Search NASA⌕ Search

SEARCH · Search NASA

Results for “Convolution”

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 1,801 records · Page 100

Structural differences between human and mouse neurons and their implementation in generative AIs

Mouse and human brains have different functions that depend on their neuronal networks. We analyzed nanometer-scale three-dimensional structures of brain tissues of the mouse medial prefrontal cortex and compared them with structures of the human anterior cingulate cortex. The obtained results indicated that mouse neuronal somata are smaller and neurites are thinner than those of human neurons. We implemented these characteristics of mouse neurons in convolutional layers of a generative adversarial network (GAN) and a denoising diffusion implicit model (DDIM), which were then subjected to image generation tasks using photo datasets of cat faces, cheese, human faces, birds, and automobiles. The mouse-mimetic GAN outperformed a standard GAN in the image generation task using the cat faces and cheese photo datasets, but underperformed for human faces and birds. The mouse-mimetic DDIM gave similar results, suggesting that the nature of the datasets affected the results. Analyses of the five datasets indicated differences in their image entropy, which should influence the number of parameters required for image generation. The preferences of the mouse-mimetic AIs coincided with the impressions commonly associated with mice. The relationship between the neuronal network and brain function should be investigated by implementing other biological findings in artificial neural networks.

generative AI↗

Deep learning of structural morphology imaged by scanning X-ray diffraction microscopy

Scanning X-ray nanodiffraction microscopy is a powerful technique for spatially resolving nanoscale structural morphologies by diffraction contrast. One of the critical challenges in experimental nanodiffraction data analysis is posed by the convergence angle of nanoscale focusing optics which creates simultaneous dependency of the far-field scattering data on three independent components of the local strain tensor-corresponding to dilation and two potential rigid body rotations of the unit cell. All three components are in principle resolvable through a spatially mapped sample tilt series; however, traditional data analysis is computationally expensive and prone to artifacts. In this study, we implement NanobeamNN, a convolutional neural network specifically tailored to the analysis of scanning probe X-ray microscopy data. NanobeamNN learns lattice strain and rotation angles from simulated diffraction of a focused X-ray nanobeam by an epitaxial thin film and can directly make reasonable predictions on experimental data without the need for additional fine-tuning. We demonstrate that this approach represents a significant advancement in computational speed over conventional methods, as well as a potential improvement in accuracy over the current standard.

Luo, Aileen [Cornell Univ., Ithaca, NY (United Sta↗

Differentiable multiphase flow model for physics-informed machine learning in reservoir pressure management

Accurate subsurface reservoir pressure control is extremely challenging due to geological heterogeneity and multiphase fluid-flow dynamics. Predicting behavior in this setting relies on high-fidelity physics-based simulations that are computationally expensive. Yet, the uncertain, heterogeneous properties that control these flows make it necessary to perform many of these expensive simulations, which is often prohibitive. To address these challenges, we introduce a physics-informed machine learning workflow that couples a fully differentiable multiphase flow simulator, which is implemented in the DPFEHM framework with a convolutional neural network (CNN). The CNN learns to predict fluid extraction rates from heterogeneous permeability fields to enforce pressure limits at critical reservoir locations. By incorporating transient multiphase flow physics into the training process, our method enables more practical and accurate predictions for realistic injection-extraction scenarios compared to previous works. To speed up training, we pretrain the model on single-phase, steady-state simulations and then finetune it on full multiphase scenarios, which dramatically reduces the computational cost. We demonstrate that high-accuracy training can be achieved with fewer than three thousand full-physics multiphase flow simulations – compared to previous estimates requiring up to ten million. This drastic reduction in the number of simulations is achieved by leveraging transfer learning from much less expensive single phase simulations.

