Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Network inference”

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 199 records · Page 11
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAs

Neural networks with sub-microsecond inference latency are required by many critical applications. Targeting such applications deployed on FPGAs, we present High Granularity Quantization (HGQ), a quantization-aware training framework that optimizes parameter bit-widths through gradient descent. Unlike conventional methods, HGQ determines the optimal bit-width for each parameter independently, making it suitable for hardware platforms supporting heterogeneous arbitrary precision arithmetic. In our experiments, HGQ shows superior performance compared to existing network compression methods, achieving orders of magnitude reduction in resource consumption and latency while maintaining the accuracy on several benchmark tasks. These improvements enable the deployment of complex models previously infeasible due to resource or latency constraints. HGQ is open-source and is used for developing next-generation trigger systems at the CERN ATLAS and CMS experiments for particle physics, enabling the use of advanced machine learning models for real-time data selection with sub-microsecond latency.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2026

Knowledge Graph of RB-Tnseq Data from Fitness Browser (KP-DP1)

Motivation: Predicting microbial gene fitness across environmental conditions remains a central challenge for predictive phenomics and autonomous experimentation. Fitness assays generate large volumes of genotype–phenotype measurements difficult to integrate with experimental metadata and biological function in a form that supports mechanistic reasoning. Knowledge graphs offer a semantic framework for unifying modalities and enabling context-aware inference. Results: We build GIMME (Graph Inference for Microbial Metabolism Exploration), a semantically grounded knowledge graph that unifies gene fitness measurements spanning 10 Pseudomonas species with experimental metadata and biological context. Media are decomposed into chemical components and experiments carry structured links to natural-language descriptions. The resulting graph supports two inference modes: (1) symbolic graph traversal to surface candidate gene–environment and gene–chemical associations, and (2) learned inference using heterogeneous graph neural networks that propagate information across neighborhoods. We formulate link regression over (gene, media, experiment) triplets, combining learned gene embeddings with pretrained LLM sourced text embeddings of node descriptions to predict gene fitness. We then augment a baseline MLP with an auxiliary message-passing encoder (GraphSAGE/GAT) that propagates information over gene–protein–function and media–chemical subgraphs, and fuse the two pathways with a gated residual connection. This approach produces strong agreement with held-out fitness measurements (GraphSAGE Pearson r 0.74) while also highlighting inference challenges in extreme-fitness regimes. We aggregate GAT edge-attention weights by relation type and layer to estimate which biological and environmental relations most influence fitness predictions. Conclusion: This work explores using knowledge graphs as “context graphs” for microbial phenotype prediction. They provide a rich substrate which enables explainable retrieval of supporting evidence, and provides a natural bridge to autonomous workflows that prioritize the next experiment.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Using limited neural networks to assess relative mechanistic influence on shock heating in granular solids

The rapid compaction of granular media results in localized heating that can induce chemical reactions, phase transformations, and melting. However, there are numerous mechanisms in play that can be dependent on a variety of microstructural features. Machine learning techniques such as neural networks offer a ubiquitous method to develop models for physical processes. Limiting what kind of microstructural information is used as an input and assessing normalized changes in network error, the relative importance of different mechanisms can be inferred. Here we utilize binned, initial density information as network inputs to predict local shock heating in a granular high explosive trained from large-scale molecular dynamics simulations. In this study, the spatial extent of the density field used in the network is altered to assess the importance and relevant length scales of the physical mechanisms in play, where different microstructural features result in different predictive capabilities.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Inferring protein expression changes from mRNA in Alzheimer’s dementia using deep neural networks

Identifying the molecular systems and proteins that modify the progression of Alzheimer’s disease and related dementias (ADRD) is central to drug target selection. However, discordance between mRNA and protein abundance, and the scarcity of proteomic data, has limited our ability to advance candidate targets that are mainly based on gene expression. Therefore, by using a deep neural network that predicts protein abundance from mRNA expression, here we attempt to track the early protein drivers of ADRD. Specifically, by applying the clei2block deep learning model to 1192 brain RNA-seq samples, we identify protein modules and disease-associated expression changes that were not directly observed at the mRNA level. Moreover, pseudo-temporal trajectory inference based on the predicted proteome became more closely correlated with cognitive decline and hippocampal atrophy compared to RNA-based trajectories. This suggests that the predicted changes in protein expression could provide a better molecular representation of ADRD progression. Furthermore, overlaying clinical traits on protein pseudotime trajectory identifies protein modules altered before cognitive impairment. These results demonstrate how our method can be used to identify potential early protein drivers and possible drug targets for treating and/or preventing ADRD.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

The Effect of the Prior and the Experimental Design on the Inference of the Precision Matrix in Gaussian Chain Graph Models

