Search NASA⌕ Search

SEARCH · Search NASA

Results for “VISION”

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 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Improving streamflow predictions across CONUS by integrating advanced machine learning models and diverse data

Accurate streamflow prediction is crucial to understand climate impacts on water resources and develop effective adaption strategies. A global long short-term memory (LSTM) model, using data from multiple basins, can enhance streamflow prediction, yet acquiring detailed basin attributes remains a challenge. To overcome this, we introduce the Geo-vision transformer (ViT)-LSTM model, a novel approach that enriches LSTM predictions by integrating basin attributes derived from remote sensing with a ViT architecture. Applied to 531 basins across the Contiguous United States, our method demonstrated superior prediction accuracy in both temporal and spatiotemporal extrapolation scenarios. Geo-ViT-LSTM marks a significant advancement in land surface modeling, providing a more comprehensive and effective tool for better understanding the environment responses to climate change.

Tayal, Kshitij↗
DOE OSTI2024

Machine learning materials properties with accurate predictions, uncertainty estimates, domain guidance, and persistent online accessibility

One compelling vision of the future of materials discovery and design involves the use of machine learning (ML) models to predict materials properties and then rapidly find materials tailored for specific applications. However, realizing this vision requires both providing detailed uncertainty quantification (model prediction errors and domain of applicability) and making models readily usable. At present, it is common practice in the community to assess ML model performance only in terms of prediction accuracy (e.g. mean absolute error), while neglecting detailed uncertainty quantification and robust model accessibility and usability. Here, we demonstrate a practical method for realizing both uncertainty and accessibility features with a large set of models. We develop random forest ML models for 33 materials properties spanning an array of data sources (computational and experimental) and property types (electrical, mechanical, thermodynamic, etc). All models have calibrated ensemble error bars to quantify prediction uncertainty and domain of applicability guidance enabled by kernel-density-estimate-based feature distance measures. All data and models are publicly hosted on the Garden-AI infrastructure, which provides an easy-to-use, persistent interface for model dissemination that permits models to be invoked with only a few lines of Python code. We demonstrate the power of this approach by using our models to conduct a fully ML-based materials discovery exercise to search for new stable, highly active perovskite oxide catalyst materials.

domain of applicability↗
DOE OSTI2024

Introducing SpaceNet 9 - Cross-Modal Satellite Imagery Registration for Natural Disaster Responses

Computer vision algorithms are increasingly leveraged to accelerate geospatial analysis for disaster response and recovery. As the diversity of remote sensing imagery grows with optical, SAR, and other modalities, a perquisite for analytics is cross-modal image registration. There is a high potential to harness computer vision for this pre-processing requirement toward enabling downstream analytics such as heterogeneous change detection, automated feature extraction, and data fusion. Advancement in these areas has the potential to simplify data wrangling tasks and further accelerate disaster response timelines. The SpaceNet 9 challenge (launching in mid-2024) focuses on addressing the cross-modal image registration problem and demonstrating the utility of such modules on earthquake impacted scenarios. This paper describes the motivation for the SpaceNet 9 and provides a first overview of the dataset, the baseline algorithm, and implications for seeking cross-modal image registration in Earth observation. Code is available at https://github.com/SpaceNetChallenge/SpaceNet9.

Hansch, Ronny↗
DOE OSTI2024

Pretraining Billion-Scale Geospatial Foundational Models on Frontier

As AI workloads increase in scope, generalization capability becomes challenging for small task-specific models and their demand for large amounts of labeled training samples increases. On the contrary, Foundation Models (FMs) are trained with internet-scale unlabeled data via self-supervised learning and have been shown to adapt to various tasks with minimal fine-tuning. Although large FMs have demonstrated significant impact in natural language processing and computer vision, efforts toward FMs for geospatial applications have been restricted to smaller size models, as pretraining larger models requires very large computing resources equipped with state-of-the-art hardware accelerators. Current satellite constellations collect 100+TBs of data a day, resulting in images that are billions of pixels and multimodal in nature. Such geospatial data poses unique challenges opening up new opportunities to develop FMs. We investigate billion scale FMs and HPC training profiles for geospatial applications by pretraining on publicly available data. We studied from end-to-end the performance and impact in the solution by scaling the model size. Our larger 3B parameter size model achieves up to 30% improvement in top1 scene classification accuracy when comparing a 100M parameter model. Moreover, we detail performance experiments on the Frontier supercomputer, America's first exascale system, where we study different model and data parallel approaches using PyTorch's Fully Sharded Data Parallel library. Specifically, we study variants of the Vision Transformer architecture (ViT), conducting performance analysis for ViT models with size up to 15B parameters. By discussing throughput and performance bottlenecks under different parallelism configurations, we offer insights on how to leverage such leadership-class HPC resources when developing large models for geospatial imagery applications.