25 ENERGY STORAGE↗

A non-intrusive framework using acoustic signals and deep learning for boiling diagnostics in visual-limited environments

Accurate monitoring of boiling heat transfer is critical for safeguarding high-power systems operating in environments where conventional optical diagnostics are hindered by radiation fields or restricted visual accessibility. This study presents a non-intrusive framework that integrates hydroacoustic sensing with deep learning to infer near-wall boiling characteristics and enable predictive thermal assessment without visual access. In a prototypical subcooled flow-boiling facility representative of the Isotope Production Facility (IPF) at Los Alamos, hydrophones capture boiling-induced acoustic emissions that are transformed into background-removed Short-Time Fourier Transform (STFT) spectrograms. A convolutional neural network (CNN) then regresses heat flux, wall superheat, and key bubble parameters directly from these spectrograms. The CNN achieved predictive accuracy under nominal conditions and demonstrated robustness and generalization under acoustic noise for Signal-to-Noise Ratios (SNRs) down to approximately 0 dB. When integrated into an ANSYS CFX wall-boiling model, the acoustically inferred parameters reproduced boiling curve and critical heat flux (CHF) values consistent with image-based benchmarks. Furthermore, the model retained reliable performance under moderate variations in bulk temperature, flow rate, and hydrophone placement, confirming its generalizability across practical boundary conditions. These results demonstrate the feasibility of hydroacoustic-based deep learning as a viable path toward real-time, radiation-tolerant boiling diagnostics and predictive thermal safety assessment in inaccessible systems such as the IPF.

42 ENGINEERING↗

Fast and accurate view classification of echocardiograms using deep learning

Echocardiography is essential to cardiology. However, the need for human interpretation has limited echocardiography’s full potential for precision medicine. Deep learning is an emerging tool for analyzing images but has not yet been widely applied to echocardiograms, partly due to their complex multi-view format. The essential first step toward comprehensive computer-assisted echocardiographic interpretation is determining whether computers can learn to recognize these views. We trained a convolutional neural network to simultaneously classify 15 standard views (12 video, 3 still), based on labeled still images and videos from 267 transthoracic echocardiograms that captured a range of real-world clinical variation. Our model classified among 12 video views with 97.8% overall test accuracy without overfitting. Even on single low-resolution images, accuracy among 15 views was 91.7% vs. 70.2–84.0% for board-certified echocardiographers. Data visualization experiments showed that the model recognizes similarities among related views and classifies using clinically relevant image features. Our results provide a foundation for artificial intelligence-assisted echocardiographic interpretation.

Madani, Ali↗

Large electromechanical strain and unconventional domain switching near phase convergence in a Pb-free ferroelectric

In many ferroelectrics, large electromechanical strains are observed near regions of composition- or temperature- driven phase coexistence. Phenomenologically, this is attributed to easy re-orientation of the polarization vector and/or phase transition, although their effects are highly convoluted and difficult to distinguish experimentally. Here, we used synchrotron X-ray scattering and digital image correlation to differentiate between the microscopic mechanisms leading to large electrostrains in an exemplary Pb-free piezoceramic Sn-doped barium calcium zirconate titanate. Large electrostrains of ~0.2% measured at room-temperature are attributed to an unconventional effect, wherein polarization switching is aided by a reversible phase transition near the tetragonal-orthorhombic phase boundary. Additionally, electrostrains of ~0.1% or more could be maintained from room temperature to 140°C due to a succession of different microscopic mechanisms. In situ X-ray diffraction elucidates that while 90° domain reorientation is pertinent below the Curie temperature ( T C ), isotropic distortion of polar clusters is the dominant mechanism above T C .

36 MATERIALS SCIENCE↗

Multi-resolution partial differential equations preserved learning framework for spatiotemporal dynamics

Traditional data-driven deep learning models often struggle with high training costs, error accumulation, and poor generalizability in complex physical processes. Physics-informed deep learning (PiDL) addresses these challenges by incorporating physical principles into the model. Most PiDL approaches regularize training by embedding governing equations into the loss function, yet this depends heavily on extensive hyperparameter tuning to weigh each loss term. To this end, we propose to leverage physics prior knowledge by “baking” the discretized governing equations into the neural network architecture via the connection between the partial differential equations (PDE) operators and network structures, resulting in a PDE-preserved neural network (PPNN). This method, embedding discretized PDEs through convolutional residual networks in a multi-resolution setting, largely improves the generalizability and long-term prediction accuracy, outperforming conventional black-box models. The effectiveness and merit of the proposed methods have been demonstrated across various spatiotemporal dynamical systems governed by spatiotemporal PDEs, including reaction-diffusion, Burgers’, and Navier-Stokes equations.

