Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Decoder”

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 307 records · Page 17

Compact video content representation for video coding using low multi-linear tensor rank approximation with dynamic core tensor order

Tensor is a multi-way representation of an entity that is widely used in many applications of mathematics and physics. The wide range of tensor algebra operations attract the researchers of graphical and vision field to identify unique methods for various applications such as segmentation, compression, indexing and so on. In this paper, low multi-linear rank approximation of a tensor is used for decomposition so as to perform compression on a video that is represented as a 4D tensor. Thus, the encoder has blocks for (1) multilinear rank approximation method so as to aid decomposition, (2) sparsity removal of residual data to reduce the required memory storage to a small level, (3) quantization on the sparse less residual data and (4) LZ77 dictionary coding for the video. The decoder uses a tensor reconstruction block along with residual error correction block that reduces loss/error in the reconstructed video. The size of core tensor is an important factor in rank approximation. It is identified at run time depending on the video contents. This size is determined adaptively using Tikhonov’s regularization method. The best value of core tensor size is identified with the corner of L-curve which preserves the video contents from heavy loss/error. Experimental results of the proposed work on comparison with H.264/AVC compression method indicate that the proposed method achieves up to 10% improvement in compression ratio with the least amount of loss and a maximum signal to noise ratio of 0.14. The proposed system gives better compression ratio than H.265 for videos with more number of frames without compromising quality.

97 MATHEMATICS AND COMPUTING↗

Machine learning-driven descriptions of protein dynamics at solid-liquid interfaces

This chapter has described how ML has enabled quantitative analysis of HS-AFM data to discover the physical phenomena governing protein dynamics and ordering at solid-liquid interfaces. The research detailed in this chapter modeled the rotation models of protein nanorods, the discovery of which would otherwise not be possible. By tracking the trajectories of individual protein rods from frame to frame, it was possible to model Brownian type motion and behaviors and Levy-flight dynamics that had not previously been shown. We also described the application of the Python package AtomAI, which has been developed specifically to analyze and extract physical phenomena, providing exemplar code for training an ensemble of deep neural networks to produce the semantic segmentation of AFM data and functions for encoding and decoding local environments. We last described a combinatorial approach to analyze very noisy data with a densely covered substrate where the emergence of order for the protein liquid crystals could be elucidated. By combining the methods from Case 1 and 2, it was possible to obtain the center of mass and angle for each rod in the images and track the assembly of the rods over time into a 2D liquid crystal array on the surface of mica.

protein dynamics, solid-liquid interfaces, atomic ↗

eBits: Compact stream of mesh refinements for remote visualization

Here, we focus on applications where a remote client needs to visualize or process a complex, manifold triangle mesh, M , but only in a relatively small, user controlled, Region of Interest (RoI) at a time. The client first downloads a coarse base mesh , pre-computed on the server via a series of simplification passes on M , one per Level of Detail (LoD), each pass identifying an independent set of triangles, collapsing them, and, for each collapse, storing, in a Vertex Expansion Record (VER), the information needed to reverse the collapse. On each client initiated RoI modification request, the server pushes to the client a selected subset of these VERs, which, when decoded and applied to refine the mesh locally, ensure that the portion in the RoI is always at full resolution. The eBits approach proposed here offers state of the art compression ratios (using less than 2.5 bits per new full resolution RoI triangle when the RoI has more than 2000 vertices to transmit the connectivity for the selective refinements) and fine-grain control (allowing the user to adjust the RoI by small increments). The effectiveness of eBits results from several novel ideas and novel variations of previous solutions. We represent the VERs using persistent labels so that they can be applied in different orders within a given LoD. The server maintains a shadow copy of the client’s mesh. To avoid sending IDs identifying which vertices should be expanded, we either transmit, for each new vertex, a compact encoding of its death tag –the LoD at which it will be expanded if it lies in the Rol–or transmit vertex masks for the RoI and its neighboring vertices. We also propose a three-step simplification that reduces the overall transmission cost by increasing both the simplification effectiveness and the regularity of the valences in the resulting meshes.

