Search NASA⌕ Search

SEARCH · Search NASA

Results for “ML Surrogate”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Surrogate modeling of Monte Carlo radiation transport with convolutional neural networks for shielding optimization

Here, we present a machine learning (ML)-based surrogate model using convolutional neural networks (CNN) designed to emulate the attenuation of neutron fields as they pass through various shielding materials. This model can compute the outgoing neutron flux almost instantaneously and achieves reasonable accuracy compared to traditional Monte Carlo (MC)-based codes, which are computationally intensive. This emulator alleviates the complexity of neutron radiation transport through shielding materials by reducing the dimensionality and enables shielding optimization for a known radiation environment. This optimization process, which would have taken an unrealistic timeline due to several complex radiation transport simulations, can now be achieved in minutes, thus increasing computational capabilities in radiation shielding assessment. We demonstrate the applications of this emulator in computing effective dose rates and optimizing shielding solutions for a heavy-ion accelerator facility, such as the Facility for Rare Isotope Beams, where secondary neutrons produced via beam interactions dominate the radiation environment.

accelerator shielding↗
DOE OSTI2021

Adaptive Machine Learning for Robust Diagnostics and Control of Time-Varying Particle Accelerator Components and Beams

Machine learning (ML) is growing in popularity for various particle accelerator applications including anomaly detection such as faulty beam position monitor or RF fault identification, for non-invasive diagnostics, and for creating surrogate models. ML methods such as neural networks (NN) are useful because they can learn input-output relationships in large complex systems based on large data sets. Once they are trained, methods such as NNs give instant predictions of complex phenomenon, which makes their use as surrogate models especially appealing for speeding up large parameter space searches which otherwise require computationally expensive simulations. However, quickly time varying systems are challenging for ML-based approaches because the actual system dynamics quickly drifts away from the description provided by any fixed data set, degrading the predictive power of any ML method, and limits their applicability for real time feedback control of quickly time-varying accelerator components and beams. In contrast to ML methods, adaptive model-independent feedback algorithms are by design robust to un-modeled changes and disturbances in dynamic systems, but are usually local in nature and susceptible to local extrema. In this work, we propose that the combination of adaptive feedback and machine learning, adaptive machine learning (AML), is a way to combine the global feature learning power of ML methods such as deep neural networks with the robustness of model-independent control. We present an overview of several ML and adaptive control methods, their strengths and limitations, and an overview of AML approaches.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

EXERGETIC: De-Risking Next-Generation Resilient Geothermal Hybrids via At-Scale Evaluation Using Virtual Emulation Digital Twin Environment for Efficient Operation

