Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “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 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
NASA NTRS2007

Spatial and Temporal Varying Thresholds for Cloud Detection in Satellite Imagery

A new cloud detection technique has been developed and applied to both geostationary and polar orbiting satellite imagery having channels in the thermal infrared and short wave infrared spectral regions. The bispectral composite threshold (BCT) technique uses only the 11 micron and 3.9 micron channels, and composite imagery generated from these channels, in a four-step cloud detection procedure to produce a binary cloud mask at single pixel resolution. A unique aspect of this algorithm is the use of 20-day composites of the 11 micron and the 11 - 3.9 micron channel difference imagery to represent spatially and temporally varying clear-sky thresholds for the bispectral cloud tests. The BCT cloud detection algorithm has been applied to GOES and MODIS data over the continental United States over the last three years with good success. The resulting products have been validated against "truth" datasets (generated by the manual determination of the sky conditions from available satellite imagery) for various seasons from the 2003-2005 periods. The day and night algorithm has been shown to determine the correct sky conditions 80-90% of the time (on average) over land and ocean areas. Only a small variation in algorithm performance occurs between day-night, land-ocean, and between seasons. The algorithm performs least well. during he winter season with only 80% of the sky conditions determined correctly. The algorithm was found to under-determine clouds at night and during times of low sun angle (in geostationary satellite data) and tends to over-determine the presence of clouds during the day, particularly in the summertime. Since the spectral tests use only the short- and long-wave channels common to most multispectral scanners; the application of the BCT technique to a variety of satellite sensors including SEVERI should be straightforward and produce similar performance results.

Jedlovec, Gary↗
NASA NTRS2007

Processing Satellite Imagery To Detect Waste Tire Piles

A methodology for processing commercially available satellite spectral imagery has been developed to enable identification and mapping of waste tire piles in California. The California Integrated Waste Management Board initiated the project and provided funding for the method s development. The methodology includes the use of a combination of previously commercially available image-processing and georeferencing software used to develop a model that specifically distinguishes between tire piles and other objects. The methodology reduces the time that must be spent to initially survey a region for tire sites, thereby increasing inspectors and managers time available for remediation of the sites. Remediation is needed because millions of used tires are discarded every year, waste tire piles pose fire hazards, and mosquitoes often breed in water trapped in tires. It should be possible to adapt the methodology to regions outside California by modifying some of the algorithms implemented in the software to account for geographic differences in spectral characteristics associated with terrain and climate. The task of identifying tire piles in satellite imagery is uniquely challenging because of their low reflectance levels: Tires tend to be spectrally confused with shadows and deep water, both of which reflect little light to satellite-borne imaging systems. In this methodology, the challenge is met, in part, by use of software that implements the Tire Identification from Reflectance (TIRe) model. The development of the TIRe model included incorporation of lessons learned in previous research on the detection and mapping of tire piles by use of manual/ visual and/or computational analysis of aerial and satellite imagery. The TIRe model is a computational model for identifying tire piles and discriminating between tire piles and other objects. The input to the TIRe model is the georeferenced but otherwise raw satellite spectral images of a geographic region to be surveyed. The TIRe model identifies the darkest objects in the images and, on the basis of spatial and spectral image characteristics, discriminates against other dark objects, which can include vegetation, some bodies of water, and dark soils. The TIRe model can identify piles of as few as 100 tires. The output of the TIRe model is a binary mask showing areas containing suspected tire piles and spectrally similar features. This mask is overlaid on the original satellite imagery and examined by a trained image analyst, who strives to further discriminate against non-tire objects that the TIRe model tentatively identified as tire piles. After the analyst has made adjustments, the mask is used to create a synoptic, geographically accurate tire-pile survey map, which can be overlaid with a road map and/or any other map or set of georeferenced data, according to a customer s preferences.

