Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Network Models”

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 415 records · Page 23
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Ca X ML: Chemistry‐informed machine learning explains mutual changes between protein conformations and calcium ions in calcium‐binding proteins using structural and topological features

Proteins' flexibility is a feature in communicating changes in cell signaling instigated by binding with secondary messengers, such as calcium ions, associated with the coordination of muscle contraction, neurotransmitter release, and gene expression. When binding with the disordered parts of a protein, calcium ions must balance their charge states with the shape of calcium-binding proteins and their versatile pool of partners depending on the circumstances they transmit. Accurately determining the ionic charges of those ions is essential for understanding their role in such processes. However, it is unclear whether the limited experimental data available can be effectively used to train models to accurately predict the charges of calcium-binding protein variants. Here, we developed a chemistry-informed, machine-learning algorithm that implements a game theoretic approach to explain the output of a machine-learning model without the prerequisite of an excessively large database for high-performance prediction of atomic charges. We used the ab initio electronic structure data representing calcium ions and the structures of the disordered segments of calcium-binding peptides with surrounding water molecules to train several explainable models. Network theory was used to extract the topological features of atomic interactions in the structurally complex data dictated by the coordination chemistry of a calcium ion, a potent indicator of its charge state in protein. Our design created a computational tool of Ca X ML, which provided a framework of explainable machine learning model to annotate ionic charges of calcium ions in calcium-binding proteins in response to the chemical changes in an environment. Our framework will provide new insights into protein design for engineering functionality based on the limited size of scientific data in a genome space.

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

How Does Flow Alteration Propagate Across a Large, Highly Regulated Basin? Dam Attributes, Network Context, and Implications for Biodiversity

Abstract Large dams are a leading cause of river ecosystem degradation. Although dams have cumulative effects as water flows downstream in a river network, most flow alteration research has focused on local impacts of single dams. Here we examined the highly regulated Colorado River Basin (CRB) to understand how flow alteration propagates in river networks, as influenced by the location and characteristics of dams as well as the structure of the river network—including the presence of tributaries. We used a spatial Markov network model informed by 117 upstream‐downstream pairs of monthly flow series (2003–2017) to estimate flow alteration from 84 intermediate‐to‐large dams representing >83% of the total storage in the CRB. Using Least Absolute Shrinkage and Selection Operator regression, we then investigated how flow alteration was influenced by local dam properties (e.g., purpose, storage capacity) and network‐level attributes (e.g., position, upstream cumulative storage). Flow alteration was highly variable across the network, but tended to accumulate downstream and remained high in the main stem. Dam impacts were explained by network‐level attributes (63%) more than by local dam properties (37%), underscoring the need to consider network context when assessing dam impacts. High‐impact dams were often located in sub‐watersheds with high levels of native fish biodiversity, fish imperilment, or species requiring seasonal flows that are no longer present. These three biodiversity dimensions, as well as the amount of dam‐free downstream habitat, indicate potential to restore river ecosystems via controlled flow releases. Our methods are transferrable and could guide screening for dam reoperation in other highly regulated basins.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Cross-Linker Selection Controls Glass Transition Elevation or Reduction in Dynamic Covalently Bonded Polymer Networks

Introducing cross-links is a powerful approach to improve polymeric material performance relevant to controlling viscoelasticity, thermal and creep resistance, degradability, and efficient membrane separations. The chemically specific glass transition temperature T g is of fundamental importance in determining the time scales of key dynamical processes and physical state of the material in such applications. Here, we study experimentally how the introduction of relatively large cross-linking molecules in slowly exchanging dynamic bond-forming polymers (vitrimers) impacts vitrification for diverse polymer chemistries and a wide range of cross-link fractions. We find T g can increase, decrease, or even remain essentially unchanged, in qualitative contrast to the generic elevation of T g in traditional permanent polymer networks. We formulate an effective terpolymer network model to understand this rich behavior, which emerges as a consequence of a competition between pure cross-linking and generalized plasticization effects. The latter is associated with the tunable cross-linker size and intrinsic dynamic mobility that can offset slowing down due to traditional permanent cross-linking constraints. Here, a new strategy for functional polymer network design is suggested based on adjusting the relative importance of the two competing physical effects, which potentially can significantly enhance energy savings in applications while retaining other intrinsic properties germane to advanced materials performance.

