Search NASA⌕ Search

SEARCH · Search NASA

Results for “Neural Patterning”

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 433 records · Page 24
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Detecting rare neutral atomic-carbon absorbers with a deep neural network

ABSTRACT C i absorbers play an important role as indicators for exploring the presence of cold gas in the interstellar medium of galaxies. However, the current data base of C i absorbers is very limited due to their weak absorption feature and rarity. Here, we report results from a search of C i λλ1560, 1656 absorption lines using Mg ii absorbers as signposts with modified deep learning algorithms, which provides a very quick way to search for weak C i absorber candidates. A total of 107 C i absorbers were detected, which nearly doubles the size of previously known samples. In addition, we found 17 C i absorbers to be associated with 2175 Å dust absorbers (2DAs), i.e. about 16 per cent C i absorbers are associated with 2DAs. Comparing the average dust depletion patterns of C i absorbers with those of damped Lyman α absorbers (DLAs), Mg ii absorbers, Ca ii absorbers, and 2175 Å dust absorbers (2DAs) shows that C i absorbers generally have environments with more dust than DLAs, Mg ii, and Ca ii absorbers, but similar to dust in 2DAs. Similarity between the dust depletion pattern of C i absorbers to that of the warm disc in the Milky Way indicates that C i absorption clouds are possibly associated with disc components in distant galaxies. Therefore, C i absorbers are confirmed to be excellent probes to trace cold gas and dust in the Universe.

Ge, Jian↗
NASA NTRS1989

Cloud cover determination in polar regions from satellite imagery

The objectives are to develop a suitable validation data set for evaluating the effectiveness of the International Satellite Cloud Climatology Project (ISCCP) algorithm for cloud retrieval in polar regions, to identify limitations of current procedures and to explore potential means to remedy them using textural classifiers, and to compare synoptic cloud data from model runs with observations. Toward the first goal, a polar data set consisting of visible, thermal, and passive microwave data was developed. The AVHRR and SMMR data were digitally merged to a polar stereographic projection with an effective pixel size of 5 sq km. With this data set, two unconventional methods of classifying the imagery for the analysis of polar clouds and surfaces were examined: one based on fuzzy sets theory and another based on a trained neural network. An algorithm for cloud detection was developed from an early test version of the ISCCP algorithm. This algorithm includes the identification of surface types with passive microwave, then temporal tests at each pixel location in the cloud detection phase. Cloud maps and clear sky radiance composites for 5 day periods are produced. Algorithm testing and validation was done with both actural AVHRR/SMMR data, and simulated imagery. From this point in the algorithm, groups of cloud pixels are examined for their spectral and textural characteristics, and a procedure is developed for the analysis of cloud patterns utilizing albedo, IR temperature, and texture. In a completion of earlier work, empirical analyses of arctic cloud cover were explored through manual interpretations of DMSP imagery and compared to U.S. Air Force 3D-nephanalysis. Comparisons of observed cloudiness from existing climatologies to patterns computed by the GISS climate model were also made.

Barry, R. G.↗
NASA NTRS2004

Fossil Signatures Using Elemental Abundance Distributions and Bayesian Probabilistic Classification

Elemental abundances (C6, N7, O8, Na11, Mg12, Al3, P15, S16, Cl17, K19, Ca20, Ti22, Mn25, Fe26, and Ni28) were obtained for a set of terrestrial fossils and the rock matrix surrounding them. Principal Component Analysis extracted five factors accounting for the 92.5% of the data variance, i.e. information content, of the elemental abundance data. Hierarchical Cluster Analysis provided unsupervised sample classification distinguishing fossil from matrix samples on the basis of either raw abundances or PCA input that agreed strongly with visual classification. A stochastic, non-linear Artificial Neural Network produced a Bayesian probability of correct sample classification. The results provide a quantitative probabilistic methodology for discriminating terrestrial fossils from the surrounding rock matrix using chemical information. To demonstrate the applicability of these techniques to the assessment of meteoritic samples or in situ extraterrestrial exploration, we present preliminary data on samples of the Orgueil meteorite. In both systems an elemental signature produces target classification decisions remarkably consistent with morphological classification by a human expert using only structural (visual) information. We discuss the possibility of implementing a complexity analysis metric capable of automating certain image analysis and pattern recognition abilities of the human eye using low magnification optical microscopy images and discuss the extension of this technique across multiple scales.

