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 1,405 records · Page 78

Multilevel-in-width training for deep neural network regression

A common challenge in regression is that for many problems, the degrees of freedom required for a high-quality solution also allows for overfitting. Regularization is a class of strategies that seek to restrict the range of possible solutions so as to discourage overfitting while still enabling good solutions, and different regularization strategies impose different types of restrictions. In this paper, we present a multilevel regularization strategy that constructs and trains a hierarchy of neural networks, each of which has layers that are wider versions of the previous network's layers. Here, we draw intuition and techniques from the field of Algebraic Multigrid (AMG), traditionally used for solving linear and nonlinear systems of equations, and specifically adapt the Full Approximation Scheme (FAS) for nonlinear systems of equations to the problem of deep learning. Training through V-cycles then encourage the neural networks to build a hierarchical understanding of the problem. We refer to this approach as multilevel-in-width to distinguish from prior multilevel works which hierarchically alter the depth of neural networks. The resulting approach is a highly flexible framework that can be applied to a variety of layer types, which we demonstrate with both fully connected and convolutional layers. We experimentally show with PDE regression problems that our multilevel training approach is an effective regularizer, improving the generalize performance of the neural networks studied.

97 MATHEMATICS AND COMPUTING↗

Photovoltaic failure and degradation modes

The extensive photovoltaic field reliability literature was analyzed and reviewed. Future work is prioritized based upon information assembled from recent installations, and inconsistencies in degradation mode identification are discussed to help guide future publication on this subject. Reported failure rates of photovoltaic modules fall mostly in the range of other consumer products; however, the long expected useful life of modules may not allow for direct comparison. In general, degradation percentages are reported to decrease appreciably in newer installations that are deployed after the year 2000. However, these trends may be convoluted with varying manufacturing and installation quality world-wide. Modules in hot and humid climates show considerably higher degradation modes than those in desert and moderate climates, which warrants further investigation. Delamination and diode/j-box issues are also more frequent in hot and humid climates than in other climates. The highest concerns of systems installed in the last 10 years appear to be hot spots followed by internal circuitry discoloration. Encapsulant discoloration was the most common degradation mode, particularly in older systems. In newer systems, encapsulant discoloration appears in hotter climates, but to a lesser degree. Lastly, thin-film degradation modes are dominated by glass breakage and absorber corrosion, although the breadth of information for thin-film modules is much smaller than for x-Si.

14 SOLAR ENERGY↗

Quantifying leaf symptoms of sorghum charcoal rot in images of field‐grown plants using deep neural networks

Abstract Charcoal rot of sorghum (CRS) is a significant disease affecting sorghum crops, with limited genetic resistance available. The causative agent, Macrophomina phaseolina (Tassi) Goid, is a highly destructive fungal pathogen that targets over 500 plant species globally, including essential staple crops. Utilizing field image data for precise detection and quantification of CRS could greatly assist in the prompt identification and management of affected fields and thereby reduce yield losses. The objective of this work was to implement various machine learning algorithms to evaluate their ability to accurately detect and quantify CRS in red‐green‐blue images of sorghum plants exhibiting symptoms of infection. EfficientNet‐B3 and a fully convolutional network emerged as the top‐performing models for image classification and segmentation tasks, respectively. Among the classification models evaluated, EfficientNet‐B3 demonstrated superior performance, achieving an accuracy of 86.97%, a recall rate of 0.71, and an F1 score of 0.73. Of the segmentation models tested, FCN proved to be the most effective, exhibiting a validation accuracy of 97.76%, a recall rate of 0.68, and an F1 score of 0.66. As the size of the image patches increased, both models’ validation scores increased linearly, and their inference time decreased exponentially. This trend could be attributed to larger patches containing more information, improving model performance, and fewer patches reducing the computational load, thus decreasing inference time. The models, in addition to being immediately useful for breeders and growers of sorghum, advance the domain of automated plant phenotyping and may serve as a foundation for drone‐based or other automated field phenotyping efforts. Additionally, the models presented herein can be accessed through a web‐based application where users can easily analyze their own images.