Copolymers↗
DOE OSTI2025

Increasing Mosquito Abundance Under Global Warming

Mosquitoes are a key virus vector that poses significant health threats globally, affecting 700 million individuals and causing 1 million deaths annually. Accurately predicting mosquito abundance and dispersion remains a challenge. Complex interactions between mosquito dynamics and various environmental factors, notably hydrology, contribute to this challenge. Existing models typically focus on precipitation and temperature and often overlook further impacts of hydrological variables within mosquito modeling. In this study, we developed an artificial intelligence‐based model for mosquito dynamics, explicitly accounting for different hydrological variables, such as precipitation, soil moisture and streamflow. Using Toronto, Canada, as a case study, we identified causal relationships between changes in mosquito populations, hydrological factors, vegetation (e.g., leaf area index), and climate variables (e.g., daylight length, precipitation, and temperature). We embedded these relationships into a Long Short‐Term Memory (LSTM) Neural Network Model capable of accurately detecting mosquito dynamics across annual, seasonal, and monthly time scales. The LSTM is able to explain, on average, approximately 40% of the variance in the observed mosquito abundance data. Using the calibrated model, we predicted that the summer season mosquito abundance would increase by ∼16% and ∼19% under an intermediate greenhouse emission scenario, Shared Socioeconomic Pathway (SSP) 2–4.5, and a high greenhouse emission scenario, SSP5‐8.5, respectively. We expect that this model can serve as a valuable tool and inform science‐based decisions affecting mosquito dynamics and public health. It can also build a foundation for future risk analysis at the regional and larger scales.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

ARPA-E Grid Optimization (GO) Competition Challenge 3

Synthetic Input Data and Team Results for the GO Competition Challenge 3 for Events 1 - 4 and the Sandbox, along with problem and format descriptions and code to validate data and solutions, are available here. Data for industry scenarios will not be made public. The Grid Optimization (GO) Competition Challenge 3 focused on the security-constrained optimal power flow (SCOPF) problem. It is part of a continuing effort begun with Challenges 1 and 2, to successfully discover, develop, and test innovative and disruptive software solutions for critical energy challenges and to overcome existing barriers. The broader goal of the of the GO Competition is to accelerate the development of transformational and disruptive methods for solving problems related to the electric power grid and to provide a transparent, fair, and comprehensive evaluation of new solution methods. Challenge 3 used multiperiod dynamic markets, including advisory models for extreme weather events, day-ahead markets, and the real-time markets with an extended look-ahead. In Event 4, whose submission window was August 31-September 4, 2023, 14 teams solved for the objective values of 669 scenarios (39 scenarios required solutions both with and without line switching being allowed). The 591 synthetic scenarios from 9 network models (3.6 GB) are available here. Ten teams were funded to participate and 7 won prizes totaling $2,400,000. The largest prize ($550,000) went to Mississippi State University. An additional $600,000 was awarded in Event 3 (6/15-16/2023). No prizes were awarded in Events 1 (1/25-27/2023) or 2 (4/13-14/2023). For more information on the competition and challenge see the "GO Competition Challenge 3 Information" resource below.

ACOPF↗
DOE OSTI2024

Anticipating Technical Expertise and Capability Evolution in Research Communities Using Dynamic Graph Transformers

The ability to anticipate global technical expertise and capability evolution trends is essential for national and global security, especially in safety-critical domains such as nuclear nonproliferation (NN) and rapidly emerging fields like artificial intelligence (AI). Here, in this work, we extend traditional statistical relational learning approaches (e.g., link prediction in collaboration networks) and formulate a problem of anticipating technical expertise and capability evolution using dynamic heterogeneous graph representations. We develop novel capabilities to forecast collaboration patterns, authorship behavior, and technical capability evolution at different granularities (e.g., scientist and institution levels) in two distinct research fields. We implement a dynamic graph transformer (DGT) neural architecture, which pushes the state-of-the-art graph neural network models by: 1) forecasting heterogeneous (rather than homogeneous) nodes and edges; and 2) relying on both discrete- and continuous-time inputs. We demonstrate that our DGT models predict collaboration, partnership, and expertise patterns with 0.26, 0.73, and 0.53 mean reciprocal rank values for AI and 0.48, 0.93, and 0.22 for NN domains. DGT model performance exceeds the best-performing static graph baseline models by 30%–80% across AI and NN domains. Our findings demonstrate that DGT models boost inductive task performance when previously unseen nodes appear in the test data for the domains with emerging collaboration patterns (e.g., AI). Specifically, models accurately predict which established scientists will collaborate with early career scientists and vice versa in the AI domain.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Stochastic Thermo-Hydro Modeling and Neural Network Surrogate Development for Thermal Resource Assessment of the Galleries-to-Calories Geobattery