Hoover, Richard B.↗
DOE OSTI2026

Deciphering the Solvation Structure of Aqueous ZnCl 2 Solutions from X-ray Absorption Spectra Using the Interpretable Graph Neural Network

Machine learning (ML) provides powerful pathways for predicting spectroscopic observables from atomic structures, but its broader impact depends on making model predictions interpretable in terms of physical and chemical principles. Here, we introduce a physics-guided graph neural network (GNN) model that predicts Zn K-edge X-ray spectroscopy (XAS) spectra of aqueous ZnCl 2 solutions. Training data are generated from ab initio XAS calculations on molecular dynamics snapshots obtained using a machine learning interatomic potential. The GNN reproduces experimental spectra across concentrations from dilute (<0.1 m) to highly concentrated (30 m, “water-in-salt”) regimes and scales efficiently to large, disordered liquid systems beyond the reach of conventional ab initio approaches. Gradient-based attribution analysis reveals that the model learns physically meaningful structure-spectrum relationships. Ligand-specific attributions reflect orbital hybridization patterns and the origin of the excitations derived from the density functional theory. Bond-length attributions recover spectral shifts consistent with multiple-scattering theory. Finally, this work bridges data-driven prediction with electronic-structure theory, establishing a general paradigm for interpretable ML that links atomic structure, electronic structure, and spectroscopic observables.

25 ENERGY STORAGE↗
DOE OSTI2026

Forced Component Estimation Statistical Method Intercomparison Project (ForceSMIP)

Anthropogenic climate change is unfolding rapidly, yet its regional manifestation can be obscured by internal variability. A primary goal of climate science is to identify the externally forced climate response from among the noise of internal variability. Separating the forced response from internal variability can be addressed in climate models by using a large ensemble to average over different possible realizations of internal variability. However, with only one realization of the real world, it is a major challenge to isolate the forced response directly in observations. In the Forced Component Estimation Statistical Method Intercomparison Project (ForceSMIP), contributors used existing and newly developed statistical and machine learning methods to estimate the forced response over 1950–2022 within individual realizations of the climate system. Participants used neural networks, linear inverse models, fingerprinting methods, and low-frequency component analysis, among other approaches. These methods were trained using large ensembles from multiple climate models and then applied to observations. Here, we evaluate method performance within large ensembles and investigate the estimates of the forced response in observations. Our results show that many different types of methods are skillful for estimating the forced response in climate models, though the relative skill of individual methods varies depending on the variable and evaluation metric. Methods with comparable skill in models can give a wide range of estimates of the forced response pattern in observations, illustrating the epistemic uncertainty in forced response estimates. ForceSMIP gives new insights into the forced response in observations, its uncertainty, and methods for its estimation.

Climate attribution↗
NASA NTRS2000

Trainable Gene Regulation Networks with Applications to Drosophila Pattern Formation

This chapter will very briefly introduce and review some computational experiments in using trainable gene regulation network models to simulate and understand selected episodes in the development of the fruit fly, Drosophila melanogaster. For details the reader is referred to the papers introduced below. It will then introduce a new gene regulation network model which can describe promoter-level substructure in gene regulation. As described in chapter 2, gene regulation may be thought of as a combination of cis-acting regulation by the extended promoter of a gene (including all regulatory sequences) by way of the transcription complex, and of trans-acting regulation by the transcription factor products of other genes. If we simplify the cis-action by using a phenomenological model which can be tuned to data, such as a unit or other small portion of an artificial neural network, then the full transacting interaction between multiple genes during development can be modelled as a larger network which can again be tuned or trained to data. The larger network will in general need to have recurrent (feedback) connections since at least some real gene regulation networks do. This is the basic modeling approach taken, which describes how a set of recurrent neural networks can be used as a modeling language for multiple developmental processes including gene regulation within a single cell, cell-cell communication, and cell division. Such network models have been called "gene circuits", "gene regulation networks", or "genetic regulatory networks", sometimes without distinguishing the models from the actual modeled systems.

