Search NASA⌕ Search

SEARCH · Search NASA

Results for “multimodal dataset”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Global Multimodal Dataset for Nighttime Light Super-Resolution

The dataset is a collection of spatially and temporally registered high-resolution and low-resolution nighttime light (NTL) images, high-resolution land-use binary masks, and high-resolution road density images from around the world. The NTL images are sourced from the NASA Black Marble product VNP46A2 and the LuoJia1-01 satellite. The land-use binary masks are derived from Google's and the World Resources Institute's DynamicWorld dataset, and the road density images are sourced from OpenStreetMap.

Nighttime lights↗
DOE OSTI2023

Sputter-Deposited Mo Thin Films: Multimodal Characterization of Structure, Surface Morphology, Density, Residual Stress, Electrical Resistivity, and Mechanical Response

Multimodal datasets of materials are rich sources of information which can be leveraged for expedited discovery of process–structure–property relationships and for designing materials with targeted structures and/or properties. For this data descriptor article, we provide a multimodal dataset of magnetron sputter-deposited molybdenum (Mo) thin films, which are used in a variety of industries including high temperature coatings, photovoltaics, and microelectronics. In this dataset we explored a process space consisting of 27 unique combinations of sputter power and Ar deposition pressure. Here, the phase, structure, surface morphology, and composition of the Mo thin films were characterized by x-ray diffraction, scanning electron microscopy, atomic force microscopy, and Rutherford backscattering spectrometry. Physical properties—namely, thickness, film stress and sheet resistance—were also measured to provide additional film characteristics and behaviors. Additionally, nanoindentation was utilized to obtain mechanical load-displacement data. The entire dataset consists of 2072 measurements including scalar values (e.g., film stress values), 2D linescans (e.g., x-ray diffractograms), and 3D imagery (e.g., atomic force microscopy images). An additional 1889 quantities, including film hardness, modulus, electrical resistivity, density, and surface roughness, were derived from the experimental datasets using traditional methods. Minimal analysis and discussion of the results are provided in this data descriptor article to limit the authors’ preconceived interpretations of the data. Overall, the data modalities are consistent with previous reports of refractory metal thin films, ensuring that a high-quality dataset was generated. The entirety of this data is committed to a public repository in the Materials Data Facility.

36 MATERIALS SCIENCE↗
DOE OSTI2024

From Data to Insights: A Covariate Analysis of the IARPA BRIAR Dataset for Multimodal Biometric Recognition Algorithms at Altitude and Range

This paper examines covariate effects on fused whole body biometrics performance in the IARPA BRIAR dataset, specifically focusing on UAV platforms, elevated positions, and distances up to 1000 meters. The dataset includes outdoor videos compared with indoor images and controlled gait recordings. Normalized raw fusion scores relate directly to predicted false accept rates (FAR), offering an intuitive means for interpreting model results. A linear model is developed to predict biometric algorithm scores, analyzing their performance to identify the most influential covariates on accuracy at altitude and range. Weather factors like temperature, wind speed, solar loading, and turbulence are also investigated in this analysis. The study found that resolution and camera distance best predicted accuracy and findings can guide future research and development efforts in long-range/elevated/UAV biometrics and support the creation of more reliable and robust systems for national security and other critical domains.

Bolme, David↗
DOE OSTI2024

Unsupervised physics-informed disentanglement of multimodal data

Here, we introduce physics-informed multimodal autoencoders (PIMA) - a variational inference framework for discovering shared information in multimodal datasets. Individual modalities are embedded into a shared latent space and fused through a product-of-experts formulation, enabling a Gaussian mixture prior to identify shared features. Sampling from clusters allows cross-modal generative modeling, with a mixture-of-experts decoder that imposes inductive biases from prior scientific knowledge and thereby imparts structured disentanglement of the latent space. This approach enables cross-modal inference and the discovery of features in high-dimensional heterogeneous datasets. Consequently, this approach provides a means to discover fingerprints in multimodal scientific datasets and to avoid traditional bottlenecks related to high-fidelity measurement and characterization of scientific datasets.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

RadioGalaxyNET: Dataset and novel computer vision algorithms for the detection of extended radio galaxies and infrared hosts

Abstract Creating radio galaxy catalogues from next-generation deep surveys requires automated identification of associated components of extended sources and their corresponding infrared hosts. In this paper, we introduce RadioGalaxyNET, a multimodal dataset, and a suite of novel computer vision algorithms designed to automate the detection and localization of multi-component extended radio galaxies and their corresponding infrared hosts. The dataset comprises 4 155 instances of galaxies in 2 800 images with both radio and infrared channels. Each instance provides information about the extended radio galaxy class, its corresponding bounding box encompassing all components, the pixel-level segmentation mask, and the keypoint position of its corresponding infrared host galaxy. RadioGalaxyNET is the first dataset to include images from the highly sensitive Australian Square Kilometre Array Pathfinder (ASKAP) radio telescope, corresponding infrared images, and instance-level annotations for galaxy detection. We benchmark several object detection algorithms on the dataset and propose a novel multimodal approach to simultaneously detect radio galaxies and the positions of infrared hosts.

