Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “residual network”

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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Data-Driven Learning of Non-Autonomous Systems

We present a numerical framework for recovering unknown non-autonomous dynamical systems with time-dependent inputs. To circumvent the difficulty presented by the non-autonomous nature of the system, our method transforms the solution state into piecewise integration of the system over a discrete set of time instances. The time-dependent inputs are then locally parameterized by using a proper model, for example, polynomial regression, in the pieces determined by the time instances. This transforms the original system into a piecewise parametric system that is locally time invariant. We then design a deep neural network structure to learn the local models. Once the network model is constructed, it can be iteratively used over time to conduct global system prediction. We provide theoretical analysis of our algorithm and present a number of numerical examples to demonstrate the effectiveness of the method.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Improving deep learning-based protein distance prediction in CASP14

Abstract Motivation Accurate prediction of residue–residue distances is important for protein structure prediction. We developed several protein distance predictors based on a deep learning distance prediction method and blindly tested them in the 14th Critical Assessment of Protein Structure Prediction (CASP14). The prediction method uses deep residual neural networks with the channel-wise attention mechanism to classify the distance between every two residues into multiple distance intervals. The input features for the deep learning method include co-evolutionary features as well as other sequence-based features derived from multiple sequence alignments (MSAs). Three alignment methods are used with multiple protein sequence/profile databases to generate MSAs for input feature generation. Based on different configurations and training strategies of the deep learning method, five MULTICOM distance predictors were created to participate in the CASP14 experiment. Results Benchmarked on 37 hard CASP14 domains, the best performing MULTICOM predictor is ranked 5th out of 30 automated CASP14 distance prediction servers in terms of precision of top L/5 long-range contact predictions [i.e. classifying distances between two residues into two categories: in contact (<8 Angstrom) and not in contact otherwise] and performs better than the best CASP13 distance prediction method. The best performing MULTICOM predictor is also ranked 6th among automated server predictors in classifying inter-residue distances into 10 distance intervals defined by CASP14 according to the precision of distance classification. The results show that the quality and depth of MSAs depend on alignment methods and sequence databases and have a significant impact on the accuracy of distance prediction. Using larger training datasets and multiple complementary features improves prediction accuracy. However, the number of effective sequences in MSAs is only a weak indicator of the quality of MSAs and the accuracy of predicted distance maps. In contrast, there is a strong correlation between the accuracy of contact/distance predictions and the average probability of the predicted contacts, which can therefore be more effectively used to estimate the confidence of distance predictions and select predicted distance maps. Availability and implementation The software package, source code and data of DeepDist2 are freely available at https://github.com/multicom-toolbox/deepdist and https://zenodo.org/record/4712084#.YIIM13VKhQM. Supplementary information Supplementary data are available at Bioinformatics online.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Upsampling Monte Carlo reactor simulation tallies in depleted LWR assemblies fueled with LEU and HALEU using a convolutional neural network

Simulating nuclear reactor cores at the highest achievable spatial and energy resolution is critical in modeling these systems accurately. Increasing the resolution, however, can dramatically increase the memory and central processing unit time required to run simulations. A convolutional neural network was shown previously to accurately upsample tally results of simulated light water reactor assemblies fueled with fresh, low enriched uranium. Here, we show that a convolutional neural network can be used to upsample tally results in assemblies containing fresh and depleted fuel enriched from 1.6 to 19.9 atom percent. The network was trained using neutron flux tallies from simulations of light water reactor assemblies with a range of fuel and coolant temperatures and a diverse selection of geometries. Accurate predictions of flux tallies are possible even on test assemblies with geometries and burnup levels well outside the range of those present in the training and validation data. The network improves the data density by a factor of 8 over a broad range of light water reactor assemblies while incurring insignificant additional computational cost to a Monte Carlo simulation.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2021

Fault Detection on Seismic Structural Images Using a Nested Residual U-Net

Automatic identification of faults on seismic structural images is a challenging yet crucial task in quantitative seismic interpretation. Human picking or attribute-based fault detection methods may misidentify faults on noisy, complex seismic images. In this work, we develop a new automatic fault detection method using a nested residual U-shaped convolutional neural network. Each of the encoders and decoders in this neural network is a residual U-Net, leading to a nested architecture. The final fault map results from the fusion of three fault maps with low, medium, and high fault resolutions. We demonstrate the excellent fault-detection capability of our nested neural network using a series of synthetic and field seismic images. We find that our approach produces clearer and more interpretable fault maps than the current state-of-the-art U-Net fault detection method, particularly on noisy seismic images. Our new automatic fault detection method can facilitate reliable quantitative seismic interpretation on field seismic images.

