SEARCH · Engineering Papers
Results for “decoding”
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.
EQ_phase_detection
The EQ_phase_detection software is designed to scan continuous daily waveforms to detect earthquake phase arrivals from local to regional (150 km) events. The detections are made with a deep learning encoder-decoder model. When the model detects an earthquake in the waveforms, a second model is implemented to classify the first arriving motions. Both deep learning models are trained with the Tensorflow package using publicly available benchmark data sets. The software input is a path to a directory that contains waveforms in mseed format and the associated response files in xml format. The output is a data table of time stamped detections, signal amplitude, signal-to-noise ratio, and softmax probability of the detection in a generic format applicable to post-processing association algorithms for event locations. Additionally, the p-wave and s-wave waveforms are saved in a data table for rapid access when producing improved locations using correlation-based techniques. The software is designed for multiprocessing with multiple GPU’s for rapid processing of large data sets. The configuration file provides flexibility in the trained models implemented and allows access to multiple models trained for different sampling rates or input dimensions. This is particularly useful for regions with multiple networks that do not have the same data parameters.
AIRES-NODE
This software package performs time series forecasting for engineering systems using neural controlled differential equations. Neural controlled differential equations are continuous time analogues to recurrent neural networks. AIRES-NODE is particularly well suited for dynamic systems which are subject to external forcing terms and time-dependent boundary conditions. AIRES-NODE provides an encoder-decoder architecture which allows for variable-length forecasts to be made and is not limited to a fixed time step size when forecasting. Additionally, by utilizing a novel combination of a variational autoencoder and neural controlled differential equations, the AIRES-NODE package is capable of producing probabilistic future forecasts.
Cybersecurity-Tools/V2W-BERT
Software Vulnerabilities to Weakness Mapping. V2W-BERT optimizes the learnable parameters θ of Fθ in two steps. In the first step, the pre-trained BERT language model is further fine-tuned with CVE/CWE descriptions specific to cyber security. In the second step, the trained BERT model is employed in a Siamese network architecture to establish links between CVEs and CWEs. The architecture takes a specific CVE-CWE pair as input and predicts whether the CVE belongs to the CWE or not, with a confidence value. V2W-BERT includes a Mask Language Model (LM) based Reconstruction Decoder to ensure that the descriptions’ contexts are not changed too much during the training process.
PNNL-CompBio/pf-gnn_pli
We have developed a deep learning based method to decode the protein-ligand interactions and predict their probability of binding. We use 3-Dimensional structure of proteins and ligand molecules with the ligand docked to the receptor and use the information at the interaction region to assess the binding of the protein-ligand complex.
FTL: Transfer Learning Nonlinear Plasma Dynamic Transitions in Low Dimensional Embeddings (FTL) v1.0
Fusion Transfer Learning (FTL) model provides a new paradigm to study high-dimensional dynamical behaviors, such as those in fusion plasma systems. The knowledge transfer process leverages a pre-trained neural encoder-decoder network, initially trained on linear simulations, to effectively capture nonlinear dynamics. The low-dimensional embeddings extract the coherent structures of interest, while preserving the inherent dynamics of the complex system. Experimental results highlight FTL's capacity to capture transitional behaviors and dynamical features in plasma dynamics -- a task often challenging for conventional methods. The model developed in this study is generalizable and can be extended broadly through transfer learning to address various magnetohydrodynamics (MHD) modes.