97 MATHEMATICS AND COMPUTING↗

STSR-INR: Spatiotemporal super-resolution for multivariate time-varying volumetric data via implicit neural representation

Implicit neural representation (INR) has surfaced as a promising direction for solving different scientific visualization tasks due to its continuous representation and flexible input and output settings. We present STSR-INR, an INR solution for generating simultaneous spatiotemporal super-resolution for multivariate time-varying volumetric data. Inheriting the benefits of the INR-based approach, STSR-INR supports unsupervised learning and permits data upscaling with arbitrary spatial and temporal scale factors. Unlike existing GAN- or INR-based super-resolution methods, STSR-INR focuses on tackling variables or ensembles and enabling joint training across datasets of various spatiotemporal resolutions. Here we achieve this capability via a variable embedding scheme that learns latent vectors for different variables. In conjunction with a modulated structure in the network design, we employ a variational auto-decoder to optimize the learnable latent vectors to enable latent-space interpolation. To combat the slow training of INR, we leverage a multi-head strategy to improve training and inference speed with significant speedup. We demonstrate the effectiveness of STSR-INR with multiple scalar field datasets and compare it with conventional tricubic+linear interpolation and state-of-the-art deep-learning-based solutions (STNet and CoordNet).

97 MATHEMATICS AND COMPUTING↗

Edge dislocations in dicalcium silicates: Experimental observations and atomistic analysis

Understanding defects and influence of dislocations on dicalcium silicates (Ca{sub 2}SiO{sub 4}) is a challenge in cement science. We report a high-resolution transmission electron microscopy image of edge dislocations in Ca{sub 2}SiO{sub 4}, followed by developing a deep atomic understanding of the edge dislocation-mediated properties of five Ca{sub 2}SiO{sub 4} polymorphs. By decoding the interplay between core dislocation energies, core structures, and nucleation rate of reactivity, we find that γ-C2S and α-C2S polymorphs are the most favorable polymorphs for dislocations in Ca{sub 2}SiO{sub 4}, mainly due to their large pore channels which take away majority of the distortions imposed by edge dislocations. Furthermore, in the context of edge dislocation, while α-C2S represents the most active polymorph for reactivity and crystal growth, β-C2S represents the most brittle polymorph suitable for grinding. This work is the first report on the atomistic-scale analysis of edge dislocation-mediated properties of Ca{sub 2}SiO{sub 4} and may open up new opportunities for tuning fracture and reactivity processes of Ca{sub 2}SiO{sub 4} and other cement components.

36 MATERIALS SCIENCE↗

Geometric learning for computational mechanics Part II: Graph embedding for interpretable multiscale plasticity

The history-dependent behaviors of classical plasticity models are often driven by internal variables evolved according to phenomenological laws. The difficulty to interpret how these internal variables represent a history of deformation, the lack of direct measurement of these internal variables for calibration and validation, and the weak physical underpinning of those phenomenological laws have long been criticized as barriers to creating realistic models. In this work, geometric machine learning on graph data (e.g. finite element solutions) is used as a means to establish a connection between nonlinear dimensional reduction techniques and plasticity models. Geometric learning-based encoding on graphs allows the embedding of rich time-history data onto a low-dimensional Euclidean space such that the evolution of plastic deformation can be predicted in the embedded feature space. Finally, a corresponding decoder can then convert these low-dimensional internal variables back into a weighted graph such that the dominating topological features of plastic deformation can be observed and analyzed.

42 ENGINEERING↗

Fourier-DeepONet: Fourier-enhanced deep operator networks for full waveform inversion with improved accuracy, generalizability, and robustness

In this article, full waveform inversion (FWI) infers the subsurface structure information from seismic waveform data by solving a non-convex optimization problem. Data-driven FWI has been increasingly studied with various neural network architectures to improve accuracy and computational efficiency. Nevertheless, the applicability of pre-trained neural networks is severely restricted by potential discrepancies between the source function used in the field survey and the one utilized during training. Here, we develop a Fourier-enhanced deep operator network (Fourier-DeepONet) for FWI with the generalization of seismic sources, including the frequencies and locations of sources. Specifically, we employ the Fourier neural operator as the decoder of DeepONet, and we utilize source parameters as one input of Fourier-DeepONet, facilitating the resolution of FWI with variable sources. To test Fourier-DeepONet, we develop three new and realistic FWI benchmark datasets (FWI-F, FWI-L, and FWI-FL) with varying source frequencies, locations, or both. Our experiments demonstrate that compared with existing data-driven FWI methods, Fourier-DeepONet obtains more accurate predictions of subsurface structures in a wide range of source parameters. Moreover, the proposed Fourier-DeepONet exhibits superior robustness when handling data with Gaussian noise or missing traces and sources with Gaussian noise, paving the way for more reliable and accurate subsurface imaging across diverse real conditions.