Astronomy & Astrophysics↗
DOE OSTI2021

Recent Developments in Femtosecond Laser-Enabled TriBeam Systems

Streams of multimodal three-dimensional (3D) and four-dimensional (4D) data are revolutionizing our ability to design and predict the behavior of a broad array of advanced materials systems. Over the last 10 years, a new 3D imaging platform consisting of a femtosecond (fs) pulsed laser coupled with a focused ion beam scanning electron microscope (FIB SEM) has been developed by UC Santa Barbara in collaboration with Thermo Fisher Scientific (formerly FEI). The femtosecond-laser-enabled FIB SEM, called the TriBeam, has become one of the only 3D serial sectioning methods available that can gather millimeter-scaled multimodal datasets at sub-μm voxel resolutions; these length scales are critical for many materials problems. Multimodal chemical, crystallographic, and morphological information can be gathered rapidly on a layer-by-layer basis and reconstructed in 3D. Large (gigabyte to terabyte scale) 3D datasets have been generated for a broad array of materials systems, including metallic alloys, ceramics, biomaterials, polymer- and ceramic-matrix composites, and semiconductors. The research tasks conducted have resulted in a completely new design, operating with a dual-wavelength femtosecond-pulsed laser on a plasma focused ion beam (PFIB) platform.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Scaling Subspace-Driven Approaches Using Information Fusion

In this work, we seek to exploit the deep structure of multi-modal data to robustly exploit the group subspace distribution of the information using the Convolutional Neural Networks (CNNs) formalism. Upon unfolding the set of subspaces constituting each data modality, and learning their corresponding encoders, an optimized integration of the generated inherent information is carried out to yield a characterization of various classes. Referred to as deep Multimodal Robust Group Subspace Clustering (DRoGSuRe), this approach is compared against the independently developed state-of-the-art approach named Deep Multimodal Subspace Clustering (DMSC). Experiments on different multimodal datasets show that our approach is competitive and more robust in the presence of noise.

Ghanem, Sally↗
DOE OSTI2026

MOSAIC-CONUS: A Multimodal, Multi-Temporally Paired Dataset for Earth Sciences

Earth embeddings—vector representations of geographic locations indexed in space and time—are emerging as a unifying interface for geospatial AI. However, their quality depends not only on model design, but on how multimodal Earth observation (EO) data are spatially indexed, temporally aligned, and cross-modally associated during pretraining. We introduce MOSAIC-CONUS (Multimodal Observations with Spatially Aligned Imagery, Urban Points of Interest, In-Situ Measurements and Text Captions), a large-scale EO dataset over the contiguous United States, organized around 250,000 stratified point indices that serve as stable spatial keys across seven modalities: active radar, passive optical imagery, lidar-derived elevation, land cover, functional context, hydrometeorological measurements, and textual summaries. Unlike existing EO datasets, MOSAIC-CONUS introduces four contributions not jointly addressed in prior work: 1. an open-source, large-scale multimodal EO corpus structured around point-indexed data designed to support Earth embedding learning; 2. explicit radar-optical pairing tables spanning twelve temporal alignment regimes, formalizing cross-sensor alignment as a controllable variable for analyzing how temporal mismatch across modalities influences learned embeddings quality; 3. a benchmark suite spanning cross-modal retrieval, annual nightlights regression, and basin-held-out streamflow prediction, positioning MOSAIC-CONUS as a benchmark-ready resource for multimodal AI systems; and 4. a language-based embedding layer through co-registered textual summaries, enabling Earth embeddings to function as a queryable interface for agentic AI systems. The dataset and pairing protocols are publicly released.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Data Fusion for the Development of a Multimodal Freight Transload Facilities Dataset in the U.S.

