Search NASA⌕ Search

SEARCH · Search NASA

Results for “Model development”

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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Reduced-Order Modeling of Hydrogen Releases from Vent Stacks and with Wind Effects

Here, the physical release behavior of hydrogen is important to understand from a safety and design perspective. The consequences of unignited pressurized gaseous hydrogen plumes exiting vent stacks were considered by extending and modifying existing general hydrogen plume models. Entrainment, vent stack backpressure, and the flow regime of hydrogen exiting the vent were found to be significant factors affecting plume shape and size, but further investigation and validation with unchoked, low-Froude-number flows is recommended to improve the model’s robustness. Additionally, models for the effects of wind on unignited plume momentum and entrainment were added to explore this behavior. Wind was assumed to increase mixing of hydrogen with the ambient air, and to affect the momentum of the released jet. Introducing wind into the plume model led to a shorter plume for all wind and jet directions. A high counter-flowing wind led to non-physical results and challenges in interpreting the visualization. The proposed jet plume wind sub-models (specifically entrainment coefficients) were fit and compared to experimental data of different releases of hydrogen into a wind tunnel, but the quantity of data available and experimental conditions were limited. Thus, collection of more empirical data and for a wider range of conditions is recommended for improvement of the proposed computational models. Developing reduced-order models for these physical phenomena can improve accessibility to predicted physical behavior and the rate at which hydrogen systems can be safely designed and deployed.

entrainment↗
DOE OSTI2025

Machine learning-enabled discovery of ionic liquid–solvent electrolytes exhibiting high ionic conductivity

Ionic liquids (ILs), which are a class of materials with versatile nature and growing popularity, are facing impediments toward widespread usage as electrolytes due to various factors such as low ionic conductivity, high viscosity, high market price etc. One of the ways these limitations can be addressed is by mixing ILs with a molecular solvent. In a combinatorial sense, there exists an immense number of specific IL–solvent combinations. An exhaustive experimental or even simulation-based investigation of the chemical space spanned by such combinations can be extremely time-consuming, expensive, and nearly impossible. An alternative approach is to employ machine learning-based models developed from available databases. Although there exists prior literature that integrates machine learning to investigate mixtures of specific solvents with ILs, these models lack generalization necessitating development of a large number of ML models to handle various solvents. To remedy this shortcoming, as a part of designing green electrolytes with high ionic conductivity that can have potential applications in next-generation batteries and solar cells, this work aims to develop a unified machine learning model to predict ionic conductivity of any IL–solvent mixture system. In this regard, three models, namely, Random Forest, extreme gradient boosting (XGBoost), and artificial neural network (ANN) were formulated using the NIST ILThermo database. The dataset contained 549 unique ionic liquids from 16 cation families and 81 unique solvents, representing a total of 23 712 datapoints. SHAPLEY additive explanation (SHAP) method was used to assess the impact of various features on model prediction and their significance was compared with literature to gain physical insight about the model behavior. Finally, using the developed models, approximately 2.5 million IL–solvent mixtures at five different compositions were screened at room temperature. The high-throughput screening yielded nearly 19 000 IL–solvent mixtures for which ionic conductivity was found to exceed the ionic conductivity of conventional Li-ion battery electrolyte.

25 ENERGY STORAGE↗
DOE OSTI2025

Multi-agent AI collaboration for digital twin development and assessment

Developing a digital twin (DT) model involves different steps that encompass formulating requirements, model development, implementation, and assessment with respect to real applications. Human expertise is required to coordinate and implement different steps in the DT development and assessment process. However, certain parts of this process can be automated using artificial intelligence (AI) agents for efficient workflow development. In this work, we test and analyze a multiagent AI collaboration with humans in the loop to automate different elements of the DT development and assessment process. To implement the workflow for multiagent AI DT development and assessment, we use Autogen, a multiagent framework developed by Microsoft. Autogen offers a modular and flexible framework for configuring and designing task-specific multiagent workflows. In this framework, large language models (LLMs) form the core intelligence of the AI agents where the quality and performance of the automated element is governed by the inherent capabilities and knowledge base of the LLM. We use retrieval augmented generation to supplement the LLM with relevant domain-specific information for DT requirement formulation. We illustrate this multiagent workflow using a case study on a thermal energy storage system, focusing on how AI agents can collaborate with humans to expedite and optimize different elements of DT development and assessment process.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2025