97 MATHEMATICS AND COMPUTING↗

Global field reconstruction from sparse sensors with Veronoi tessellation-assisted deep learning

Achieving accurate and robust global situational awareness of a complex time-evolving field from a limited number of sensors has been a longstanding challenge. This reconstruction problem is especially difficult when sensors are sparsely positioned in a seemingly random or unorganized manner, which is often encountered in a range of scientific and engineering problems. Moreover, these sensors can be in motion and can become online or offline over time. The key leverage in addressing this scientific issue is the wealth of data accumulated from the sensors. As a solution to this problem, we propose a data-driven spatial field recovery technique founded on a structured grid-based deep-learning approach for arbitrary positioned sensors of any numbers. It should be noted that the naïve use of machine learning becomes prohibitively expensive for global field reconstruction and is furthermore not adaptable to an arbitrary number of sensors. In the present work, we consider the use of Voronoi tessellation to obtain a structured-grid representation from sensor locations enabling the computationally tractable use of convolutional neural networks. One of the central features of the present method is its compatibility with deep-learning based super-resolution reconstruction techniques for structured sensor data that are established for image processing. The proposed reconstruction technique is demonstrated for unsteady wake flow, geophysical data, and three-dimensional turbulence. The current framework is able to handle an arbitrary number of moving sensors, and thereby overcomes a major limitation with existing reconstruction methods. The presented technique opens a new pathway towards the practical use of neural networks for real-time global field estimation.

Fukami, Kai↗

Topological structure of complex predictions

Abstract Current complex prediction models are the result of fitting deep neural networks, graph convolutional networks or transducers to a set of training data. A key challenge with these models is that they are highly parameterized, which makes describing and interpreting the prediction strategies difficult. We use topological data analysis to transform these complex prediction models into a simplified topological view of the prediction landscape. The result is a map of the predictions that enables inspection of the model results with more specificity than dimensionality-reduction methods such as tSNE and UMAP. The methods scale up to large datasets across different domains. We present a case study of a transformer-based model previously designed to predict expression levels of a piece of DNA in thousands of genomic tracks. When the model is used to study mutations in the BRCA1 gene, our topological analysis shows that it is sensitive to the location of a mutation and the exon structure of BRCA1 in ways that cannot be found with tools based on dimensionality reduction. Moreover, the topological framework offers multiple ways to inspect results, including an error estimate that is more accurate than model uncertainty. Further studies show how these ideas produce useful results in graph-based learning and image classification.

Computer Science↗

Defect graph neural networks for materials discovery in high-temperature clean-energy applications

We present a graph neural network approach that fully automates the prediction of defect formation enthalpies for any crystallographic site from the ideal crystal structure, without the need to create defected atomic structure models as input. Here we used density functional theory reference data for vacancy defects in oxides, to train a defect graph neural network (dGNN) model that replaces the density functional theory supercell relaxations otherwise required for each symmetrically unique crystal site. Interfaced with thermodynamic calculations of reduction entropies and associated free energies, the dGNN model is applied to the screening of oxides in the Materials Project database, connecting the zero-kelvin defect enthalpies to high-temperature process conditions relevant for solar thermochemical hydrogen production and other energy applications. The dGNN approach is applicable to arbitrary structures with an accuracy limited principally by the amount and diversity of the training data, and it is generalizable to other defect types and advanced graph convolution architectures. In conclusion, it will help to tackle future materials discovery problems in clean energy and beyond.

97 MATHEMATICS AND COMPUTING↗

Exploiting deep learning and volunteered geographic information for mapping buildings in Kano, Nigeria

Buildings in the developing world are inadequately mapped. Lack of such critical geospatial data adds unnecessary challenges to locating and reaching a large segment of the world’s most vulnerable population, impeding sustainability goals ranging from disaster relief to poverty reduction. Use of volunteered geographic information (VGI) has emerged as a widely accepted source to fill such voids. Despite its promise, availability of building maps for developing countries significantly lags behind demand. We present a new approach, coupling deep convolutional neural networks (CNNs) with VGI for automating building map generation from high-resolution satellite images for Kano state, Nigeria. Specifically, we trained a CNN with VGI building outlines of limited quality and quantity and generated building maps for a 50,000 km 2 area. Resulting maps are in strong agreement with existing settlement maps and require a fraction of the manual input needed for the latter. The VGI-based maps will provide support across multiple facets of socioeconomic development in Kano state, and demonstrates potential advancements in current mapping capabilities in resource constrained countries.