Event Fanout/Receiver (evfr) v1.0
The event fanout-receiver is an event-based timing system implementation capable of synchronizing (with respect to clock, events and triggers) to an upstream event generator. This can be used in 2 modes: fanout or receiver. the first one receives 1 upstream timing streams and fanouts it to 36. The second one receives and decodes the stream. This has been in use by ALS for many years and this is a similar implementation, but providing a more flexible configuration
HydraGNN v4.0
The new version of HydraGNN v4.0 provides additional core capabilities, such as: Inclusion of multi-body atomistic cluster expansion MACE, polarizable atom interaction neural network PAINN, and equivariant principal neighborhood aggregation (PNAEq) among the message passing layers supported -Inclusion of graph transformers to directly model long-range interactions between nodes that are distant in the graph topology Integration of graph transformers with message passing layers by combining the graph embedding generated by the two mechanisms, which allows for an improved expressivity of the HydraGNN architecture Improved re-implementation of multi-task learning (MTL) to allow its use for stabilized training across imbalanced, multi-source, multi-fidelity data Introduction of multi-task parallelism, a newly proposed type of model parallelism specifically for MTL architectures, which allows to dispatch different output decoding heads to different GPU devices Integration of multi-task parallelism with pre-existing distributed data parallelism to enable a 2D parallelization for distributed training Improved portability of the distributed training across Intel GPUs, which has been testes on ALCF exascale supercomputer Aurora Inclusion of 2-level fine-grained energy profilers portable across NVIDIA, AMD, and Intel GPUs to monitor the power and energy consumption associated with different functions executed by the HydraGNN code during data pre-load and training Restructuring of previous examples and inclusion of new sets of examples to illustrate the download, preprocess, and training of HydraGNN models on new large-scale open-source datasets for atomistic materials modeling (e.g., Alexandria, Transition1x, OMat24, OMol25)
Assessing Tropical Pacific-induced Predictability of Southern California Precipitation Using a Novel Multi-input Multi-output Autoencoder
We construct a novel Multi-Input Multi-Output Autoencoder-decoder (MIMO-AE) to capture the non-linear relationship of Southern California precipitation and tropical Pacific Ocean sea surface temperature. The MIMO-AE is trained on both monthly TP-SST and SC-PRECIP anomalies simultaneously. The co-variability of the two fields in the MIMO-AE shared nonlinear latent space can be condensed into an index, termed the MIMO-AE index. We use a transfer learning approach to train a MIMO-AE on the combined dataset of 100 years of output from a historical simulation with the Energy Exascale Earth Systems Model version 1 and a segment of observational data. We further use Long Short-Term Memory networks to assess sub-seasonal predictability of SC-PRECIP using the MIMO-AE index. We find that the MIMO-AE index provides enhanced predictability of SC-PRECIP for a lead-time of up-to four months as compared to Niño 3.4 index and the El Niño Southern Oscillation Longitudinal Index.
An explainable variational autoencoder model for three-dimensional acoustic emission source localization in hollow cylindrical structures
We introduce an explainable variational autoencoder for three-dimensional (3D) localization of acoustic emission sources in hollow cylindrical structures, with an unsupervised approach. This research capitalizes on multi-arrival waveforms generated by helical path propagation in cylindrical geometries to enable efficient two-receiver localization. By integrating the modal characteristics of Lamb modes under multi-path conditions, we demonstrate that two sets of time-of-arrival differences and peak amplitudes extracted from one receiver can serve as effective localization features. This initial approach identifies four potential source locations, highlighting the feasibility of two-receiver source localization using traditional feature extraction methods. However, direct extraction can be challenging when mode overlaps occur, complicating the localization process. To address this, our work proposes a novel waveform-based method. This method leverages the consistent dispersion characteristics within isotropic materials, where each unique combination of mode arrival times and peak amplitudes constructs a distinct waveform. This distinctiveness overcomes the ambiguities associated with mode overlaps, significantly enhancing the method’s precision and robustness. Our approach adopts a data-driven strategy for waveform-based localization using variational autoencoder (VAE). VAE discerns waveform patterns for localization, while also addressing data uncertainties. The VAE’s encoder and decoder networks capture the localization process and the source’s influence on waveform generation, respectively, guiding latent variables to segregate waveforms by source in the latent space. The design of the learning process focuses on specific localization characteristics to enhance result explainability. Localization predictions are generated by projecting test waveforms, not included in the training set, onto a trained latent space. The prediction is determined using a nearest-neighbor approach based on the closest latent representation of a source. Validation with pencil-lead-break tests on a metallic pipe confirmed our method’s effectiveness, achieving an averaged 3D localization accuracy of 0.84.
