Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “transfer learning.”

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 919 records · Page 51
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Allosterically coupled conformational dynamics in solution prepare the sterol transfer protein StarD4 to release its cargo upon interaction with target membranes

Complex mechanisms regulate the cellular distribution of cholesterol, a critical component of eukaryote membranes involved in regulation of membrane protein functions directly and through the physiochemical properties of membranes. StarD4, a member of the steroidogenic acute regulator-related lipid-transfer (StART) domain (StARD)-containing protein family, is a highly efficient sterol-specific transfer protein involved in cholesterol homeostasis. Its mechanism of cargo loading and release remains unknown despite recent insights into the key role of phosphatidylinositol phosphates in modulating its interactions with target membranes. We have used large-scale atomistic Molecular dynamics (MD) simulations to study how the dynamics of cholesterol bound to the StarD4 protein can affect interaction with target membranes, and cargo delivery. We identify the two major cholesterol (CHL) binding modes in the hydrophobic pocket of StarD4, one near S136&S147 (the Ser-mode), and another closer to the putative release gate located near W171, R92&Y117 (the Trp-mode). We show that conformational changes of StarD4 associated directly with the transition between these binding modes facilitate the opening of the gate. To understand the dynamics of this connection we apply a machine-learning algorithm for the detection of rare events in MD trajectories (RED), which reveals the structural motifs involved in the opening of a front gate and a back corridor in the StarD4 structure occurring together with the spontaneous transition of CHL from the Ser-mode of binding to the Trp-mode. Further analysis of MD trajectory data with the information-theory based NbIT method reveals the allosteric network connecting the CHL binding site to the functionally important structural components of the gate and corridor. Mutations of residues in the allosteric network are shown to affect the performance of the allosteric connection. These findings outline an allosteric mechanism which prepares the CHL-bound StarD4 to release and deliver the cargo when it is bound to the target membrane.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Discovering Blind Geothermal Systems in the Great Basin Region: An Integrated Geologic and Geophysical Approach for Establishing Geothermal Play Fairways: All Phases

Most geothermal resources in the Great Basin region of the western USA are blind, and thus the discovery of new commercial-grade systems requires synthesis of favorable characteristics for geothermal activity. The geothermal play fairway concept involves integration of multiple parameters indicative of geothermal activity to identify promising areas for new development. This project integrated multiple datasets to apply the play fairway concept and assess geothermal potential in a large region of the Great Basin in Nevada. It is therefore referred to as the Nevada play fairway project. This project was a strong collaborative effort between several organizations, led by the Nevada Bureau of Mines and Geology at the University of Nevada, Reno, but with key support from the U.S. Geological Survey, ATLAS Geosciences, Inc,, Hi-Q Geophysical, Inc., Lawrence Berkeley National Laboratory, Utah Geological Survey, and Innovative Geothermal Ltd. In Budget Period 1 of this project, available data for nine geologic, geochemical, and geophysical parameters were initially synthesized to produce a new detailed geothermal potential map of 96,000 km2 from west-central to eastern Nevada. These parameters were grouped into subsets and individually weighted to delineate rankings for local permeability, intermediate permeability, regional permeability, and thermal potential, which collectively defined geothermal play fairways (i.e., most likely locations for significant geothermal fluid flow). This initial work was aimed at reducing the risks in regional exploration and therefore facilitating discovery of new commercial-grade systems in blind settings, as well as in areas with surface expressions of geothermal activity. Budget Period 2 of the project involved detailed analysis of some of the most promising areas identified in Phase 1. Twenty-four highly prospective areas, including both known undeveloped systems and previously undiscovered potential blind systems, were identified for further analysis. After reconnaissance of these areas, five of the most promising sites were selected for detailed studies. Multiple techniques were employed in the detailed studies, including geologic mapping, shallow temperature surveys, gravity surveys, Lidar, geochemical studies, seismic reflection analysis, and 3D modeling. The goal of the detailed studies was to identify specific areas with the highest likelihood for high permeability and thermal fluids, such that drill sites could be targeted. Three main sets of predictive maps were generated for each detailed study area: 1) play fairway maps, 2) play fairway error maps, and 3) direct evidence maps. Local- and intermediate-scale permeability models were revised to reflect results of the detailed geologic, geophysical, and geochemical analyses. Budget Period 3 of the project involved more detailed geophysical analyses and temperature-gradient (TG) drilling in southeastern Gabbs Valley and northern Granite Springs Valley, deemed the two most promising sites, with the goal of providing preliminary validation of the play fairway methodology. In southeastern Gabbs Valley, the collocation of a favorable structural setting (displacement transfer zone and fault intersections), Quaternary faults, intersecting and terminating gravity gradients, magnetic low, shallow (2 m) temperature anomaly, low resistivity anomaly, and promising geothermometry from nearby water wells provided evidence for a blind system. Drilling of six TG holes defines an apparent geothermal system at this locality with temperatures as high as 124°C at 152 m. This system is blind, with no surface hot springs, fumaroles, or paleo-geothermal deposits. For northern Granite Springs Valley, a favorable structural setting (termination of a major Quaternary normal fault), terminating gravity gradient, magnetic gradient, newly discovered sinter deposits, nearby warm water wells, previously drilled TG holes in the vicinity, and promising geothermometry suggest a hidden system. Drilling of six new TG holes yields temperatures of ~96°C at ~250 m, suggesting the presence of a geothermal system. Major lessons learned in the course of this project include: 1) initially identified sites commonly include multiple favorable structural settings at a finer scale; 2) promising sites in Cenozoic basins cannot be recognized without detailed geophysical surveys; and 3) play fairway analysis should be refined as the exploration program vectors into the most promising sites and finer-scale data are acquired. In addition to producing copious amounts of data, this project resulted in 16 published papers, 10 abstracts, more than 40 presentations across the U.S. and abroad (including several keynote addresses), 2 Masters theses, and 7 media reports.