PBE-HIL (Powering the Blue Economy Hardware-in-the-Loop models) [SWR-25-37]

Powering the Blue Economy Hardware-in-the-Loop models (PBE-HIL) is a repository of Power Hardware-in-the-loop models developed for typical Powering the Blue Economy market loads and power requirements. The HIL models were developed to be as generic and functional as possible, meaning that the user can easily configure these models to represent their unique PBE design. These PBE load and power requirement HIL models can then be used to inform marine energy converter (MEC) and power electronics design, as well as be used in laboratory testing using HIL equipment, leading to improved understanding of MEC performance and lower risk prior to open-water MEC deployment.

Labuschagne, Hannes [National Renewable Energy Lab↗
DOE OSTI2024

Analysis of AP1000 Small-Break Loss-of-Coolant Accident Using Reactor Transient Simulator

The Westinghouse Electric Company’s Advanced Passive Reactor (AP1000) is characterized by the incorporation of passive safety systems (PSSs) designed to ensure core cooling during transient events. The assessment of PSSs requires evaluation of their performance through a combination of experiments and simulations employing various thermal-hydraulic codes. In addition, detailed evaluation of PSSs for a specific reactor system transient analysis such as loss-of-coolant-accident analysis supports understanding representative integral effects test facility development and the further evolution model development and assessment process. Developing a reactor system code is a complex and time-consuming process that requires significant engineering expertise and effort. It can take several months to even years to complete in the early stages of reactor system design and analysis. However, this process can be expedited through the use of transient simulator models for similar reactor systems, which can be used for lesson learning and training purposes. This study uses the Personal Computer Transient Analyzer (PCTRAN) code. The main advantage of PCTRAN is its ease of use and ability to run faster than real time. This study presents the results obtained for a small-break loss-of-coolant accident (SBLOCA) for two breaks using the full version (licensed) of PCTRAN. The purpose of this investigation is to evaluate the overall system behavior during the postulated SBLOCA event as well as assess the capability of the PCTRAN code to reproduce the system response during transient events. The obtained results were compared with the Westinghouse NOTRUMP system code. The PCTRAN code proved to be reliable in predicting the qualitative behavior of the system in both transient cases. As for the system response, it was found that it is contingent on the activation time of the PSSs. The differences in reactor coolant system pressure between the two codes were attributed to the critical flow model and simplification of mass and energy balance. Despite PCTRAN’s limitations, it can still provide a reasonable prediction of various reactor parameters such as pressure, mass flow rate, and void fraction during a SBLOCA scenario. It is worth noting that PCTRAN currently employs a bulk approach similar to that of the Modular Accident Analysis Program (MAAP) and MELCOR codes. However, the upcoming version of PCTRAN will include an artificial intelligence–based detection and accident prevention system, as well as different models for different reactor components. Consequently, PCTRAN has the potential to be upgraded to match the system thermal-hydraulic codes of the U.S. Nuclear Regulatory Commission and become more widely used in cybersecurity to safeguard nuclear power plants from cyberattacks.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2025

Design, Optimization, and Control of Floating Offshore Wind Farms for Optimal Energy Production (Final report)