Skiles, Joseph↗
NASA NTRS2012

Detection of Coccolithophore Blooms in Ocean Color Satellite Imagery: a Generalized Approach for Use with Multiple Sensors

A generalized coccolithophore bloom classifier has been developed for use with ocean color imagery. The bloom classifier was developed using extracted satellite reflectance data from SeaWiFS images screened by the default bloom detection mask. In the current application, we extend the optical water type (OWT) classification scheme by adding a new coccolithophore bloom class formed from these extracted reflectances. Based on an in situ coccolithophore data set from the North Atlantic, the detection levels with the new scheme were between 1,500 and 1,800 coccolithophore cellsmL and 43,000 and 78,000 lithsmL. The detected bloom area using the OWT method was an average of 1.75 times greater than the default bloom detector based on a collection of SeaWiFS 1 km imagery. The versatility of the scheme is shown with SeaWiFS, MODIS Aqua, CZCS and MERIS imagery at the 1 km scale. The OWT scheme was applied to the daily global SeaWiFS imagery mission data set (years 19972010). Based on our results, average annual coccolithophore bloom area was more than two times greater in the southern hemisphere compared to the northern hemi- sphere with values of 2.00 106 km2 and 0.75 106 km2, respectively. The new algorithm detects larger bloom areas in the Southern Ocean compared to the default algorithm, and our revised global annual average of 2.75106 km2 is dominated by contributions from the Southern Ocean.

chlorophyll fluorescence↗
NASA NTRS2016

Geocam Space: Enhancing Handheld Digital Camera Imagery from the International Space Station for Research and Applications

Handheld astronaut photography of the Earth has been collected from the International Space Station (ISS) since 2000, making it the most temporally extensive remotely sensed dataset from this unique Low Earth orbital platform. Exclusive use of digital handheld cameras to perform Earth observations from the ISS began in 2004. Nadir viewing imagery is constrained by the inclined equatorial orbit of the ISS to between 51.6 degrees North and South latitude, however numerous oblique images of land surfaces above these latitudes are included in the dataset. While unmodified commercial off-the-shelf digital cameras provide only visible wavelength, three-band spectral information of limited quality current cameras used with long (400+ mm) lenses can obtain high quality spatial information approaching 2 meters/ground pixel resolution. The dataset is freely available online at the Gateway to Astronaut Photography of Earth site (http://eol.jsc.nasa.gov), and now comprises over 2 million images. Despite this extensive image catalog, use of the data for scientific research, disaster response, commercial applications and visualizations is minimal in comparison to other data collected from free-flying satellite platforms such as Landsat, Worldview, etc. This is due primarily to the lack of fully-georeferenced data products - while current digital cameras typically have integrated GPS, this does not function in the Low Earth Orbit environment. The Earth Science and Remote Sensing (ESRS) Unit at NASA Johnson Space Center provides training in Earth Science topics to ISS crews, performs daily operations and Earth observation target delivery to crews through the Crew Earth Observations (CEO) Facility on board ISS, and also catalogs digital handheld imagery acquired from orbit by manually adding descriptive metadata and determining an image geographic centerpoint using visual feature matching with other georeferenced data, e.g. Landsat, Google Earth, etc. The lack of full geolocation information native to the data makes it difficult to integrate astronaut photographs with other georeferenced data to facilitate quantitative analysis such as urban land cover/land use classification, change detection, or geologic mapping. The manual determination of image centerpoints is both time and labor-intensive, leading to delays in releasing geolocated and cataloged data to the public, such as the timely use of data for disaster response. The GeoCam Space project was funded by the ISS Program in 2015 to develop an on-orbit hardware and ground-based software system for increasing the efficiency of geolocating astronaut photographs from the ISS (Fig. 1). The Intelligent Robotics Group at NASA Ames Research Center leads the development of both the ground and on-orbit systems in collaboration with the ESRS Unit. The hardware component consists of modified smartphone elements including cameras, central processing unit, wireless Ethernet, and an inertial measurement unit (gyroscopes/accelerometers/magnetometers) reconfigured into a compact unit that attaches to the base of the current Nikon D4 camera - and its replacement, the Nikon D5 - and connects using the standard Nikon peripheral connector or USB port. This provides secondary, side and downward facing cameras perpendicular to the primary camera pointing direction. The secondary cameras observe calibration targets with known internal X, Y, and Z position affixed to the interior of the ISS to determine the camera pose corresponding to each image frame. This information is recorded by the GeoCam Space unit and indexed for correlation to the camera time recorded for each image frame. Data - image, EXIF header, and camera pose information - is transmitted to the ground software system (GeoRef) using the established Ku-band USOS downlink system. Following integration on the ground, the camera pose information provides an initial geolocation estimate for the individual film frame. This new capability represents a significant advance in geolocation from the manual feature-matching approach for both nadir and off-nadir viewing imagery. With the initial geolocation estimate, full georeferencing of an image is completed using the rapid tie-pointing interface in GeoRef, and the resulting data is added to the Gateway to Astronaut Photography of Earth online database in both Geotiff and Keyhole Markup Language (kml) formats. The integration of the GeoRef software component of Geocam Space into the CEO image cataloging workflow is complete, and disaster response imagery acquired by the ISS crew is now fully georeferenced as a standard data product. The on-orbit hardware component (GeoSens) is in final prototyping phase, and is on-schedule for launch to the ISS in late 2016. Installation and routine use of the Geocam Space system for handheld digital camera photography from the ISS is expected to significantly improve the usefulness of this unique dataset for a variety of public- and private-sector applications.