Tsaris, Aristeidis (aris)↗
DOE OSTI2024

Improving Robustness of Spectrogram Classifiers with Neural Stochastic Differential Equations

Signal analysis and classification is fraught with high levels of noise and perturbation. Computer-vision-based deep learning models applied to spectrograms have proven useful in the field of signal classification and detection; however, these methods aren't designed to handle the low signal-to-noise ratios inherent within non-vision signal processing tasks. While they are powerful, they are currently not the method of choice in the inherently noisy and dynamic critical infrastructure domain, such as smart-grid sensing, anomaly detection, and non-intrusive load monitoring. Currently, these models can be brittle, which makes them susceptible to noisy input. This also means they have sub-optimal stability of explanation outputs. Experts and technicians using these models to make decisions in real world scenarios need assurance that a model is performing as it is supposed to. The classification or prediction outputs it generates should be sound and grounded, not likely to change in the presence of shifting noise landscapes. In this work, we explore the idea of Neural Stochastic Differential Equations (NSDE's) to improve the robustness of models trained to classify time series data and the effect of NSDE's on the explainability of outputs. We then test the effectiveness of these approaches by applying them to a non-intrusive load monitoring (NILM) dataset that consists of simulated harmonic signals injected into a real building.

Brogan, Joel↗
DOE OSTI2025

Location generalizability of image-based air quality models

This paper is to be submitted at the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Computer Vision for Earth Observation workshop. The full paper abstract is below: The ability to rapidly quantify atmospheric pollutants is important both for global emissions monitoring and for mitigating the adverse effects that follow a hazardous chemical release. In the aftermath of a chemical release, imagery is often the only available resource to assess local conditions. Recent work has demonstrated initial success in predicting particulate matter pollution from imagery; however, these results are tied to a specific site and do not generalize to new geographic locations. In this work, we seek to understand how easily deep learning models generalize to new locations in the context of image-based air quality assessments, targeting two distinct tasks: (1) broad measures of particulate matter pollution, and (2) the mass of a given chemical released in hazardous plumes. For the latter, we focus on sulfur dioxide, a toxic aerosol and a major component of particulate matter pollution caused by industrial fossil fuel consumption. To develop a model that operates in the widest possible range of environments, we test different training strategies, including the use of new geolocation foundation models. The best performing models achieve >80% accuracy when evaluating unseen imagery at previously seen sites, but we find significant drops in performance when evaluating imagery from unseen sites, at best 65%. Additionally, we present the public release of the National Parks Air Quality Index Dataset, a new medium-sized dataset that pairs imagery with sensor-based air quality measurements at 15 different national parks.

Byler, Eleanor B. [BATTELLE (PACIFIC NW LAB)]↗
DOE OSTI2026

YOLO11 to SAM2 pipeline for feature extraction from nuclear test films

The response to the effects of nuclear detonations is supported by models that describe the evolution of the nuclear fireball and cloud and the associated transport of active debris. Validation of those descriptions relies on data from the nuclear test operations. Video records of those events offer a rich source of information that was exploited to a limited extent in historic analyses. Computer vision and machine learning techniques are powerful tools that can be used to increase the number of measurements that can be obtained from those films. In this work, we apply computer vision techniques to automatically track the temporal evolution of the nuclear fireball. In particular, we apply You Only Look Once 11 (YOLO11) and Segment Anything Model 2 (SAM2) in combination with minimal human intervention to digitized versions of the original nuclear test films. As part of the proposed workflow, the YOLO11 model is applied to films to determine bounding boxes for the fireball within each frame. These are then used as inputs to SAM2, which uses image segmentation to determine the fireball boundaries and their temporal evolution. We assess the accuracy of our approach by using it to determine the energy released during the Trinity nuclear test and comparing the results with previous analyses based on manual measurements.