The uncertainty and irregularity of ocean waves and the ocean environment is a major factor in the development of commercial scale floating wind turbines as the operation of floating structures in such an environment can lead to irregular and unpredictable loading, fatigue, and ultimately a reduction in the operational life of the turbine system which affects energy production over the lifetime of the turbine. Control solutions that can limit float motions and mitigate stressful events on the structure become essential for extending lifetime and limiting the operational uncertainty of a floating wind turbine. Digital twins are computational replicas of physical systems that operate in parallel with the operation of the physical system. Given advanced knowledge of a systems input, digital twins have the ability to predict the behavior of a system in advance, which can be valuable in the control of that system. In this project, we developed and assessed potential digital twin models developed in house and openly available (OpenFast) for use in the real time control of the six degree of freedom response motions of a floating wind turbine in ocean waves. Coupling these models with near-field real time irregular sea surface (wve) measurement/sensings and prediction models, we used the digital twin to predict how the floating turbine will respond to the incoming waves. Applying this information to a motion control system of the float, one can limit and control float motions to prevent undesirable loading events/large angular motions, thus increasing system life and ultimately contributing to optimizing energy production. Due to the computational intensity of operating a digital twin in real time, we investigated the use of artificial intelligence techniques to speed-up the processes of the digital twin, as well as the wave reconstruction/prediction models. Model tank testing at the University of Rhode Island and University of Maine both validated and demonstrated the developed techniques on simple float geometries and a scale model of the NREL 15 MW reference turbine.

17 WIND ENERGY↗
DOE OSTI2024

Wavelength modulation laser-induced fluorescence for plasma characterization

Laser-Induced Fluorescence (LIF) spectroscopy is an essential tool for probing ion and atom velocity distribution functions (VDFs) in complex plasmas. VDFs carry information about the kinetic properties of species that is critical for plasma characterization. Accurate interpretation of these functions is challenging due to factors such as multicomponent distributions, broadening effects, and background emissions. Our research investigates the use of Wavelength Modulation (WM) LIF to enhance the sensitivity of VDF measurements. Unlike standard Amplitude Modulation (AM) methods, WM–LIF measures the derivative of the LIF signal. This approach makes variations in VDF shape more pronounced. VDF measurements with WM–LIF were investigated with both numerical modeling and experimental measurements. The developed model enables the generation of both WM and AM signals, facilitating comparative analysis of fitting outcomes. Experiments were conducted in a weakly collisional argon plasma with magnetized electrons and non-magnetized ions. Measurements of the argon ion VDFs employed a narrow-band tunable diode laser, which scanned the 4p 4 D 7/2 –3d 4 F 9/2 transition centered at 664.553 nm in vacuum. A lock-in amplifier detected the second harmonic WM signal, which was generated by modulating the laser wavelength with an externally controlled piezo-driven mirror of the diode laser. Finally, our findings indicate that the WM–LIF signal is more sensitive to fitting parameters, allowing for better identification of VDF parameters such as the number of distribution components, their temperatures, and velocities. In addition, WM–LIF can serve as an independent method to verify AM measurements and is particularly beneficial in environments with substantial light noise or background emissions, such as those involving thermionic cathodes and reflective surfaces.

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

Modeling Oxygen Partial Pressure in Solid Oxide Electrolysis Cells: The Microstructure Effect

Oxygen partial pressure is an important thermodynamic state variable that affects both the performance and degradation of solid oxide electrolysis cells. In this work, a 3D model developed from Virkar’s 1D model has been applied to reconstructed and synthetic microstructures of Ni-YSZ-GDC-LSCF cell. The effect of the microstructures, including the thickness of the YSZ and GDC layer, and the compositions of the hydrogen and oxygen electrode, on the distribution of oxygen partial pressure has been investigated. The results show that the maximum oxygen partial pressure may occur on the interface between oxygen electrode and GDC layer or between GDC layer and YSZ layer depending on the rate of oxygen ion exchange between GDC and YSZ. A thicker GDC layer lowers the maximum oxygen partial pressure in the cell, while a thicker YSZ layer lowers the maximum oxygen partial pressure in the hydrogen electrode. In addition, the Ni:YSZ ratio and porosity also affects the maximum partial pressure. These findings provide insights on mitigating degradation in solid oxide electrolysis cell by tuning the microstructures.