Stefanov, William L.↗
NASA NTRS2018

Enabling Technologies for Deep Space Motion Imagery

From the beginning of the Space Age, imagery, particularly motion imagery, has been a part of crewed and uncrewed missions. As technologies have evolved the imagery gets better, more compelling, and more useful for operations and monitoring of systems, crew, and spacecraft. Film, video and live television have engaged the public and sparked the imaginations of engineers, scientists, and artists alike. As we look forward now to crewed missions beyond low-Earth orbit, such as the Deep Space Gateway being considered as a pre-cursor to future crewed Mars missions, there are both opportunities and challenges in implementing a multi-faceted imaging system that advances mission capabilities and technology.This paper will present a vision for an imaging system that is relevant for operations of the ISS and future crewed missions in deep space, with a detailed look at some of the key innovative technologies required to enable such a system. In addition, impacts to Space Operations, video distribution to the public and to science investigators, and video system interoperability will be presented. Opportunities where standardization can enable interoperability are also identified for those imagery and communications functions planned for inclusion in the Consultative Committee for Space Data Systems (CCSDS) Blue Book.

Grubbs, Rodney↗
NASA NTRS2018

NASA's Land, Atmosphere Near Real-Time Capability for EOS (LANCE): Delivering Data and Imagery to Meet the Needs of Near Real-Time Applications

NASA's Land, Atmosphere Near real-time Capability for EOS (LANCE) is a virtual system that provides near real-time EOS data and imagery from the AIRS, AMSR2, LIS (ISS), MISR, MLS, MODIS, MOPITT, OMI, OMPS, and VIIRS instruments, to meet the needs of scientists and application users interested in monitoring a wide variety of natural and man-made phenomena. NRT imagery from LANCE are available through NASA's Global Imagery Browse Services (GIBS), Worldview, FIRMS and most recently through Worldview Snapshots – a low band width application that has replaced the Rapid Response Subsets. Over the past year: data and imagery from the Lightning Imaging Sensor (LIS) on board the International Space Station (ISS), OMPS and VIIRS-Land have been added to LANCE. In the coming year LANCE will integrate the MODIS NRT Global Flood product, VIIRS Black Marble nighttime lights and Cloud Mask and Aerosol Dark Target from VIIRS Atmosphere. Here we provide a brief overview of LANCE, focusing on what's new and describing how these new data sets have been used to monitor lightning flashes, hurricanes and fires. For more information on LANCE visit: https://earthdata.nasa.gov/lance.

Davies, Diane↗
NASA NTRS2019

Towards the Development of Real-Time Normalized Burn Ratio (NBR) and Delta NBR Imagery from GOES-16/17 and S-NPP

Burned landscapes present difficult hydrologic forecasting challenges for National Weather Service Offices. Burned soils and landscapes can be conducive to the development of flash flooding and landslides from heavy precipitation events. The severity of the burn scar can be directly related to the risk for debris flows and flash flooding. Burned Area Reflectance Classification (BARC) map is generated to indicate the degree of burn severity, which is generated initially by high-resolution satellite imagery from sources such as Landsat, and later by labor-intensive efforts conducted at the burn scar by Burned Area Emergency Response (BAER) teams. The challenge for operational meteorologists is that these sources of information are not readily available in near real-time. Landsat imagery, for example, may only be available about once every eight days, and cloudy conditions can obstruct the observation of the burn scar during a single pass. BAER teams cannot conduct assessments until the wildfire has been at least 40 percent contained (up to 80 percent in some regions), and the process itself can take further days to weeks to complete depending on a number of factors. To help remedy this lapse in knowledge, NASA SPoRT has developed the generation of NBR imagery in the Advanced Weather Interactive Processing System (AWIPS) using data from the operational GOES 16 and 17 satellites and S-NPP. This presentation will discuss the development of the GOES- and SNPP-derived NBR and dNBR imagery and their initial evaluation by real-time decision makers.