To withstand the growing demand of commodity volume and its strain on the transportation infrastructure, it is necessary to identify the flow of commodities by route and mode. However, a national multimodal freight routing model does not exist for the U.S. The development of such model requires multiple building blocks, such as virtual representations of roadway, railway, and waterway networks, transload facilities (TFs), and access/egress links. Most of these blocks have a robust database in the U.S., except for the TFs. Here, this paper presents the fusion of dispersed and heterogeneous representations of multimodal TFs into a single, comprehensive, geospatial freight TF dataset. The TF dataset is derived from several sources, including the U.S. Army Corps of Engineers Master Docks Plus, the National Transportation Atlas Database, the Intermodal Association of North America, industry publications, and other public information. First, individual datasets were queried and reconciled. A geocoding/reverse geocoding process was applied to get the best street address and latitude/longitude location for each terminal. Then, duplicate terminals were identified by a fuzzy match algorithm based on terminal name and location, and removed. Validation was performed by visual inspection of random facilities. The main contributions of this work are: a publicly available version of the TF dataset, including facility location and multimodal transfer capability of 9,003 facilities, and an enterprise-version with the same facilities but including commodity handling capabilities. The main purpose of developing the TF dataset is to inform multimodal routing algorithms. The proposed TF dataset allows for credibly modeling the multimodal transfer of commodities within shipment routes.

Commodity Routing↗
DOE OSTI2026

Heterogeneous Multi-Domain Dataset Synthesis to Facilitate Privacy and Risk Assessments in Smart City IoT

The emergence of the Smart Cities paradigm and the rapid expansion and integration of Internet of Things (IoT) technologies within this context have created unprecedented opportunities for high-resolution behavioral analytics, urban optimization, and context-aware services. However, this same proliferation intensifies privacy risks, particularly those arising from cross-modal data linkage across heterogeneous sensing platforms. To address these challenges, this paper introduces a comprehensive, statistically grounded framework for generating synthetic, multimodal IoT datasets tailored to Smart City research. The framework produces behaviorally plausible synthetic data suitable for preliminary privacy risk assessment and as a benchmark for future re-identification studies, as well as for evaluating algorithms in mobility modeling, urban informatics, and privacy-enhancing technologies. As part of our approach, we formalize probabilistic methods for synthesizing three heterogeneous and operationally relevant data streams—cellular mobility traces, payment terminal transaction logs, and Smart Retail nutrition records—capturing the behaviors of a large number of synthetically generated urban residents over a 12-week period. The framework integrates spatially explicit merchant selection using K-Dimensional (KD)-tree nearest-neighbor algorithms, temporally correlated anchor-based mobility simulation reflective of daily urban rhythms, and dietary-constraint filtering to preserve ecological validity in consumption patterns. In total, the system generates approximately 116 million mobility pings, 5.4 million transactions, and 1.9 million itemized purchases, yielding a reproducible benchmark for evaluating multimodal analytics, privacy-preserving computation, and secure IoT data-sharing protocols. To show the validity of this dataset, the underlying distributions of these residents were successfully validated against reported distributions in published research. We present preliminary uniqueness and cross-modal linkage indicators; comprehensive re-identification benchmarking against specific attack algorithms is planned as future work. This framework can be easily adapted to various scenarios of interest in Smart Cities and other IoT applications. By aligning methodological rigor with the operational needs of Smart City ecosystems, this work fills critical gaps in synthetic data generation for privacy-sensitive domains, including intelligent transportation systems, urban health informatics, and next-generation digital commerce infrastructures.

IoT↗
DOE OSTI2024

LUCID Thrust 1 - Dataset Identification and Biodata Catalog Creation

The LUCID DOE consortium, part of the Department of Energy’s Biological and Environmental Research (BER) program, advances Low Dose Radiation (LDR) research through multidisciplinary efforts across seven key thrusts. This document focuses on Thrust 1, which centers on the creation of curated multimodal population health datasets and supports broader efforts within the LUCID program, including AI-based hypothesis generation, experimental design, and the study of LDR-induced health risks. Specifically, it describes the identification and cataloging of Thrust 1’s curated LDR datasets and biodata, emphasizing their critical role in supporting various research thrusts within the consortium, with potential applications in healthcare and public policy. In addition, the document includes an evaluation of three Large Language Models (LLMs)—GPT-4, SOLAR-10B, and Mixtral-8x7B—based on their ability to extract features from 25 LDR studies. The results indicate that GPT-4 performed the best, while Mixtral-8x7B demonstrated limited knowledge. Overall, this work advances understanding in radiation protection, risk assessment, and medical treatments, while providing valuable resources for researchers, educators, and policymakers.