Harnessing redox proteomics to study metabolic regulation and stress response in lignin-fed Rhodococci
Abstract Background Rhodococci are studied for their bacterial ligninolytic capabilities and proclivity to accumulate lipids. Lignin utilization is a resource intensive process requiring a variety of redox active enzymes and cofactors for degradation as well as defense against the resulting toxic byproducts and oxidative conditions. Studying enzyme expression and regulation between carbon sources will help decode the metabolic rewiring that stymies lignin to lipid conversion in these bacteria. Herein, a redox proteomics approach was applied to investigate a fundamental driver of carbon catabolism and lipid anabolism: redox balance. Results A consortium of Rhodococcus strains was employed in this study given its higher capacity for lignin degradation compared to monocultures. This consortium was grown on glucose vs. lignin under nitrogen limitation to study the importance of redox balance as it relates to nutrient availability. A modified bottom–up proteomics workflow was harnessed to acquire a general relationship between protein abundance and protein redox states. Global proteomics results affirm differential expression of enzymes involved in sugar metabolism vs. those involved in lignin degradation and aromatics metabolism. As reported previously, several enzymes in the lipid biosynthetic pathways were downregulated, whereas many involved in β-oxidation were upregulated. Interestingly, proteins involved in oxidative stress response were also upregulated perhaps in response to lignin degradation and aromatics catabolism, which require oxygen and reactive oxygen species and generate toxic byproducts. Enzymes displaying little-to-no change in abundance but differences in redox state were observed in various pathways for carbon utilization (e.g., β‑ketoadipate pathway), lipid metabolism, as well as nitrogen metabolism (e.g., purine scavenging/synthesis), suggesting potential mechanisms of redox-dependent regulation of metabolism. Conclusions Efficient lipid production requires a steady carbon and energy flux while balancing fundamental requirements for enzyme production and cell maintenance. For lignin, we theorize that this balance is difficult to establish due to resource expenditure for enzyme production and stress response. This is supported by significant changes to protein abundances and protein cysteine oxidation in various metabolic pathways and redox processes.
Hidden Markov Model: a shortest unique representative approach to detect the protein toxins, virulence factors and antibiotic resistance genes
Objective: Currently, next generation sequencing (NGS) is widely used to decode potential novel or variant pathogens both in emergent outbreaks and in routine clinical practice. However, the efficient identification of novel or diverged pathogenomic compositions remains a big challenge. It is especially true for short DNA sequence fragments from NGS, since sequence similarity searching is vulnerable to false negatives or false positives, as is mismatching or matching with unrelated proteins. Therefore, this study aimed to establish a bioinformatics approach that can generate unique motif sequences for profiling searching, resulting in high specificity and sensitivity. Results: In this study, we introduced a Shortest Unique Representative Hidden Markov Model (HMM) approach to identify bacterial toxin, virulence factor (VF), and antimicrobial resistance (AR) in short sequence reads. We first construct unique representative domain sequences of toxin genes, VFs, and ARs to avoid potential false positives, and then to use HMM models to accurately identify potential toxin, VF, and AR fragments. The benchmark shows this approach can achieve relatively high specificity and sensitivity if the appropriate cutoff value is applied. Our approach can be used to recognize the protein sequences of known toxins and pathogens, identifies their common characteristics and then searches for similar sequences in other organisms.