15 GEOTHERMAL ENERGY↗
DOE OSTI2022

Correlating Time-Resolved Pressure Measurements With Rim Sealing Effectiveness for Real-Time Turbine Health Monitoring

Purge flow is bled from the upstream compressor and supplied to the under-platform region to prevent hot main gas path ingress that damages vulnerable under-platform hardware components. A majority of turbine rim seal research has sought to identify methods of improving sealing technologies and understanding the physical mechanisms that drive ingress. While these studies directly support the design and analysis of advanced rim seal geometries and purge flow systems, the studies are limited in their applicability to real-time monitoring required for condition-based operation and maintenance. As operational hours increase for in-service engines, this lack of rim seal performance feedback results in progressive degradation of sealing effectiveness, thereby leading to reduced hardware life. To address this need for rim seal performance monitoring, this study utilizes measurements from a one-stage turbine research facility operating with true-scale engine hardware at engine-relevant conditions. Time-resolved pressure measurements collected from the rim seal region are regressed with sealing effectiveness through the use of common machine learning techniques to provide real-time feedback of sealing effectiveness. Two modeling approaches are presented that use a single sensor to predict sealing effectiveness accurately over a range of two turbine operating conditions. Here, the results show that an initial purely data-driven model can be further improved using domain knowledge of relevant turbine operations, which yields sealing effectiveness predictions within 3% of measured values.

42 ENGINEERING↗
DOE OSTI2022

Bridging Python to Silicon: The SODA Toolchain

Systems performing scientific computing, data analysis, and machine learning tasks have a growing demand for application-specific accelerators that can provide high computational performance while meeting strict size and power requirements. However, the algorithms and applications that need to be accelerated are evolving at a rate that is incompatible with manual design processes based on hardware description languages. Agile hardware design tools based on compiler techniques can help by quickly producing an application-specific integrated circuit (ASIC) accelerator starting from a high-level algorithmic description. Here, we present the software-defined accelerator (SODA) synthesizer, a modular and open-source hardware compiler that provides automated end-to-end synthesis from high-level software frameworks to ASIC implementation, relying on multilevel representations to progressively lower and optimize the input code. Our approach does not require the application developer to write any register-transfer level code, and it is able to reach up to 364 giga floating point operations per second (GFLOPS)/W efficiency (32-bit precision) on typical convolutional neural network operators.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Learning to Trigger: Reinforcement Learning at the Large Hadron Collider