Gonzalez, Emmanuel M.↗

The Wormholes Within: A Study of 1, 3, 5–Triamino–2, 4, 6–Trinitrobenzene Crystal Morphology by Micro and Nano–Scale X–Ray Computed Tomography and its Effects Upon the Shock Sensitivity of Detonation

We report that we understand heterogeneous-explosive detonation only to the extent that we can first measure the salient chemical and microstructural features. Barring an inordinate amount of trial and error, we can tailor the detonation properties of our HE formulations only to the extent that we understand (at least qualitatively) the same effects. As an insensitive high explosive, 1, 3, 5-triamino-2, 4, 6-trinitrobenzene (TATB) burns more heterogeneously than conventional high explosives, making its detonation properties sensitive to microstructure. The Benziger route can produce various grain morphologies depending on the amount of water used in the amination step. So-called dry-aminated (DA) TATB crystals are riddled with a void structure called wormholes, which are washed out ammonium chloride (NH4Cl) inclusions that form during synthesis. So-called wet-aminated (WA) TATB crystals do not contain NH 4 Cl inclusions but possess a very convoluted external structure. Using both micro and nano-scale CT, we explore three DA-TATB lots that reflect evolutionary processing changes, plus one WA-TATB material. Micro CT imaged crystal collections show the exterior grain structure, revealing its roughness and providing a crude particle size measurement. The DA-TATB lots that test most sensitively in the LANL ECOT corner-turning test are roughest, having the appearance of being “corroded”. Nano-scale CT reveals both internal NH 4 Cl inclusions and void structures. The DA-TATB lots that tested intermediate and high sensitivity in ECOT exhibited similar wormhole structures, which were more extensive than that of the low-sensitivity lot. The least sensitive DA-TATB lot also retained more NH 4 Cl, consistent with reduced connectivity of voids to the surface.

1, 3, 5-triamino-2,4↗

Automated Scoring of Morphological Changes in Images of Pentaerythritol Tetranitrate

Recent advances in characterization techniques that generate large datasets of material microstructure images require robust, automated image-processing. We applied an unsupervised anomaly detection method called feature anomaly detection system (FADS) to automatically detect and quantify microstructure changes in images of the explosive pentaerythritol tetranitrate (PETN) aged at various temperatures. We demonstrated the FADS approach on two-dimensional images extracted from computed tomography scans, but the same technique can be readily applied to other imaging modalities. FADS calculates anomaly scores on the basis of differences in filter activations of nominal and test data in pretrained convolutional neural networks. The FADS scores successfully differentiated between pristine PETN and PETN aged at a temperature where material coarsening occurred. Morphological metric analysis of segmented images verified observed trends in FADS scores as a function of aging temperature and aging time, specifically by calculating volume fractions, specific boundary lengths, two-point correlation functions, and local thicknesses. Here, the FADS technique has two important advantages compared to traditional morphological analysis: First, it uses grayscale images as input, rather than images that are segmented to separate the appropriate phases; and second, FADS scores capture any type of changes among image sets, rather than requiring prior knowledge or selection of a relevant set of metrics.

Accelerated aging↗

Hierarchical, rotation‐equivariant neural networks to select structural models of protein complexes

Abstract Predicting the structure of multi‐protein complexes is a grand challenge in biochemistry, with major implications for basic science and drug discovery. Computational structure prediction methods generally leverage predefined structural features to distinguish accurate structural models from less accurate ones. This raises the question of whether it is possible to learn characteristics of accurate models directly from atomic coordinates of protein complexes, with no prior assumptions. Here we introduce a machine learning method that learns directly from the 3D positions of all atoms to identify accurate models of protein complexes, without using any precomputed physics‐inspired or statistical terms. Our neural network architecture combines multiple ingredients that together enable end‐to‐end learning from molecular structures containing tens of thousands of atoms: a point‐based representation of atoms, equivariance with respect to rotation and translation, local convolutions, and hierarchical subsampling operations. When used in combination with previously developed scoring functions, our network substantially improves the identification of accurate structural models among a large set of possible models. Our network can also be used to predict the accuracy of a given structural model in absolute terms. The architecture we present is readily applicable to other tasks involving learning on 3D structures of large atomic systems.

Eismann, Stephan↗

Combination of deep neural network with attention mechanism enhances the explainability of protein contact prediction

Abstract Deep learning has emerged as a revolutionary technology for protein residue‐residue contact prediction since the 2012 CASP10 competition. Considerable advancements in the predictive power of the deep learning‐based contact predictions have been achieved since then. However, little effort has been put into interpreting the black‐box deep learning methods. Algorithms that can interpret the relationship between predicted contact maps and the internal mechanism of the deep learning architectures are needed to explore the essential components of contact inference and improve their explainability. In this study, we present an attention‐based convolutional neural network for protein contact prediction, which consists of two attention mechanism‐based modules: sequence attention and regional attention. Our benchmark results on the CASP13 free‐modeling targets demonstrate that the two attention modules added on top of existing typical deep learning models exhibit a complementary effect that contributes to prediction improvements. More importantly, the inclusion of the attention mechanism provides interpretable patterns that contain useful insights into the key fold‐determining residues in proteins. We expect the attention‐based model can provide a reliable and practically interpretable technique that helps break the current bottlenecks in explaining deep neural networks for contact prediction. The source code of our method is available at https://github.com/jianlin-cheng/InterpretContactMap .