Lei, Yinkai↗
DOE OSTI2025

Validation of Numerical Tools for Calculating Reactivity Feedback in Sodium Fast Reactors Using SEFOR Experimental Data

The Southwest Experimental Fast Oxide Reactor (SEFOR) was an experimental sodium-cooled fast breeder reactor operated from 1969 to 1972 with experiments designed to measure Doppler reactivity feedback in a wide temperature range from around 350 °F to temperatures approaching the melting point of mixed oxide fuel of around 5000 °F, providing valuable data for code validations. Co-supported by the Department of Energy (DOE) Fast Reactor Program (FRP) and the DOE Nuclear Energy Advanced Modeling and Simulation (NEAMS) program, the SEFOR benchmark project focused on using the experimental data to validate numerical tools that are used in industry and academia to design and license sodium-cooled fast reactors (SFRs). By the end of FY-25, substantial progress was achieved in the SEFOR benchmark study. A variety of numerical tools commonly used for modeling SFRs were applied to develop models for SEFOR core configurations I-D, I-E, I-I, and I-J. These included Monte Carlo codes such as MCNP, Serpent, and Shift; deterministic codes such as the legacy Argonne Reactor Computation (ARC) suite and the high-fidelity NEAMS code Griffin; and the system analysis code SAS4A/SASSYS-1 (SAS). Using these models, both SEFOR zero-power experiments and power-ascending tests were successfully simulated. Comparisons were performed against experimental measurements of core criticalities, reflector worth, kinetics parameters (Λ/βeff), isothermal reactivity feedback (from 350 °F to 760 °F at zero power), and power-ascending reactivity feedback (as power increased from 0.4 MW to 17 MW). In general, these comparisons demonstrated very good agreement between numerical results and experimental data. In Fiscal Year 26 (FY-26), the SEFOR benchmark project will continue to address the modeling issues identified in FY-25. Effort will focus on the simulation of reactivity insertion transients in SEFOR core II using the ARC/SAS model. Future work will also focus on incorporating BISON into the SEFOR core modeling process to enable the first Multiphysics simulations of the isothermal tests based on the MOOSE framework.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2025

Internally Catalyzed Hydrogen Atom Transfer (I-CHAT)—A New Class of Reactions in Combustion Chemistry

The current paradigm of low-T combustion and autoignition of hydrocarbons is based on the sequential two-step oxygenation of fuel radicals. The key chain-branching occurs when the second oxygenation adduct (OOQOOH) is isomerized releasing an OH radical and a key ketohydroperoxide (KHP) intermediate. The subsequent homolytic dissociation of relatively weak O–O bonds in KHP generates two more radicals in the oxidation chain leading to ignition. Based on the recently introduced intramolecular “catalytic hydrogen atom transfer” mechanism (J. Phys. Chem. 2024, 128, 2169), abbreviated here as I-CHAT, we have identified a novel unimolecular decomposition channel for KHPs to form their classical isomers—enol hydroperoxides (EHP). The uncertainty in the contribution of enols is typically due to the high computed barriers for conventional (“direct”) keto–enol tautomerization. Remarkably, the I-CHAT dramatically reduces such barriers. The novel mechanism can be regarded as an intramolecular version of the intermolecular relay transfer of H-atoms mediated by an external molecule following the general classification of such processes (Catal. Rev.-Sci. Eng. 2014, 56, 403). Here, we present a detailed mechanistic and kinetic analysis of the I-CHAT-facilitated pathways applied to n-hexane, n-heptane, and n-pentane models as prototype molecules for gasoline, diesel, and hybrid rocket fuels. We particularly examined the formation kinetics and subsequent dissociation of the γ-enol-hydroperoxide isomer of the most abundant pentane-derived isomer γ-C5-KHP observed experimentally. To gain molecular-level insight into the I-CHAT catalysis, we have also explored the role of the internal catalyst moieties using truncated models. All applied models demonstrated a significant reduction in the isomerization barriers, primarily due to the decreased ring strain in transition states. In addition, the longer-range and sequential H-migration processes were also identified and illustrated via a combined double keto–enol conversion of heptane-2,6-diketo-4-hydroperoxide as a potential chain-branching model. To assess the possible impact of the I-CHAT channels on global fuel combustion characteristics, we performed a detailed kinetic analysis of the isomerization and decomposition of γ-C5-KHP comparing I-CHAT with key alternative reactions—direct dissociation and Korcek channels. Calculated rate parameters were implemented into a modified version of the n-pentane kinetic model developed earlier using RMG automated model generation tools (ACS Omega, 2023, 8, 4908). Simulations of ignition delay times revealed the significant effect of the new pathways, suggesting an important role of the I-CHAT pathways in the low-T combustion of large alkanes.