58 GEOSCIENCES↗
DOE OSTI2020

Nuclear Canister Corrosion Detection

The software titled "nccd" is used for running residual neural networks (ResNets) on images of nuclear canisters. The software provides only the code for the implementation (based on the fastai library), but it does not share the image data. The compute code allows the use of residual nets (and more generally of other deep learning models) for classifying images from nuclear canisters as corroded. or intact. An image is considered to be corroded if it contains pitting or stress corrosion cracks. The code trains ResNets on image tiles extracted from original images from nuclear canisters, and then implements a classification rule, which can be applied to a validation set to decide if each original image is corroded or intact. The software automates the process of using images taken from nuclear canisters to detect corrosion. It provides also scope for future research directions on the basis of the existing research and code.

Papamarkou, Theodore↗
NASA NTRSDate not supplied

A Framework for the Analysis of Deep Neural Networks in Autonomous Aerospace Applications using Bayesian Statistics

Deep Neural Networks (DNNs) are considered to be key components in many autonomous systems. Applications range from vision-based obstacle avoidance to intelligent/learning control and planning. Safety-critical applications as found in the aerospace domain require that the behavior of the DNN is validated and tested rigorously for safety of the autonomous system (AUS). In this paper, we present a framework to support testing of DNNs and the analysis of the network structure. Our framework employs techniques from statistical modeling and active learning to effectively generate test cases for DNN safety testing and performance analysis. We will present results of a case study on a physics-based Deep recurrent residual neural network (DR-RNN), which has been trained to emulate the aerodynamics behavior of a fixed-wing aircraft.

Deep Neural networks↗
DOE OSTI2023

An Ensemble of Neural Networks for Moist Physics Processes, Its Generalizability and Stable Integration

Abstract With the recent advances in data science, machine learning has been increasingly applied to convection and cloud parameterizations in global climate models (GCMs). This study extends the work of Han et al. (2020, https://doi.org/10.1029/2020MS002076 ) and uses an ensemble of 32‐layer deep convolutional residual neural networks, referred to as ResCu‐en, to emulate convection and cloud processes simulated by a superparameterized GCM, SPCAM. ResCu‐en predicts GCM grid‐scale temperature and moisture tendencies, and cloud liquid and ice water contents from moist physics processes. The surface rainfall is derived from the column‐integrated moisture tendency. The prediction uncertainty inherent in deep learning algorithms in emulating the moist physics is reduced by ensemble averaging. Results in 1‐year independent offline validation show that ResCu‐en has high prediction accuracy for all output variables, both in the current climate and in a warmer climate with +4K sea surface temperature. The analysis of different neural net configurations shows that the success to generalize in a warmer climate is attributed to convective memory and the 1‐dimensional convolution layers incorporated into ResCu‐en. We further implement a member of ResCu‐en into CAM5 with real world geography and run the neural‐network‐enabled CAM5 (NCAM) for 5 years without encountering any numerical integration instability. The simulation generally captures the global distribution of the mean precipitation, with a better simulation of precipitation intensity and diurnal cycle. However, there are large biases in temperature and moisture in high latitudes. These results highlight the importance of convective memory and demonstrate the potential for machine learning to enhance climate modeling.