The DOE-GTO-funded project, award number 5.1.2.12, entitled "EXERGETIC - De-risking Next Generation Resilient Geothermal Hybrids via at-Scale Evaluation Using a Virtual Emulation Digital Twin Environment for Efficient Operation," advances the solution to these challenges by developing and validating a geothermal co-emulation environment implemented at the National Laboratory of the Rockies (NLR)'s Advanced Research on Integrated Energy Systems (ARIES) platform. This framework enables the de-risking of next-generation geothermal and geothermal hybrid systems through high-fidelity modeling, real-time digital emulation, advanced control strategies, and techno-economic assessment. The project focused on geothermal hybrid configurations that integrate geothermal power plants with concentrated solar power and underground thermal energy storage, enabling enhanced efficiency, flexibility, and grid support capabilities. The main goal of this project was the development of a geothermal digital co-emulation environment to demonstrate the technical and economic value of geothermal hybrid systems and their contribution to grid stability and flexibility. The EXERGETIC framework combined physics-based models, controls, and real assets at ARIES, including digital real-time simulators (DRTS), a 20-MW-scale controllable grid interface (CGI), and a 2-MW conventional generator. Detailed transient models were developed for the key subsystems of a hybrid geothermal plant, including parabolic trough solar collectors, reservoir thermal energy storage (RTES), and a binary Organic Rankine Cycle (ORC) power plant. The ORC model explicitly captured thermal inertia and off-design operation and integrated control strategies to dynamically respond to electric load profiles. The models were validated against published experimental and numerical studies, demonstrating strong agreement and confirming the accuracy and robustness of the modeling approach. The resulting digital twin represents geothermal-solar-storage systems at multiple scales (1 MW to 100 MW) and enables realistic emulation of grid-connected operation. The control architecture allows the geothermal resource to provide stable baseload generation, while solar and stored thermal energy supply flexible, dispatchable support during periods of high demand or variable grid conditions. A key contribution of the EXERGETIC project is the demonstration that geothermal hybrid systems can be designed to be active grid assets rather than passive baseload generators. Using the ARIES platform, the digital twin was evaluated under multiple grid scenarios, including load following, voltage support at the distribution level, and frequency response at the transmission level. Results show that hybrid geothermal systems can respond effectively to dynamic grid conditions, providing inertia-like behavior, primary frequency support, and voltage regulation through coordinated control. In addition to the performance and grid services capability analysis of geothermal and hybrid geothermal systems, the EXERGETIC project also focused on scalability and techno-economic analysis of geothermal hybrid plants. In particular, for the scalability analysis, machine-learning (ML)-based surrogate models were trained using data generated from the geothermal digital twin under different grid-connected scenarios and plant capacities. These ML models demonstrated strong interpolation and extrapolation capabilities across plant sizes, accurately reproducing both steady-state and transient responses with very low errors. Regarding the techno-economic analysis, plant performance results were integrated with cost models for hybrid geothermal systems, and the levelized cost of electricity (LCOE) was used as the main economic metric to evaluate system performance across a range of system capacities, solar shares, solar multiples, and storage durations. Results indicate that economies of scale significantly reduce geothermal LCOE as plant capacity increases, with large-scale systems (25-100 MW) achieving substantially lower costs than small plants. Hybridization with solar thermal energy and storage further improves economic performance by increasing capacity utilization and enabling flexible dispatch. In addition, thermal storage plays a critical role in reducing LCOE by maximizing geothermal, solar, and stored energy resources. In summary, the results from this project demonstrate that geothermal hybrid systems represent a promising alternative for increasing the energy conversion efficiency of geothermal technologies, contributing to the preservation of geothermal resources, and supporting the transition of geothermal plants from traditional baseload resources into flexible, resilient, and cost-competitive energy conversion technologies.

15 GEOTHERMAL ENERGY↗
DOE OSTI2025

Accelerating computational fluid dynamics simulation of post-combustion carbon capture modeling with MeshGraphNets

Packed columns are commonly used in post-combustion processes to capture CO 2 emissions by providing enhanced contact area between a CO 2 -laden gas and CO 2 -absorbing solvent. To study and optimize solvent-based post-combustion carbon capture systems (CCSs), computational fluid dynamics (CFD) can be used to model the liquid–gas countercurrent flow hydrodynamics in these columns and derive key determinants of CO 2 -capture efficiency. However, the large design space of these systems hinders the application of CFD for design optimization due to its high computational cost. In contrast, data-driven modeling approaches can produce fast surrogates to study large-scale physics problems. We build our surrogates using MeshGraphNets (MGN), a graph neural network framework that efficiently learns and produces mesh-based simulations. We apply MGN to a random packed column modeled with over 160K graph nodes and a design space consisting of three key input parameters: solvent surface tension, inlet velocity, and contact angle. Our models can adapt to a wide range of these parameters and accurately predict the complex interactions within the system at rates over 1700 times faster than CFD, affirming its practicality in downstream design optimization tasks. This underscores the robustness and versatility of MGN in modeling complex fluid dynamics for large-scale CCS analyses.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Coupling High-Throughput Experiments and Regression Algorithms to Optimize PGM-Free ORR Electrocatalyst Synthesis