Time-series metagenomics reveals changing protistan ecology of a temperate dimictic lake
Abstract Background Protists, single-celled eukaryotic organisms, are critical to food web ecology, contributing to primary productivity and connecting small bacteria and archaea to higher trophic levels. Lake Mendota is a large, eutrophic natural lake that is a Long-Term Ecological Research site and among the world’s best-studied freshwater systems. Metagenomic samples have been collected and shotgun sequenced from Lake Mendota for the last 20 years. Here, we analyze this comprehensive time series to infer changes to the structure and function of the protistan community and to hypothesize about their interactions with bacteria. Results Based on small subunit rRNA genes extracted from the metagenomes and metagenome-assembled genomes of microeukaryotes, we identify shifts in the eukaryotic phytoplankton community over time, which we predict to be a consequence of reduced zooplankton grazing pressures after the invasion of a invasive predator (the spiny water flea) to the lake. The metagenomic data also reveal the presence of the spiny water flea and the zebra mussel, a second invasive species to Lake Mendota, prior to their visual identification during routine monitoring. Furthermore, we use species co-occurrence and co-abundance analysis to connect the protistan community with bacterial taxa. Correlation analysis suggests that protists and bacteria may interact or respond similarly to environmental conditions. Cryptophytes declined in the second decade of the timeseries, while many alveolate groups (e.g., ciliates and dinoflagellates) and diatoms increased in abundance, changes that have implications for food web efficiency in Lake Mendota. Conclusions We demonstrate that metagenomic sequence-based community analysis can complement existing efforts to monitor protists in Lake Mendota based on microscopy-based count surveys. We observed patterns of seasonal abundance in microeukaryotes in Lake Mendota that corroborated expectations from other systems, including high abundance of cryptophytes in winter and diatoms in fall and spring, but with much higher resolution than previous surveys. Our study identified long-term changes in the abundance of eukaryotic microbes and provided context for the known establishment of an invasive species that catalyzes a trophic cascade involving protists. Our findings are important for decoding potential long-term consequences of human interventions, including invasive species introduction.
Orthogonal spatial coding with stimulated parametric down-conversion
Orthogonal optical coding is widely used in classical multi-user communication networks. Using the phase conjugation property of stimulated parametric down-conversion, we extend the current time-domain orthogonal optical coding scheme to the spatial domain to encode and decode image information. In this process, the idler beam inherits the complex conjugate of the field information encoded in the seed beam. An encoding phase mask introduced onto the input seed beam blurs the image transferred to the idler. The original image is restored by passing the coded transferred image through a corrective phase mask placed in the momentum space of the idler beam. We expect that this scheme can also inspire new techniques in secure image transmission, aberration cancellation, and frequency conversion imaging.
High-dimensional quantum key distribution using orbital angular momentum of single photons from a colloidal quantum dot at room temperature
High-dimensional quantum key distribution (HDQKD) is a promising avenue to address the inherent limitations of basic quantum key distribution (QKD) protocols. However, experimental realizations of HDQKD to date have relied on indeterministic photon sources that limit the achievable key rate. In this paper, we demonstrate a full emulation of a HDQKD system using a single colloidal giant quantum dot (gQD) as a deterministic, compact, and room-temperature single-photon source (SPS). We demonstrate a practical protocol by encoding information in a high-dimensional space (d = 3) of the orbital angular momentum of the photons. Our experimental configuration incorporates two spatial light modulators for encoding and decoding the spatial information carried by individual photons. Our experimental demonstration establishes the feasibility of utilizing high radiative quantum yield gQDs as practical SPSs for HDQKD. We also experimentally demonstrate surpassing the traditional d = 2 QKD capacity with comparable error rates, indicating a significant improvement in performance while maintaining reliability.
