extensively trained on existing TC data sets and creates for each TC a dynamic mask, based on the evolving shape and life cycle of that specific event. Once a TC mask is created, a switch is then activated in the data assimilation system to alter the thinning, ingesting more CrIS radiances within the moving mask, thus increasing the TC sampling. After the TC dissipates, the assimilation of CrIS radiances reverts to normal data density. Results of TC segmentation provided by a state-of-the-art generative machine learning model known as the Denoising Diffusion Probabilistic Model (DDPM) are compared to the previously used U-Net model. The new approach surpasses the performance of the previously developed one. The methodology is applied to both clear-sky and cloud-cleared radiances. Benefits from the latter methodology, particularly in improving the structure of TCs and the intensity forecasts, are presented.

Oreste Reale↗
NASA NTRS2021

Three-dimensional estimation of deciduous forest canopy structure and leaf area using multi-directional, leaf-on and leaf-off airborne lidar data

Airborne laser scanning (ALS) has been widely used to map gap probability and leaf area index (LAI) distribution at plot and landscape scales. As an indirect measurement, most ALS methods to estimate LAI combine waveform or point density information with supporting field measurements such as the leaf angle distribution, gap probability, or direct LAI measures. The development of a more independent estimation approach would facilitate more widespread use of existing ALS data to investigate patterns of forest structure and build realistic 3-D vegetation scenes to simulate remote sensing imagery and energy balance. Here, we develop a data processing workflow (named PVlad) using ALS point cloud apparent reflectance to estimate LAI and voxel-based leaf area density (LAD), aiming to reduce the need for associated field measurements such as the gap probability. The adaptation of the path volume (PV) concept derived from apparent reflectance integrates information from multi-directional ALS pulses, and quantifies the percentage exploration of each voxel for classification and occlusion correction, such that rigorous volumetric sampling approaches can be developed to derive LAI and LAD. The PVlad workflow was applied to discrete-return lidar data (Riegl VQ480i) acquired by NASA Goddard's LiDAR, Hyperspectral and Thermal Imager (G-LiHT) Airborne Imager during leaf-on (summer) and leaf-off (spring) conditions at the Smithsonian Environmental Research Center (SERC). The estimates of LAI and LAD captured structural differences between mature, logged, and intermediate-aged stands over eight deciduous forest plots. The derived LAI values were compared to field litter collection measurements, and the derived LAD vertical distribution was compared to the output of the VoxLAD model using terrestrial laser scan (TLS) field survey data. Using voxel sizes ranging from 0.5 m to 5 m, overall LAI estimation showed linear fitting coefficient bias and for 1 and 2 m voxel sizes, and vertical LAD distribution showed strong correlation with and for 0.5 and 1m voxel sizes. For every forest stand, upper-canopy LAD had a low variance for voxel sizes of ≤ . Application of PVlad to the G-LiHT and other similar ALS data archives enables the development of fine-resolution LAI map products, including voxelization of LAD for ecosystem science and radiative transfer simulations of remote sensing imagery or surface energy balance.

Tiangang Yin↗
NASA NTRS2015

Mission Adaptive UAS Platform for Earth Science Resource Assessment

NASA Ames Research Center has led a number of important Earth science remote sensing missions including several directed at the assessment of natural resources. A key asset for accessing high risk airspace has been the 180 kg class SIERRA UAS platform, providing mission durations of up to 8 hrs at altitudes up to 3 km. Recent improvements to this mission capability are embodied in the incipient SIERRA-B variant. Two resource mapping problems having unusual mission characteristics requiring a mission adaptive capability are explored here. One example involves the requirement for careful control over solar angle geometry for passive reflectance measurements. This challenges the management of resources in the coastal ocean where solar angle combines with sea state to produce surface glint that can obscure the ocean color signal. Furthermore, as for all scanning imager applications, the primary flight control priority to fly the UAS directly to the next waypoint should compromise with the requirement to minimize roll and crab effects in the imagery. A second example involves the mapping of natural resources in the Earth's crust using precision magnetometry. In this case the vehicle flight path must be oriented to optimize magnetic flux gradients over a spatial domain having continually emerging features, while optimizing the efficiency of the spatial mapping task. These requirements were highlighted in several recent Earth Science missions including the October 2013 OCEANIA mission directed at improving the capability for hyperspectral reflectance measurements in the coastal ocean, and the Surprise Valley Mission directed at mapping sub-surface mineral composition and faults, using high-sensitivity magentometry. This paper reports the development of specific aircraft control approaches to incorporate the unusual and demanding requirements to manage solar angle, aircraft attitude and flight path orientation, and efficient (directly geo-rectified) surface and sub-surface mapping, including the near-time optimization of these sometimes conflicting requirements. *