Berndt, Emily↗
NASA NTRS2021

Generating Flood Probability Map Based on Combined Use of Synthetic Aperture Radar and Optical Imagery

Despite a lot of efforts to respond flood hazards with remote sensing data, it is still difficult to generate an accurate flood map using solely optical or radar imagery. While optical data is relatively high-resolution and does not suffer from speckle noise compared to radar data, it is very likely to be impacted by cloud and shadow. On the other hand, radar imagery can be used in all weather conditions due to its capability of penetrating clouds. Although a significant improvement of flood monitoring capability is achieved by using radar data, it is still challenging to map urban floods because of strong backscattering by man-made structures. Therefore, complementary use of optical and radar imagery in flood response is required, particularly in urban areas. In this study, we have adopted the Bayesian Joint Probability function to combine two different flood products generated from SAR and optical imagery. Flood detection with SAR data relies on the difference of backscatter signals between standing water and rougher land surface, while a Normalized Difference Water Index (NDWI) approach is used for optical data. Specifically, Planet Dove data with its 3m spatial resolution is used with higher weight values to detect flood extent in urban areas.

floods↗
NASA NTRS2022

Integrated Topographic Corrections Improve Forest Mapping Using Landsat Imagery

In mountainous environments, topography strongly affects the reflectance due to illumination effects and cast shadows, which introduce errors in land cover classifications. However, topographic correction is not routinely implemented in standard data pre-processing chains (e.g., Landsat Analysis Ready Data), and there is a lack of consensus whether topographic correction is necessary, and if so, how to conduct it. Furthermore, methods that correct simultaneously for atmospheric and topographic effects are becoming available, but they have not been compared directly. Our objects were to investigate (1) the effectiveness of two topographic correction approaches that integrate atmospheric and topographic correction, (2) improvements in classification accuracy when analyzing topographically corrected single-date imagery (14 July 2016 and 2 October 2016), versus a full Landsat time series from 2014 to 2016, and 3) improvements in classification accuracy when including additional terrain information (i.e., topographic slope, elevation, and aspect). We developed a physical based model and compared it with an enhanced C-correction, both of which integrate atmospheric and topographic correction. We compared classification accuracies with and without topographic correction using combinations of single-date imagery, image composites and spectral-temporal metrics generated from the full Landsat time series, and additional terrain information in the Caucasus Mountains. We found that both the enhanced C-correction and the physical model performed very well and largely eliminated the correlation (Pearson’s correlation coefficient r ranges from 0.06 to 0.24) between surface reflectance and illumination condition, but the physical model performed best (r ranges from 0.05 to 0.11). Both image composites, and spectral-temporal metrics generated from corrected imagery, resulted in significantly (p ≤ 0.05) higher classification accuracies and better forest classifications, especially for the mixed forests. Adding terrain information reduced classification error significantly, but not as much as topographic correction. In summary, topographic correction remains necessary, even when analyzing a full Landsat time series and including a digital elevation model in the classification. We recommend that topographic correction should be applied when analyzing Landsat satellite imagery in mountainous region for forest cover classification.

Atmospheric correction↗
NASA NTRSDate not supplied

FloodPlanet: High-Resolution Commercial Imagery for Training and Validation of Deep Learning-Based Models of Inundation Extent

