Search NASA⌕ Search

SEARCH · Search NASA

Results for “complex simulation”

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 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Active Learning for Metamaterial Optimization on HPC and QC Integrated Systems

Active learning algorithms, integrating machine learning, quantum computing and optics simulation in an iterative loop, offer a promising approach to optimizing metamaterials. However, these algorithms can face difficulties in optimizing highly complex structures due to computational limitations. High-performance computing (HPC) and quantum computing (QC) integrated systems can address these issues by enabling parallel computing. In this study, we develop an active learning algorithm working on HPC-QC integrated systems. We evaluate the performance of optimization processes within active learning (i.e., training a machine learning model, problem-solving with quantum computing, and evaluating optical properties through wave-optics simulation) for highly complex metamaterial cases. Our results showcase that utilizing multiple cores on the integrated system can significantly reduce computational time, thereby enhancing the efficiency of optimization processes. Therefore, we expect that leveraging HPC-QC integrated systems helps effectively tackle large-scale optimization challenges in general.

Kim, Seongmin↗
DOE OSTI2025

Defining quantum-ready primitives for hybrid HPC-QC supercomputing: a case study in Hamiltonian simulation

As computational demands in scientific applications continue to rise, hybrid high-performance computing (HPC) systems integrating classical and quantum computers (HPC-QC) are emerging as a promising approach to tackling complex computational challenges. One critical area of application is Hamiltonian simulation, a fundamental task in quantum physics and other large-scale scientific domains. This paper investigates strategies for quantum-classical integration to enhance Hamiltonian simulation within hybrid supercomputing environments. By analyzing computational primitives in HPC allocations dedicated to these tasks, we identify key components in Hamiltonian simulation workflows that stand to benefit from quantum acceleration. To this end, we systematically break down the Hamiltonian simulation process into discrete computational phases, highlighting specific primitives that could be effectively offloaded to quantum processors for improved efficiency. Our empirical findings provide insights into system integration, potential offloading techniques, and the challenges of achieving seamless quantum-classical interoperability. We assess the feasibility of quantum-ready primitives within HPC workflows and discuss key barriers such as synchronization, data transfer latency, and algorithmic adaptability. These results contribute to the ongoing development of optimized hybrid solutions, advancing the role of quantum-enhanced computing in scientific research.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Online thermal profile prediction for large format additive manufacturing: A hybrid CNN-LSTM based approach

Large format additive manufacturing (LFAM) is an advanced 3D printing technique that efficiently fabricates large-scale components through a layer-by-layer extrusion and deposition process. Accurate surface layer temperature monitoring is essential to prevent manufacturing failures and ensure final product quality. Traditional physics-based offline approaches for simulating thermal behavior are often inefficient and complex, posing challenges on real-time, in-situ monitoring. Here, to address this, we propose a data-driven hybrid CNN-LSTM model to predict sequential thermal images of arbitrary length using real-time infrared thermal imaging. In this approach, a Convolutional Neural Networks (CNN) is trained offline to capture spatial features, reduce dimensional complexity, and enhance time efficiency, while a stacked Long Short-Term Memory (LSTM) is applied online to capture temporal information for improved prediction of future thermal behavior in subsequent printing layers. Model performance is evaluated using MSE, SSIM, and PSNR metrics and is benchmarked against stacked LSTM and convolutional LSTM models, demonstrating superior accuracy and applicability. Additionally, to mitigate noise from moving extruders and gantry backgrounds in thermal images, a fine-tuned semantic segmentation model is implemented offline to extract printing geometry, enabling precise temperature tracking along the tool path for further thermal analysis. The frameworks developed in this study significantly advance temperature monitoring, thermal analysis, and in-situ manufacturing control for LFAM, bridging the gap between theoretical modeling and practical application.

Geometry extraction↗
DOE OSTI2025

Micropolar deep material network

This study extends the Deep Material Network (DMN), a physics-informed machine learning framework, to predict the homogenized mechanical response of composite materials with micropolar (Cosserat-type) constitutive behavior. This extension incorporates microstructure-dependent size effects, enabling accurate, efficient, and size-aware predictions for composites with complex internal architectures. While traditional, direct numerical simulation micropolar models effectively capture size effects by introducing extra local degrees of freedom, they bring significant computational challenges, particularly for multiscale analyses relevant to engineering applications. The micropolar DMN developed in this paper achieves high accuracy while significantly reducing computation time compared to micropolar direct numerical simulations. This advancement enables multiscale analyses and parameter studies that were previously impractical, such as high-cycle fatigue simulations and comprehensive investigations of internal length scale effects notably in size-dependent plastic response and the optimization of lattice structures. By uniting microstructure-sensitive modeling, physics-driven learning, and scalable surrogate modeling, the micropolar DMN paves the way for accelerated material design, large-scale parametric studies, and the reliable incorporation of size-dependent effects across a wide range of engineering applications, including optimization and next-generation composite design.