High-throughput scientific facilities such as the Large Hadron Collider depend on real-time event filtering (\textit{triggering}) under tight constraints on bandwidth, latency, and storage. In practice, trigger menus are largely static and hand-tuned and can become suboptimal as detector conditions, pileup, and background composition drift over time. We cast online threshold tuning as a sequential decision-making problem: a reinforcement learning agent ingests streaming summaries of recent rates and signal-sensitive features and updates trigger thresholds to maximize signal efficiency while tracking a target background rate within a tolerance band. We adapt Group-Filtered Policy Optimization (GFPO) to streaming control and introduce two variants (GFPO-F, GFPO-FR) that enforce background rate feasibility during training. On a benchmark that emulates realistic collider operation, we study two representative triggers: a total transverse energy ($H_{T}$) trigger sensitive to pileup variation, and an anomaly-detection (AD) trigger based on reconstruction loss for rare or non-standard signatures. On Monte Carlo streams, our agent increases the fraction of in-tolerance time intervals by 48% ($H_T$) and 28% (AD), with a cumulative gain of up to 2% in signal efficiency on those in-tolerance intervals. Transferring from simulation to \emph{real} collision data (CMS Run 283408), the same agent, without fine-tuning, achieves a 56% ($H_T$) and 28% (AD) in-tolerance improvement over baselines, with further signal-efficiency gain on both triggers. To our knowledge, this is the \emph{first} demonstration of RL-based trigger control on real Large Hadron Collider collision data. Code is available at https://github.com/Zixind/GFPO_LHC (see repo for details).

Ding, Zixin [Chicago U.]↗
DOE OSTI2026

Operational Evolution of FTS3: A DevOps Driven Approach to Elastic Operations

The File Transfer Service (FTS3) is a distributed data movement service developed at CERN and widely used to transfer data across the Worldwide LHC Computing Grid (WLCG). At Fermilab, FTS3 supports data transfers for multiple experiments, including Intensity Frontier experiments such as DUNE, enabling reliable data movement between WebDAV endpoints in Europe and the Americas.​ At CHEP 2021, we reported on the initial containerized deployment of FTS3 on OKD, the community Kubernetes distribution of Red Hat OpenShift. In this work, we present the subsequent evolution of this deployment, focusing on new operational capabilities introduced to improve scalability, robustness, and long-term maintainability.​ We describe the adoption of more secure and reproducible container build workflows, the integration of DevOps-driven operational practices, and enhancements in monitoring and automation. A key new result is the introduction of horizontal scaling and elastic resource management, allowing FTS3 components to dynamically adapt to workload variations while maintaining service reliability. We also discuss improvements in fault tolerance and operational procedures derived from production experience.​ Finally, we summarize lessons learned from operating FTS3 as a Kubernetes-native service and outline how these developments have improved the resilience and efficiency of data movement operations at Fermilab.

Munoz Flores, Victor Leopoldo [Fermilab]↗
DOE OSTI2024

Hiding-in-Plain-Sight (HiPS) Attack on CLIP for Targetted Object Removal from Images

Machine learning models are known to be vulnerable to adversarial attacks, but prior works have mostly focused on single-modalities. With the rise of large multi-modal models (LMMs) like CLIP, which combine vision and language capabilities, new vulnerabilities have emerged. However, these multimodal targeted attacks aim to completely change the model's output to what the adversary wants. In many realistic scenarios, an adversary might seek to make only subtle modifications to the output, so that the changes go unnoticed by downstream models or even by humans. We introduce Hiding-in-Plain-Sight (HiPS) attacks, a novel class of adversarial attacks that subtly modifies model predictions by selectively concealing target object(s), as if the target object was absent from the scene. We propose two HiPS attack variants, HiPS-cls and HiPS-cap, and demonstrate their effectiveness in transferring to downstream image captioning models, such as CLIP-Cap, for targeted object removal from image captions.

Daw, Arka [ORNL] (ORCID:0009000633191271)↗
DOE OSTI2025

Multimodal super-resolution: discovering hidden physics and its application to fusion plasmas

Understanding complex physical systems often requires integrating data from multiple diagnostics, each with limited resolution or coverage. We present a machine learning framework that reconstructs synthetic high-temporal-resolution data for a target diagnostic using information from other diagnostics, without direct target measurements during the inference. This multimodal super-resolution technique improves diagnostic robustness and enables monitoring even in case of measurement failures or degradation. Applied to fusion plasmas, our method targets edge-localized modes (ELMs), which can damage plasma-facing materials. By reconstructing super-resolution Thomson Scattering data from complementary diagnostics, we uncover fine-scale plasma dynamics and validate the role of resonant magnetic perturbations (RMPs) in ELM suppression through magnetic island formation. The approach provides new observation supporting the plasma profile flattening due to these islands. Our results demonstrate the framework’s ability to generate high-fidelity synthetic diagnostics, offering a powerful tool for ELM control development in future reactors like ITER. The approach is broadly transferable to other domains facing sparse, incomplete, or degraded diagnostic data, opening new avenues for discovery.

