SEARCH · Engineering Papers

Results for “remote training”

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

SourceResearch connectionFrom yearThrough year

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

At least 613 records · Page 34

All sources NASA NTRS DOE OSTI

NASA NTRS2023

Toward Physics-informed Neural Networks for 3D Multi-layer Cloud Mask Reconstruction

Three-dimensional (3D) cloud retrievals are critical for understanding their impact on climate and other applications such as aviation safety, weather prediction, and remote sensing. However, obtaining high-resolution and accurate vertical representation of clouds remains unsolved due to the limitations imposed by satellite instrumentation, viewing conditions, and the complexity of cloud dynamics. Cloud masks are essential for comprehending various cloud vertical properties, but deriving accurate 3D cloud masks from 2D satellite imagery data is a challenging task. To tackle these challenges, we introduce a physics-informed loss function for training deep learning models that can extend 2D cloud images into 3D cloud masks. The proposed loss, called CloudMask Loss, is composed of two domain knowledge-informed loss terms: one for evaluating cloud position and thickness, and the other for measuring the number of layers. By combining these loss terms, we improve the trainability of the deep learning models for more accurate and meaningful results. We apply the proposed loss function to different neural networks and demonstrate significant improvements in multi-layer cloud mask reconstruction. Utilizing the same neural network architecture, our proposed loss outperforms standard binary crossentropy loss in terms of multi-layer cloud classification accuracy, number of layers accuracy, and thickness mean absolute error (MAE). The proposed loss function can be readily integrated into various neural network architectures, resulting in substantial performance gains in 3D cloud mask generation.

multi-layer clouds↗

DOE OSTI2023

An Agenda for Multimodal Foundation Models for Earth Observation

Archives of remote sensing (RS) data are increasing swiftly as new sensing modalities with enhanced spatiotemporal resolution become operational. While promising new breakthroughs, the sheer volume of RS archives stretches the limits of human analysts and existing AI tools, as most models are: i) limited to single data modalities; ii) task-specific; iii) heavily reliant on labeled data. The emerging Foundation Models (FMs) have the potential to address these limitations. Trained on vast unlabeled datasets through self-supervised learning, FMs enable generic feature extraction that facilitate specialization to a wide variety of downstream tasks. This paper describes a vision towards an FM for multimodal Earth Observation data (FM4EO), discussing key building blocks and open challenges. We put particular emphasis on multimodal reasoning, a topic underexplored in EO. Our ultimate goal is a practical path toward FM4EO with capacity to unlock breakthroughs in few-shot learning scenarios, multimodal geographic knowledge integration, synthesis, and hypothesis generation.

Ambrozio Dias, Philipe↗

NASA NTRSDate not supplied

Remote Sensing of Lineage Functional Types for Modeling and Monitoring Biodiversity

Hyperspectral remote sensing has the potential to continuously scale plant function and plant diversity information from landscape to global extents. Numerous studies have indicated that VSWIR (400-2500 nm) reflectance properties of vegetation capture evolutionarily conserved biochemical, structural, and other functional attributes of plant species. Spectral properties conserved in plants provide the opportunity to both 1) aggregate species into lineages with improved classification accuracy and 2) link those lineages directly to plant traits. Full realization of this goal will enable parameterization of Land Surface Models (LSMs) with remotely sensed information, e.g., canopy nitrogen, and better representations of biodiversity and functional diversity in biogeographic studies. In this study, we use hyperspectral AVIRIS data from the 2013 HyspIRI campaign over the Southern Sierra Nevada, California flight box to investigate the potential for incorporating evolutionary thinking into landcover classification. We link the airborne hyperspectral data with vegetation plot data from roughly 1372 surveys and a phylogeny representing 1361 species. We aggregate species into lineages ranging from species level groups down to similar number of Plant Functional Types as often used in LSMs. We assessed the ability of Random Forest and Partial Least Squares Discriminant Analysis to discriminate across these different phylogenetic scales and determine the optimal number of lineages to classify. Although there are some temporal and spatial differences in our training data, our best approaches achieved moderate classification accuracy (Kappa > 0.65). Given an optimal number of lineages, we explored approaches to improve classifications including machine learning and unmixing approaches. This work suggests that lineage-based methods may be a promising way to leverage the huge amounts of data that will come from high resolution and high return interval hyperspectral data planned for the Surface Biology and Geology mission with sparsely sampled existing ground-based ecological data.