59 BASIC BIOLOGICAL SCIENCES↗

Protein model quality assessment using rotation–equivariant transformations on point clouds

Machine learning research concerning protein structure has seen a surge in popularity over the last years with promising advances for basic science and drug discovery. Working with macromolecular structure in a machine learning context requires an adequate numerical representation, and researchers have extensively studied representations such as graphs, discretized 3D grids, and distance maps. As part of CASP14, we explored a new and conceptually simple representation in a blind experiment: atoms as points in 3D, each with associated features. These features—initially just the basic element type of each atom—are updated through a series of neural network layers featuring rotation-equivariant convolutions. Starting from all atoms, we further aggregate information at the level of alpha carbons before making a prediction at the level of the entire protein structure. We find that this approach yields competitive results in protein model quality assessment despite its simplicity and despite the fact that it incorporates minimal prior information and is trained on relatively little data. As a result, its performance and generality are particularly noteworthy in an era where highly complex, customized machine learning methods such as AlphaFold 2 have come to dominate protein structure prediction.

59 BASIC BIOLOGICAL SCIENCES↗

An autonomous robot for shell and tube heat exchanger inspection

Shell and tube heat exchangers (STHEs) are critical to energy conversion efficiency of power plants. Eddy current examination is a way to evaluate working conditions of these tubes. However, the current testing apparatus requires human to manually insert an eddy current testing (ECT) probe into and extract it out of individual tubes, and meanwhile monitor measurement results for diagnosis. It is a time-consuming and labor-intensive procedure even for an experienced technician. To tackle this challenge, in this study, we developed a robot enabled ECT system for autonomous inspection of STHEs. The robotic platform employs Mecanum wheeled chassis for high mobility, machine vision to locate tube bundle and tube inlets, a rotational Cartesian mechanism to operate at planes with all possible inclinations, and a task-specific mechanism for ECT probe delivery. Machine vision locates tube bundle and tube inlets by an April tag detection algorithm and a Circle Hough Transform algorithm, respectively. Assisted by a guiding cone, the ECT probe is continuously fed into the tubes with a fill factor of 0.819. In conclusion, during this process, the eddy current data are automatically collected and real-time analyzed by convolutional neural networks, showing accuracy of nearly 100% for identifying defective and nondefective tubes and 85% for four types of defective tubes and nondefective tubes.

42 ENGINEERING↗

Seismic savanna: machine learning for classifying wildlife and behaviours using ground‐based vibration field recordings

Abstract We develop a machine learning approach to detect and discriminate elephants from other species, and to recognise important behaviours such as running and rumbling, based only on seismic data generated by the animals. We demonstrate our approach using data acquired in the Kenyan savanna, consisting of 8000 h seismic recordings and 250 k camera trap pictures. Our classifiers, different convolutional neural networks trained on seismograms and spectrograms, achieved 80%–90% balanced accuracy in detecting elephants up to 100 m away, and over 90% balanced accuracy in recognising running and rumbling behaviours from the seismic data. We release the dataset used in this study: SeisSavanna represents a unique collection of seismic signals with the associated wildlife species and behaviour. Our results suggest that seismic data offer substantial benefits for monitoring wildlife, and we propose to further develop our methods using dense arrays that could result in a seismic shift for wildlife monitoring.

Szenicer, Alexandre↗

A Hybrid Deep Learning Architecture for Classification of Microscopic Damage on NIF Laser Optics

Accurately classifying microscopic damage helps automate the repair and recycling of National Ignition Facility optics and informs the study of damage initiation and growth. This complex 12-class problem previously required human experts to distinguish and label the various damage morphologies. Finding image analysis methods to extract and calculate distinguishing features would be time consuming and challenging, so we sought to automate this task by using convolutional neural networks (CNNs) pretrained on the ImageNet database to take advantage of its automated feature discovery and extraction. We compared three model architectures on this dataset and found the one with highest overall accuracy, 99.17%, was a novel hybrid architecture, one in which we removed the final decision-making layer of the deep learner and replaced it with an ensemble of decision trees (EDT). This combines the power of feature extraction by CNNs with the decision-making strength of EDT. The accuracy of the hybrid architecture over the deep learning alone is shown to be significantly improved. Furthermore, we applied this novel hybrid architecture to an entirely different dataset, one containing images of repaired damage sites, and improved on the previously published findings, also with a demonstrably significant increase in accuracy over using the deep learner alone.