Biochemistry & Molecular Biology↗
DOE OSTI2026

Geothermal Heat Pump System Showcase: Short-Term Validation of Borehole Heat Exchanger Performance from Field Data to Numerical Modeling: Preprint

Since 2011, a geothermal heat pump (GHP) system has been operating to provide space heating and cooling for the Solar Radiation and Research Laboratory building at the National Laboratory of the Rockies (NLR) in Golden, Colorado. The system consists of 23 vertical boreholes, each extending to a depth of 300 ft (91 m), connected to 11 water-to-air heat pump units and four circulation pumps. Between fiscal years 2023 and 2025, additional power meters and temperature sensors were retrofitted to support detailed system performance assessment and model development. This study presents preliminary monitoring results and the development of an initial numerical model of the borehole heat exchanger field. The model incorporated site-specific geometry, ground thermal properties derived from thermal response tests, and ambient temperatures, and simulated system behavior over a representative operating day in September. Model predictions of outlet temperatures were compared against corresponding field measurements. Results showed that modeling initialized with a simplified linear subsurface temperature gradient presents systematic discrepancies in outlet temperature, whereas incorporating depth-resolved borehole temperature measurements for initialization yields substantially improved agreement with observations. The findings highlight the sensitivity of short-term predictive modeling to the representation of initial subsurface thermal conditions and underscore the value of high-resolution field measurements for model calibration and validation. These preliminary results inform ongoing efforts to extend the modeling framework to longer time horizons and to refine monitoring and modeling strategies that support the design guidance and operational optimization of GHP systems in research and commercial buildings.

15 GEOTHERMAL ENERGY↗
DOE OSTI2025

Architecture-Aware Models of AI Engines for High-Performance Matrix Matrix Multiplication

The AI Engine (AIE) architecture, available in systems from mobile SoCs to server-class FPGAs, aims to efficiently execute AI/ML tasks through a two-dimensional array of compute tiles. Previous work on AIEs has explored different approaches to mapping computation across spatial arrays, but the compute kernel running on each tile has not been the focus. Additionally, the AIE-ML architecture introduces memory tiles and omits programmable logic, requiring new approaches to staging and moving data throughout the array. In this work we update analytical models developed for CPUs to produce the design of high performance kernels while introducing new model considerations such as memory structure, throughput, and latency as required by the AIE hardware. We evaluate our models by developing AIE-ML kernels for matrix multiplication in low-precision data types showing performance up to 95% of compute peak for the kernel when data resides in local memory and above 90% of compute peak when data resides in main memory.