Hyperspectral↗

DOE OSTI2025

Detection of Diversion in a Realistic Heat Pipe Microreactor Using Supervised Machine Learning

Microreactors (MRs) pose new challenges for international safeguards. Here, their small size and mass reproducibility make them ideal for deployment in greater numbers and in remote locations, making the job of safeguards inspectors more challenging. Machine learning (ML) is currently being applied to many fields to augment human performance and increase automation; in particular, ML could be used to provide insight for international inspectors to help detect the diversion of nuclear fuel from MR cores. Four ML model types (k-nearest neighbors, decision tree, random forest, and histogram-based gradient boosted ensemble) were trained on integrated flux and critical control drum angle data generated with Serpent 2 for a realistic heat pipe MR design, achieving nearly 100% binary classification accuracy of nominal and diversion core configurations by the end of 1 full power year for three of the four model types. Regression model variants were also trained, using the same input data, for predicting the number of fuel pins diverted. Root-mean-square errors below 5% of the total number of fuel pins were achieved by the 1 full power year mark for all models.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗

NASA NTRS1976

Results from the Crop Identification Technology Assessment for Remote Sensing (CITARS) project

The author has identified the following significant results. It was found that several factors had a significant effect on crop identification performance: (1) crop maturity and site characteristics, (2) which of several different single date automatic data processing procedures was used for local recognition, (3) nonlocal recognition, both with and without preprocessing for the extension of recognition signatures, and (4) use of multidate data. It also was found that classification accuracy for field center pixels was not a reliable indicator of proportion estimation performance for whole areas, that bias was present in proportion estimates, and that training data and procedures strongly influenced crop identification performance.

Bauer, M. E.↗

DOE OSTI2025

Multi-frequency progressive refinement for learned inverse scattering

Interpreting scattered acoustic and electromagnetic wave patterns is a computational task that enables remote imaging in a number of important applications, including medical imaging, geophysical exploration, sonar and radar detection, and nondestructive testing of materials. However, accurately and stably recovering an inhomogeneous medium from far-field scattered wave measurements is a computationally difficult problem, due to the nonlinear and non-local nature of the forward scattering process. We design a neural network, called Multi-Frequency Inverse Scattering Network (MFISNet), and a training method to approximate the inverse map from far-field scattered wave measurements at multiple frequencies. We consider three variants of MFISNet, with the strongest performing variant inspired by the recursive linearization method — a commonly used technique for stably inverting scattered wavefield data — that progressively refines the estimate with higher frequency content. MFISNet outperforms past methods in regimes with high-contrast, heterogeneous large objects, and inhomogeneous unknown backgrounds.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1994

Simulation of arthroscopic surgery using MRI data

With the availability of Magnetic Resonance Imaging (MRI) technology in the medical field and the development of powerful graphics engines in the computer world the possibility now exists for the simulation of surgery using data obtained from an actual patient. This paper describes a surgical simulation system which will allow a physician or a medical student to practice surgery on a patient without ever entering an operating room. This could substantially lower the cost of medial training by providing an alternative to the use of cadavers. This project involves the use of volume data acquired by MRI which are converted to polygonal form using a corrected marching cubes algorithm. The data are then colored and a simulation of surface response based on springy structures is performed in real time. Control for the system is obtained through the use of an attached analog-to-digital unit. A remote electronic device is described which simulates an imaginary tool having features in common with both arthroscope and laparoscope.

Heller, Geoffrey↗

NASA NTRS2009

Smart Ultrasound Remote Guidance Experiment (SURGE) Preliminary Findings

To date, diagnostic quality ultrasound images were obtained aboard the International Space Station (ISS) using the ultrasound of the Human Research Facility (HRF) rack in the Laboratory module. Through the Advanced Diagnostic Ultrasound in Microgravity (ADUM) and the Braslet-M Occlusion Cuffs (BRASLET SDTO) studies, non-expert ultrasound operators aboard the ISS have performed cardiac, thoracic, abdominal, vascular, ocular, and musculoskeletal ultrasound assessments using remote guidance from ground-based ultrasound experts. With exploration class missions to the lunar and Martian surfaces on the horizon, crew medical officers will necessarily need to operate with greater autonomy given communication delays (round trip times of up to 5 seconds for the Moon and 90 minutes for Mars) and longer periods of communication blackouts (due to orbital constraints of communication assets). The SURGE project explored the feasibility and training requirements of having non-expert ultrasound operators perform autonomous ultrasound assessments in a simulated exploration mission outpost. The project aimed to identify experience, training, and human factors requirements for crew medical officers to perform autonomous ultrasonography. All of these aims pertained to the following risks from the NASA Bioastronautics Road Map: 1) Risk 18: Major Illness and Trauna; 2) Risk 20) Ambulatory Care; 3) Risk 22: Medical Informatics, Technologies, and Support Systems; and 4) Risk 23: Medical Skill Training and Maintenance.