Here, we investigate whether (and how) experimental design could aid in the estimation of the precision matrix in a Gaussian chain graph model, especially the interplay between the design, the effect of the experiment and prior knowledge about the effect. Estimation of the precision matrix is a fundamental task to infer biological graphical structures like microbial networks. We compare the marginal posterior precision of the precision matrix under four priors: flat, conjugate Normal-Wishart, Normal-MGIG and a general independent. Under the flat and conjugate priors, the Laplace-approximated posterior precision is not a function of the design matrix rendering useless any efforts to find an optimal experimental design to infer the precision matrix. In contrast, the Normal-MGIG and general independent priors do allow for the search of optimal experimental designs, yet there is a sharp upper bound on the information that can be extracted from a given experiment. We confirm our theoretical findings via a simulation study comparing (i) the KL divergence between prior and posterior and (ii) the Stein’s loss difference of MAPs between random and no experiment. Our findings provide practical advice for domain scientists conducting experiments to better infer the precision matrix as a representation of a biological network.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Assessing Decadal Predictability in an Earth-System Model Using Explainable Neural Networks

We show that explainable neural networks can identify regions of oceanic variability that contribute predictability on decadal timescales in a fully coupled Earth-system model. The neural networks learn to use sea-surface temperature anomalies to predict future continental surface temperature anomalies. We then use a neural-network explainability method called layerwise relevance propagation to infer which oceanic patterns lead to accurate predictions made by the neural networks. In particular, regions within the North Atlantic Ocean and North Pacific Ocean lend the most predictability for surface temperature across continental North America. We apply the proposed methodology to decadal variability, although the concept is generalizable to other timescales of predictability. Furthermore, while our approach focuses on predictable patterns of internal variability within climate models, it should be generalizable to observational data as well. Our study contributes to the growing evidence that explainable neural networks are important tools for advancing geoscientific knowledge.

58 GEOSCIENCES↗
DOE OSTI2024

A Full-Stack Exploration of Language-Based Parallelism in Fortran 2023

This poster explores native parallel features in Fortran 2023 through the lens of supporting applications with libraries, compilers, and parallel runtimes. The language revision informally named Fortran 2008 introduced parallelism in the form of Single Program Multiple Data (SPMD) execution with two broad feature sets: (1) loop-level parallelism via do concurrent and (2) a Partitioned Global Address Space (PGAS) comprised of distributed “coarray” data structures. Fortran’s native parallelism has demonstrated high performance [1] and reduced the burden of inserting what sometimes amounts to more directives than code. Several compilers support both feature sets, typically by translating do concurrent into serial do loops annotated by parallel directives and by translating SPMD/PGAS features into direct calls to a communication library. Our research focuses primarily on two questions: (1) can the compiler’s parallel runtime library be developed in the language being compiled (Fortran) and (2) can we define an interface to the runtime that liberates compilers from being hardwired to one runtime and vice versa. We are answering these questions by developing the Parallel Runtime Interface for Fortran (PRIF) [2] and the Co-Array Fortran Framework of Efficient Interfaces to Network Environments (Caffeine) [3]. Caffeine is initially targeting adoption by LLVM Flang, a new open-source Fortran compiler developed by a broad community in industry, academia, and government labs. We are also exploring the use of these features in Inference-Engine, a deep learning library designed to facilitate neural network training and inference for high-performance computing applications written in modern Fortran.

Rasmussen, Katherine↗
DOE OSTI2024

A deep learning approach to fast analysis of collective Thomson scattering spectra

Fast analysis of collective Thomson scattering ion acoustic wave features using a deep convolutional neural network model is presented. The network was trained from spectra to predict the plasma parameters, including ion velocities, population fractions, and ion and electron temperatures. A fully kinetic particle-in-cell simulation was used to model a laboratory astrophysics experiment and simulate a diagnostic image of the ion acoustic wave feature. Network predictions were compared with Bayesian inference of the plasma model parameters for both the simulated and experimentally measured images. Both approaches were fairly accurate predicting the simulated image and the network predictions matched a good portion of the Bayesian results for the experimentally measured image. The Bayesian approach is more robust to noise and motivates future work to train deep learning models with realistic noise. The advantage of the deep learning model is making thousands of predictions in a few hundred milliseconds, compared to a few seconds to minutes per prediction for the optimization and Bayesian approaches presented here. The results demonstrate promising capabilities of deep learning models to analyze Thomson data orders of magnitude faster than conventional methods when using the neural network for standalone analysis. If more rigorous analysis is needed, neural network predictions can be used to quickly initialize other optimization methods and increase chances of success. This is especially useful when the dataset becomes very large or highly dimensional and manually refining initial conditions for the entire dataset are no longer tractable.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2023

Examining Rail Transportation Route of Crude Oil in the United States Using Crowdsourced Social Media Data