47 OTHER INSTRUMENTATION↗

Surface analysis insight note: Differentiation methods applicable to noisy data for determination of sp2‐ versus sp3‐hybridization of carbon allotropes and AES signal strengths

The derivatives of the spectra are commonly used for quantification in Auger Electron Spectroscopy (AES) spectra, while the derivative of the KLL C Auger line has proven to be valuable in obtaining a measure of the relative proportions of sp 2 ‐ and sp 3 ‐hybridization using the D‐parameter in both AES and X‐ray Photoelectron Spectroscopy (XPS). Differentiation of X‐ray Photoelectron Spectroscopy (XPS) and Auger Electron Spectroscopy (AES) spectra by numerical means is presented and illustrated for polymeric, such as PEEK and Nylon, as well as for graphitic materials including highly ordered pyrolytic graphite and graphene oxide. The most commonly available Savitzky–Golay method is explained mathematically and developed through the case of constructing a 5‐point quadratic polynomial convolution kernel suitable for differentiating spectra of adequate signal to noise. The concept of differentiation of spectra where signal to noise is less than adequate is also developed. Two alternative strategies to Savitzky–Golay differentiation are presented, which fit curves to data that allow derivatives to be obtained where Savitzky–Golay would otherwise fail. These alternative methods involve constructing a parametric curve that fits data over the entire energy interval of interest. Derivatives of spectra are then obtained by differentiating these parametric curves directly. A comparison of results for different materials for which specific sp 2 ‐ vs sp 3 ‐hybridized carbon proportions are of interest is used to emphasize the importance of characterizing methods used to differentiate spectra and understanding the characteristics of instrumentation used to measure spectra. The case for using Principal Component Analysis noise reduction with C KLL spectra is made for spectra collected from a heterogeneous graphene oxide sample.

Fairley, Neal↗

Understanding Superatomic Ag Nanohydrides

Abstract Bulk Ag hydrides are extremely challenging to make even at very high pressures, but they may become stable as the particle size shrinks to the nanometer regime. Here, the formation and electronic structure of Ag nanohydrides are investigated from a superatomic perspective by density functional theory. It is found that as the coverage increases, adsorption energy of hydrogen atoms on Ag 38 cluster to form Ag 38 H 2 n nanohydride ( n is from 1 to 15) can be energetically favorable with respect to bare Ag 38 and H 2 . Furthermore, the adsorbed hydrogen atoms contribute their 1s electrons to the superatom electron count and behave as a metal instead of a ligand. The electronic structure of the silver nanohydrides follows the superatomic complex model, leading to magic or relatively more stable compositions such as Ag 38 H 2 , Ag 38 H 20 , and Ag 38 H 30 , which correspond to 40‐electron, 58‐electron, and 68‐electron shell closings, respectively. Angular momentum analyses of the superatomic orbitals suggest a convoluted interaction of geometry, symmetry, and orbital splitting.

He, Xiang↗

Deep Learning‐Assisted Automated Single Cell Electroporation Platform for Effective Genetic Manipulation of Hard‐to‐Transfect Cells

Abstract Genome engineering of cells using CRISPR/Cas systems has opened new avenues for pharmacological screening and investigating the molecular mechanisms of disease. A critical step in many such studies is the intracellular delivery of the gene editing machinery and the subsequent manipulation of cells. However, these workflows often involve processes such as bulk electroporation for intracellular delivery and fluorescence activated cell sorting for cell isolation that can be harsh to sensitive cell types such as human‐induced pluripotent stem cells (hiPSCs). This often leads to poor viability and low overall efficacy, requiring the use of large starting samples. In this work, a fully automated version of the nanofountain probe electroporation (NFP‐E) system, a nanopipette‐based single‐cell electroporation method is presented that provides superior cell viability and efficiency compared to traditional methods. The automated system utilizes a deep convolutional network to identify cell locations and a cell‐nanopipette contact algorithm to position the nanopipette over each cell for the application of electroporation pulses. The automated NFP‐E is combined with microconfinement arrays for cell isolation to demonstrate a workflow that can be used for CRISPR/Cas9 gene editing and cell tracking with potential applications in screening studies and isogenic cell line generation.