Bayesian inference of structured latent spaces from neural population activity with the orthogonal stochastic linear mixing model
The brain produces diverse functions, from perceiving sounds to producing arm reaches, through the collective activity of populations of many neurons. Determining if and how the features of these exogenous variables (e.g., sound frequency, reach angle) are reflected in population neural activity is important for understanding how the brain operates. Often, high-dimensional neural population activity is confined to low-dimensional latent spaces. However, many current methods fail to extract latent spaces that are clearly structured by exogenous variables. This has contributed to a debate about whether or not brains should be thought of as dynamical systems or representational systems. Here, we developed a new latent process Bayesian regression framework, the orthogonal stochastic linear mixing model (OSLMM) which introduces an orthogonality constraint amongst time-varying mixture coefficients, and provide Markov chain Monte Carlo inference procedures. We demonstrate superior performance of OSLMM on latent trajectory recovery in synthetic experiments and show superior computational efficiency and prediction performance on several real-world benchmark data sets. We primarily focus on demonstrating the utility of OSLMM in two neural data sets: μ ECoG recordings from rat auditory cortex during presentation of pure tones and multi-single unit recordings form monkey motor cortex during complex arm reaching. We show that OSLMM achieves superior or comparable predictive accuracy of neural data and decoding of external variables (e.g., reach velocity). Most importantly, in both experimental contexts, we demonstrate that OSLMM latent trajectories directly reflect features of the sounds and reaches, demonstrating that neural dynamics are structured by neural representations. Together, these results demonstrate that OSLMM will be useful for the analysis of diverse, large-scale biological time-series datasets.
Manifold Learning-Based Polynomial Chaos Expansions for High-Dimensional Surrogate Models
In this work we introduce a manifold learning-based method for uncertainty quantification (UQ) in systems describing complex spatiotemporal processes. Our first objective is to identify the embedding of a set of high-dimensional data representing quantities of interest of the computational or analytical model. For this purpose, we employ Grassmannian diffusion maps, a two-step nonlinear dimension reduction technique which allows us to reduce the dimensionality of the data and identify meaningful geometric descriptions in a parsimonious and inexpensive manner. Polynomial chaos expansion is then used to construct a mapping between the stochastic input parameters and the diffusion coordinates of the reduced space. An adaptive clustering technique is proposed to identify an optimal number of clusters of points in the latent space. The similarity of points allows us to construct a number of geometric harmonic emulators which are finally utilized as a set of inexpensive pretrained models to perform an inverse map of realizations of latent features to the ambient space and thus perform accurate out-of-sample predictions. Thus, the proposed method acts as an encoder-decoder system which is able to automatically handle very high-dimensional data while simultaneously operating successfully in the small-data regime. The method is demonstrated on two benchmark problems and on a system of advection-diffusion-reaction equations which model a first-order chemical reaction between two species. In all test cases, the proposed method is able to achieve highly accurate approximations which ultimately lead to the significant acceleration of UQ tasks.
Denoising Seismograms in the Time Domain Using a Deep Learning Model
Deep learning has emerged as a transformative tool for enhancing the extraction of reliable information from seismograms, addressing the increasing demand for precise and efficient seismic data analysis. We introduce an innovative encoder–decoder deep learning model, named WaveDenoiser, designed for noise reduction in the time domain, thereby eliminating the need for spectrogram computations that have been used for existing deep learning tools and significantly improving processing speed. Utilizing the benchmark dataset that is Stanford Earthquake Dataset, we developed three models of varying sizes: base, medium, and large. Notably, the large (referred to as WaveDenoiser) model demonstrated superior performance, achieving a median signal‐to‐noise ratio improvement of 8.8 dB on in‐distribution unseen data (in the same geographic region) and 7.7 dB on out‐distribution unseen data (in a new geographic region), outpacing both the base and medium models. Further evaluation of the WaveDenoiser model revealed a reduction in median arrival‐time errors by 0.02 s for P waves and 0.01 s for S waves when processing waveforms prior to phase picking using PhaseNet on in‐distribution unseen data. When tested on out‐distribution unseen data, the model also effectively reduced the P‐wave median arrival‐time error by 0.02 and 0.01 s in median arrival‐time error for S waves. Importantly, the application of WaveDenoiser resulted in a significant reduction of phase picking outliers by 1.1% to 3.6% for both P and S waves. In addition, we achieved over five times acceleration in processing speed compared with the seisBench implementation of DeepDenoiser. Our findings underscore the potential of WaveDenoiser as a powerful tool for improving seismic data analysis and processing efficiency.