The Galleries-to-Calories Geobattery concept explores the use of abandoned coal mine workings for large-scale thermal energy transport and storage. The system involves injecting waste heat from a supercomputing facility into flooded mine galleries, where groundwater flow can store and transport thermal energy for potential recovery in downgradient district heating and cooling applications. To evaluate the feasibility and performance of the Geobattery under geological and operational uncertainty, we developed a suite of stochastic thermo-hydrological (TH) simulations using Monte Carlo sampling of key uncertain parameters (e.g., permeability, porosity, thermal conductivity, specific heat capacity) and operating conditions (e.g., injection rate, injection temperature). Results identified injection rate and temperature as the most influential parameters governing thermal front propagation, while the geometry of the room-and-pillar structure played a critical role in directing the extent and orientation of thermal advancement. Optimal combinations of material properties for maximizing heat recovery were also determined. To address the high computational cost of coupled-process stochastic modeling, we trained a neural network surrogate model on 24,000 physics-based realizations, achieving an R² > 0.99 and MAE < 0.1 for temperature predictions at monitoring locations. This surrogate enabled an additional 100,000 realizations for global sensitivity analysis and probabilistic thermal resource assessment. The integrated stochastic physics–surrogate modeling framework offers a computationally efficient tool for quantifying uncertainty, identifying key drivers, and informing early-stage design decisions for Geobattery systems.

15 - GEOTHERMAL ENERGY↗
DOE OSTI2025

Coherency-Constrained Spectral Clustering for Power Network Reduction

This paper presents a methodology for reducing the complexity of large-scale power network models using spectral clustering, aggregation of electrical components, and cost function approximation. Two approaches are explored using unconstrained and constrained spectral clustering to determine areas for effective system reduction. Once the system areas are determined, both loads and generators by type are aggregated, and their new cost function is approximated through polynomial curve-fitting or statistical methods. The performance of reduced networks is evaluated in terms of their ability to follow the true daily cost of the original system over a 24-hour period considering a set of several days. Two test systems are taken as test beds. Application of the methodology to a modified version of the IEEE 39-bus system reduces it from 17 generators to a 4-bus system and 9 generators with about 93% of accuracy. Similarly, the IEEE 118-bus system is reduced from 19 generators to a 3-bus system with three aggregated units achieving over 99% of accuracy. These findings address scalability challenges and enhance accuracy for high and mid-loading level conditions, and by aggregating thermal units with similar cost functions.

42 ENGINEERING↗
DOE OSTI2024

Upsampling Monte Carlo Reactor Simulation Tallies in Depleted Sodium-Cooled Fast Reactor Assemblies Using a Convolutional Neural Network

The computational demand of neutron Monte Carlo transport simulations can increase rapidly with the spatial and energy resolution of tallied physical quantities. Convolutional neural networks have been used to increase the resolution of Monte Carlo simulations of light water reactor assemblies while preserving accuracy with negligible additional computational cost. Here, we show that a convolutional neural network can also be used to upsample tally results from Monte Carlo simulations of sodium-cooled fast reactor assemblies, thereby extending the applicability beyond thermal systems. The convolutional neural network model is trained using neutron flux tallies from 300 procedurally generated nuclear reactor assemblies simulated using OpenMC. Validation and test datasets included 16 simulations of procedurally generated assemblies, and a realistic simulation of a European sodium-cooled fast reactor assembly was included in the test dataset. We show the residuals between the high-resolution flux tallies predicted by the neural network and high-resolution Monte Carlo tallies on relative and absolute bases. The network can upsample tallies from simulations of fast reactor assemblies with diverse and heterogeneous materials and geometries by a factor of two in each spatial and energy dimension. The network’s predictions are within the statistical uncertainty of the Monte Carlo tallies in almost all cases. This includes test assemblies for which burnup values and geometric parameters were well outside the ranges of those in assemblies used to train the network.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2023

Mechanisms of metabolic adaptation in the duckweed Lemna gibba: an integrated metabolic, transcriptomic and flux analysis