Jalalvand, Azarakhsh [Princeton Univ., NJ (United ↗
DOE OSTI2025

MS25: Materials Science-Focused Benchmark Data Set for Machine Learning Interatomic Potentials

Here, we present MS25, a benchmark data set for evaluating machine learning interatomic potentials (MLIPs) across diverse materials-relevant systems including MgO surfaces, liquid water, zeolites, a catalytic Pt surface reaction, high-entropy alloys (HEAs), and disordered Zr-oxides. Five MLIP architectures (MACE, NequIP, Allegro, MTP, and Torch-ANI) are trained and tested, focusing not only on traditional metrics (energies, forces, and stresses) but also explicitly validating derived physical observables such as lattice constants, volumes, and reaction barriers. We find that most models reach comparable accuracy on standard error metrics across the simple systems, although equivariant MLIPs offer 1.5–2× improvements over nonequivariant MLIPs in energy and force error for structurally complex or compositionally disordered environments such as HEAs and Zr–O systems. Our analysis highlights that low errors in energy and force predictions do not guarantee reliable observables, emphasizing the necessity of explicit validation. We demonstrate limitations in cross-framework transferability, as models trained on one zeolite framework (CHA) fail to reliably generalize to predictions of structurally distinct frameworks (e.g., MFI). Size-extensive tests show some dependence on system size for MgO, resulting from forced periodicity. The HEA and Zr–O data sets are identified as challenging tests for future benchmarks and MLIP model architecture developments as they show significant differentiation in error between MLIP architectures and are still relatively difficult at 1000 training images. Moving forward, we recommend that benchmarking efforts shift their focus from marginal accuracy improvements in energy and force errors toward identifying and understanding model failure modes, rigorously assessing transferability, and evaluating how their errors affect observable predictions. For researchers looking to choose an MLIP architecture, we suggest selecting equivariant MLIP architectures if the complexity of the system is a challenge. For simple materials problems, auxiliary features such as integration with molecular dynamics engines, trade-offs between computational data set generation cost vs MLIP inference speed, and framework integration may play a more important decision factor than small differences in error metrics that are unlikely to matter for production-level research.

chemical structure↗
DOE OSTI2026

Improving Building Footprint Extraction Using NAIP and 3DEP Lidar Derived Features with Deep Learning

Accurate building footprint extraction is critical for applications ranging from population estimation to disaster management. Although optical imagery provides detailed spectral information, it often struggles with shadows, occlusions, and background clutter in dense urban environments. Lidar data, by contrast, offer precise elevation and structural attributes but face challenges such as variable point density and noise. This study integrates multispectral imagery from the U.S. Department of Agriculture (USDA) National Agriculture Imagery Program (NAIP) with lidar-derived feature height and intensity from the U.S. Geological Survey (USGS) 3D Elevation Program (3DEP) to improve footprint extraction using a U-Net–based deep learning model. A six-band input stack (RGB, near-infrared, height, intensity) was developed, normalized, and tiled for training and evaluation against Microsoft Global Building Footprints (GBF). Results from the Houston, TX test site show that the six-band model achieved a precision of 0.86, recall of 0.88, F1 score of 0.87, and Intersection-over-Union (IoU) of 0.76, consistently outperforming four-band baselines by reducing false positives while maintaining sensitivity. Predictions on withheld Houston tiles confirmed strong within-region generalization, yielded a precision of 0.78, recall of 0.81, F1 score of 0.79, and IoU of 0.66. Qualitative analysis further revealed limitations stemming from both training label quality and vegetation–building confusion. These findings demonstrate the complementary value of integrating spectral and structural information for robust building footprint extraction and how domain adaptation strategies can be used to enhance cross-regional transferability.