Meteorology & Atmospheric Sciences↗
DOE OSTI2023

Scaling Resolution of Gigapixel Whole Slide Images Using Spatial Decomposition on Convolutional Neural Networks

Gigapixel images are prevalent in scientific domains ranging from remote sensing, and satellite imagery to microscopy, etc. However, training a deep learning model at the natural resolution of those images has been a challenge in terms of both, overcoming the resource limit (e.g. HBM memory constraints), as well as scaling up to a large number of GPUs. In this paper, we trained Residual neural Networks (ResNet) on 22,528 x 22,528-pixel size images using a distributed spatial decomposition method on 2,304 GPUs on the Summit Supercomputer. We applied our method on a Whole Slide Imaging (WSI) dataset from The Cancer Genome Atlas (TCGA) database. WSI images can be in the size of 100,000 x 100,000 pixels or even larger, and in this work we studied the effect of image resolution on a classification task, while achieving state-of-the-art AUC scores. Moreover, our approach doesn't need pixel-level labels, since we're avoiding patching from the WSI images completely, while adding the capability of training arbitrary large-size images. This is achieved through a distributed spatial decomposition method, by leveraging the non-block fat-tree interconnect network of the Summit architecture, which enabled GPU-to-GPU direct communication. Finally, detailed performance analysis results are shown, as well as a comparison with a data-parallel approach when possible.

Tsaris, Aristeidis (aris)↗
DOE OSTI2024

Exploring the fragmentation efficiency of proteins analyzed by MALDI-TOF-TOF tandem mass spectrometry using computational and statistical analyses

Matrix-assisted laser desorption/ionization time-of-flight-time-of-flight (MALDI-TOF-TOF) tandem mass spectrometry (MS/MS) is a rapid technique for identifying intact proteins from unfractionated mixtures by top-down proteomic analysis. MS/MS allows isolation of specific intact protein ions prior to fragmentation, allowing fragment ion attribution to a specific precursor ion. However, the fragmentation efficiency of mature, intact protein ions by MS/MS post-source decay (PSD) varies widely, and the biochemical and structural factors of the protein that contribute to it are poorly understood. With the advent of protein structure prediction algorithms such as Alphafold2, we have wider access to protein structures for which no crystal structure exists. In this work, we use a statistical approach to explore the properties of bacterial proteins that can affect their gas phase dissociation via PSD. We extract various protein properties from Alphafold2 predictions and analyze their effect on fragmentation efficiency. Our results show that the fragmentation efficiency from cleavage of the polypeptide backbone on the C-terminal side of glutamic acid (E) and asparagine (N) residues were nearly equal. In addition, we found that the rearrangement and cleavage on the C-terminal side of aspartic acid (D) residues that result from the aspartic acid effect (AAE) were higher than for E- and N-residues. From residue interaction network analysis, we identified several local centrality measures and discussed their implications regarding the AAE. We also confirmed the selective cleavage of the backbone at D-proline bonds in proteins and further extend it to N-proline bonds. Finally, we note an enhancement of the AAE mechanism when the residue on the C-terminal side of D-, E- and N-residues is glycine. To the best of our knowledge, this is the first report of this phenomenon. Our study demonstrates the value of using statistical analyses of protein sequences and their predicted structures to better understand the fragmentation of the intact protein ions in the gas phase.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

Microstructural modification of additively manufactured metals by electropulsing

Additive manufacturing (AM) promises rapid development cycles and fabrication of ready-to-use, geometrically-complex parts. The metallic parts produced by AM often contain highly non-equilibrium microstructures, e.g. chemical microsegregation and residual dislocation networks. While such microstructures can enhance some material properties, they are often undesirable. Many AM parts are thus heat-treated after fabrication, a process that significantly slows production. This study investigated if electropulsing, the process of sending high-current-density electrical pulses through a metallic part, could be used to modify the microstructures of AM 316 L stainless steel (SS) and AlSi10Mg parts fabricated by selective laser melting (SLM) more rapidly than thermal annealing. Electropulsing has shown promise as a rapid postprocessing method for materials fabricated using conventional methods, e.g. casting and rolling, but has never been applied to AM materials. For both the materials used in this study, as-fabricated SLM parts contained significant chemical heterogeneity, either chemical microsegregation (316 L SS) or a cellular interdendritic phase (AlSi10Mg). In both cases, annealing times on the order of hours at high homologous temperatures are necessary for homogenization. Using electropulsing, chemical microsegregation was eliminated in 316 L SS samples after 10, 16 ms electrical pulses. In AlSi10Mg parts, electropulsing produced spheroidized Si-rich particles after as few as 15, 16 ms electrical pulses with a corresponding increase in ductility. Finally, this study demonstrated that electropulsing can be used to modify the microstructures of AM metals.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Attention-based convolutional capsules for evapotranspiration estimation at scale