Over the past decades, significant improvement has been achieved in the performance of platinum group metal-free (PGM-free) materials as an alternative to Pt-based electrocatalysts for oxygen reduction reaction (ORR). However, further progress in ORR activity requires evaluation of precursors and synthesis approaches. In response to this challenge, we generated a first of its kind experimental data set of 36 samples using high-throughput synthesis and activity measurements. Several control parameters (e.g., Fe precursor identity, the precursor content, and pyrolysis temperature) were varied. We then developed several state-of-the-art machine learning (ML) based regression models to predict ORR activity, dependent on selected synthesis variables. Through an iterative algorithm, higher prediction accuracy (smaller root-mean-square error) was achieved. We identified that gradient boosting regression (GBR) and support vector regression (SVR), among several methods, work best for this data set. Aided by our ML-based surrogate models, we decided to alter catalyst synthesis conditions, which resulted in a 36% increase in measured ORR activity in comparison to the maximum ORR mass activity value of 21.9 A/g catalyst in the original data set. Overall, this combined experiment and machine learning approach represents a promising path forward toward developing highly efficient next-generation ORR electrocatalysts and, more generally, functional materials.

25 ENERGY STORAGE↗
DOE OSTI2021

An adaptive approach to machine learning for compact particle accelerators

Abstract Machine learning (ML) tools are able to learn relationships between the inputs and outputs of large complex systems directly from data. However, for time-varying systems, the predictive capabilities of ML tools degrade if the systems are no longer accurately represented by the data with which the ML models were trained. For complex systems, re-training is only possible if the changes are slow relative to the rate at which large numbers of new input-output training data can be non-invasively recorded. In this work, we present an approach to deep learning for time-varying systems that does not require re-training, but uses instead an adaptive feedback in the architecture of deep convolutional neural networks (CNN). The feedback is based only on available system output measurements and is applied in the encoded low-dimensional dense layers of the encoder-decoder CNNs. First, we develop an inverse model of a complex accelerator system to map output beam measurements to input beam distributions, while both the accelerator components and the unknown input beam distribution vary rapidly with time. We then demonstrate our method on experimental measurements of the input and output beam distributions of the HiRES ultra-fast electron diffraction (UED) beam line at Lawrence Berkeley National Laboratory, and showcase its ability for automatic tracking of the time varying photocathode quantum efficiency map. Our method can be successfully used to aid both physics and ML-based surrogate online models to provide non-invasive beam diagnostics.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Machine Learning for Mapping Multipactor Susceptibility in RF Systems: Capabilities and Generalization Constraints

Multipactor is a surface-driven electron avalanche phenomenon that degrades the performance and reliability of radio-frequency (RF) systems in particle accelerator and vacuum electronics applications. Multipactor behavior in a given device structure is conventionally assessed through susceptibility charts, which provide a parameter-space characterization of the instability. In this work, we assess the capabilities of machine-learning (ML) models to learn and predict such susceptibility charts and analyze the constraints governing their generalization across materials. Using a simulation-derived dataset spanning six distinct secondary-electron-yield material profiles in a canonical two-surface planar geometry, we train supervised regression models and artificial neural networks to predict the time-averaged electron growth rate, δavg, across the relevant parameter space. Model performance is evaluated using metrics that explicitly probe the structure of susceptibility charts, including Intersection over Union, Structural Similarity Index, and correlation analysis. Tree-based ensemble models outperform neural-network models in reconstructing susceptibility regions and in generalizing across material domains. Principal-component analysis reveals disjoint material feature distributions, indicating that the piecewise mode structure of multipactor susceptibility is difficult to represent with a single global model and that generalization is constrained by data coverage rather than by model complexity. An exhaustive reduced-coverage study further shows that sparse material-space coverage can yield mean performance in the same general range but producing large variability in the susceptibility-region overlap. These results clarify the capabilities of ML-based surrogate models for parameter-space characterization of multipactor discharge. They also provide guidance for their appropriate use in RF system design.