Binder, Elliott D. [Carnegie Mellon University, Pi↗
DOE OSTI2024

CIGS Technology Advancement via Fundamental Modeling of Defect/Impurity Interactions (Final Technical Report)

The primary goals of the proposed work were to provide modeling tools (and the associated insight which comes along with model development) for design and optimization of CuIn x Ga 1-x Se 2 (CIGS) and CdSeTe (CST) solar cell manufacturing processes and to establish the foundation for comprehensive end-to-end predictive modeling tools to enable optimization of thin film photovoltaic technology for performance, cost, yield, and reliability. The initial focus of efforts within this project was to develop coupled process/optical/device models for CIGS PV technology and to work with Siva Power to apply that TCAD (technology computer-aided design) system to improve the efficiency and reduce manufacturing costs for CIGS solar cells. Our approach to that end was to generate an extensive database of DFT calculations and to use those calculations via statistical thermodynamics methods and Monte Carlo simulation to develop and characterize models for the behavior of native defects as well as intentional and unintentional impurities, including the redistribution of the primary components of CIGS films. Increased effort went toward coupling those models for defect behavior and composition evolution to the performance of multicrystalline CIGS solar cells via prediction of doping level and recombination lifetime as function of manufacturing process. In the second budget period, the project pivoted to developing a similar system for the CdSeTe system, focused especially on understanding the role of Se/Te alloy concentration. Execution of the project resulted in the successful development of TCAD systems for both CIGS and CdSeTe thin film PV within the Synopsys Sentaurus framework by utilizing the Alagator interface. In the first budget period of the project, we developed quantitative models for the major components of CIGS PV and implemented them within a framework that couples process, optical, and device simulation. From the insights we have gained, we identified novel opportunities for enhancing CIGS solar cell performance and have laid the groundwork to further optimize the layer structure, composition profile, and thermal cycles for substantially improved efficiency and lower manufacturing costs. For the CIGS system, process changes to achieve greater than 1% absolute enhancement in efficiency were identified, but testing of those approaches was stymied by lack of a domestic CIGS manufacturing partner after the closure of Siva Power as well as Miasole. For CdSeTe, a fully capable TCAD system only became ready to apply near the end of the project period, so substantial opportunities remain to apply those models to enhance the leading thin film PV technology.

14 SOLAR ENERGY↗
DOE OSTI2024

From minimum-viable-products to full models: a step-wise development of diagnostic forward models in support of design, analysis and modelling on the ST40 tokamak

Like most magnetic confined fusion experiments, the ST40 tokamak started off with a small subset of diagnostics and gradually increased the diagnostic set to include more complex and comprehensive systems. To make the most of each operational phase, forward models of various diagnostics are used and developed to aid design, provide consistency-checks during commissioning, test analysis methods, and build workflows to constrain high-level parameters to inform interpretation, theory and modelling. For new models and new analysis workflows, minimum-viable-products are released early, and their complexity is increased in a step-wise manner, facilitating the support of all programme phases on multiple parallel applications, while enabling learning opportunities and feedback loops. In this contribution we review the philosophy, scope and architecture of the framework under development. We discuss the details of some forward models, with examples on how they are used to aid diagnostic design, to investigate analysis methodologies through synthetic data, and how they are embedded in experimental analysis workflows. We compare previously published experimental results with new, more advanced analysis workflows employing more recent, detailed models and new diagnostic data, providing confirmation of the published material from the 2021–22 experimental campaign.

integrated data analysis↗
DOE OSTI2026

A Generic and Multifunctional Electromagnetic Transient Model for Grid-Following Inverters

This article presents a generic and multi-functional electromagnetic transient (EMT) dynamic model of grid following (GFL) inverter-based resource (IBR) using the PSCAD software platform. The features of the developed model includes the flexibility in selecting various types and combinations of DC sources covering PV modules, battery modules, ideal DC source module, as well as flexibility in selecting either switched or averaged model of inverter. This model also covers exhaustive lists of controller logic covering open-loop/closed-loop PQ dispatch control, DC voltage and AC terminal voltage control along with the conventional current control designed in dq-domain, ate- domain and positive-negative sequence domain. Moreover, this model is equipped with the flexibility in selecting various types of current limiting schemes that includes saturation-based as well as latching-based current limiter, anti-windup protection. Moreover, the EMT model is agnostic to the MVA rating and is suitable for interfacing transmission systems by being complaint with the IEEE Std. 2800. The generality in the power circuits and the multi-functional options in operation and control of the developed EMT model makes it suitable for both academia and industry to study various power system aspects not limited to but such as fault behavior of GFL IBR and impacts on protection system, transient stability of a system interfaced with large number of GFL IBRs etc.