Mjolsness, Eric↗
NASA NTRS2002

An amphioxus nodal gene (AmphiNodal) with early symmetrical expression in the organizer and mesoderm and later asymmetrical expression associated with left-right axis formation

The full-length sequence and zygotic expression of an amphioxus nodal gene are described. Expression is first detected in the early gastrula just within the dorsal lip of the blastopore in a region of hypoblast that is probably comparable with the vertebrate Spemann's organizer. In the late gastrula and early neurula, expression remains bilaterally symmetrical, limited to paraxial mesoderm and immediately overlying regions of the neural plate. Later in the neurula stage, all neural expression disappears, and mesodermal expression disappears from the right side. All along the left side of the neurula, mesodermal expression spreads into the left side of the gut endoderm. Soon thereafter, all expression is down-regulated except near the anterior and posterior ends of the animal, where transcripts are still found in the mesoderm and endoderm on the left side. At this time, expression also begins in the ectoderm on the left side of the head, in the region where the mouth later forms. These results suggest that amphioxus and vertebrate nodal genes play evolutionarily conserved roles in establishing Spemann's organizer, patterning the mesoderm rostrocaudally and setting up the asymmetrical left-right axis of the body.

Non-NASA Center↗
NASA NTRS1995

Neural tuning characteristics of auditory primary afferents in the chicken embryo

Primary afferent activity was recorded from the cochlear ganglion in chicken embryos (Gallus domesticus) at 19 days of incubation (E19). The ganglion was accessed via the recessus scala tympani and impaled with glass micropipettes. Frequency tuning curves were obtained using a computerized threshold tracking procedure. Tuning curves were evaluated to determine characteristics frequencies (CFs), CF thresholds, slopes of low and high frequency flanks, and tip sharpness (Q10dB). The majority of tuning curves exhibited the typical 'V' shape described for older birds and, on average, appeared relatively mature based on mean values for CF thresholds (59.6 +/- 20.3 dBSPL) and tip sharpness (Q10dB = 5.2 +/- 3). The mean slopes of low (61.9 +/- 37 dB/octave) and high (64.6 +/- 33 dB/octave) frequency flanks although comparable were somewhat less than those reported for 21-day-old chickens. Approximately 14% of the tuning curves displayed an unusual 'saw-tooth' pattern. CFs ranged from 188 to 1623 Hz. The highest CF was well below those reported for post-hatch birds. In addition, a broader range of Q10dB values (1.2 to 16.9) may related to a greater variability in embryonic tuning curves. Overall, these data suggest that an impressive functional maturity exists in the embryo at E19. The most significant sign of immaturity was the limited expression of high frequencies. It is argued that the limited high CF in part may be due to the developing middle ear transfer function and/or to a functionally immature cochlear base.

Non-NASA Center↗
NASA NTRS1990

Non-Lipschitzian neural dynamics

A novel approach is presented which is motivated by an attempt to remove one of the most fundamental limitations of artificial neural networks: their rigid behavior as compared with even the simplest biological systems. It is demonstrated that non-Lipschitzian dynamics, based on the faliure of the Lipschitz conditions at repellers, displays a new qualitative effect, i.e., a multichoice response to periodic external excitations. This makes it possible to construct unpredictable systems, represented in the form of coupled activation and learning dynamical equations. It is shown that unpredictable systems can be controlled by sign strings which uniquely define the system behavior by specifying the direction of the motions at the critical points. Unpredictable systems driven by sign strings are extremely flexible and can serve as a powerful tool for complex pattern recognition.