43 PARTICLE ACCELERATORS↗
DOE OSTI2022

Uncertainty Quantification for Dissimilar Material Joints Under Corrosion Environment

Abstract Self-Piercing Riveting (SPR) is one of the most commonly used methods for joining dissimilar materials in the automotive industry. These joints are popular due to their adaptability, high performance and short cycle time. However, since these joints involve two dissimilar materials, they are susceptible to galvanic corrosion in the presence of an electrolyte which is driven by the difference in the equilibrium potential of the metals. This can affect the safety and resilience of these joints. In this paper, we focus on galvanic corrosion in Al-Fe SPR joints. A Machine learning (ML) based surrogate model, which is based off of FE simulations, for statistical corrosion analysis is developed. This model enables the resilience and reliability analysis of SPR joints under corrosion environment. In this study, first a physics-based finite element (FE) corrosion model has been developed to simulate the galvanic corrosion between a Fe cathode and an Al anode of a SPR joint. This model takes into account the effect of the crystal microstructure of the Al anode and the precipitation of the corrosion product. Several geometric and environmental factors including crevice gap, roughness of anode, conductivity, pH and the temperature of the electrolyte that effect corrosion are investigated. A thorough Uncertainty Quantification (UQ) analysis is conducted for the overall corrosion behavior of the Fe-Al SPR joints using a novelistic Probabilistic Confidence-Based Adaptive Sampling (PCAS) technique. PCAS is used to train the surrogate model by identifying the critical sampling points and thus reducing the overall computational costs. It is found that the electrolyte temperature has the largest effects on the material loss and needs to be managed closely for better corrosion control. By understanding the corrosion performance and resultant uncertainty impact on SPR joints, the reliability and resilience of these joints can be improved.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Enhanced prediction of terrestrial feedbacks to the coastal carbon cycle:using machine learning to improve sub-grid biogeochemical processes

Focal Areas: The paper aims to improve predictability of the coastal carbon cycle through improved model representation and quantification of the terrestrial feedbacks to aquatic ecosystems. The paper covers two focus areas, 1. Improved predictive modeling of terrestrial and aquatic biogeochemistry through ML-enabled surrogate models, and 2. Employing machine learning to integrate multimodal data sets collected across terrestrial and aquatic ecosystems at high spatial and temporal resolution.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Multiscale and Machine Learning Modeling for Process-informed Microstructure Prediction in Additively Manufactured Materials Using MALAMUTE

Advanced Materials and Manufacturing Technologies (AMMT) program under the Department of Energy Office of Nuclear Energy, aims to develop and qualify additively-manufactured materials for nuclear applications. The key challenges to these efforts are the microstructural variabilities observed on the AM products and their impact on the properties and performance of the material in extreme environments. AMMT is using a combination of high-through-put experimental and modeling techniques to accelerate the qualification efforts. Conventionally, in-situ and ex-situ characterizations and testing are performed to correlate different aspects of the AM process to the final product and its performance. However, adopting a trial-and-error approach to experimentally evaluate the vast range of process parameters required to capture the microstructural variabilities is cost-prohibitive. Modeling and simulation provide a comparatively inexpensive way to understand and correlate the microstructural evolution to the processing conditions. The modeling and simulation work-packages within the AMMT program aims to use physics-based and machine learning modeling capabilities to develop a digital twin for AM that can correlate the process conditions to the final product and establish a process-structure-property-performance (PSPP) correlation for AM materials. The melting and subsequent solidification that occurs during the AM process is a complex phenomenon that requires multiscale multiphysics analysis. Idaho National Laboratory’s (INL) Multiphysics Object-Oriented Simulation Environment (MOOSE), specifically the MOOSE Application Library for Advanced Manufacturing UTilitiEs (MALAMUTE) software, provides an ideal platform for developing the multiphysics multiscale model to explore the intricacies of the microstructural evolution during the AM processes within a single framework. Furthermore, given that such full-fidelity simulations can be computationally intensive, reduced order models are necessary to explore the PSPP space for AM materials in an efficient, reliable, and cost-effective way. This work package focuses on understanding the role of process variabilities on the various microstructural characteristics of the AM materials. Microstructures unique to AM materials, such as compositional micro-heterogeneity and dislocation cells, are of particular interest here since they can influence the creep properties and radiation performance. In fiscal year (FY) 24, we significantly advanced upon our work in the last fiscal year, both on physics-based and ML models. The alloy solidification model available in MOOSE has been extended to incorporate the thermodynamic properties and free energy relevant to 316SS. The model demonstrates the Cr segregation that occurs during solidifcation. It is demonstrated that rate of solidification and solute segregation is primarily influence by the cooling rate dictating the level of freezing. This work captures the microstructural variabilities at the subgrain level that are often missing in the part-scale models. With an aim to connect the microstructural evolution model to realistic process conditions, a reduced order model is developed for predicting the thermal conditions around meltpool from high-fidelity process simulations. Furthermore, machine learning approach is used to accelerate the temperature prediction during the AM process. In the following years, MALAMUTE will be used to connect different aspects of the models and quantitatively predict the microstructural evolution. The developed ML-based surrogate model will consider the process conditions as the input to predict the microstructural features in a cost-effective way. The generated microstructures can be used by other work packages under AMMT to evaluate the properties and environmental response of the material at the mesoscale. Thus, this work help identify the key microstructural features at the subgrain level that are significant in property/performance prediction of the AM products. This work will provide inputs to the large-scale process variability models to reevaluate and validate assumptions/simplifications made in the part-scale models. Furthermore, through active learning this work will help identify the data need from both modeling and experimental sides for development of a robust digital twin for AM.