Hurst, Victor↗

NASA NTRS2021

Highland Lakes Water Resources: Using NASA Earth Observations to Improve Detection Systems for Harmful Algal Events in the Highland Lakes in Central Texas

Beginning in 2019, harmful algal events in Austin, Texas, caused canine deaths in the Lady Bird Lake and Lake Travis reservoirs. These reservoirs are part of the larger Highland Lakes chain, managed by the Lower Colorado River Authority (LCRA) and the City of Austin Department of Watershed Protection (CoA DWP), which fulfill municipal, commercial, and agricultural water demands. Given the recent increase in favorable algal event conditions in central Texas, the LCRA and CoA DWP partnered with NASA DEVELOP to improve algal event early-warning systems through the application of remote sensing and machine learning. An Earth observation-based algal monitoring system will assist the responsible agencies in predicting algal conditions and communicating hazards to the public. The NASA DEVELOP team utilized Landsat 8 Operational Land Imager (OLI) and Sentinel-2 Multispectral Instrument (MSI) data to produce products including chlorophyll-a concentrations, cyanobacteria detections, turbidity, and water surface temperature. Chlorophyll-a concentrations were retrieved with a pre-trained machine learning model (mixture density network) and spectral indices, while the other products were derived from spectral indices. In situ field data were used to validate and quantify uncertainties for each product. The validations show strong correlations for chlorophyll-a and water surface temperature. Time series analyses of chlorophyll-a concentrations show peaks in the severe drought years (2015 and 2016). This project's resulting products enable monitoring of environmental proxies relevant to algal event presence in the Highland Lakes chain and will ultimately support water management, decision making, and risk communication.

Kaitlynn Hietpas↗

DOE OSTI2022

Automated detection of mild cognitive impairment and dementia from voice recordings: A natural language processing approach

Automated computational assessment of neuropsychological tests would enable widespread, cost-effective screening for dementia. A novel natural language processing approach is developed and validated to identify different stages of dementia based on automated transcription of digital voice recordings of subjects’ neuropsychological tests conducted by the Framingham Heart Study (n = 1084). Transcribed sentences from the test were encoded into quantitative data and several models were trained and tested using these data and the participants’ demographic characteristics. Average area under the curve (AUC) on the held-out test data reached 92.6%, 88.0%, and 74.4% for differentiating Normal cognition from Dementia, Normal or Mild Cognitive Impairment (MCI) from Dementia, and Normal from MCI, respectively. The proposed approach offers a fully automated identification of MCI and dementia based on a recorded neuropsychological test, providing an opportunity to develop a remote screening tool that could be adapted easily to any language.

neuropsychological↗

DOE OSTI2021

Early season prediction of within-field crop yield variability by assimilating CubeSat data into a crop model

Accurate early season predictions of crop yield at the within-field scale can be used to address a range of crop production, management, and precision agricultural challenges. While the remote sensing of within-field insights has been a research goal for many years, it is only recently that observations with the required spatio-temporal resolutions, together with efficient assimilation methods to integrate these into modeling frameworks, have become available to advance yield prediction efforts. Here we explore a yield prediction approach that combines daily high-resolution CubeSat imagery with the APSIM crop model. The approach employs APSIM to train a linear regression that relates simulated yield to simulated leaf area index (LAI). That relationship is then used to identify the optimal regression date at which the LAI provides the best prediction of yield: in this case, approximately 14 weeks prior to harvest. Instead of applying the regression on satellite imagery that is coincident, or closest to, the regression date, our method implements a particle filter that integrates CubeSat-based LAI into APSIM to provide end-of-season high-resolution (3 m) yield maps weeks before the optimal regression date. The approach is demonstrated on a rainfed maize field located in Nebraska, USA, where suitable collections of both imagery and in-situ data were available for assessment. The procedure does not require in-field data to calibrate the regression model, with results showing that even with a single assimilation step, it is possible to provide yield estimates with good accuracy up to 21 days before the optimal regression date. Yield spatial variability was reproduced reasonably well, with a strong correlation to independently collected measurements (R 2 = 0.73 and rRMSE = 12%). When the field averaged yield was compared, our approach reduced yield prediction error from 1 Mg/ha (control case based on a calibrated APSIM model), to 0.5 Mg/ha (using satellite imagery alone), and then to 0.2 Mg/ha (results with assimilation up to three weeks prior to the optimal regression date). Such a capacity to provide spatially explicit yield predictions early in the season has considerable potential to enhance digital agricultural goals and improve end-of-season yield predictions.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2022