63 RADIATION, THERMAL, AND OTHER ENVIRON. POLLUTAN↗
DOE OSTI2024

SCITUNE: Aligning Large Language Models with Human-Curated Scientific Multimodal Instructions

Instruction finetuning is a popular paradigm to align large language models (LLM) with human intent. Despite its popularity, this idea is less explored in improving the LLMs to align existing foundation models with scientific disciplines, concepts and goals. In this work, we present SciTune as a tuning framework to improve the ability of LLMs to follow scientific multimodal instructions. To test our methodology, we use a human-generated scientific instruction tuning dataset and train a large multimodal model LLaMA-SciTune that connects a vision encoder and LLM for science-focused visual and language understanding. LLaMA-SciTune significantly outperforms the state-of-the-art models in the generated figure types and captions in multiple scientific multimodal benchmarks. In comparison to the models that are fine-tuned with machine generated data only, LLaMA-SciTune surpasses human performance on average and in many sub-categories on the ScienceQA benchmark.

• Artificial intelligence (AI) / machine learning ↗
DOE OSTI2024

Maven: a multimodal foundation model for supernova science

Abstract A common setting in astronomy is the availability of a small number of high-quality observations, and larger amounts of either lower-quality observations or synthetic data from simplified models. Time-domain astrophysics is a canonical example of this imbalance, with the number of supernovae observed photometrically outpacing the number observed spectroscopically by multiple orders of magnitude. At the same time, no data-driven models exist to understand these photometric and spectroscopic observables in a common context. Contrastive learning objectives, which have grown in popularity for aligning distinct data modalities in a shared embedding space, provide a potential solution to extract information from these modalities. We present Maven, the first foundation model for supernova science. To construct Maven, we first pre-train our model to align photometry and spectroscopy from 0.5 M synthetic supernovae using a contrastive objective. We then fine-tune the model on 4702 observed supernovae from the Zwicky transient facility. Maven reaches state-of-the-art performance on both classification and redshift estimation, despite the embeddings not being explicitly optimized for these tasks. Through ablation studies, we show that pre-training with synthetic data improves overall performance. In the upcoming era of the Vera C. Rubin observatory, Maven will serve as a valuable tool for leveraging large, unlabeled and multimodal time-domain datasets.

Zhang, Gemma (ORCID:0000000280198082)↗
DOE OSTI2024

U.S. Freight Transload Facilities Dataset

The U.S. Freight Transload Facilities Dataset provides location information (latitude, longitude, zip, city, county, state)for more than 9,000 facilities across 50 U.S. States where freight may be transferred between waterways, railways, and roadways. The dataset lists the known modes and available direction(s) for freight transfers at each facility as of 2024. The U.S. Freight Transload Facilities dataset was built by mining and fusing several public sources, such as the USACE Master Docks Plus, the USDOT National Transportation Atlas Database (NTAD), files from the Intermodal Association of North America (IANA), and the industry publication Bulk Transloader. The dataset constitutes a key piece of a multimodal freight transportation network and routing algorithm developed by USACE-ERDC. The dataset is shared as a .csv file. The dataset is published for research purposes and should not be considered exhaustive or authoritative.

Peterson, Steven [ORNL] (ORCID:0000000287672998)↗
NASA NTRSDate not supplied

Concept-based Analysis of Neural Networks via Vision-Language Models

The analysis of vision-based deep neural networks (DNNs) is highly desirable but it is very challenging due to the difficulty of expressing formal specifications for vision tasks and the lack of efficient verification procedures. In this paper, we propose to leverage emerging multimodal, vision-language, foundation models (VLMs) as a lens through which we can reason about vision models. VLMs have been trained on a large body of images accompanied by their textual description, and are thus implicitly aware of high-level, human-understandable concepts describing the images. We describe a logical specification language Con spec designed to facilitate writing specifications in terms of these concepts. To define and formally check Con spec specifications, we build a map between the internal representations of a given vision model and a VLM, leading to an efficient verification procedure of natural-language properties for vision models. We demonstrate our techniques on a ResNet-based classifier trained on the RIVAL-10 dataset using CLIP as the multimodal model.

Large Vision Language Models↗
DOE OSTI2024

Towards Unlocking Insights from Logbooks Using AI

Electronic logbooks contain valuable information about activities and events concerning their associated particle accelerator facilities. However, the highly technical nature of logbook entries can hinder their usability and automation. As natural language processing (NLP) continues advancing, it offers opportunities to address various challenges that logbooks present. This work explores jointly testing a tailored Retrieval Augmented Generation (RAG) model for enhancing the usability of particle accelerator logbooks at institutes like DESY, BESSY, Fermilab, BNL, SLAC, LBNL and CERN. The RAG model uses a corpus built on logbook contributions and aims to unlock insights from these logbooks by leveraging retrieval over facility datasets, including discussion about potential multimodal sources. Our goals are to increase the FAIR-ness (findability, accessibility, interoperability, and reusability) of logbooks by exploiting their information content to streamline everyday use, to enable macro-analysis for root cause analysis, and to facilitate problem-solving automation.

43 PARTICLE ACCELERATORS↗