Liu, Jung Kuan [United States Geological Survey (U↗
DOE OSTI2020

OpenCGRA: An Open-Source Unified Framework for Modeling,Testing, and Evaluating CGRAs

Coarse-grained reconfigurable arrays (CGRAs),loosely defined as arrays of functional units (e.g, adder, sub-tractor, multiplier, divider, or larger multi-operation units, butsmaller than a general-purpose core) interconnected through aNetwork-on-Chip, provide higher flexibility than domain-specificASIC accelerators while offering increased hardware efficiencywith respect to fine-grained reconfigurable devices, such as FieldProgrammable Gate Arrays (FPGAs). The fast evolving fieldsof machine learning and edge computing, which are seeing acontinuous flow of novel algorithms and larger models, makeCGRAs ideal target architectures to allow domain specializationwithout loosing too much generality. They also generally offerquicker and more effective reconfigurability than FPGAs, po-tentially allowing adaptation during actual algorithm execution,and implement a dataflow programming paradigm that adaptswell to these emerging workloads. Designing and generating aCGRA, however, still requires to define the type and number ofthe specific functional units, implement their interconnect andthe network topology, and perform its simulation and validation,given a variety of workloads of interest.In this paper, we propose OpenCGRA, a Python-based unifiedframework that integrates generation, modeling, testing and eval-uation for CGRAs. OpenCGRA is the first open-source integratedframework able to support the full top-to-bottom design flow forspecializing and implementing CGRAs: modeling at different ab-straction levels (functional level, cycle level, register-transfer level),generation, simulation, testing at different granularities (unit test-ing, integration testing, property-based testing), and characteriza-tion (area, power, and timing). OpenCGRAs will be made availableon GitHub.

CGRA, synthesis↗
DOE OSTI2025

Electron Bifurcating Hydrogenases

The importance of electron-bifurcating enzymes is manifest by their ability to maximize energy efficiency. Specifically, they couple a downhill oxidation-reduction (redox) reaction with an uphill redox reaction. Since the rapid increase in the discovery of bifurcating enzymes starting in 2008, there has been interest in incorporating their mechanistic principles into artificial/semiartificial systems to drive chemically challenging reactions. This has yet to be achieved, partly because the details of electron bifurcation, i.e. mechanisms, are largely elusive. Nevertheless, much progress has been made in understanding reactivities, structures, and some mechanistic aspects of these enzymes. Notable examples are electron-bifurcating hydrogenases, which are the focus of this chapter. The chapter is organized as follows. Section 11.1 provides an overview of hydrogenases and electron bifurcation. In Section 11.2, some physiological roles of electron-bifurcating hydrogenases are highlighted. Additionally, electron-bifurcating subunit compositions and biochemical reactivities are comprehensively tabulated, and some key points/considerations about these are noted. In Section 11.3, we discuss the known structures of these enzymes, which provide insight into their complex arrangements of redox cofactors, such as iron-sulfur clusters. Also provided are tabulations and discussions of some biophysical properties of the cofactors. In Section 11.4, we discuss the mechanistic proposals of these enzymes, which are primarily based on structural information. Areas of research that are much needed are outlined in Section 11.5. We conclude on the note that what is learned from electron-bifurcating hydrogenases has applicability to other bifurcating enzymes, nonbifurcating analogs, and mechanistic enzymology at large.

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

Deep learning-enabled probing of irradiation-induced defects in time-series micrographs

Modeling time-series data with convolutional neural networks (CNNs) requires building a model to learn in batches as opposed to training sequentially. Coupling CNNs with in situ or operando techniques opens the possibility of accurately segmenting dynamic reactions and mass transport phenomena to understand how materials behave under the conditions in which they are used. In this article, in situ ion irradiation transmission electron microscopy (TEM) images are used as inputs into the CNN to assess the defect generation rate, defect cluster density, and saturation of defects. We then use the output segmentation maps to correlate with conventional TEM micrographs to assess the model’s ability to detail nanoscale interactions. Next, we discuss the implications of preprocessing and hyperparameters on model variability, accuracy when expanded to other datasets, and the role of regularization when controlling model variance. Ultimately, we eliminate human bias when extrapolating physical metrics, speed up analysis time, decouple reactions that happen at 100 ms intervals, and deploy models that are both accurate and transferable to similar experiments.