Flooding events are becoming increasingly frequent worldwide and are known to cause extensive damage. Public optical and radar satellite imagery can be used to detect large areas of inundation in rural areas, however, long revisit times and coarse spatial resolution limit applications for short-lived events and urban areas. Commercial constellations such as those operated by Planet offer increased spatial and temporal resolution and can supplement mapping efforts to provide more information to disaster response, relief, and mitigation efforts. Deep learning requires high quality labeled data for training across coincident sensors. The FloodPlanet dataset presented here contains labeled surface water for 18 events across the world based on Planetscope imagery with coincident Harmonized Landsat Sentinel-2 ( HLS) or Sentinel-1 and builds upon the previously existing Sen1Floods11, xBD, and NASA Sentinel-1 datasets. Sen1Floods11 includes 4,831 512x512 pixel overlapping tiles of coincident Sentinel-1 and Sentinel-2 data observing 11 flood events across the world from 2017-2019. The dataset contains a combination of automated and hand-labeled surface water for use in training and validation of inundation modeling efforts. The xBD dataset identifies flood-damaged buildings and indicates the scale of damage to each (none, minor, moderate, and major) from four flood events which occurred in the United States, India, Nepal, and Bangladesh from the same time period. The NASA dataset contains hand-labeled water bodies observed in Sentinel-1 imagery during five flood events within the 2017-2019 period. The effort presented here utilizes observations from these previously investigated flood events to generate labels of surface water at the 3-5m spatial resolution provided by Planetscope and facilitate the comparison between public and commercial data. A data pipeline was built which uses clustering algorithms to pick the most suitable overlapping chips between the public data and PlanetScope data for manual labeling. Labels were created manually using NASA’s ImageLabeler tool and include areas of high- and low-confidence water. The high confidence designation is reserved for areas of open, unobstructed water while low confidence is used for areas of suspected water beneath vegetation, clouds, or cloud shadows. Expected to be released in late 2022, the FloodPlanet dataset will include tiled imagery with a unique ID for each 1024x1024 pixel tile, 7 bands of HLS data, and high- and low-confidence flood labels in both shapefile and tiff formats. The authors will follow Spatial Temporal Access Catalog (STAC) guidelines to release FloodPlanet on the Radiant Earth ML hub, which hosts public datasets for machine learning.

Alexander Melancon↗
NASA NTRSDate not supplied

Designing and Evaluating NASA SPoRT Center’s DustTracker-AI Model for Detecting Dust in NASA/NOAA Geostationary Satellite Imagery

- Near real-time identification of airborne dust in satellite imagery is important for mitigating the adverse effects of dust storms on human activities. - False color Red-Green-Blue (RGB) imagery has been used for dust detection, but it has limitations and can be difficult to interpret. - The NASA Short-term Research and Transition (SPoRT) center has developed a night-time dust detection random forest (NT-DustTracker-AI, Berndt et al. 2021) model using NASA/NOAA Geostationary Operational Environmental Satellite-16 (GOES-16) Advanced Baseline Imager (ABI) infrared imagery as inputs. - The SPoRT center has partnered with the NOAA National Weather Service to evaluate the model for use in weather forecasting operations, and preliminary results have been positive. - The SPoRT center has expanded the model to cover both day and night, continuing to use infrared imagery as inputs. This new model, known as DustTracker-AI, has shown good agreement with available dust observations

Robert A. Junod↗
NASA NTRS2022

Using commercial high-resolution satellite imagery to monitor a nuisance macroalga in the largest marine protected area in the U.S.A.

Satellite imagery is a useful tool for monitoring and mapping the distribution of invasive or nuisance algal species on coral reefs over the temporal and spatial scales needed for ecosystem management. Visual inspections of high-resolution satellite imagery were used to detect the newly discovered nuisance alga, Chondria tumulosa , at Manawai (Pearl and Hermes Atoll) in combination with ground-truthing surveys. Low-albedo (“dark”) survey sites on spur habitats were associated with mean C. tumulosa cover seven times higher than adjacent high-albedo (“light”) sites. There was an inverse relationship between C. tumulosa percent cover at ground-truthing sites and mean reflectance values. Archival satellite imagery showed that areas of high C. tumulosa cover (i.e., dark patches) were not evident on or before 2015 on the northeast backreef. This case study is the first to apply satellite imagery to target a nuisance red macroalgal bloom on a coral reef. The ability to use satellites for the detection of nuisance or invasive benthic species, such as expansive mats of C. tumulosa , provides managers with a valuable tool, especially in remote regions.