36 MATERIALS SCIENCE↗
DOE OSTI2025

White Paper: Research & Development for the Time at Temperature Approach

Recent advancements in nuclear power research are greatly improving reactor safety and performance through the development of Accident Tolerant Fuel (ATF) and Low-Enriched Uranium Plus (LEU+). These innovations can address Departure from Nucleate Boiling (DNB) margins, which are vital for reactor safety. DNB happens when the coolant switches to film boiling, significantly decreasing heat transfer and posing a risk of fuel cladding failure. The U.S. Nuclear Regulatory Commission (NRC) employs conservative DNB criteria, which can potentially restrict the operational flexibility and efficiency of reactors. The Time at Temperature (TaT) approach could provide a more detailed and adaptable operational guideline by establishing acceptable time-temperature limits, accounting for the duration a material can withstand elevated temperatures without losing its integrity. This method allows reactors to operate more efficiently and safely, offering additional operational margins, faster power adjustments, and improved fuel cycle economics. TaT criteria allow for higher power levels and more flexible responses to operational transients, particularly applicable for anticipated operational occurrences (AOOs) that result in short durations of post-DNB conditions. It enhances plant operational flexibility, allows faster startup times, and enables quicker power level adjustments, optimizing fuel loading patterns and improving fuel cycle economics. Implementing TaT limits reduces core design constraints, lowers fuel usage, and reduces costs, essential for the long-term sustainability of Light Water Reactors (LWRs). TaT maximizes the use of advanced fuel technologies like ATF and LEU+, further enhancing their economic and environmental benefits. To apply the TaT approach in existing LWRs, collaborative research activities among various DOE-sponsored programs are essential. These efforts should incorporate fuel experiments, physics-based high-fidelity modeling, ML-based surrogate modeling, and optimization techniques. This whitepaper proposes four research and development areas: 1) Investigation of the feasibility of new operations of LWR with updated safety limits; 2) Assessment of reactor operation limits through uncertainty reduction; 3) Evaluation of power uprate in virtual environment; and 4) Lattice and reactor core design for power uprate. Each area includes why this research is in need and a suggested scope of work. These comprehensive research areas ensure practical and beneficial advancements for existing reactors, translating innovations in nuclear fuel and cladding technology into improved reactor performance and safety.

