SEARCH · Engineering Papers
Results for “multimode”
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.
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.
Predictive Control for Autonomous Driving With Uncertain, Multimodal Predictions
Not provided.
A Deep Multimodal Representation Learning Framework for Accurate Molecular Properties Prediction
Drug discovery is a complex and challenging process, requiring the optimization of candidate compounds to identify those with the potential to become safe and effective drugs. Predicting molecular properties is an indispensable step in the drug discovery pipeline. Traditionally, this process is costly and time-intensive, involving multiple rounds of experiments and clinical trials, rendering it impractical for every candidate compound. Deep learning techniques have emerged as a promising approach to drug discovery to reduce the cost and time required to identify novel drugs. However, prevalent research in deep learning models focused on predicting molecular properties has primarily fixated on single-modal models, which utilize a single modality of data, neglecting the potential benefits of combining different data modalities. To overcome this limitation, we introduce MRL-Mol: a deep \textbf{M}ultimodal \textbf{R}epresentation \textbf{L}earning framework for accurate \textbf{Mol}ecular properties prediction. MRL-Mol harnesses three data modalities: sequence, graph, and image, augmenting the depth of comprehension. Leveraging a large-scale unlabeled dataset~($\sim$1M unique molecules), we pretrain MRL-Mol to extract inter- and intra-modal information. Our study demonstrates the superior performance of MRL-Mol in predicting molecular properties across six benchmark datasets, including both classification and regression tasks. Notably, MRL-Mol outperforms other state-of-the-art molecular properties prediction models. These findings suggest that by combining information from multiple data modalities, MRL-Mol can comprehend molecules better than single-modal deep learning models and identify molecular properties with better accuracy.
Topological Signatures of Adversaries in Multimodal Alignments
Topological Data Analysis for Adversarial Detection (LANL O4937) - Detects adversarial examples in vision-language models using persistent homology and two-sample testing. Combines TDA features from CLIP embeddings with statistical methods (ME, SCF, SAMMD, C2ST) for robust detection across ImageNet, CIFAR-10/100.
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.
In-situ TEM Holder for Ultrafast, Multimodal Imaging
This project developed a prototype in-situ specimen holder product to transmission electron microscope (TEM) users that drastically expand the usability of TEM by combining nanoscale laser excitation and optical signal collection. A commercial prototype has been constructed and a few nanoscale materials characterization experiments have been performed to validate its performance and demonstrate its utility in real scientific studies, for example, in-situ characterization and mapping of defects in the synthesis of nanostructures.
Building a Long-Lived 3D Multimode Quantum Processing Unit with TESLA Cavities
Superconducting radio-frequency (SRF) cavities, such as TESLA-shaped cavities, are excellent candidates for long-lived quantum memories. Integrating these cavities with nonlinear elements, such as transmons, enables universal quantum control; however, this integration can often introduce unwanted losses. In this talk, we present the successful integration of a long-lived 2-cell TESLA cavity with an ancillary qubit, forming a quantum processing unit (QPU) that allows for robust control while maintaining coherence. We demonstrate universal control of the QPU through various schemes, including ancilla-cavity sideband and echoed conditional displacement (ECD) methods, enabling fault-tolerant high-fidelity preparation of large Fock states and fast entanglement generation. These results illustrate the versatility and efficiency of our 3D quantum processing unit, paving the way for advanced quantum computing applications.
Polydiacetylene Sensor Arrays as Multimodal Tamper Indicators
Explore the source record for details and available documents.
Unsupervised physics-informed disentanglement of multimodal data
Explore the source record for details and available documents.
Evaluating and Engineering Material Properties for Desired Outcomes Using Multimodal Machine Learning
Explore the source record for details and available documents.
Electron Energy-Loss Spectroscopy and Differential Phase Contrast Imaging with Active Decision in Multimodal Electron Microscopy: Isotopic detection at the atomic scale
Isotopic engineering provides a powerful route to control phonon behavior in crystalline solids, enabling fundamental studies of lattice dynamics and heat transport at the atomic scale. Here, we directly visualize isotope-dependent phonon propagation in epitaxial Cr 2 O 3 using aberration-corrected scanning transmission electron microscopy (STEM) combined with monochromated, high-energy-resolution electron energy-loss spectroscopy (EELS). Guided by ab initio phonon calculations, we demonstrate that optical phonon modes above 70 meV are predominantly oxygen-derived and exhibit measurable redshifts upon substitution of natural 16 O by enriched 18 O. Spatially resolved vibrational spectrum imaging reveals isotope-enriched tracer layers within Cr 2 O 3 thin films, correlating isotope concentration with phonon intensity variations and vibrational energy shifts. At the nanometer and atomic scales, vibrational EELS mapping uncovers coherent phonon propagation across isotopic interfaces, consistent with theoretical phonon density of states and dispersion relations. These results establish vibrational EELS as a quantitative probe for isotope-dependent phonon transport in materials, opening new possibilities for studying energy dissipation and lattice dynamics.
Multimodal Approaches for Leveraging Domain Knowledge with State-of-the-Art Machine Learning to Engineer Biocatalysts
This grant aimed to accelerate the development of specialized enzymes—biological catalysts essential for sustainable manufacturing and medicine—by integrating traditional laboratory evolution with cutting-edge artificial intelligence. To achieve this, we developed a suite of high-throughput sequencing tools and a centralized database to bridge the gap between a protein’s genetic "code" and its physical function. By training machine learning models on large datasets, we also demonstrated the ability to move beyond slow, trial-and-error testing to a "generative" approach, where AI can independently design new, versatile enzymes like tryptophan synthases. Ultimately, these findings demonstrate that combining laboratory data with computer-guided design enables the engineering of highly efficient biological tools with unprecedented speed and precision.
Extracting Circuit Parameters from Multimodal Cavities for Lumped Element Simulations
Explore the source record for details and available documents.
Learning to Trust: Adaptive Multisource Multimodal Bayesian Data Fusion for Forensic Blast Analysis
Explore the source record for details and available documents.
Parameter extraction from electromagnetic eigenmode simulations of multimodal cavities using MFEM
Explore the source record for details and available documents.
Evaluating the Use of Foundational Chemical Language Models in Multimodal Graph Fusion
Rapid and accurate prediction of the physicochemical properties of molecules given their structures remains a key challenge in cheminformatics. Machine learning approaches offer high-throughput options, but the optimality of inductive biases and data representations are up for debate. For example, BERT-based masked language models (MLMs) can be trained in a self-supervised way on hundreds of millions to billions of readily available SMILES strings. Another option is graph neural networks (GNNs), which can operate directly on molecular structures. Yet, generating accurate molecular geometry is computationally expensive, leading to a relative scarcity in data compared to SMILES strings. It is attractive to combine these two paradigms by pre-training an LM on a large corpus of SMILES strings and embedding these representation into a geometric graph neural network. Despite the promise of such an approach, and contrary to previous studies, we find mixed results with the combination of the LMs and GNNs on several molecule datasets. In particular, we found evidence for improvement on the FreeSolv and QM7 benchmarks, but degraded performance on the ESOL, LIPO and QM9 datasets compared to a GNN baseline.
Correlative multimodal chemical imaging via machine learning
Machine learning approach can combine mass spectral imaging (MSI) techniques, one with low spatial resolution but intact molecular spectra and the other with nanometer spatial resolution but fragmented molecular signatures, to predict molecular MSI spectra with submicron spatial resolution. The machine learning approach can perform transformations on the spectral image data of the two MSI techniques to reduce dimensionality, and using a correlation technique, find relationships between the transformed spectral image data. The determined relationships can be used to generate MSI spectra of desired resolution.