Van Exel, Kimberly [ORNL] (ORCID:0009000877463894)↗
DOE OSTI2025

Distributed Cross-Channel Hierarchical Aggregation for Foundation Models

Vision-based scientific foundation models hold significant promise for advancing scientific discovery and innovation. This potential stems from their ability to aggregate images from diverse sources—such as varying physical groundings or data acquisition systems—and to learn spatio-temporal correlations using transformer architectures. However, tokenizing and aggregating images can be compute-intensive, a challenge not fully addressed by current distributed methods. In this work, we introduce the Distributed Cross-Channel Hierarchical Aggregation (D-CHAG) approach designed for datasets with a large number of channels across image modalities. Our method is compatible with any model-parallel strategy and any type of vision transformer architecture, significantly improving computational efficiency. We evaluated D-CHAG on hyperspectral imaging and weather forecasting tasks. When integrated with tensor parallelism and model sharding, our approach achieved up to a 75% reduction in memory usage and more than doubled sustained throughput on up to 1,024 AMD GPUs on the Frontier Supercomputer.

Tsaris, Aristeidis (aris) [ORNL] (ORCID:0000000277↗
DOE OSTI2025

Visual Instance-aware Prompt Tuning

Visual Prompt Tuning (VPT) has emerged as a parameter-efficient fine-tuning paradigm for vision transformers, with conventional approaches utilizing dataset-level prompts that remain the same across all input instances. We observe that this strategy results in sub-optimal performance due to high variance in downstream datasets. To address this challenge, we propose Visual Instance-aware Prompt Tuning (ViaPT), which generates instance-aware prompts based on each individual input and fuses them with dataset-level prompts, leveraging Principal Component Analysis (PCA) to retain important prompting information. Moreover, we reveal that VPT-Deep and VPT-Shallow represent two corner cases based on a conceptual understanding, in which they fail to effectively capture instance-specific information, while random dimension reduction on prompts only yields performance between the two extremes. Instead, ViaPT overcomes these limitations by balancing dataset-level and instance-level knowledge, while reducing the amount of learnable parameters compared to VPT-Deep. Extensive experiments across 34 diverse datasets demonstrate that our method consistently outperforms state-of-the-art baselines, establishing a new paradigm for analyzing and optimizing visual prompts for vision transformers.

Xiao, Xi [ORNL] (ORCID:0009000009316982)↗
DOE OSTI2024

Double Visual Defense

This is the official code for the paper "Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness". This code can be used to produce vision language models (VLMs), like LLaVA, with enhanced robustness to adversarial attacks (e.g. jailbreaks).

Bartoldson, Brian [Lawrence Livermore National Lab↗
DOE OSTI2024

DECIDER

This software offers methods and functions for building failure detectors for deep image classification models with the aid of vision-language models and LLMs. It includes functionalities for training baseline image classifiers, debiasing classifiers using vision-language models and LLMs, evaluating failure between models along with baselines. Developed using PyTorch, this software is compatible with standard neural network architectures used for imaging data. Additionally, it provides capabilities to compute evaluation metrics for assessing the performance and quality of the detectors.

Narayanaswamy, Vivek Sivaraman↗
DOE OSTI2024

Nuclear Computational Resource Center Progress and Status Report

The Nuclear Computational Resource Center (NCRC) at Idaho National Laboratory (INL), supported by the United States Department of Energy Office of Nuclear Energy (DOE-NE), provides access to supercomputer systems and protected software in support of nuclear energy research and development. The NCRC vision recognizes the central role modeling and simulation plays in nuclear energy innovation as well as ensuring the safe, secure, and efficient operations of existing nuclear energy systems. To accomplish this vision, the NCRC supports processes and systems which provide access to computational tools, supercomputing systems, and training in support of nuclear energy innovation.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2024