Effectiveness of Deep Learning Trained on SynthCity Data for Urban Point-Cloud Classification

3D object recognition is one of the most popular areas of study in computer vision. Many of the more recent algorithms focus on indoor point clouds, classifying 3D geometric objects, and segmenting outdoor 3D scenes. One of the challenges of the classification pipeline is finding adequate and accurate training data. Hence, this article seeks to evaluate the accuracy of a synthetically generated data set called SynthCity, tested on two mobile laser-scan data sets. Varying levels of noise were applied to the training data to reflect varying levels of noise in different scanners. The chosen deep-learning algorithm was Kernel Point Convolution, a convolutional neural network that uses kernel points in Euclidean space for convolution weights.

Geology↗

NASA NTRS1989

Remote-Manipulator Hand With Data-Processing Ability

A "smart" hand for remote manipulator not only senses forces acting on it and detects presence of objects in immediate vicinity but also processes sensory data and controls its gripping claws. Hand reduces computational load on control computer of manipulator system. Includes wrist body and two opposing jaws with sets of claws that mesh with each other. Jaws of hand open as wide as 8.8 cm. Brushless dc motor operates claws through bevel-gear drive train and pair of ball screws. Maximum grip force 540 N, or about 120 lb.

Bejczy, Antal K.↗

NASA NTRS2008

Piloted Evaluation of the H-Mode, a Variable Autonomy Control System, in Motion-Based Simulation

As aircraft become able to autonomously respond to a range of situations with performance surpassing human operators, we are compelled to look for new methods that help understand their use and guide the design of new, more effective forms of automation and interaction. The "H-mode" is one such method and is based on the metaphor of a well-trained horse. The concept allows the pilot to manage a broad range of control automation functionality, from augmented manual control to FMS-like coupling and automation initiated actions, using a common interface system and easily learned set of interaction skills. The interface leverages familiar manual control interfaces (e.g., the control stick) and flight displays through the addition of contextually dependent haptic-multimodal elements. The concept is relevant to manned and remotely piloted vehicles. This paper provides an overview of the H-mode concept followed by a presentation of the results from a recent evaluation conducted in a motion-based simulator. The evaluation focused on assessing the overall usability and flying qualities of the concept with an emphasis on the effects of turbulence and cockpit motion. Because the H-mode results in interactions between traditional flying qualities and management of higher-level flight path automation, these effects are of particular interest. The results indicate that the concept may provide a useful complement or replacement to conventional interfaces, and retains the usefulness in the presence of turbulence and motion.

Goodrich, Kenneth H.↗

NASA NTRS2015

Resolving Ice Cloud Optical Thickness Biases Between CALIOP and MODIS Using Infrared Retrievals

Despite its importance as one of the key radiative properties that determines the impact of upper tropospheric clouds on the radiation balance, ice cloud optical thickness (IOT) has proven to be one of the more challenging properties to retrieve from space-based remote sensing measurements. In particular, optically thin upper tropospheric ice clouds (cirrus) have been especially challenging due to their tenuous nature, extensive spatial scales, and complex particle shapes and light scattering characteristics. The lack of independent validation motivates the investigation presented in this paper, wherein systematic biases between MODIS Collection 5 (C5) and CALIOP Version 3 (V3) unconstrained retrievals of tenuous IOT (< 3) are examined using a month of collocated A-Train observations. An initial comparison revealed a factor of two bias between the MODIS and CALIOP IOT retrievals. This bias is investigated using an infrared (IR) radiative closure approach that compares both products with MODIS IR cirrus retrievals developed for this assessment. The analysis finds that both the MODIS C5 and the unconstrained CALIOP V3 retrievals are biased (high and low, respectively) relative to the IR IOT retrievals. Based on this finding, the MODIS and CALIOP algorithms are investigated with the goal of explaining and minimizing the biases relative to the IR. For MODIS we find that the assumed ice single scattering properties used for the C5 retrievals are not consistent with the mean IR COT distribution. The C5 ice scattering database results in the asymmetry parameter (g) varying as a function of effective radius with mean values that are too large. The MODIS retrievals have been brought into agreement with the IR by adopting a new ice scattering model for Collection 6 (C6) consisting of a modified gamma distribution comprised of a single habit (severely roughened aggregated columns); the C6 ice cloud optical property models have a constant g approx. = 0.75 in the mid-visible spectrum, 5-15% smaller than C5. For CALIOP, the assumed lidar ratio for unconstrained retrievals is fixed at 25 sr for the V3 data products.This value is found to be inconsistent with the constrained (predominantly nighttime) CALIOP retrievals. An experimental data set was produced using a modified lidar ratio of 32 sr for the unconstrained retrievals (an increase of 28%), selected to provide consistency with the constrained V3 results. These modifications greatly improve the agreement with the IR and provide consistency between the MODIS and CALIOP products. Based on these results the recently released MODIS C6 optical products use the single habit distribution given above, while the upcoming CALIOP V4 unconstrained algorithm will use higher lidar ratios for unconstrained retrievals.