59 BASIC BIOLOGICAL SCIENCES↗

Using Explainable Artificial Intelligence to Predict Perovskite Solar Cell Electrical Metastability from Operando Photoluminescence Images in Accelerated Stress Testing

Metal halide perovskite (MHP) solar cells exhibit a metastable response to bias governed by coupled ionic–electronic processes, complicating the conventional reciprocity relation between luminescence intensity and device open-circuit voltage (V oc ). This limits the use of luminescence as a diagnostic for device screening or accelerated stress testing, motivating new approaches that can interpret photoluminescence (PL) signals under nonequilibrium conditions. From the artificial intelligence perspective, we develop an explainable deep learning framework that integrates convolutional neural networks (CNN), long short-term memory (LSTM) layers, and an attention mechanism to learn spatiotemporal features from operando photoluminescence PL image sequences. The model achieves a mean absolute error of ±0.027 V in predicting open-circuit voltage transients and reduces extreme-tail errors by up to 78% compared to physics-based reciprocity calculations. Gradient-weighted Class Activation Mapping (Grad-CAM) provides interpretability by highlighting physically meaningful regions such as electrode edges and emergent defect features. From the engineering application perspective, this framework enables accurate, contactless prediction of device V oc and identification of degradation-relevant features during accelerated aging of perovskite solar cells. This approach demonstrates how explainable AI can enhance operando diagnostics and reliability analysis in photovoltaic devices under nonequilibrium conditions.

14 SOLAR ENERGY↗

Machine learning enables national assessment of wind plant controls with implications for land use

Summary As deployment of wind energy continues to expand, computationally efficient tools for predicting wind plant performance over a wide range of layout designs, technology innovations, and spatial locations are increasingly important for policy and investment decisions. We demonstrate two approaches to training a surrogate model to predict annual energy production (AEP) of parameterized wind plant layouts: one using a Gaussian process (GP) and the other using a fully convolutional neural network (FCNN). We leverage the powerful FCNN architecture by encoding wind plant design parameters and output response surface as an image. The FCNN produces more accurate results than the GP with mean absolute errors equivalent to 1% and 1.9% of plant rated power, respectively, although the GP performs well under limited training data and provides useful uncertainty information. We also evaluate a surrogate model for wake steering, enabling a nationwide assessment of the impact of plant control strategies and plant layout decisions. Across two million locations, we find that wake steering strategies boost AEP with relative gains upwards of 3%. Gains are most pronounced at sites without a dominant wind direction and where layout optimization is less fruitful. Additionally, we perform a nationwide sensitivity analysis showing that wake steering can mitigate wake losses from higher density plant layouts. Our results suggest that regions which have not been previously viable for wind deployment due to moderate wind resources are especially well enhanced by wake steering strategies that could help overcome land constraints and inflexible layout options, potentially identifying new deployment opportunities.

17 WIND ENERGY↗

ContourNet: Salient Local Contour Identification for Blob Detection in Fusion Plasma Simulation Data

We present ContourNet, a deep learning approach to identify salient local isocontours as blobs in large-scale 5D gyrokinetic tokamak simulation data. Blobs-regions of high turbulence that run along the edge wall down toward the diverter and can damage the tokamak-are non-well-defined features but have been empirically localized by isocontours in 2D normalized fluctuating density fields. The key of our study is to train ContourNet to follow the empirical rules to detect blobs over the time-varying simulation data. The architecture of ContourNet is a convolutional neural segmentation network: the inputs are the density field and a rasterized isocontour; the output is a set of isocontour encircling blobs. At the training stage, we feed the network with manually identified isocontours and propagated labels. At the inference stage, we extract isocontours from the segmented blob regions. Results show that our approach can achieve both high accuracy and performance, which enables scientists to understand the blob dynamics influencing the confinement of the plasma.

Blob detection↗

Finding Hidden Patterns in High Resolution Wind Flow Model Simulations

Wind flow data is critical in terms of investment decisions and policy making. High resolution data from wind flow model simulations serve as a supplement to the limited resource of original wind flow data collection. Given the large size of data, finding hidden patterns in wind flow model simulations are critical for reducing the dimensionality of the analysis. In this work, we first perform dimension reduction with two autoencoder models: the CNN-based autoencoder (CNN-AE) [1], and hierarchical autoencoder (HIER-AE) [2], and compare their performance with the Principal Component Analysis (PCA). We then investigate the super-resolution of the wind flow data. By training a Generative Adversarial Network (GAN) with 300 epochs, we obtained a trained model with 2× resolution enhancement. We compare the results of GAN with Convolutional Neural Network (CNN), and GAN results show finer structure as expected in the data field images. Also, the kinetic energy spectra comparisons show that GAN outperforms CNN in terms of reproducing the physical properties for high wavenumbers and is critical for analysis where high-wavenumber kinetics play an important role.

97 MATHEMATICS AND COMPUTING↗