Evapotranspiration (ET) measures the amount of water lost from the Earth's surface to the atmosphere and is an integral metric for both agricultural and environmental sciences. Understanding and quantifying ET is critical for achieving effective management of freshwater and irrigation systems. However, current ET estimation models suffer from a trade-off between accuracy and spatial coverage. In this study, we introduce our model Quench, a neural network architecture that achieves highly-accurate ET estimates over large continuous spatial extents. Quench uses our novel Attention-Based Convolutional Capsule for its neural network layers to identify areas of focus and efficiently extract ET information from satellite imagery. Benchmarks that profile our model's performance show substantive improvements in accuracy, with up to 128% increase in accuracy compared to traditional convolutional-based and process-based models. Finally, Quench also demonstrates consistent model performance over high geospatial variability and a diverse array of regions, seasons, climates, and vegetations.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Microsecond fingerprint stimulated Raman spectroscopic imaging by ultrafast tuning and spatial-spectral learning

Label-free vibrational imaging by stimulated Raman scattering (SRS) provides unprecedented insight into real-time chemical distributions. Specifically, SRS in the fingerprint region (400–1800 cm -1 ) can resolve multiple chemicals in a complex bio-environment. However, due to the intrinsic weak Raman cross-sections and the lack of ultrafast spectral acquisition schemes with high spectral fidelity, SRS in the fingerprint region is not viable for studying living cells or large-scale tissue samples. Here, we report a fingerprint spectroscopic SRS platform that acquires a distortion-free SRS spectrum at 10 cm -1 spectral resolution within 20 µs using a polygon scanner. Meanwhile, we significantly improve the signal-to-noise ratio by employing a spatial-spectral residual learning network, reaching a level comparable to that with 100 times integration. Collectively, our system enables high-speed vibrational spectroscopic imaging of multiple biomolecules in samples ranging from a single live microbe to a tissue slice.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2024

Biosensor and machine learning-aided engineering of an amaryllidaceae enzyme

A major challenge to achieving industry-scale biomanufacturing of therapeutic alkaloids is the slow process of biocatalyst engineering. Amaryllidaceae alkaloids, such as the Alzheimer’s medication galantamine, are complex plant secondary metabolites with recognized therapeutic value. Due to their difficult synthesis they are regularly sourced by extraction and purification from the low-yielding daffodil Narcissus pseudonarcissus. Here, we propose an efficient biosensor-machine learning technology stack for biocatalyst development, which we apply to engineer an Amaryllidaceae enzyme in Escherichia coli. Directed evolution is used to develop a highly sensitive (EC 50 = 20 μM) and specific biosensor for the key Amaryllidaceae alkaloid branchpoint 4’-O-methylnorbelladine. A structure-based residual neural network (MutComputeX) is subsequently developed and used to generate activity-enriched variants of a plant methyltransferase, which are rapidly screened with the biosensor. Functional enzyme variants are identified that yield a 60% improvement in product titer, 2-fold higher catalytic activity, and 3-fold lower off-product regioisomer formation. A solved crystal structure elucidates the mechanism behind key beneficial mutations.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Energetic and structural control of polyspecificity in a multidrug transporter

Multidrug efflux pumps are dynamic molecular machines that drive antibiotic resistance by harnessing ion gradients to export chemically diverse substrates. Despite their clinical importance, the molecular principles underlying multidrug promiscuity and energy efficiency remain poorly understood. Using multiparametric deep mutational scanning across eight substrates and two energy conditions, we deconvolute the contributions of substrate recognition, energetic coupling, and protein stability, providing an integrated, high-resolution view of multidrug transport. We find that substrate specificity arises from a distributed network of residues extending beyond the binding site, with mutations that reshape binding, coupling, conformational flexibility, and membrane interactions. Further, we apply a pH-based selection scheme to measure the effect of mutation on pH-dependent transport efficiency. By integrating these data, we reveal a fundamental relationship between efficiency and promiscuity: Highly efficient variants exhibit broad substrate profiles, while inefficient variants are narrower. In conclusion, these findings establish a direct link between energy coupling and polyspecificity, uncovering the biochemical logic underlying multidrug transport.