Safety issues associated with transporting crude oil by rail have been a concern since the boom of the U.S. domestic shale oil production in 2012. During the last decade, over 300 crude-oil-by-rail incidents have occurred in the United States. Some of them have caused adverse consequences including fire and hazardous materials leakage. However, only limited information on crude-on-rail routes and their associated risks is available to the public. To this end, this study proposed an unconventional way to reconstruct crude-on-rail routes using geotagged photos harvested from the Flickr website. The proposed method linked the geotagged photos of crude oil trains posted online with national railway networks to identify potential railway segments that those crude oil trains were traveling on. Here, a shortest path-based method was applied to infer the complete crude-on-rail routes, by utilizing the confirmed railway segments as well as their directional information. Validation of the inferred routes was performed using a public map and official crude oil incident data. The results suggested that the inferred routes based on geotagged photos had high coverage, with approximately 96% of the documented crude oil incidents aligned with the reconstructed crude-on-rail network. The inferred crude oil train routes were found to pass through several metropolitan areas of high population density, who were exposed to potential risk. These findings could improve situational awareness for policy makers and transportation planners. In addition, with the inferred routes, this study has established a good foundation for future crude oil train risk-analyses along the rail route.

42 ENGINEERING↗
DOE OSTI2024

Improved Characterization of Soil Organic Matter by Integrating FT-ICR MS, Liquid Chromatography Tandem Mass Spectrometry, and Molecular Networking: A Case Study of Root Litter Decay under Drought Conditions

Understanding of how soil organic matter (SOM) chemistry is altered in a changing climate has advanced considerably; however, most SOM components remain unidentified, impeding the ability to characterize a major fraction of organic matter and predict what types of molecules, and from which sources, will persist in soil. Here we present a novel approach to better characterize SOM extracts by integrating information from three types of analyses, and we deploy this method to characterize decaying root-detritus soil microcosms subjected to either drought or normal conditions. To observe broad differences in composition, we employed direct infusion Fourier-transform ion cyclotron resonance mass spectrometry (DI-FT-ICR MS). We complemented this with liquid chromatography tandem mass spectrometry (LC-MS/MS) to identify components by library matching. Since libraries contain only a small fraction of SOM components, we also used fragment spectral cosine similarity scores to relate unknowns and library matches through molecular networks. This integrated approach allowed us to corroborate DI-FT-ICR MS molecular formulas using library matches, which included fungal metabolites and related polyphenolic compounds. We also inferred structures of unknowns from molecular networks and improved LC-MS/MS annotation rates from ~5 to 35% by considering DI-FT-ICR MS molecular formula assignments. Under drought conditions, we found greater relative amounts of lignin-like vs condensed aromatic polyphenol formulas and lower average nominal oxidation state of carbon, suggesting reduced decomposition of SOM and/or microbes under stress. Our integrated approach provides a framework for enhanced annotation of SOM components that is more comprehensive than performing individual data analyses in parallel.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Nonvolatile Electrochemical Random‐Access Memory under Short Circuit

Abstract Electrochemical random‐access memory (ECRAM) is a recently developed and highly promising analog resistive memory element for in‐memory computing. One longstanding challenge of ECRAM is attaining retention time beyond a few hours. This short retention has precluded ECRAM from being considered for inference classification in deep neural networks, which is likely the largest opportunity for in‐memory computing. In this work, an ECRAM cell with orders of magnitude longer retention than previously achieved is developed, and which is anticipated to exceed ten years at 85 °C. This study hypothesizes that the origin of this exceptional retention is phase separation, which enables the formation of multiple effectively equilibrium resistance states. This work highlights the promises and opportunities to use phase separation to yield ECRAM cells with exceptionally long, and potentially permanent, retention times.

Kim, Diana S.↗
DOE OSTI2022

SIMILE enables alignment of tandem mass spectra with statistical significance

Abstract Interrelating small molecules according to their aligned fragmentation spectra is central to tandem mass spectrometry-based untargeted metabolomics. Current alignment algorithms do not provide statistical significance and compounds that have multiple delocalized structural differences and therefore often fail to have their fragment ions aligned. Here we align fragmentation spectra with both statistical significance and allowance for multiple chemical differences using Significant Interrelation of MS/MS Ions via Laplacian Embedding (SIMILE). SIMILE yields spectral alignment inferred structural connections in molecular networks that are not found with cosine-based scoring algorithms. In addition, it is now possible to rank spectral alignments based on p-values in the exploration of structural relationships between compounds and enhance the chemical connectivity that can be obtained with molecular networking.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Detecting operons in bacterial genomes via visual representation learning