99 GENERAL AND MISCELLANEOUS↗

Pure electronic metal-insulator transition at the interface of complex oxides

We observed complex materials in electronic phases and transitions between them often involve coupling between many degrees of freedom whose entanglement convolutes understanding of the instigating mechanism. Metal-insulator transitions are one such problem where coupling to the structural, orbital, charge, and magnetic order parameters frequently obscures the underlying physics. We demonstrate a way to unravel this conundrum by heterostructuring a prototypical multi-ordered complex oxide NdNiO3 in ultra thin geometry, which preserves the metal-to-insulator transition and bulk-like magnetic order parameter, but entirely suppresses the symmetry lowering and long-range charge order parameter. Furthermore, these findings illustrate the utility of heterointerfaces as a powerful method for removing competing order parameters to gain greater insight into the nature of the transition, here revealing that the magnetic order generates the transition independently, leading to an exceptionally rare purely electronic metal-insulator transition with no symmetry change.

36 MATERIALS SCIENCE↗

PRESTO polarization transfer to quadrupolar nuclei: Implications for dynamic nuclear polarization

In this study, we show both experimentally and numerically on a series of model systems that in experiments involving transfer of magnetization from 1 H to the quadrupolar nuclei under magic-angle-spinning (MAS), the PRESTO technique consistently outperforms traditionally used cross polarization (CP), affording more quantitative intensities, improved lineshapes, better overall sensitivity, and straightforward optimization. This advantage derives from the fact that PRESTO circumvents the convoluted and uncooperative spin dynamics during the CP transfer under MAS, by replacing the spin-locking of quadrupolar nuclei with a single central transition selective 90° pulse and using a symmetry-based recoupling sequence in the 1 H channel. This is important in the context of dynamic nuclear polarization (DNP) NMR of quadrupolar nuclei, where the efficient transfer of enhanced 1 H polarization is desired to obtain the highest sensitivity.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Is the surface oxygen exchange rate linked to bulk ion diffusivity in mixed conducting Ruddlesden–Popper phases?

There is a possible link between oxygen surface exchange rate and bulk oxygen anion diffusivity in mixed ionic and electronic conducting oxides; it is a topic of great interest and debate. While a large body of experimental evidence and theoretical analyses support a link, observed differences between bulk and surface composition of these materials are hard to reconcile with this observation. This is further compounded by potential problems with simultaneous measurement of both parameters. Here we utilize separate techniques, in situ neutron diffraction and pulsed isotopic surface exchange, to examine bulk ion mobility and surface oxygen exchange rates of three Ruddlesden-Popper phases, general form A n-1 A 2 'BnO 3n+1 , A n-1 A 2 'BnX 3n+1 ; LaSrCo 0.5 Fe 0.5 O 4-δ (n = 1), La 0.3 Sr 2.7 CoFeO 7-δ (n = 2) and LaSr 3 Co 1.5 Fe 1.5 O 10-δ (n = 3). These measurements are complemented by surface composition determination via high sensitivity-low energy ion scattering. We observe a correlation between bulk ion mobility and surface exchange rate between materials. The surface exchange rates vary by more than one order of magnitude with high anion mobility in the bulk of an oxygen vacancy-rich n = 2 Ruddlesden-Popper material correlating with rapid oxygen exchange. Furthermore this is in contrast with the similar surface exchange rates which we may expect due to similar surface compositions across all three samples. This paper conclude that experimental limitations lead to inherent convolution of surface and bulk rates, and that surface exchange steps are not likely to be rate limiting in oxygen incorporation.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Dissolution kinetics of a sodium borosilicate glass in Tris buffer solutions: impact of Tris concentration and acid (HCl/HNO 3 ) identity