Abstract Background Duckweeds are small, rapidly growing aquatic flowering plants. Due to their ability for biomass production at high rates they represent promising candidates for biofuel feedstocks. Duckweeds are also excellent model organisms because they can be maintained in well-defined liquid media, usually reproduce asexually, and because genomic resources are becoming increasingly available. To demonstrate the utility of duckweed for integrated metabolic studies, we examined the metabolic adaptation of growing Lemna gibba cultures to different nutritional conditions. Results To establish a framework for quantitative metabolic research in duckweeds we derived a central carbon metabolism network model of Lemna gibba based on its draft genome. Lemna gibba fronds were grown with nitrate or glutamine as nitrogen source. The two conditions were compared by quantification of growth kinetics, metabolite levels, transcript abundance, as well as by 13 C-metabolic flux analysis. While growing with glutamine, the fronds grew 1.4 times faster and accumulated more protein and less cell wall components compared to plants grown on nitrate. Characterization of photomixotrophic growth by 13 C-metabolic flux analysis showed that, under both metabolic growth conditions, the Calvin-Benson-Bassham cycle and the oxidative pentose-phosphate pathway are highly active, creating a futile cycle with net ATP consumption. Depending on the nitrogen source, substantial reorganization of fluxes around the tricarboxylic acid cycle took place, leading to differential formation of the biosynthetic precursors of the Asp and Gln families of proteinogenic amino acids. Despite the substantial reorganization of fluxes around the tricarboxylic acid cycle, flux changes could largely not be associated with changes in transcripts. Conclusions Through integrated analysis of growth rate, biomass composition, metabolite levels, and metabolic flux, we show that Lemna gibba is an excellent system for quantitative metabolic studies in plants. Our study showed that Lemna gibba adjusts to different nitrogen sources by reorganizing central metabolism. The observed disconnect between gene expression regulation and metabolism underscores the importance of metabolic flux analysis as a tool in such studies.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Improving Solar and Solar+Storage Screening Techniques to Reduce Utility Interconnection Time and Costs (Final Technical Report)

Residential PV installations have increased rapidly over the last decade, and the increased application volume has caused permitting delays and lower overall adoption rates. In this project, we developed and evaluated whether data-driven secondary modeling and screening techniques can help utilities assess customer applications more accurately than traditional screening shortcuts. Secondary topologies are predicted using decision trees and commonly available information, such as service transformer, customer, and street locations. Conductors were predicted using a logistic regression method based on real world object (RWO) types, service transformer ratings, conductor length, and distance to transformer. After developing the combined primary and secondary distribution network model, hosting capacity results were used to train a random forest model to predict the pass/fail likelihood of a customer application. Powerflow based models with predicted secondaries and data-driven methods both increased the screening success rate, relative to common utility heuristics, by as much as 55 percentage points. Data-driven screening techniques were described by one utility as a "right-sized" approach for residential customers given the low-risk of small errors and the high-cost of accurate modeling.

14 SOLAR ENERGY↗
DOE OSTI2022

MOFSimplify, machine learning models with extracted stability data of three thousand metal–organic frameworks

Abstract We report a workflow and the output of a natural language processing (NLP)-based procedure to mine the extant metal–organic framework (MOF) literature describing structurally characterized MOFs and their solvent removal and thermal stabilities. We obtain over 2,000 solvent removal stability measures from text mining and 3,000 thermal decomposition temperatures from thermogravimetric analysis data. We assess the validity of our NLP methods and the accuracy of our extracted data by comparing to a hand-labeled subset. Machine learning (ML, i.e. artificial neural network) models trained on this data using graph- and pore-geometry-based representations enable prediction of stability on new MOFs with quantified uncertainty. Our web interface, MOFSimplify, provides users access to our curated data and enables them to harness that data for predictions on new MOFs. MOFSimplify also encourages community feedback on existing data and on ML model predictions for community-based active learning for improved MOF stability models.