Cloud↗

NASA NTRS1974

Spectral mapping of soil organic matter

Multispectral remote sensing data were examined for use in the mapping of soil organic matter content. Computer-implemented pattern recognition techniques were used to analyze data collected in May 1969 and May 1970 by an airborne multispectral scanner over a 40-km flightline. Two fields within the flightline were selected for intensive study. Approximately 400 surface soil samples from these fields were obtained for organic matter analysis. The analytical data were used as training sets for computer-implemented analysis of the spectral data. It was found that within the geographical limitations included in this study, multispectral data and automatic data processing techniques could be used very effectively to delineate and map surface soils areas containing different levels of soil organic matter.

Kristof, S. J.↗

NASA NTRS2021

A Machine Learning Approach to Objective Identification of Dust in Satellite Imagery

Airborne dust has broad adverse effects on human activity, including aviation, human health, and agriculture. Remote sensing observations are used to detect dust and aerosols in the atmosphere using long established techniques. False color Red-Green-Blue (RGB) imagery using band differences sensitive to dust absorption (Dust RGB) is currently used operationally to assist forecasters and decision-makers in identifying dust at night, but there are still limitations, subjectivity, and nuances to image interpretation making night-time dust identification difficult even for experts. This study applies machine learning to the problem of night-time dust detection with a simple random forest (RF) model using Geostationary Operational Environmental Satellite-16 (GOES-16) Advanced Baseline Imager (ABI) infrared imagery, band differences sensitive to dust absorption, and Dust RGB color components as inputs to the model. The RF model achieves an Area-Under-Curve (AUC) of 0.97 with a standard deviation of 0.04 for dust cases. For images with dust present, the model correctly labels 85% of dust pixels and 99.96% of no-dust pixels for all dust images in the validation data set. The addition of a single null case to the training data set drastically reduces error in labeling no-dust pixels as dust from 45% to 14.5%. Application of the machine learning model to the April 13–14, 2019 dust event demonstrates the ability of the model to identify dust during night-time hours when visual dust detection is limited by the cooling ground surface characteristics.

dust↗

DOE OSTI2025

Transfer learning-based soybean LAI estimations by integrating PROSAIL, UAV, and PlanetScope imagery

Accurate Leaf Area Index (LAI) estimations at the soybean plot scale is achievable using high-resolution Unmanned Aerial Vehicle (UAV) imagery and field measurement samples. However, the limited coverage of UAV flights restricts large-scale remote sensing monitoring in expansive soybean fields. This study leverages the broad coverage and 3-m resolution of PlanetScope satellite imagery to extend LAI prediction from UAV to satellite scales through transfer learning, using UAV-scale LAI estimates as a benchmark to validate cross-scale consistency. To address this challenge, this study proposed the LAI-TransNet, a two-stage transfer learning framework designed for precise and scalable soybean LAI prediction across large areas, demonstrating its effectiveness in cross-scale monitoring. In Stage 1, a UAV-scale benchmark is established using PROSAIL-simulated UAV reflectance data (UAV-Sim) and field-measured soybean LAI. Traditional machine learning, deep learning, and transfer learning models are trained on a hybrid UAV-Sim and field-measured dataset (UAV-Sim_Measured), with the transfer learning model CNN-TL, fine-tuned using pre-trained weights derived from UAV-Sim, achieving the highest accuracy (R 2 = 0.81, RMSE = 0.64 m 2 /m 2 , rRMSE = 11.5 %). In Stage 2, LAI-TransNet is developed by fine-tuning the CNN-TL model on PlanetScope simulated data (PS-Sim), preprocessed via cross-domain mapping to align UAV and satellite spectral features. Real PlanetScope imagery is corrected for reflectance consistency with reference to UAV imagery spectral profiles. LAI-TransNet outperforms other deep learning models trained directly on PS-Sim (R 2 = 0.69 vs. 0.60–0.63), ensuring robust cross-scale consistency. In conclusion, by bridging UAV and satellite scales, LAI-TransNet enables large-scale soybean LAI monitoring, enhancing precision agriculture management through improved monitoring with the PlanetScope imagery.

Leaf area index (LAI)↗