Flight Control↗
NASA NTRS2001

PHILLS Vicarious Calibration: A WFS Experiment and Guidance for LEO-15 Calibration Efforts

On April 24, 2001, Florida Shelf Lagrangian Experiment (FSLE) cruises were accompanied by PHILLS hyperspectral overflights at 30,000 ft altitude. Robert Steward, and Jim Ivey collected remote sensing reflectance and water samples for absorption during two FSLE experiments. The PHILLS was flown on several transects over the area with vicarious calibration measurements conducted by USF from the R/V LINK. The USF slow-drop package was also deployed to collect inherent and apparent optical properties as a function of depth for an evaluation of effects of vertical structure on remote sensing spectra. The PHILLS imagery has been successfully calibrated. We show the procedures, results, derived bathymetry, and some noise effects with a 3 s period.

Carder, Kendall L.↗
NASA NTRS2004

Applying Tafkaa For Atmospheric Correction of Aviris Over Coral Ecosystems In The Hawaiian Islands

Growing concern over the health of coastal ecosystems, particularly coral reefs, has produced increased interest in remote sensing as a tool for the management and monitoring of these valuable natural resources. Hyperspectral capabilities show promising results in this regard, but as yet remain somewhat hindered by the technical and physical issues concerning the intervening water layer. One such issue is the ability to atmospherically correct images over shallow aquatic areas, where complications arise due to varying effects from specular reflection, wind blown surface waves, and reflectance from the benthic substrate. Tafkaa, an atmospheric correction algorithm under development at the U.S. Naval Research Laboratory, addresses these variables and provides a viable approach to the atmospheric correction issue. Using imagery from the Advanced Visible InfraRed Imaging Spectrometer (AVIRIS) over two shallow coral ecosystems in the Hawai ian Islands, French Frigate Shoals and Kane ohe Bay, we first demonstrate how land-based atmospheric corrections can be limited in such an environment. We then discuss the input requirements and underlying algorithm concepts of Tafkaa and conclude with examples illustrating the improved performance of Tafkaa using the same AVIRIS images.

Goodman, James A.↗
NASA NTRSDate not supplied

Overview of GSICS visible calibration methods.

Global Space-based Inter-Calibration System (GSICS) is an international collaborative effort initiated in 2005 by the World Meteorological Organization (WMO) and the Coordination Group for Meteorological Satellites (CGMS) to 1-monitor, 2-improve and 3-harmonize the quality of observations from operational weather and environmental satellites of the Global Observing System (GOS). GSICS aims at ensuring consistent accuracy among space-based observations worldwide for climate monitoring, weather forecasting, and environmental applications by 1-monitoring instrument performance, 2-operational inter-calibration of satellite instruments, 3-radiometrically scaling observations to absolute reference standards, 4-recalibration of archived datasets. Although many of the GSIC visible inter-calibration methods are based on medium pixel-level imagers such as MODIS, VIIRS, AVHRR, and geostationary sensors, the methods are applicable to high spatial resolution imagery such as Landsat. For sensor inter-calibration efforts, coincident ray-matched reflectance pairs are used to transfer the calibration from the reference to the target instrument. Spectral band adjustment factors (SBAF) are applied to account for any spectral band differences. For sensor stability monitoring, PICS, deep convective cloud (DCC) and polar ice Earth viewed targets are utilized. GSICS uses the moon for stability monitoring by using the GSICS Implementation of the USGS Robotic Lunar Observatory (ROLO) model (GIRO). GSICS is looking forward to the launch of CLARREO on the international space station (ISS) in 2023. The CLARREO hyperspectral reflective solar band (RSB) sensor will establish an absolute calibration reference in space, which will characterize invariant targets and will inter-calibrate concurrent sensors. Examples of these calibration methods will be presented at the workshop.