Barhen, Jacob↗
NASA NTRS2003

Morphology of the Vestibular Utricule in Toadfish, Opsanus Tau

The uticle is an otolith organ in the vertebrate inner ear that provides gravitoinertial acceleration information into the vestibular reflex pathways. The aim of the present study was to provide an anatomical description of this structure in the adult oyster toadfish, and establish a morphological basis for interpretation of subsequent functional studies. Light, scanning electron and transmission electron microscopy were applied to visualize the sensory epithelium and its neural innervation. Electrophysiological techniques were used to identify utricular afferents by their response to translation stimuli. Similar to nerve afferents supplying the semicircular canals and lagena, utricular afferents commonly exhibit a short-latency increase of firing rate in response to electrical activation of the central efferent pathway. Afferents were labeled with biocytin either intraaxonally or with extracellular bulk deposits. Light microscope images of serial thick sections were used to make three-dimensional reconstructions of individual labeled afferents to identify the dendritic morphology with respect to epithelial location. Scanning electron microscopy was used to visualize the surface of the otolith mass facing the otolith membrane, and the hair cell polarization patterns of strioler and extrastriolar regions. Transmission electron micrographs of serial thin sections were compiled to create a three-dimensional reconstruction of the labeled afferent over a segment of its dendritic field and to examine the hair cell-afferent synaptic contacts.

Bass, L.↗
DOE OSTI2026

Reconstruction of Six-Dimensional Phase Space

A phase space is a mathematical representation of all possible physical states of a system. Particle beams at Fermilab exist within a six-dimensional (6D) phase space defined by three positional components, (x, y, z) and three momentum components, (px, py, pz). To reconstruct this space implies taking measurement data from detectors and mapping out particle behavior using computational methods. The beam detectors, however, are only able to detect spatial distribution among the events of the beam, therefore being limited to positional data. Also, due to the vast number of events in a particle beam, it is extremely difficult to analyze and differentiate every single one’s behavior. However, with Machine Learning (ML), which can distinguish between patterns and map out particle behavior more efficiently. We first used the particle beam software, G4beamline, to simulate a 10,000-event muon beam, adjusting parameters such as initial momentum magnitude (p¬0) and virtual detector position. Using ten virtual detectors, we analyzed p0 values such that minimum 9,990 events were analyzed by every detector. We then input the data from these beam simulations to a C++ program, that randomly selects 100 events, and creates a 2D histogram based on spatial distribution, detector position, and event intensity. This process is repeated 100 times to create 100 histograms per p0 value. These images were then input to a modified ResNet18 Convolutional Neural Network (CNN) for training, and to predict p0 from some unseen set of histograms. The model was accurate when trained on momentum increments of 5 MeV/c and provided with denser training samples around highly variable test values. These results displayed machine learning being able to accurately predict p0 from being trained on different particle behaviors.

Shirlee, Jermain [Fermilab]↗
DOE OSTI2026

HARMONY: Large-Scale Architecture Search for Efficient Hybrid Language Models

As large language models scale to trillions of parameters, their computational and memory requirements present critical challenges for efficient training and deployment. While Mixture of Experts (MoE) architectures enable efficient scaling through sparse parameter activation, and state-space models like Mamba offer linear-time complexity, principled methods for combining these paradigms remain undeveloped. We introduce HARMONY (Hybrid Architecture Research for Mamba, Optimized with Neural efficiencY), a multi-objective evolutionary neural architecture search framework for discovering efficient hybrid language models that integrate Transformer attention mechanisms, Mixture-of-Experts routing, and Mamba state-space components. Through large-scale distributed search using 16,384 MI250X GPUs on the Frontier supercomputer, HARMONY explores a comprehensive design space encompassing six attention variants (MHA, MQA, GQA, MLA, SWA, and Mamba-2), variable MoE configurations with both routed and shared experts, and extensive Mamba hyperparameters. Our framework discovers heterogeneous architectures that balance training performance with computational efficiency through multi-objective optimization incorporating latency penalties and fitness-based selection. Analysis of discovered architectures reveals that optimal hybrid designs favor heterogeneous component mixing rather than homogeneous patterns, with Mamba-2 and Multi-Head Latent Attention (MLA) emerging as preferred mechanisms. Discovered architectures demonstrate superior training efficiency: our best configuration achieves a final perplexity of 1.0874 with 2.38B parameters while processing 4,320 tokens/second, outperforming significantly larger manually designed models. Full-scale evaluation shows HARMONY's top architectures achieve better loss trajectories than equivalently-sized models using state-of-the-art configurations including Mixtral, Jamba, and Samba. Additionally, we demonstrate 91% weak scaling efficiency when training discovered 36B-parameter models across 1,024 GPUs. HARMONY is released as an open framework with comprehensive tools for building and training hybrid models using expert-data-pipeline parallelism, democratizing access to automated architecture design for next-generation language models.