42 ENGINEERING↗

$\text{GPLaSDI}$: Gaussian Process-based interpretable Latent Space Dynamics Identification through deep autoencoder

Numerically solving partial differential equations (PDEs) can be challenging and computationally expensive. This has led to the development of reduced-order models (ROMs) that are accurate but faster than full order models (FOMs). Recently, machine learning advances have enabled the creation of non-linear projection methods, such as Latent Space Dynamics Identification (LaSDI). LaSDI maps full-order PDE solutions to a latent space using autoencoders and learns the system of ODEs governing the latent space dynamics. By interpolating and solving the ODE system in the reduced latent space, fast and accurate ROM predictions can be made by feeding the predicted latent space dynamics into the decoder. In this paper, we introduce GPLaSDI, a novel LaSDI-based framework that relies on Gaussian process (GP) for latent space ODE interpolations. Using GPs offers two significant advantages. First, it enables the quantification of uncertainty over the ROM predictions. Second, leveraging this prediction uncertainty allows for efficient adaptive training through a greedy selection of additional training data points. This approach does not require prior knowledge of the underlying PDEs. Consequently, GPLaSDI is inherently non-intrusive and can be applied to problems without a known PDE or its residual. Here we demonstrate the effectiveness of our approach on the Burgers equation, Vlasov equation for plasma physics, and a rising thermal bubble problem. Our proposed method achieves between 200 and 100,000 times speed-up, with up to 7% relative error.

97 MATHEMATICS AND COMPUTING↗

Bi-fidelity variational auto-encoder for uncertainty quantification

Quantifying the uncertainty of quantities of interest (QoIs) from physical systems is a primary objective in model validation. However, achieving this goal entails balancing the need for computational efficiency with the requirement for numerical accuracy. To address this trade-off, we propose a novel bi-fidelity formulation of variational auto-encoders (BF-VAE) designed to estimate the uncertainty associated with a QoI from low-fidelity (LF) and high-fidelity (HF) samples of the QoI. Here, this model allows for the approximation of the statistics of the HF QoI by leveraging information derived from its LF counterpart. Specifically, we design a bi-fidelity auto-regressive model in the latent space which is integrated within the VAE’s probabilistic encoder–decoder structure. An effective algorithm is proposed to maximize the variational lower bound of the HF log-likelihood in the presence of limited HF data, resulting in the synthesis of HF realizations with a reduced computational cost. Additionally, we introduce the concept of the bi-fidelity information bottleneck (BF-IB) to provide an information-theoretic interpretation of the proposed BF-VAE model. Our numerical results demonstrate that the BF-VAE leads to considerably improved accuracy, as compared to a VAE trained using only HF data, when limited HF data is available.

42 ENGINEERING↗

A co-kurtosis PCA based dimensionality reduction with nonlinear reconstruction using neural networks

For turbulent reacting flow systems, identification of low-dimensional representations of the thermo-chemical state space is vitally important, primarily to significantly reduce the computational cost of device-scale simulations. Principal component analysis (PCA), and its variants, are a widely employed class of methods. Recently, an alternative technique that focuses on higher-order statistical interactions, co-kurtosis PCA (CoK-PCA), has been shown to effectively provide a low-dimensional representation by capturing the stiff chemical dynamics associated with spatiotemporally localized reaction zones. While its effectiveness has only been demonstrated based on a priori analyses with linear reconstruction, in this work, we employ nonlinear techniques to reconstruct the full thermo-chemical state and evaluate the efficacy of CoK-PCA compared to PCA. Specifically, we combine a CoK-PCA-/PCA-based dimensionality reduction (encoding) with an artificial neural network (ANN) based reconstruction (decoding) and examine, a priori, the reconstruction errors of the thermo-chemical state. In addition, we evaluate the errors in species production rates and heat release rates, which are nonlinear functions of the reconstructed state, as a measure of the overall accuracy of the dimensionality reduction technique. We employ four datasets to assess CoK-PCA/PCA coupled with ANN-based reconstruction: zero-dimensional (homogeneous) reactor for autoignition of an ethylene/air mixture that has conventional single-stage ignition kinetics, a dimethyl ether (DME)/air mixture which has two-stage (low and high temperature) ignition kinetics, a one-dimensional freely propagating premixed ethylene/air laminar flame, and a two-dimensional dataset representing turbulent autoignition of ethanol in a homogeneous charge compression ignition (HCCI) engine. Finally, results from the analyses demonstrate the robustness of the CoK-PCA based low-dimensional manifold with ANN reconstruction in accurately capturing the data, specifically from the reaction zones.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