Here, understanding the corrosion behavior of glasses in near-neutral environments is crucial for many technologies including glasses for regenerative medicine and nuclear waste immobilization. To maintain consistent pH values throughout experiments in the pH = 7 to 9 regime, buffer solutions containing tris(hydroxymethyl)aminomethane (“Tris”, or sometimes called THAM) are recommended in ISO standards 10993-14 and 23317 for evaluating biomaterial degradation and utilized throughout glass dissolution behavior literature—a key advantage being the absence of dissolved alkali/alkaline earth cations (i.e. Na + or Ca 2+ ) that can convolute experimental results due to solution feedback effects. Although Tris is effective at maintaining the solution pH, it has presented concerns due to the adverse artificial effects it produces while studying glass corrosion, especially in borosilicate glasses. Therefore, many open questions still remain on the topic of borosilicate glass interaction with Tris-based solutions. We have approached this topic by studying the dissolution behavior of a sodium borosilicate glass in a wide range of Tris-based solutions at 65 °C with varied acid identity (Tris–HCl vs. Tris–HNO 3 ), buffer concentration (0.01 M to 0.5 M), and pH (7–9). The results have been discussed in reference to previous studies on this topic and the following conclusions have been made: (i) acid identity in Tris-based solutions does not exhibit a significant impact on the dissolution behavior of borosilicate glasses, (ii) ~0.1 M Tris-based solutions are ideal for maintaining solution pH in the absence of obvious undesirable solution chemistry effects, and (iii) Tris–boron complexes can form in solution as a result of glass dissolution processes. The complex formation, however, exhibits a distinct temperature-dependence, and requires further study to uncover the precise mechanisms by which Tris-based solutions impact borosilicate glass dissolution behavior.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

ChemPix: automated recognition of hand-drawn hydrocarbon structures using deep learning

Inputting molecules into chemistry software, such as quantum chemistry packages, currently requires domain expertise, expensive software and/or cumbersome procedures. Leveraging recent breakthroughs in machine learning, we develop ChemPix: an offline, hand-drawn hydrocarbon structure recognition tool designed to remove these barriers. A neural image captioning approach consisting of a convolutional neural network (CNN) encoder and a long short-term memory (LSTM) decoder learned a mapping from photographs of hand-drawn hydrocarbon structures to machine-readable SMILES representations. We generated a large auxiliary training dataset, based on RDKit molecular images, by combining image augmentation, image degradation and background addition. Additionally, a small dataset of ~600 hand-drawn hydrocarbon chemical structures was crowd-sourced using a phone web application. These datasets were used to train the image-to-SMILES neural network with the goal of maximizing the hand-drawn hydrocarbon recognition accuracy. By forming a committee of the trained neural networks where each network casts one vote for the predicted molecule, we achieved a nearly 10 percentage point improvement of the molecule recognition accuracy and were able to assign a confidence value for the prediction based on the number of agreeing votes. The ensemble model achieved an accuracy of 76% on hand-drawn hydrocarbons, increasing to 86% if the top 3 predictions were considered.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Resolving buried optoelectronic features in metal halide perovskites via modulation spectroscopy studies

As research on both bulk and low dimensional metal halide perovskites (MHPs) continues to grow, the tools necessary to gain insights into their exotic and highly convoluted optoelectronic features must also expand. Electroabsorption (EA) is a modulation spectroscopy technique that is exceptionally valuable at deconvoluting overlapping spectral features as well as discerning between different electronic environments in semiconductors. This review outlines the critical shortcomings of traditional optical spectroscopy in determining essential properties such as the bandgap and exciton binding energy. In this report we provide a brief overview of the working principles of EA, focusing on the differences between bound and unbound charge carriers that result in unique behavior when interacting with an applied electric field. We discuss key studies highlighting the unique characterization available when coupling EA spectroscopy with traditional steady-state optical tools to investigate interesting and complex optical features in MHPs. We conclude that EA is a crucial tool for pushing the boundaries of our understanding of the optoelectronic properties of MHP thin films. When other optical characterization methods fall short in the richness of data provided, EA can bridge the knowledge gap to provide a complete optoelectronic characterization of novel MHPs and deepen the understanding of current structures and compositions as a function of their structural and morphological dimensionality.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Refine your search to explore more results.