Burns, Kory (ORCID:0000000158019909)↗
DOE OSTI2022

Enabling Sustainable Landscape Design for Continual Improvement of Operating Bioenergy Supply Systems

This unique and highly effective project catalyzed collaboration among government, university, and private sector partners through a multi-state research and technology transfer project designed to support continuous improvement of bioenergy feedstock supply systems. Conceived and built upon the foundation created by prior DOE investments in the Billion Ton Study, Sun Grant Regional Project, and many other feedstock production, harvest, storage and transportation studies, this project addressed seven tasks with more than 29 subtasks. All goals were met with key accomplishments being: (1) on-farm establishment of potential perennial plant mixtures that could not only become sustainable feedstock sources but also enhance soil health, (2) a reduction in potential wind and water erosion by improving corn stover harvest techniques and incorporating cover crops into current row-crop production systems, (3) reduced potential for surface and groundwater contamination while also increasing potential biodiversity and sustainability of Midwestern USA landscapes, and (4) development of site-specific land management, data visualization, and sustainability assessment tools. Twenty-two Case Studies highlighting accomplishments and lessons learned through this public-private partnership investment are incorporated into this final report. On-farm and replicated field plot studies were used to provide the real-world data needed to verify baseline assumptions for extensive feedstock logistic modeling and greenhouse gas (GHG) assessments needed to develop sustainable bioenergy and bio-product industries at national and international scales.

09 BIOMASS FUELS↗
DOE OSTI2023

Characterizing Structure-Dependent TiS 2 /Water Interfaces Using Deep-Neural-Network-Assisted Molecular Dynamics

As a promising layered electrode material, TiS 2 -based capacitive deionization (CDI) devices for water desalination have attracted significant attention. However, TiS 2 /H 2 O interfacial features, potentially important for device optimization, remain unidentified. Using Deep Potential Molecular Dynamics (DPMD), we characterized distinct aqueous interfaces introduced by four TiS 2 terminations expected to be present as water intercalates into TiS 2 , namely, Armchair, Zigzag, Zigzag-L, and Zigzag-R. First, we assessed important representative physical properties of the system to validate the deep potentials (DPs). DPMD simulations agree well with experiments and first-principles simulations, suggesting the DPs are accurate and reliable. Subsequent simulations of these TiS 2 /water interfaces revealed how TiS 2 surface termination influences the structure of interfacial water. This effect is most evident in the first and second water layers close to the TiS 2 surface, and more pronounced when spontaneous dissociative adsorption of water occurs. The extent of water dissociation on each surface was evaluated using enhanced sampling. Zigzag-L is the only interface where proton transfer from adsorbed water to TiS 2 surface S atoms is thermodynamically and kinetically favored. The coexistence of surface four-fold-coordinated Ti (Ti 4c ) and one-fold-coordinated S (S 1c ) is found to be essential to making proton transfer feasible on the Zigzag-L surface. Furthermore, remaining unprotonated S 1c atoms can act as good proton acceptors after water dissociation. Thus, TiS 2 with Zigzag-L termination may be a surface to avoid in CDI device construction, given that pH fluctuations adversely affect performance. Furthermore, this work provides new understanding of TiS 2 /H 2 O interfacial features that could aid future design and optimization of TiS 2 -based CDI devices for water desalination.

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

A computational pipeline to generate a synthetic dataset of metal ion sorption to oxides for AI/ML exploration

The charged mineral/electrolyte interfaces are ubiquitous in the surface and subsurface–including the surroundings of the geological disposal sites for radioactive waste. Therefore, understanding how ions interact with charged surfaces is critically important for predicting radionuclide mobility in the case of waste leakage. At present, the Surface Complexation Models (SCMs) are the most successful thermodynamic frameworks to describe ion retention by mineral surfaces. SCMs are interfacial speciation models that account for the effect of the electric field generated by charged surfaces on sorption equilibria. These models have been successfully used to analyze and interpret a broad range of experimental observations including potentiometric and electrokinetic titrations or spectroscopy. Unfortunately, many of the current procedures to solve and fit SCM to experimental data are not optimal, which leads to a non-transferable or non-unique description of interfacial electrostatics and consequently of the strength and extent of ion retention by mineral surfaces. Recent developments in Artificial Intelligence (AI) offer a new avenue to replace SCM solvers and fitting algorithms with trained AI surrogates. Unfortunately, there is a lack of a standardized dataset covering a wide range of SCM parameter values available for AI exploration and training–a gap filled by this study. Here, we described the computational pipeline to generate synthetic SCM data and discussed approaches to transform this dataset into AI-learnable input. First, we used this pipeline to generate a synthetic dataset of electrostatic properties for a broad range of the prototypical oxide/electrolyte interfaces. The next step is to extend this dataset to include complex radionuclide sorption and complexation, and finally, to provide trained AI architectures able to infer SCMs parameter values rapidly from experimental data. Here, we illustrated the AI-surrogate development using the ensemble learning algorithms, such as Random Forest and Gradient Boosting. These surrogate models allow a rapid prediction of the SCM model parameters, do not rely on an initial guess, and guarantee convergence in all cases.