Contiguous genes in prokaryotes are often arranged into operons. Detecting operons plays a critical role in inferring gene functionality and regulatory networks. Human experts annotate operons by visually inspecting gene neighborhoods across pileups of related genomes. These visual representations capture the inter-genic distance, strand direction, gene size, functional relatedness, and gene neighborhood conservation, which are the most prominent operon features mentioned in the literature. By studying these features, an expert can then decide whether a genomic region is part of an operon. We propose a deep learning based method named Operon Hunter that uses visual representations of genomic fragments to make operon predictions. Using transfer learning and data augmentation techniques facilitates leveraging the powerful neural networks trained on image datasets by re-training them on a more limited dataset of extensively validated operons. Our method outperforms the previously reported state-of-the-art tools, especially when it comes to predicting full operons and their boundaries accurately. Furthermore, our approach makes it possible to visually identify the features influencing the network’s decisions to be subsequently cross-checked by human experts.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

Interface learning in fluid dynamics: Statistical inference of closures within micro–macro-coupling models

Many complex multiphysics systems in fluid dynamics involve using solvers with varied levels of approximations in different regions of the computational domain to resolve multiple spatiotemporal scales present in the flow. The accuracy of the solution is governed by how the information is exchanged between these solvers at the interface and several methods have been devised for such coupling problems. In this article, we construct a data-driven model by spatially coupling a microscale lattice Boltzmann method (LBM) solver and macroscale finite difference method (FDM) solver for reaction-diffusion systems. The coupling between the micro-macro solvers has one to many mapping at the interface leading to the interface closure problem, and we propose a statistical inference method based on neural networks to learn this closure relation. The performance of the proposed framework in a bifidelity setting partitioned between the FDM and LBM domain shows its promise for complex systems where analytical relations between micro-macro solvers are not available.

42 ENGINEERING↗
DOE OSTI2023

Variational deep learning of equilibrium transition path ensembles

Here, we present a time-dependent variational method to learn the mechanisms of equilibrium reactive processes and efficiently evaluate their rates within a transition path ensemble. This approach builds off of the variational path sampling methodology by approximating the time-dependent commitment probability within a neural network ansatz. The reaction mechanisms inferred through this approach are elucidated by a novel decomposition of the rate in terms of the components of a stochastic path action conditioned on a transition. This decomposition affords an ability to resolve the typical contribution of each reactive mode and their couplings to the rare event. The associated rate evaluation is variational and systematically improvable through the development of a cumulant expansion. We demonstrate this method in both over- and under-damped stochastic equations of motion, in low-dimensional model systems, and in the isomerization of a solvated alanine dipeptide. In all examples, we find that we can obtain quantitatively accurate estimates of the rates of the reactive events with minimal trajectory statistics and gain unique insights into transitions through the analysis of their commitment probability.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Three-dimensional reconstruction of laser-direct-drive inertial confinement fusion hot-spot plasma from x-ray diagnostics on the OMEGA laser facility (invited)

A deep-learning convolutional neural network (CNN) is used to infer, from x-ray images along multiple lines of sight, the low-mode shape of the hot-spot emission of deuterium–tritium (DT) laser-direct-drive cryogenic implosions on OMEGA. The motivation of this approach is to develop a physics-informed 3-D reconstruction technique that can be performed within minutes to facilitate the use of the results to inform changes to the initial target and laser conditions for the subsequent implosion. The CNN is trained on a 3D radiation-hydrodynamic simulation database to relate 2D x-ray images to 3D emissivity at stagnation. The CNN accounts for the lack of an absolute spatial reference and the different bands of photon energies in the x-ray images. While previous works studied the effect of mode-1 asymmetries on implosion performance using nuclear diagnostics, this work focuses on the effect of mode 2 inferred from x-ray diagnostics on implosion performance. A current analysis of 19 DT cryogenic implosions indicates there is an upper limit of ~20% reduction in the neutron yield caused by an ℓ = 2 amplitude for ℓ 2 /ℓ 0 ≤ 0.32. Here, these conclusions are supported by 2D simulations.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2021

Distributed Inference with Sparse and Quantized Communication

Here, we consider the problem of distributed inference where agents in a network observe a stream of private signals generated by an unknown state, and aim to uniquely identify this state from a finite set of hypotheses. We focus on scenarios where communication between agents is costly, and takes place over channels with finite bandwidth. To reduce the frequency of communication, we develop a novel event-triggered distributed learning rule that is based on the principle of diffusing low beliefs on each false hypothesis. Building on this principle, we design a trigger condition under which an agent broadcasts only those components of its belief vector that have adequate innovation, to only those neighbors that require such information. We prove that our rule guarantees convergence to the true state exponentially fast almost surely despite sparse communication, and that it has the potential to significantly reduce information flow from uninformative agents to informative agents. Next, to deal with finite-precision communication channels, we propose a distributed learning rule that leverages the idea of adaptive quantization. We show that by sequentially refining the range of the quantizers, every agent can learn the truth exponentially fast almost surely, while using just 1 bit to encode its belief on each hypothesis. For both our proposed algorithms, we rigorously characterize the trade-offs between communication-efficiency and the learning rate.

42 ENGINEERING↗