42 - ENGINEERING↗
DOE OSTI2020

Identifying Entangled Physics Relationships through Sparse Matrix Decomposition to Inform Plasma Fusion Design [Slides]

The National Ignition Facility (NIF), is a large laser-based inertial confinement fusion (ICF) research device and various input variables in the experimental data are described. The overview included sections on: high-dimensional experimental dataset; surrogate model selection; ML to interpret complex coupling between inputs; importance of variables; Surrogate performance; and, future work.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2023

HIGH-LOW FIDELITY THERMAL HYDRAULIC COUPLING USING AI/MACHINE LEARNING ALGORITHMS

The primary goal of the US Department of Energy (DOE) office of Nuclear Energy Integrated Energy Systems (IES) program is to develop the tools and framework for coupling multi-scale and multi-physical thermal and electrical energy usage and storage systems. High- and low-fidelity (high–low) coupling is a key feature of multi-scale, multi-component systems and has been an important focus of research in the nuclear energy community for the past two decades. An essential feature of demonstrating the capability to couple high-fidelity and low-fidelity systems for real-time applications are surrogate/reduced order models (ROM). For the purposes of this study, surrogate models are essentially Blackbox models, typically developed using supervised Machine learning (ML) algorithms. The surrogate models can be used to mimic the response of high-fidelity models to represent large historical datasets and coupled with more general low-fidelity system models distributed as Functional Mock-up Interface (FMI) or Functional Mock-up Units (FMU) modules. The example is demonstrated with Spallation Neutron Source (SNS) First Target Station flow loop data. The flow loop is a liquid mercury loop with a pump, piping, heat exchange, and internal heat generation in the target window. This work elucidates some of the potential benefits and future needs of developing tools for high–low system coupling of energy systems.

Williams, Wesley↗
DOE OSTI2022

Accelerating Multiscale Materials Modeling with Machine Learning

The focus of this project is to accelerate and transform the workflow of multiscale materials modeling by developing an integrated toolchain seamlessly combining DFT, SNAP, LAMMPS, (shown in Figure 1-1) and a machine-learning (ML) model that will more efficiently extract information from a smaller set of first-principles calculations. Our ML model enables us to accelerate first-principles data generation by interpolating existing high fidelity data, and extend the simulation scale by extrapolating high fidelity data (10 2 atoms) to the mesoscale (10 4 atoms). It encodes the underlying physics of atomic interactions on the microscopic scale by adapting a variety of ML techniques such as deep neural networks (DNNs), and graph neural networks (GNNs). We developed a new surrogate model for density functional theory using deep neural networks. The developed ML surrogate is demonstrated in a workflow to generate accurate band energies, total energies, and density of the 298K and 933K Aluminum systems. Furthermore, the models can be used to predict the quantities of interest for systems with more number of atoms than the training data set. We have demonstrated that the ML model can be used to compute the quantities of interest for systems with 100,000 Al atoms. When compared with 2000 Al system the new surrogate model is as accurate as DFT, but three orders of magnitude faster. We also explored optimal experimental design techniques to choose the training data and novel Graph Neural Networks to train on smaller data sets. These are promising methods that need to be explored in the future.

36 MATERIALS SCIENCE↗
DOE OSTI2023

One System, Many Models: Designing a Surrogate Model for Sulfur Thermal Energy Storage: Preprint

Industrial process heating (IPH) relies primarily on thermal energy generated by fossil fuel combustion to produce, treat, and alter manufactured goods. Thermal energy storage (TES) helps reduce the carbon footprint of IPH systems by facilitating the utilization of renewable and waste heat sources. A promising new TES technology uses elemental sulfur as the heat-storage medium. The design of sulfur TES systems can be evaluated with the aid of computational fluid dynamics (CFD). However, the computational cost of such CFD efforts is prohibitive to comprehensive optimizations over design parameters. To reduce this computational cost, machine learning (ML) models can be developed to act as surrogates for CFD. In this paper, we describe the process of building and evaluating surrogate ML models for facilitating optimization of sulfur TES systems for IPH. To enforce the thermodynamic relationship between the two modeled quantities, we develop a hybrid model for sulfur temperature using both direct predictions of temperature and calculations of temperature from predictions of the heat transfer coefficient. The hybrid model enforces this constraint at the expense of the slightly reduced accuracy compared to two disjoint models. The overall high accuracy observed in our model evaluation demonstrates the usefulness of such surrogate modeling for studying TES systems. This work contributes to the field of TES surrogate modeling by offering a novel accurate hybrid approach to predicting simultaneously the heat transfer coefficient and temperature of the heat storage medium.