Visible calibration methods↗
NASA NTRS2022

An Assessment of SNPP and NOAA20 VIIRS RSB Calibration Performance in NASA SIPS Reprocessed Collection-2 L1B Data Products

Two VIIRS sensors onboard the SNPP and NOAA20 satellites have been successfully operating for over 10 and 4 years, respectively, providing the worldwide user community with high-quality imagery and radiometric measurements of the land, atmosphere, cryosphere, and oceans. This study provides a temporal radiometric stability and calibration consistency assessment of the SNPP and NOAA20 VIIRS reflective solar bands using the latest NASA SIPS C2 L1B products. Several independent vicarious approaches are used to examine the stability of SNPP VIIRS and consistency of the at-sensor reflectance between the two VIIRS instruments. These approaches include observations from simultaneous nadir overpasses, the Libya-4 desert and Dome C snow/ice sites, and deep convective clouds. The impact of existing band spectral differences on the reflectance measurements is accounted for utilizing scene-specific hyperspectral observations provided by the SCIAMACHY sensor onboard the ENVISAT platform. Results indicate that both SNPP and NOAA20 VIIRS reflectances are stable within 1% over their mission periods for all bands, except for a few bands in the visible range from SNPP VIIRS that show more upward drifts at high radiances. NOAA20 VIIRS reflectances are systematically lower than SNPP by 2 to 4% for most bands, with the exception of few short wavelength bands where it is seen to be up to 7%.

VIIRS↗
NASA NTRS2026

Proactive Wildfire Management: A Remote Sensing and Multimodal CNN-MLP Architecture for Ignition Risk Forecasting

As the frequency and intensity of wildfires increase, with fire seasons now starting earlier and ending later than they have over the past decades, current monitoring systems, such as lookout towers and satellites, are hindered by cloud cover, low-resolution imagery, and static data gaps that fail to track vegetation moisture levels fast enough to catch rapid pre-ignition changes. This report proposes a Machine Learning-enabled Wildfire Ignition Prediction framework that combines satellite monitoring with dynamic and high-resolution remote sensing from Unmanned Aerial Vehicle (UAV) swarms. The method would use multispectral and thermal data from the Landsat program to create a baseline for vegetation health, calculating a two-band Enhanced Vegetation Index (EVI2) and the moisture content of the vegetation. These inputs will later be fused with microscale UAV weather data, including thermal hotspots found through thick canopies, hyperspectral chemical signatures of pre-visual combustion, and local weather streams. The multispectral satellite, multispectral Light Detection and Ranging (LiDAR), and thermal data would then be processed through a Convolutional Neural Network (CNN), alongside a Multilayer Perceptron (MLP) for the micro-weather telemetry. The outputs of these networks would be fused into a single feature representation and passed through a final prediction network to generate real-time ignition risk scores and hotspot alerts. Model performance would be assessed using standard classification metrics, including a Receiver Operating Characteristic - Area Under the Curve (ROC AUC) and F1 score. This system would allow first responders to identify high-risk zones and intervene before ignition occurs, improving emergency response time compared to current approaches.

machine learning↗
NASA NTRSDate not supplied

A Deep Neural Network for Achieving Spectrally Consistent and Seamless Infrared Radiance Measurements Across Geostationary Satellite Domains

The NASA Clouds and the Earth's Radiant Energy System (CERES) project provides the scientific community with observed top-of-atmosphere (TOA) shortwave and longwave fluxes for climate monitoring and climate model validation. To achieve this goal, CERES relies on TOA broadband fluxes derived from geostationary satellite (GEO) imagery to account for the diurnal flux variations between the CERES observation intervals. Consistent global flux derivation depends on accurate and consistent cloud retrievals. Scene-dependent spectral measurement inconsistency of the instruments that make up the contiguous ring of GEO observations (GEO-Ring), as well as limb darkening effects, can cause discontinuities in derived cloud properties and radiative fluxes at the boundaries of adjacent imager domains. Although the algorithms utilize radiative transfer models to account for instrument-band-dependent atmospheric correction and viewing zenith angle (VZA) dependency, small discontinuities may persist due to uncertainties inherent to the multiple imager-specific algorithms. Furthermore, while hyperspectral-instrument-based spectral band adjustment factors may effectively account for spectrally induced bias, they are less effective at reducing variance owed to the specific composition of the viewed scene, which is challenging to robustly characterize. As such, this article highlights the use of a deep neural network (DNN) to resolve spectral-and VZA-induced biases between GEO-Ring imagers. The DNN uses available infrared (IR) channels from the GEO instruments, along with viewing and solar illumination geometry, to estimate homogenized, VIIRS-like IR radiances for use in the GEO cloud algorithm. This approach is effective at mitigating scene-dependent spectral variance and VZA dependency, resulting in consistent radiance measurements across the GEO-Ring, thereby leading toward a more seamless global cloud assessment.

deep learning↗