Invasive↗
NASA NTRS2023

Front Range Wildland Fires: Evaluating the Efficacy of Remote Sensing Imagery in Monitoring Forest Fuels Treatment Methods

Over the last several decades, wildfire frequency and severity in forested areas along Colorado’s Front Range have increased due to a buildup of fuels. This has led to an increase in forest treatments, as well as an increased need to evaluate the success of these treatments. Remote sensing products offer an efficient and cost-effective way to monitor forest treatments; however, not all remote sensing products and analysis techniques have been explored by Coloradan land managers. Specifically, project partners at the Colorado State Forest Service (CSFS) and the Colorado Forest Restoration Institute (CFRI) were interested in using an effective and streamlined method of mapping canopy cover to better monitor forest treatment success. To support their needs, the NASA DEVELOP Front Range Wildland Fires team explored National Agricultural Imagery Program (NAIP) imagery at different spatial resolutions and numbers of training points with NASA’s Shuttle Radar Topography Mission (SRTM) Data Elevation Model (DEM) as a predictor in addition to NAIP imagery spectral predictors. From this analysis, we created classified canopy cover rasters, and compared accuracy metrics across model iterations. We also determined that the best performing model, with an overall accuracy of 0.900 uses 2021 NAIP imagery at 2-meter resolution, 800 training points, 200 testing points, does not use topographic predictors, and reclassifies shadow pixels via a pre-selected NDVI threshold.

Remote Sensing↗
DOE OSTI2022

Panel-Segmentation: A Python Package for Automated Solar Array Metadata Extraction Using Satellite Imagery

The NREL Python Panel-Segmentation package is a toolkit that automates the process of extracting accurate and valuable metadata related to solar array installations, using publicly available Google Maps satellite imagery. Previously published work includes automated azimuth estimation for individual solar installations in satellite images. Our continued research focuses on automated detection and classification of solar installation mounting configuration (tracking or fixed-tilt; rooftop, ground, or carport). Specifically, a Faster-RCNN Resnet-50 feature pyramid network (FPN) model was trained and validated on 862 manually labeled satellite images. This model was used to perform object detection on satellite imagery, locating and classifying individual solar installations' mounting configuration and type. Model results showed a mean average precision score (mAP) of 77.79%, with the model strongest at detecting fixed-tilt ground mount and fixed-tilt carport installations. The object detection model and its outputs have been incorporated into the Panel-Segmentation package's automated metadata extraction pipeline, which returns the mounting configuration and azimuth for individual solar arrays in satellite imagery. The complete image data set with labels has been released on the U.S. Department of Energy (DOE) DuraMAT DataHub, to encourage further research in this area.

deep learning↗
DOE OSTI2026

Integrating very-high-resolution imagery, Sentinel-2 time-series data, and machine learning to map shrub fractional abundance across arid and semi-arid ecosystems in China

Shrub fractional abundance (SFA), the proportion of shrub cover per unit area, serves as a critical indicator of environmental aridity and ecosystem health in arid and semi-arid regions, particularly across the Mongolian steppe. However, large-scale SFA mapping in Mongolian steppe ecosystems remains challenging due to the small crown size of shrubs, their sparse distribution, and spectral overlap with coexisting low vegetation (e.g., grasses and herbs), which hinders accurate detection using coarser-resolution satellite data or traditional field surveys. To address these challenges, we developed a two-step approach that integrates very-high-resolution (VHR) imagery, time-series Sentinel-2 data, and deep learning techniques. First, we generated high-accuracy benchmark maps of individual shrub crowns from 0.5 m VHR imagery by combining manual segmentation with a hybrid deep learning framework (Dino V2 and convolutional neural networks). Second, we used these shrub crown maps as training data to build an XGBoost model for predicting SFA from 20 m Sentinel-2 time-series data, leveraging phenological information to improve estimation. We validated our approach across 70 sites (1km 2 each) in the Inner Mongolia Autonomous Region, which is representative of Mongolian steppe ecosystems. From VHR imagery, we mapped 1.31 million shrub crowns with an accuracy of R 2 = 0.92. Scaling up with Sentinel-2 data yielded regional SFA maps with an R 2 = 0.60. Further SHAP (SHapley Additive exPlanations) analysis on the developed XGBoost model revealed that phenological metrics (particularly observations in early-May, mid-July, and late-September), which distinguish shrub phenology from that of other land cover types (e.g., grasses and bare soil), were the most influential predictors of SFA. Finally, our regional SFA maps uncovered unimodal relationships between shrub distribution and climate variables, peaking at mean annual minimum temperatures near 0 °C and annual precipitation around 200 mm. Collectively, these findings demonstrate how the integration of multi-source remote sensing and machine learning can overcome historical limitations in SFA mapping, enabling accurate, spatially continuous assessments across vast Inner-Mongolian steppe ecosystems. Our framework has the potential to be applied to other steppe ecosystems and dryland ecosystems across the Mongolian steppe and beyond, offering a foundation for improved monitoring and ecological impact assessments in the face of global climate changes.