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

Introducing the 9500 Node Distribution Test System to Support Advanced Power Applications: An Operations-Focused Approach

The 9500 Node Test System is a representative section of distribution power system model developed as a part of the GridAPPS-D™ project, an effort funded by DOE as a part of the Grid Modernization Lab Consortium (GMLC) program. The test system was developed to fulfill a growing need to represent the rapidly evolving state of electric distribution systems by combining elements of legacy infrastructure systems, modern feeder topologies, and an anticipated future with smart grid technologies. It also provides a network model capable of supporting the simulation of operational scenarios such as the ones in a utility distribution control center. This test system allows the evaluation of the performance of advanced power applications in real-time, such as one that simulates the operations of an Advanced Distribution Management Systems (ADMS), Distributed Energy Resource Management Systems (DERMS), etc. in a Distribution control center. This model is an extension of the widely used IEEE 8500 Node Test Feeder and is currently being validated to become an IEEE test case to help increase adoption and widespread usage among both academia and industry. It is a full-size model representative of a section of a utility’s distribution system with multiple feeders fed from different substations. The model includes multiple distribution circuits, a sub-transmission system, multiple substations, behind the meter customer rooftop photovoltaics (PV), and multiple utility-scale distributed energy resources. To enable accurate simulations of operational scenarios, the 9500 Node Test System is designed to support procedure-based operations, with the ability to realistically demonstrate switching operations, feeder reconfiguration, adjustment of volt-var control equipment, dispatch of distributed generation, and response to planned and unplanned outages. The 9500 Node Test System includes three radial distribution feeders with 12.3 MVA of average load, consisting of both medium voltage and low voltage equipment each supplied by a different distribution substation. The three distribution feeders are connected to each other through Normally-Open switches which can be closed when needed to simulate restoration scenarios due to a fault. One feeder represents today’s grid with low penetration of customer-side renewables. The second represents a potential future grid with microgrids and 100% renewable penetration. The third has no customer generation resources, a district steam plant, and a utility-scale solar farm. The three diverse circuits were created to allow the simulation of both today’s situation as well as potential future scenarios. All three feeders have customers connected by low-voltage secondary triplex lines. This test system meets all requirements outlined in the report for creating a simulation environment that would enable discussion between key technical stakeholders as well as having the potential to accelerate operational application development and their subsequent testing and integration. The new model is a possible representation of what we believe the distribution grid may look like in the future: a high penetration of renewables, reconfigurable radial and mesh topology, numerous DERs, islanded microgrids, and significantly increased data and measurement density. The system supports both the solution of existing and newer algorithms but also enables the evaluation of applications in a realistic operational environment defined by task oriented procedural steps that represent the interaction between the control center operator and field personnel.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Predictive Modeling and Uncertainty Quantification in Condition Monitoring of Active Components: A Reactor Coolant Pump Use Case

This work develops data-driven models for onset of thermal barrier leakage in reactor coolant pumps. It incorporates uncertainty quantification to enhance the reliability and robustness of pre- dictions. Using synthetic data generated by the Generic Pressurized Water Reactor simulator, realistic degradation scenarios were simulated across lifecycle stages—beginning, middle, and end of life. Key variables, including differential pressure, flow rate, vibration, and temperatures, were analyzed using machine learning framework. The fully connected neural network models demonstrated exceptional performance, achieving R2 scores exceeding 0.99 and root mean square errors as low as around 8.23 × 10-2 gallon per minute (gpm) for the three stages of the lifecy- cle. UQ analysis further validated the model’s robustness, with narrow uncertainty bounds during steady-state operations and appropriately wider bounds during transitional phases, reflecting the physical behavior of the system. This work addresses important gaps in real-time condition moni- toring and regulatory compliance by integrating advanced condition monitoring technologies with UQ into IST programs. The ability to detect thermal barrier leakage early and quantify prediction reliability supports optimizing maintenance strategies while ensuring nuclear power plants’ safe and reliable operation.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2025