Biological Sciences↗
DOE OSTI2024

Machine learning for the identification of phase transitions in interacting agent-based systems: A Desai-Zwanzig example

Deriving closed-form analytical expressions for reduced-order models, and judiciously choosing the closures leading to them, has long been the strategy of choice for studying phase- and noise-induced transitions for agent-based models (ABMs). In this paper, we propose a data-driven framework that pinpoints phase transitions for an ABM—the Desai-Zwanzig model—in its mean-field limit, using a smaller number of variables than traditional closed-form models. To this end, we use the manifold learning algorithm Diffusion Maps to identify a parsimonious set of data-driven latent variables, and we show that they are in one-to-one correspondence with the expected theoretical order parameter of the ABM. We then utilize a deep learning framework to obtain a conformal reparametrization of the data-driven coordinates that facilitates, in our example, the identification of a single parameter-dependent ordinary differential equation (ODE) in these coordinates. Additionally, we identify this ODE through a residual neural network inspired by a numerical integration scheme (forward Euler). We then use the identified ODE—enabled through an odd symmetry transformation—to construct the bifurcation diagram exhibiting the phase transition.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Forward variable selection enables fast and accurate dynamic system identification with Karhunen-Loève decomposed Gaussian processes

A promising approach for scalable Gaussian processes (GPs) is the Karhunen-Loève (KL) decomposition, in which the GP kernel is represented by a set of basis functions which are the eigenfunctions of the kernel operator. Such decomposed kernels have the potential to be very fast, and do not depend on the selection of a reduced set of inducing points. However KL decompositions lead to high dimensionality, and variable selection thus becomes paramount. This paper reports a new method of forward variable selection, enabled by the ordered nature of the basis functions in the KL expansion of the Bayesian Smoothing Spline ANOVA kernel (BSS-ANOVA), coupled with fast Gibbs sampling in a fully Bayesian approach. It quickly and effectively limits the number of terms, yielding a method with competitive accuracies, training and inference times for tabular datasets of low feature set dimensionality. Theoretical computational complexities are O ( N P 2 ) in training and O ( P ) per point in inference, where N is the number of instances and P the number of expansion terms. The inference speed and accuracy makes the method especially useful for dynamic systems identification, by modeling the dynamics in the tangent space as a static problem, then integrating the learned dynamics using a high-order scheme. The methods are demonstrated on two dynamic datasets: a ‘Susceptible, Infected, Recovered’ (SIR) toy problem, along with the experimental ‘Cascaded Tanks’ benchmark dataset. Comparisons on the static prediction of time derivatives are made with a random forest (RF), a residual neural network (ResNet), and the Orthogonal Additive Kernel (OAK) inducing points scalable GP, while for the timeseries prediction comparisons are made with LSTM and GRU recurrent neural networks (RNNs) along with the SINDy package.

Hayes, Kyle↗
DOE OSTI2024

Transfer learning for metamaterial design and simulation

Abstract We demonstrate transfer learning as a tool to improve the efficacy of training deep learning models based on residual neural networks (ResNets). Specifically, we examine its use for study of multi-scale electrically large metasurface arrays under open boundary conditions in electromagnetic metamaterials. Our aim is to assess the efficiency of transfer learning across a range of problem domains that vary in their resemblance to the original base problem for which the ResNet model was initially trained. We use a quasi-analytical discrete dipole approximation (DDA) method to simulate electrically large metasurface arrays to obtain ground truth data for training and testing of our deep neural network. Our approach can save significant time for examining novel metasurface designs by harnessing the power of transfer learning, as it effectively mitigates the pervasive data bottleneck issue commonly encountered in deep learning. We demonstrate that for the best case when the transfer task is sufficiently similar to the target task, a new task can be effectively trained using only a few data points yet still achieve a test mean absolute relative error of 3 % with a pre-trained neural network, realizing data reduction by a factor of 1000.

Peng, Rixi↗