Li, Chunhui↗
DOE OSTI2020

Implementing Mixed Reality Tools to Support Mission Delivery at Hanford - 20520

Mission Support Alliance's (MSA) Public Works and Information Systems organizations have been working with Microsoft Corporation to develop and implement mixed reality operational solutions using their HoloLens technology. This collaborative effort is intended to drive innovative solutions and significantly improve MSA's efficiency in performing work at the Hanford Site. HoloLens, a mixed reality tool, is a commercial off-the-shelf technology that combines a head-mounted viewing screen with applications to help people and organizations learn, communicate, and collaborate more effectively through the use of mixed reality. https://microsoft.com/en-us/hololens MSA's initial pilot successfully demonstrated its ability to use mixed reality utilizing HoloLens' advanced features in a variety of ways, illustrating the potential efficiency gains previously stated as goals of this pilot. These achievements include the development of proprietary technology that allows synchronization between a HoloLens device and a mobile device or alternate global positioning system (GPS) device. This synchronization enables the HoloLens device to access real time GPS location data anywhere on the Hanford Site. This real time location data, combined with MSA's improved Hanford Geographical Information System (GIS) data, enables the mixed reality pilot application to identify underground utility systems as well as related utility attributes. This ability will aid utility workers in several areas, including excavation activities, the placement of large cranes, identifying interactions and conflicts with future underground utility placements and, eventually, recognizing and de-conflicting tank waste transfer system valve alignments. The HoloLens mixed reality application is also able to provide full or small scale holographic images of a facility's digital twin. This feature will allow MSA's Water and Sewer Utilities team to train and validate procedures associated with the new water treatment facility virtually, before it is constructed. This reduces the amount of time it takes to complete the training and procedure validation, and accelerates the overall construction schedule. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2025

CAFE AU LAIT: Compute-Aware Federated Augmented Low-Rank AI Training

Federated finetuning is crucial for unlocking the knowledge embedded in pretrained Large Language Models (LLMs) when data are geographically distributed across clients. Unlike finetuning with data from a single institution, federated finetuning allows collaboration across multiple institutions, enabling the utilization of diverse and decentralized datasets while preserving data privacy. Given the high computing costs of LLM training and the emphasis on energy efficiency in Federated Learning (FL), Low-Rank Adaptation (LoRA) has emerged as a widely adopted algorithm due to its significantly reduced number of trainable parameters. However, this assumes that all data silos have the necessary computing resources to compute local updates of LLMs. Nevertheless, in practice, the computing resources across clients are highly heterogeneous: while some may have access to hundreds of GPUs, others might have limited or no GPU access. Recently, federated finetuning using synthetic data has been proposed, allowing clients to participate in a collaborative training run without training LLMs locally. However, our experimental results reveal a performance gap between models trained using synthetic data and those trained using local updates. Motivated by the observed heterogeneity in computing resources and the performance gap, we propose a novel two-stage algorithm that leverages the storage and computing capabilities of a strong server. In the first stage, under the coordination of the strong server, clients with limited computing resources collaborate to generate synthetic data, which is transferred to and stored on the strong server. In the second stage, the strong server uses this synthetic data on behalf of the resource-constrained clients to perform federated LoRA finetuning alongside clients with sufficient computing resources. This approach ensures that all clients can participate in the finetuning process. Experimental results demonstrate that incorporating local updates from even a small fraction of clients improves performance compared to using synthetic data for all clients. Furthermore, we incorporate the Gaussian mechanism in both stages to guarantee client-level differential privacy.

Wang, Jiayi [ORNL]↗