14 SOLAR ENERGY↗
DOE OSTI2024

A Generic and Multi-Functional Electromagnetic Transient Model for Grid-Following Inverter: Preprint

This article presents a generic and multi-functional electromagnetic transient (EMT) dynamic model of grid following (GFL) inverter-based resource (IBR) using the PSCAD TM software platform. The features of the developed model includes the flexibility in selecting various types and combinations of DC sources covering PV modules, battery modules, ideal DC source module, as well as flexibility in selecting either switched or averaged model of inverter. This model also covers exhaustive lists of controller logic covering open-loop/closed-loop PQ dispatch control, DC voltage and AC terminal voltage control along with the conventional current control designed in dq-domain, aB- domain and positive-negative sequence domain. Moreover, this model is equipped with the flexibility in selecting various types of current limiting schemes that includes saturation-based as well as latching-based current limiter, anti-windup protection. Moreover, the EMT model is agnostic to the MVA rating and is suitable for interfacing transmission systems by being complaint with the IEEE Std. 2800. The generality in the power circuits and the multi-functional options in operation and control of the developed EMT model makes it suitable for both academia and industry to study various power system aspects not limited to but such as fault behavior of GFL IBR and impacts on protection system, transient stability of a system interfaced with large number of GFL IBRs etc.

grid following inverter↗
DOE OSTI2025

Learning plasma dynamics and robust rampdown trajectories with predict-first experiments at TCV

The rampdown phase of a tokamak pulse is difficult to simulate and often exacerbates multiple plasma instabilities. To reduce the risk of disrupting operations, we leverage advances in Scientific Machine Learning (SciML) to combine physics with data-driven models, developing a neural state-space model (NSSM) that predicts plasma dynamics during Tokamak à Configuration Variable (TCV) rampdowns. The NSSM efficiently learns dynamics from a modest dataset of 311 pulses with only five pulses in a reactor-relevant high-performance regime. The NSSM is parallelized across uncertainties, and reinforcement learning (RL) is applied to design trajectories that avoid instability limits. High-performance experiments at TCV show statistically significant improvements in relevant metrics. A predict-first experiment, increasing plasma current by 20% from baseline, demonstrates the NSSM’s ability to make small extrapolations. The developed approach paves the way for designing tokamak controls with robustness to considerable uncertainty and demonstrates the relevance of SciML for fusion experiments.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

Transfer learning nonlinear plasma dynamic transitions in low dimensional embeddings via deep neural networks

Deep learning algorithms provide a new paradigm to study high-dimensional dynamical behaviors, such as those in fusion plasma systems. Development of novel, data-driven model reduction methods, coupled with detection of abnormal modes with plasma physics, opens a unique opportunity to identify plasma instabilities through automated construction of parsimonious models that can be tuned to balance accuracy and cost. Our fusion transfer learning (FTL) model demonstrates success in rapidly reconstructing nonlinear kink mode structures by learning from a limited amount of nonlinear simulation data. The knowledge transfer process leverages a pre-trained neural encoder–decoder network, initially trained on linear simulations, to effectively capture nonlinear dynamics. The low-dimensional embeddings extract the coherent structures of interest, while preserving the inherent dynamics of the complex system. Experimental results highlight FTL’s capacity to capture transitional behaviors and dynamical features in plasma dynamics—a task often challenging for conventional methods. The model developed in this study is generalizable and can be extended broadly through transfer learning to address various magnetohydrodynamics modes.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