Herron, Emily [ORNL] (ORCID:0000000273008172)↗
NASA NTRS1990

30 years of adaptive neural networks - Perceptron, Madaline, and backpropagation

Fundamental developments in feedforward artificial neural networks from the past thirty years are reviewed. The history, origination, operating characteristics, and basic theory of several supervised neural-network training algorithms (including the perceptron rule, the least-mean-square algorithm, three Madaline rules, and the backpropagation technique) are described. The concept underlying these iterative adaptation algorithms is the minimal disturbance principle, which suggests that during training it is advisable to inject new information into a network in a manner that disturbs stored information to the smallest extent possible. The two principal kinds of online rules that have developed for altering the weights of a network are examined for both single-threshold elements and multielement networks. They are error-correction rules, which alter the weights of a network to correct error in the output response to the present input pattern, and gradient rules, which alter the weights of a network during each pattern presentation by gradient descent with the objective of reducing mean-square error (averaged over all training patterns).

Widrow, Bernard↗
NASA NTRS2024

Evaluation of Machine Learning and Deep Learning Algorithms for Fire Prediction in Southeast Asia

Vegetation fires are prevalent in South/Southeast Asian countries, making fire prediction crucial due to their potential environmental, economic, and social impacts. Accurate predictions of fires facilitate timely interventions, helping to mitigate uncontrolled fires that can lead to biodiversity loss and air quality issues. In this study, we utilize VIIRS satellite-derived fire data alongside six machine learning and deep learning models—Simple Persistence, Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), CNN-LSTM, and ConvLSTM—to determine the most effective fire prediction model, using Root Mean Square Error (RMSE) as the metric. Our results indicate that the CNN model is the most reliable in regions with spatial dependencies, such as Brunei, Indonesia, Malaysia, the Philippines, Timor-Leste, and Thailand. Conversely, the ConvLSTM model excels in countries with complex spatiotemporal dynamics like Laos, Myanmar, and Vietnam. The CNN-LSTM hybrid model also performed well in Cambodia, suggesting a need for a balanced approach in areas requiring both spatial and temporal feature extraction. Furthermore, simpler models like Persistence and MLP showed limitations in capturing dynamic patterns and temporal dependencies. Our findings highlight the importance of evaluating models before implementing any decision support systems (DSS) in fire management. By tailoring models to specific regional fire data, we can enhance prediction accuracy and responsiveness, ultimately improving fire risk management in Southeast Asia and beyond.

Deep learning↗
DOE OSTI2025

A derecho climatology (2004–2021) in the United States based on machine learning identification of bow echoes

Due to their persistent widespread severe winds, derechos pose significant threats to human safety and property, with impacts comparable to many tornadoes and hurricanes. Yet, automated detection of derechos remains challenging due to the absence of spatiotemporally continuous observations and the complex criteria employed to define the phenomenon. This study presents an objective derecho detection approach capable of automatically identifying derechos through both observations and model results. The approach is grounded in a physically based definition of derechos and integrates three algorithms: (1) the Python Flexible Object Tracker (PyFLEXTRKR) algorithm to track mesoscale convective systems (MCSs), (2) a semantic segmentation convolutional neural network to identify bow echoes, and (3) a comprehensive classification algorithm to detect derechos within MCS life cycles and distinguish derecho-producing from non-derecho-producing MCSs. Using this approach, we developed a novel high-resolution (4 km and hourly) observational dataset of derechos and accompanying derecho-producing MCSs over the United States east of the Rocky Mountains from 2004 to 2021. The dataset consists of two subsets based on different gust speed data sources and is analyzed to document the climatology of derechos in the United States. On average, 12–15 derechos are identified per year, aligning with previous estimations (∼6–21 events annually). The spatial distribution and seasonal variation patterns are consistent with prior studies, showing peak occurrences in the Great Plains and the Midwest during the warm season. Additionally, during the study period, derechos account for approximately 3.1 % of measured damaging gusts (≥25.93 m s−1) over the eastern United States. The dataset is publicly available at https://doi.org/10.5281/zenodo.14835362 (Li et al., 2025).