computational fluid dynamics↗
DOE OSTI2022

Unified Language Frontend for Physic-Informed AI/ML

Artificial intelligence and machine learning (AI/ML) are becoming important tools for scientific modeling and simulation as in several other fields such as image analysis and natural language processing. ML techniques can leverage the computing power available in modern systems and reduce the human effort needed to configure experiments, interpret and visualize results, draw conclusions from huge quantities of raw data, and build surrogates for physics based models. Domain scientists in fields like fluid dynamics, microelectronics and chemistry can automate many of their most difficult and repetitive tasks or improve the design times by use of the faster ML-surrogates. However, modern ML and traditional scientific highperformance computing (HPC) tend to use completely different software ecosystems. While ML frameworks like PyTorch and TensorFlow provide Python APIs, most HPC applications and libraries are written in C++. Direct interoperability between the two languages is possible but is tedious and error-prone. In this work, we show that a compiler-based approach can bridge the gap between ML frameworks and scientific software with less developer effort and better efficiency. We use the MLIR (multi-level intermediate representation) ecosystem to compile a pre-trained convolutional neural network (CNN) in PyTorch to freestanding C++ source code in the Kokkos programming model. Kokkos is a programming model widely used in HPC to write portable, shared-memory parallel code that can natively target a variety of CPU and GPU architectures. Our compiler-generated source code can be directly integrated into any Kokkosbased application with no dependencies on Python or cross-language interfaces.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2023

Closing in on Hydrologic Predictive Accuracy: Combining the Strengths of High-Fidelity and Physics-Agnostic Models

Applications of process-based models (PBM) for predictions are confounded by multiple uncertainties and computational burdens, resulting in appreciable errors. A novel modeling framework combining a high-fidelity PBM with surrogate and machine learning (ML) models is developed to tackle these challenges and applied for streamflow prediction. A surrogate model permits high computational efficiency of a PBM solution at a minimum loss of its accuracy. A novel probabilistic ML model partitions the PBM-surrogate prediction errors into reducible and irreducible types, quantifying their distributions that arise due to both explicitly perceived uncertainties (such as parametric) or those that are entirely hidden to the modeler (not included or unexpected). Using this approach, we demonstrate a substantial improvement of streamflow predictive accuracy for a case study urbanized watershed. Such a framework provides an efficient solution combining the strengths of high-fidelity and physics-agnostic models for a wide range of prediction problems in geosciences.

58 GEOSCIENCES↗
DOE OSTI2026

Surrogate model for third-integer resonance extraction at the Fermilab Delivery Ring

We present an ongoing work in which a surrogate model is being developed to reproduce the response dynamics of the third-integer resonant extraction process in the Delivery Ring (DR) at Fermilab. This is in pursuit of smoothly extracting circulating beam to the Mu2e Experiment’s production target, whereby the goal is to extract a uniform slice of the circulating 1e12 protons in the DR over 25,000 turns (43 ms). The DR contains 3 harmonic sextupoles that excite a third-integer resonance and three fast, tune-ramping quadrupole magnets that drive the horizontal tune towards the 29/3 resonance. In our initial work, the surrogate model trains on a semi-analytical simulation provided in the same format as live data. Using Reinforcement Learning (and other potential ML methods), the trained surrogate acts as the “environment” in which a simple ML control agent could learn to dynamically adjust the quadrupole ramp at 430 break points within the 43 microsecond spill window. The controller will be hosted on a dedicated Arria 10 FPGA. In this work, we report the accuracy and fidelity of the surrogate model in comparison to the response dynamics of the physics simulator.

Narayanan, Aakaash [Fermilab]↗