Evaluating the limitations of Bayesian metabolic control analysis

AbstractBayesian Metabolic Control Analysis (BMCA) has emerged as a promising framework for inferring metabolic control coefficients in data-limited scenarios by integrating Bayesian inference with linlog rate laws. However, its predictive accuracy and limitations remain underexplored. This study systematically evaluates BMCA’s ability to infer elasticity values, flux control coefficients (FCCs), and concentration control coefficients (CCCs) under varying data availability conditions using three synthetic metabolic network models. Our findings highlight the strengths and weaknesses of BMCA, guiding its application in metabolic engineering and emphasizing the need for methodological refinements.Author summaryUnderstanding how enzymes control metabolic pathways is crucial for optimizing biomanufacturing and synthetic biology applications. Bayesian Metabolic Control Analysis (BMCA) is a promising computational method that integrates Bayesian inference with metabolic control analysis to estimate key control parameters, even in cases with limited experimental data. However, the accuracy and limitations of BMCA remain unclear. In this study, we systematically evaluate BMCA using three synthetic metabolic networks to determine how different types of physiological data impact its predictive performance. We find that BMCA requires flux and enzyme concentration data for accurate predictions, while external metabolite concentrations contribute little. Additionally, BMCA fails to predict elasticity values beyond a magnitude of 1.5 and reliably infer allosteric regulation, even when strong regulatory interactions exist. In addition, BMCA does not accurately rank metabolic control points, which may limit its utility in identifying key enzymes in engineered pathways. Our work provides practical insights into when and how BMCA can be applied, guiding future research in metabolic modeling and control analysis.

Shin, Janis (ORCID:0000000216572455)↗
DOE OSTI2023

Comparative Study of High-Resolution LysB29(Nε-myristoyl) des(B30) Insulin Structures Display Novel Dynamic Causal Interrelations in Monomeric-Dimeric Motions

The treatment of insulin-dependent diabetes mellitus is characterized by artificial supplementation of pancreatic β-cell ability to regulate sugar levels in the blood. Even though various insulin analogs are crucial for reasonable glycemic control, understanding the dynamic mechanism of the insulin analogs may help to improve the best-protracted insulin analog to assist people with type 1 diabetes (T1D) to live comfortably while maintaining tight glycemic control. Here, we present the high-resolution crystal structure of NN304, known as insulin detemir, to 1.7 Å resolution at cryogenic temperature. We computationally further investigated our crystal structure’s monomeric-dimeric conformation and dynamic profile by comparing it with a previously available detemir structure (PDB ID: 1XDA). Our structure (PDB ID: 8HGZ), obtained at elevated pH, provides electrostatically triggered minor movements in the equilibrium between alternate conformational substates compared to the previous structure, suggesting it might induce an intermediate state in the dissociation pathway of the insulin detemir’s hexamer:dihexamer equilibrium. Supplemented with orientational cross-correlation analysis by a Gaussian network model (GNM), this alternate oligomeric conformation offers the distinct cooperative motions originated by loose coupling of distant conformational substates of a protracted insulin analog that has not been previously observed.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Live cell imaging of cellular dynamics in poplar wood using computational cannula microscopy

This study presents significant advancements in computational cannula microscopy for live imaging of cellular dynamics in poplar wood tissues. Leveraging machine-learning models such as pix2pix for image reconstruction, we achieved high-resolution imaging with a field of view of 55µm using a 50µm-core diameter probe. Our method allows for real-time image reconstruction at 0.29 s per frame with a mean absolute error of 0.07. We successfully captured cellular-level dynamics in vivo , demonstrating morphological changes at resolutions as small as 3µm. We implemented two types of probabilistic neural network models to quantify confidence levels in the reconstructed images. This approach facilitates context-aware, human-in-the-loop analysis, which is crucial for in vivo imaging where ground-truth data is unavailable. Using this approach we demonstrated deep in vivo computational imaging of living plant tissue with high confidence (disagreement score ⪅0.2). This work addresses the challenges of imaging live plant tissues, offering a practical and minimally invasive tool for plant biologists.

Ingold, Alexander (ORCID:0009000752380016)↗
DOE OSTI2023

DDStore: Distributed Data Store for Scalable Training of Graph Neural Networks on Large Atomistic Modeling Datasets

Graph neural networks (GNNs) are a class of Deep Learning models used in designing atomistic materials for effective screening of large chemical spaces. To ensure robust prediction, GNN models must be trained on large volumes of atomistic data on leadership class supercomputers. Even with the advent of modern architectures that consist of multiple storage layers that include node-local NVMe devices in addition to device memory for caching large datasets, extreme-scale model training faces I/O challenges at scale.We present DDStore, an in-memory distributed data store designed for GNN training on large-scale graph data. DDStore provides a hierarchical, distributed, data caching technique that combines data chunking, replication, low-latency random access, and high throughput communication. DDStore achieves near-linear scaling for training a GNN model using up to 1000 GPUs on the Summit and Perlmutter supercomputers, and reaches up to a 6.15x reduction in GNN training time compared to state-of-the-art methodologies.

Choi, Jong Youl↗