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS1994

Experiment K-7-18: Effects of Spaceflight in the Muscle Adductor Longus of Rats Flown in the Soviet Biosatellite Cosmos 2044: A Study Employing Neural Cell Adhesion Molecules (N-CAM) Immunocytochemistry and Conventional Morphological Techniques (Light and Electron Microscopy) - Part 1

The effects of spaceflight upon the 'slow' muscle adductor longus was examined in rats flown in the Soviet Biosatellite COSMOS 2044. Three groups - synchronous, vivarium and basal served as controls. The techniques employed included standard methods for light microscopy, N-CAM immunocytochemistry and electron microscopy. Light microscopic observations revealed myofiber atrophy, contraction bands and segmental necrosis accompanied by cellular infiltrates composed of macrophages, leucocytes and mononuclear cells. N-CAM immunoreactivity was seen (N-CAM-IR) on the myofiber surface, satellite cells and in regenerating myofibers reminiscent of myotubes. Ultrastructural alterations included Z band streaming, disorganization of myofibrillar architecture, sarcoplasmic degradation, extensive segmental necrosis with preservation of the basement membrane, degenerative phenomena of the capillary endothelium and cellular invasion of necrotic areas. Regenerating myofibers were identified by the presence of increased amounts of ribosomal aggregates and chains of polyribosomes associated with myofilaments that displayed varied distributive patterns. The principal electron microscopic changes of the neuromuscular junctions consisted of a decrease or absence of synaptic vesicles, degeneration of axon terminals, increased number of microtubules, vacant axonal spaces and axonal sprouting. The present observations indicate that major alterations such as myofibrillar disruption and necrosis, muscle regeneration and denervation and synaptic remodeling at the level of the neuromuscular junction may take place during spaceflight.

Daunton, N. G.↗
NASA NTRS1993

A Novel Optical/digital Processing System for Pattern Recognition

This paper describes two processing algorithms that can be implemented optically: the Radon transform and angular correlation. These two algorithms can be combined in one optical processor to extract all the basic geometric and amplitude features from objects embedded in video imagery. We show that the internal amplitude structure of objects is recovered by the Radon transform, which is a well-known result, but, in addition, we show simulation results that calculate angular correlation, a simple but unique algorithm that extracts object boundaries from suitably threshold images from which length, width, area, aspect ratio, and orientation can be derived. In addition to circumventing scale and rotation distortions, these simulations indicate that the features derived from the angular correlation algorithm are relatively insensitive to tracking shifts and image noise. Some optical architecture concepts, including one based on micro-optical lenslet arrays, have been developed to implement these algorithms. Simulation test and evaluation using simple synthetic object data will be described, including results of a study that uses object boundaries (derivable from angular correlation) to classify simple objects using a neural network.

Boone, Bradley G.↗
NASA NTRS2003

Improved Autoassociative Neural Networks

Improved autoassociative neural networks, denoted nexi, have been proposed for use in controlling autonomous robots, including mobile exploratory robots of the biomorphic type. In comparison with conventional autoassociative neural networks, nexi would be more complex but more capable in that they could be trained to do more complex tasks. A nexus would use bit weights and simple arithmetic in a manner that would enable training and operation without a central processing unit, programs, weight registers, or large amounts of memory. Only a relatively small amount of memory (to hold the bit weights) and a simple logic application- specific integrated circuit would be needed. A description of autoassociative neural networks is prerequisite to a meaningful description of a nexus. An autoassociative network is a set of neurons that are completely connected in the sense that each neuron receives input from, and sends output to, all the other neurons. (In some instantiations, a neuron could also send output back to its own input terminal.) The state of a neuron is completely determined by the inner product of its inputs with weights associated with its input channel. Setting the weights sets the behavior of the network. The neurons of an autoassociative network are usually regarded as comprising a row or vector. Time is a quantized phenomenon for most autoassociative networks in the sense that time proceeds in discrete steps. At each time step, the row of neurons forms a pattern: some neurons are firing, some are not. Hence, the current state of an autoassociative network can be described with a single binary vector. As time goes by, the network changes the vector. Autoassociative networks move vectors over hyperspace landscapes of possibilities.

Hand, Charles↗