Summary: Nuclear Energy Critical Material Waste Reduction and Supply Chain Solutions Enabled by Advanced Manufacturing

In September 2020, the U.S. government issued an executive order to address the threat to the domestic supply chain from its reliance on critical minerals (CMs) from foreign competitors and to support the domestic mining and processing industry. A national strategy on CMs with impact on the U.S. Department of Energy’s (DOE’s) vision for 2021–2031 was developed. This vision embraces science and technology to re-establish U.S. competitiveness in the CM and material supply chains by (a) scientific innovation and technologies to ensure resilient and secure CMs and maintain a domestic material supply chain, (b) building a long-term minerals and materials innovation ecosystem to foster new capabilities to mitigate CM supply chain challenges, (c) increasing private sector adoption for sustaining the domestic CM supply chain, and (d) coordinating with international partners and federal agencies to diversify global supply chains and ensure the adoption of best practices for sustainable mining and processing (DOE 2021).

36 MATERIALS SCIENCE↗
DOE OSTI2024

Preliminary Characterization and Evaluation on ShAPE Manufactured 316H and ODS Steels

This study provides the first- of- a- kind results of direct tube formation through shear assisted processing and extrusion (ShAPE) for oxide dispersion strengthened (ODS) steel material; previously only bar was successfully made. The Advanced Materials and Manufacturing Technology (AMMT) program develops cross-cutting technologies in support of a broad range of nuclear reactor technologies and maintains U.S. leadership in materials and manufacturing technologies for nuclear energy applications. The overarching vision of AMMT is to accelerate the development, qualification, demonstration, and deployment of advanced materials and manufacturing technologies to enable reliable and economical nuclear energy. Solid-state advanced manufacturing techniques can overcome some of the challenges in liquid-based additive manufacturing processes and should therefore be considered in material design and manufacturing as well. The work presented in this report forms part of a study on solid-state additive manufacturing techniques of 316 stainless steels and ODS steel components and supports the vision and goals of the AMMT program relevant to accelerate the development and deployment of advanced manufacturing processes. Achieving this can provide a safety improvement through larger safety margins, economic benefit for higher efficiency during operation, and a cost reduction through more effective manufacturing processes and less waste.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Weapon Material Program: FY24 Annual Report

The Weapon Material Program (WMP) framework was started in July of Fiscal Year (FY) 2022, along with other Mission Support organizations. The first year was about building the organization with the right people, identifying needs, and developing a vision for expectations. It was also a year to move forward with new equipment and technology for weapon material processes. With numerous improvements, WMP is building world-class systems for production, warehousing, and analytical testing. FY 2023 was a year of development. The WMP was a new organization defining its identity, its focus, and its mission. At the end of FY 2023, WMP evaluated its current position and its immediate needs along with its future goals. The entire organization set out on this FY 2024 journey to success. The lack of funding, staffing, and visibility dramatically impacted weapon material operations, testing, and qualifications. This neglect required numerous areas to be addressed and improvement plans to be developed and implemented. WMP processes, procedures, and overall business operations were dramatically in need of updating, revision, and formal documentation. This included all areas: technology, equipment, facility modifications/upgrades, and testing improvements. To ensure organizational improvement and forward momentum in FY 2024, WMP executed a multi-faceted strategic vision. Action items included the following: • Filling open positions with capable personnel who would contribute to a more robust organization • Establishing more formal operations and problem-solving techniques • Improving departmental procedures to align with expanding scope • Improving training • Establishing collaboration meetings with other departments/organizations • Focusing on the importance of identifying and mitigating concerns with At-Risk Materials (@RM) • Leading modernization eff orts for Blending and Packaging (B&P) We are on the verge of a transformational improvement in all of our processes in support of the mission. The following area achievements outlined in this report reflect the hard work toward achieving the goal of “being the material Subject Matter Experts in the nuclear enterprise”.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
DOE OSTI2024