A Decomposition-Based Learn-To-Optimize Approach with Feasibility Layer Assistance for Sub-Hourly Unit Commitment

Sub-hourly unit commitment (UC) with 15-min intervals is gaining significant attention as a way to respond rapidly to the fluctuations in electricity supply and demand introduced by renewable resources. However, the increased temporal resolution and complex inter-temporal dependencies pose substantial computational challenges for traditional optimization methods. To this end, this paper explores a decomposition-based learn-to-optimize approach. Building on recent advances in machine learning, our method revisits the long- overlooked Lagrangian relaxation framework, which is a classical decomposition technique that enables tractable subproblem solving. These smaller subproblems are inherently well-suited for machine learning, as their reduced dimensionality and structural regularity allow predictive models to efficiently learn and generalize solution patterns. We thus propose a generic predictive model, which embeds Gated Recurrent Units (GRUs) and Attention in the encoder-decoder structure, and integrate a rule-based feasibility layer to capture temporal dependencies, reduce training effort, and improve feasibility w.r.t. unit-level constraints. Our method has been validated on the IEEE 118-bus system, demonstrating promising performance in solving sub-hourly UC problems efficiently and feasibly.

97 MATHEMATICS AND COMPUTING↗

Locality-aware and load-balanced static task scheduling for MapReduce

Task scheduling for MapReduce jobs has been an active area of research with the objective of decreasing the amount of data transferred during the shuffle phase via exploiting data locality. In the literature, generally only the scheduling of reduce tasks is considered with the assumption that scheduling of map tasks is already determined by the input data placement. However, in cloud or HPC deployments of MapReduce, the input data is located in a remote storage and scheduling map tasks gains importance. Here, we propose models for simultaneous scheduling of map and reduce tasks in order to improve data locality and balance the processors’ loads in both map and reduce phases. Our approach is based on graph and hypergraph models which correctly encode the interactions between map and reduce tasks. Partitions produced by these models are decoded to schedule map and reduce tasks. A two-constraint formulation utilized in these models enables balancing processors’ loads in both map and reduce phases. The partitioning objective in the hypergraph models correctly encapsulates the minimization of data transfer when a local combine step is performed prior to shuffle, whereas the partitioning objective in the graph models achieve the same feat when a local combine is not performed. Here, we show the validity of our scheduling on the MapReduce parallelizations of two important kernel operations – sparse matrix–vector multiplication (SpMV) and generalized sparse matrix–matrix multiplication (SpGEMM) – that are widely encountered in big data analytics and scientific computations. Compared to random scheduling, our models lead to tremendous savings in data transfer by reducing data traffic from several hundreds of megabytes to just a few megabytes in the shuffle phase and consequently leading up to 2.6x and 4.2x speedup for SpMV and SpGEMM, respectively.

97 MATHEMATICS AND COMPUTING↗

Development of a new ion mobility time-of-flight mass spectrometer

Complex samples require multidimensional measurements with high resolution for full characterization of biological and environmental systems. To address this challenge, we developed a drift tube-based ion mobility spectrometry-Orbitrap mass spectrometry (IMS-Orbitrap MS) platform. To circumvent the timing difference between the fast IMS separation and the slow Orbitrap MS acquisition, we utilized a dual gate and pseudorandom sequence to multiplex ions into the drift tube and Orbitrap. The instrument was designed to operate in signal averaging (SA), single multiplexing (SM) and double multiplexing (DM) IMS modes to fully optimize the signal-to-ratio of the measurements. For the SM measurements, a previously developed algorithm was used to reconstruct the IMS data, while a new algorithm was developed for the DM analyses. The new algorithm is a two-step process that first recovers the SM data from the encoded DM data and then decoded the SM data. The algorithm also performs multiple refining procedures in order to minimize the demultiplexing artifacts traditionally observed in such scheme. The new IMS-Orbitrap MS platform was demonstrated for the analysis of proteomic and petroleum samples, where the integration of IMS and high mass resolution proved essential for accurate assignment of molecular formulae.

47 OTHER INSTRUMENTATION↗

Latent code-based fusion: A Volterra neural network approach

We propose a deep structure encoder using Volterra Neural Networks (VNNs) to seek a latent representation of multi-modal data whose features are jointly captured by a union of subspaces. The so-called self-representation embedding of the latent codes leads to a simplified fusion which is driven by a similarly constructed decoding. The Volterra Filter architecture achieved reduction in parameter complexity is primarily due to controlled non-linearities being introduced by the higher-order convolutions in lieu of generalized activation functions. Experimental results on two different datasets have shown a significant improvement in the clustering performance for VNNs auto-encoder over conventional Convolutional Neural Networks (CNNs) auto-encoder. In addition, we also show that the proposed approach demonstrates a much-improved sample complexity over CNN-based auto-encoder with a robust classification performance.