Arid and semi-arid landscapes↗
DOE OSTI2021

The Illumination of Thunderclouds by Lightning: 4. Volumetric Thunderstorm Imagery

Optical instruments such as the Geostationary Lightning Mapper (GLM) detect lightning based on transient changes in cloud illumination. The horizontal location of lightning is determined from the coordinates of the pixels on the imaging array illuminated during the flash. However, the vertical position of the lightning pulses (approximated by GLM “groups”) below the cloud top cannot be routinely measured from a single space-based instrument. In our prior work, we have developed a machine learning algorithm that can infer optical source altitude for a given pulse based on how the optical energy is distributed across the group footprint and the local Advanced Baseline Imager Cloud-Top Height (CTH). In this fourth part of our thundercloud illumination study, we leverage these source altitudes to generate volumetric GLM imagery of a Colombia thunderstorm. We find that 3D versions of the current GLM meteorological imagery products (that describe thunderstorm kinematics) and thundercloud imagery products (that depict how the flashes appear from space) provide additional insights into lightning activity in the thunderstorm that are lost in the vertical integration used to generate the current 2D GLM gridded products. This new volumetric imaging capability provides a more comprehensive picture of where lightning occurs in the storm, how its physical characteristics vary across three-dimensional space, and how its optical emissions interact with surrounding the cloud medium.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

A Machine Learning Framework for Predicting Microphysical Properties of Ice Crystals From Cloud Particle Imagery

The microphysical properties of ice crystals are important because they significantly alter the radiative properties and spatiotemporal distributions of clouds, which in turn strongly affect Earth's climate. However, it is challenging to measure key properties of ice crystals, such as mass or morphological features. Here, we present a proof-of-concept framework for predicting three-dimensional (3D) microphysical properties of ice crystals from in situ two-dimensional (2D) imagery. First, we computationally generated synthetic ice crystals using 3D modeling software along with geometric parameters estimated from the 2021 Ice Cryo-Encapsulation Balloon (ICEBall) field campaign. Then, we used synthetic crystals to train machine learning (ML) models to predict effective density ($ρ_e$), effective surface area ($A_e$), and number of bullets ($N_b$) from synthetic rosette imagery. On unseen synthetic images, our ML models accurately predicted ice crystal properties. ResNet-18 performed best, achieving $R^2$ values of 0.99 and 0.98 for $ρ_e$ and $A_e$, respectively, and MAE of 0.10 for mathematical equation in single view tasks. Stereo view ResNet-18 further reduced RMSE by 40% for $ρ_e$ and $A_e$ and reduced MAE by 0.08 for $N_b$. This work provides a novel ML-driven framework for estimating ice microphysical properties from in situ imagery, which will allow for downstream constraints on microphysical parameterizations, such as the mass-size relationship.

Ko, J. [Columbia Univ., New York, NY (United State↗
DOE OSTI2022

UAV remote sensing imagery - Miscanthus trials 2020 - Energy Farm - UIUC

Aerial imagery utilized as input in the manuscript "Deep convolutional neural networks exploit high spatial and temporal resolution aerial imagery to predict key traits in miscanthus" . Data was collected over M. Sacchariflorus and Sinensis breeding trials at the Energy Farm, UIUC in 2020. Flights were performed using a DJI M600 mounted with a Micasense Rededge multispectral sensor at 20 m altitude around solar noon. Imagery is available as tif file by field trial and date (10). The post-processing of raw images into orthophoto was performed in Agisoft Metashape software. Each crop surface model and multispectral orthophoto was stacked into an unique raster stack by date and uploaded here. Each raster stack includes 6 layers in the following order: Layer 1 = crop surface model, Layer 2 = Blue, Layer 3 = Green, Layer 4 = Red, Layer 5 = Rededge, and Layer 6 = NIR multispectral bands. Msa raster stacks were resampled to 1.67 cm spatial resolution and Msi raster stacks were resampled to 1.41 cm spatial resolution to ease their integration into further analysis. 'MMDDYYYY' is the date of data collection, 'MSA' is M. Sacchariflorus trial, 'MSI' is Miscanthus Sinensis trial, 'CSM' is crop surface model layer, and 'MULTSP' are the five multispectral bands.

bioenergy↗