Mixing-Controlled Compression Ignition Combustion with Low-Lifecycle-CO 2 Fuels

Reducing lifecycle carbon-dioxide (CO 2 ) and toxic emissions via electrification or switching to carbon-free fuels is not currently feasible for many off-road, rail, and marine applications. This is due to factors including excessive cost, weight, or size of a battery of sufficient capacity to meet the application requirements, lack of infrastructure, insufficient time for recharging, demanding duty cycles, and severe ambient conditions. The guiding vision for the activities described herein is to enable rapid, cost-effective reductions of the environmental impacts of such applications by using improved, high efficiency engine combustion strategies with currently available and emerging low lifecycle-CO 2 fuels (LLCFs). This report summarizes progress toward achieving this vision in two project areas. The first is a Technology Commercialization Fund (TCF) project focused on facilitating the commercialization of ducted fuel injection (DFI) with LLCFs. The second is a more fundamental, Advanced Combustion Engines (ACE) research project focused on elucidating a new strategy called lean mixing-controlled combustion (LMCC) for use with emerging LLCFs.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2024

Automated Inspection of Criticality Control Overpacks for Surplus Plutonium Disposition: Qualification Update – 25313

In an effort to reduce the amount of nuclear waste in South Carolina, the Department of Energy (DOE) tasked the Savannah River Site (SRS) with diluting and disposing of the amount of plutonium in the state. This process involves the movement and shipment of over 100,000 criticality control overpacks (CCOs) throughout the project lifespan, lending itself to the use of automation to reduce worker radiation exposure and more efficiently utilize human capital. Due to the large scope, this overarching process was broken down into several different “automation projects” to be developed. The first opportunity pursued was the receipt and inspection of empty CCO drums coming into SRS, identified as Automation Project 1 (AP1), and is the focus of this paper. AP1 was developed to unpack incoming CCOs and inspect them for unwanted foreign objects and any damage to the drum or its contents. This process is accomplished by the combination of an automated guided vehicle (AGV) that delivers CCOs to a robotic arm which uses a suite of custom tools to disassemble a CCO, inspect the inside and outside of the CCO and its inner criticality control container (CCC), reassemble the CCC and CCO, and apply a tamper indicating device (TID) to the inspected drum. In past years, the robotic work cell had been developed in a small-scale testing facility for proof-of-concept. This year, major improvements were made to the robotic work cell to perform the process, including integration into the final facility where CCOs will be inspected. Other technical improvements include the implementation of sensor feedback and safety relays into the control system to allow the state of the work cell to be better tracked, and additional development of the TID application process to complete the robotic inspection. Further enhancements were made to the robotic vision processes and robot pathing, as well as development on a computer vision inspection process to detect inspection criteria anomalies in CCOs. In addition to developmental improvements, the work cell underwent a six-month testing period to ensure the project requirements were met. Results of this testing period demonstrate the work cell’s capability to meet project throughput goals at an acceptable level, successfully document the status of each CCO inspected, and reduce the toll on technical operations’ human power by two thirds. At the time of this paper, the work cell is capable of autonomously handling up to eight CCOs with an AGV, delivering CCOs to and from the robot work cell, and having a robotic arm perform a full receipt and inspection procedure on each CCO. Moving forward, repeatability will be improved so that these CCOs can be run back-to-back seamlessly, as well as improving the system to handle more significant edge cases and failure modes.

Spivey, Nicholas↗
DOE OSTI2025

Advanced Materials and Manufacturing Technologies (AMMT) 2025 Roadmap

The mission of the Advanced Materials and Manufacturing Technologies (AMMT) program is to accelerate the development, qualification, demonstration, and deployment of advanced materials and manufacturing technologies in support of the United States (US) leadership in a broad range of nuclear energy applications. The vision of the AMMT program is the expansion of reliable and economical nuclear energy enabled by advanced materials and manufacturing technologies. Four major goals were set to realize the mission and vision of the AMMT program, including: (1) develop advanced materials and manufacturing technologies that have cross-reactor applications, (2) establish and demonstrate a rapid qualification framework that supports diverse materials and manufacturing technology needs, (3) evaluate materials performance in a range of nuclear environments, and (4) accelerate commercialization of new technologies through technology maturation. The program is designed to deliver solutions that support a wide range of reactor technologies.

36 MATERIALS SCIENCE↗