97 MATHEMATICS AND COMPUTING↗

Ancestral archaea expanded the genetic code with pyrrolysine

The pyrrolysyl-tRNA synthetase (PylRS) facilitates the cotranslational installation of the 22nd amino acid pyrrolysine. Owing to its tolerance for diverse amino acid substrates, and its orthogonality in multiple organisms, PylRS has emerged as a major route to install noncanonical amino acids into proteins in living cells. Recently, a novel class of PylRS enzymes was identified in a subset of methanogenic archaea. Enzymes within this class (ΔPylSn) lack the N-terminal tRNA-binding domain that is widely conserved amongst PylRS enzymes, yet remain active and orthogonal in bacteria and eukaryotes. In this study, we use biochemical and in vivo UAG-readthrough assays to characterize the aminoacylation efficiency and substrate spectrum of a ΔPylSn class PylRS from the archaeon Candidatus Methanomethylophilus alvus. We show that, compared with the full-length enzyme from Methanosarcina mazei, the Ca. M. alvus PylRS displays reduced aminoacylation efficiency but an expanded amino acid substrate spectrum. To gain insight into the evolution of ΔPylSn enzymes, we performed molecular phylogeny using 156 PylRS and 105 pyrrolysine tRNA (tRNA Pyl ) sequences from diverse archaea and bacteria. This analysis suggests that the PylRS•tRNA Pyl pair diverged before the evolution of the three domains of life, placing an early limit on the evolution of the Pyl-decoding trait. Furthermore, our results document the coevolutionary history of PylRS and tRNA Pyl and reveal the emergence of tRNA Pyl sequences with unique A73 and U73 discriminator bases. The orthogonality of these tRNA Pyl species with the more common G73-containing tRNA Pyl will enable future efforts to engineer PylRS systems for further genetic code expansion.

59 BASIC BIOLOGICAL SCIENCES↗

Multiscale graph neural network autoencoders for interpretable scientific machine learning

The goal of this work is to address two limitations in autoencoder-based models: latent space interpretability and compatibility with unstructured meshes. This is accomplished here with the development of a novel graph neural network (GNN) autoencoding architecture with demonstrations on complex fluid flow applications. To address the first goal of interpretability, the GNN autoencoder achieves reduction in the number nodes in the encoding stage through an adaptive graph reduction procedure. Further, this reduction procedure essentially amounts to flowfieldconditioned node sampling and sensor identification, and produces interpretable latent graph representations tailored to the flowfield reconstruction task in the form of so-called masked fields. These masked fields allow the user to (a) visualize where in physical space a given latent graph is active, and (b) interpret the time-evolution of the latent graph connectivity in accordance with the time-evolution of unsteady flow features (e.g. recirculation zones, shear layers) in the domain. To address the goal of unstructured mesh compatibility, the autoencoding architecture utilizes a series of multi-scale message passing (MMP) layers, each of which models information exchange among node neighborhoods at various lengthscales. The MMP layer, which augments standard single-scale message passing with learnable coarsening operations, allows the decoder to more efficiently reconstruct the flowfield from the identified regions in the masked fields. Analysis of latent graphs produced by the autoencoder for various model settings are conducted using unstructured snapshot data sourced from large-eddy simulations in a backward-facing step (BFS) flow configuration with an OpenFOAM-based flow solver at high Reynolds numbers.

97 MATHEMATICS AND COMPUTING↗

Feature-adjacent multi-fidelity physics-informed machine learning for partial differential equations

Physics-informed neural networks have emerged as an alternative method for solving partial differential equations. However, for complex problems, the training of such networks can still require high-fidelity data which can be expensive to generate. To reduce or even eliminate the dependency on high-fidelity data, we propose a novel multi-fidelity architecture which is based on a feature space shared by the low- and high-fidelity solutions. In the feature space, the projections of the low-fidelity and high-fidelity solutions are adjacent by constraining their relative distance. The feature space is represented with an encoder and its mapping to the original solution space is effected through a decoder. In conclusion, the proposed multi-fidelity approach is validated on forward and inverse problems for steady and unsteady problems described by partial differential equations.

97 MATHEMATICS AND COMPUTING↗