36 MATERIALS SCIENCE↗
DOE OSTI2025

MOOSE-based Tritium Migration Analysis Program, Version 8 (TMAP8) for advanced open-source tritium transport and fuel cycle modeling

Tritium management is critical for the safety, sustainability, and economics of fusion energy systems, and advanced and reliable modeling tools help accelerate the development of tritium technologies. This paper presents the Tritium Migration Analysis Program, Version 8 (TMAP8), an open-source, MOOSE-based application developed to provide state-of-the-art tritium transport and fuel cycle modeling capabilities. TMAP8 aims to expand the capabilities of previous versions (i.e., TMAP4 and TMAP7) by leveraging modern computational techniques, ensuring high software quality assurance standards (key to building trust), and enabling multispecies, multiscale, and multiphysics simulations for integrated tritium transport modeling in complex geometries. This paper outlines TMAP8’s scope and rigorous development practices, emphasizing its transparency, accessibility, modularity, and reliability. We present the current suite of verification and validation cases based on those from TMAP4, demonstrating TMAP8’s accuracy and reliability against analytical solutions and experimental data. Additionally, the paper showcases TMAP8’s integrated fuel cycle modeling capabilities, highlighting its applicability at various scales and levels. The TMAP8 code and documentation are openly available, promoting collaborative development and widespread adoption within the fusion community. Future work will soon expand TMAP8’s verification and validation suite to include those from TMAP7 and other recent experimental studies for validation.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2025

Strongly nonlinear wave propagation in elasto-plastic metamaterials: Low-order dynamic modeling

Nonlinear elastic metamaterials are known to support a variety of dynamic phenomena that enhance our capacity to manipulate elastic waves. Since these properties stem from complex, subwavelength geometry, full-scale dynamic simulations are often prohibitively expensive at scales of interest. Prior studies have therefore utilized low-order effective medium models, such as discrete mass-spring lattices, to capture essential properties in the long-wavelength limit. While models of this type have been successfully implemented for a wide variety of nonlinear elastic systems, they have predominantly considered dynamics depending only on the instantaneous kinematics of the lattice, neglecting history-dependent effects, such as wear and plasticity. Here, to address this limitation, the present study develops a lattice-based modeling framework for nonlinear elastic metamaterials undergoing plastic deformation. Due to the history- and rate-dependent nature of plasticity, the framework generally yields a system of differential-algebraic equations whose computational cost is significantly greater than an elastic system of comparable size. We demonstrate the method using several models inspired by classical lattice dynamics and continuum plasticity theory and explore means to obtain empirical plasticity models for general geometries, thereby gaining insight into the influence of microstructural plasticity on effective material performance, which can be used to improve the design of nonlinear mechanical metamaterials.

Dynamic simulation↗
DOE OSTI2025

A review of thermo-hydro-mechanical modeling of coupled processes in fractured rock: From continuum to discontinuum perspective

Coupled thermo-hydro-mechanical (THM) processes in fractured rock are playing a crucial role in geoscience and geoengineering applications. Diverse and conceptually distinct approaches have emerged over the past decades in both continuum and discontinuum perspectives leading to significant progress in their comprehending and modeling. This review paper offers an integrated perspective on existing modeling methodologies providing guidance for model selection based on the initial and boundary conditions. By comparing various models, one can better assess the uncertainties in predictions, particularly those related to the conceptual models. The review explores how these methodologies have significantly enhanced the fundamental understanding of how fractures respond to fluid injection and production, and improved predictive capabilities pertaining to coupled processes within fractured systems. It emphasizes the importance of utilizing advanced computational technologies and thoroughly considering fundamental theories and principles established through past experimental evidence and practical experience. The selection and calibration of model parameters should be based on typical ranges and applied to the specific conditions of applications. The challenges arising from inherent heterogeneity and uncertainties, nonlinear THM coupled processes, scale dependence, and computational limitations in representing field scale fractures are discussed. Realizing potential advances on computational capacity calls for methodical conceptualization, mathematical modeling, selection of numerical solution strategies, implementation, and calibration to foster simulation outcomes that intricately reflect the nuanced complexities of geological phenomena. Future research efforts should focus on innovative approaches to tackle the hurdles and advance the state-of-the-art in this critical field of study.

Coupling scheme↗
DOE OSTI2025

Clifford Circuit-Based Heuristic Optimization of Fermion-To-Qubit Mappings

Simulation of interacting Fermionic Hamiltonians is one of the most promising applications of quantum computers. However, the feasibility of analyzing Fermionic systems with a quantum computer hinges on the efficiency of Fermion-to-qubit mappings that encode nonlocal Fermionic degrees of freedom in local qubit degrees of freedom. While recent studies have highlighted the importance of designing Fermion-to-qubit mappings that are tailored to specific problem Hamiltonians, the methods proposed so far either are restricted to a narrow class of mappings or they use computationally expensive and unscalable brute-force search algorithms. Here, in this work, we address this challenge by designing a heuristic numerical optimization framework for Fermion-to-qubit mappings. To this end, we first translate the Fermion-to-qubit mapping problem to a Clifford circuit optimization problem and then use simulated annealing to optimize the average Pauli weight of the problem Hamiltonian. For all Fermionic Hamiltonians we have considered, the numerically optimized mappings outperform their conventional counterparts, including ternary-tree-based mappings that are known to be optimal for single creation and annihilation operators. We find that our optimized mappings yield between 15% and 40% improvements on the average Pauli weight when the simulation Hamiltonian has an intermediate level of complexity. Most remarkably, the optimized mappings improve the average Pauli weight for 6 × 6 nearest-neighbor hopping and Hubbard models by more than 40% and 20%, respectively. Surprisingly, we also find specific interaction Hamiltonians for which the optimized mapping outperforms any ternary-tree-based mapping. Our results establish heuristic numerical optimization as an effective method for obtaining mappings tailored for specific Fermionic Hamiltonian.

Hamiltonians↗
DOE OSTI2024

Diffusion-Limited Kinetics in Reactive Systems

A proper representation of chemical kinetics is vital to understanding, modeling, and optimizing many important chemical processes. In liquid and surface phases, where diffusion is slow, the rate at which the reactants diffuse together limits the overall rate of many elementary reactions. Commonly, the textbook Smoluchowski theory is utilized to estimate effective rate coefficients in the liquid phase. On surfaces, modelers commonly resort to much more complex and expensive Kinetic Monte Carlo (KMC) simulations. Here, in this study, we extend the Smoluchowski model to allow the diffusing species to undergo chemical reactions and derive analytical formulas for the diffusion-limited rate coefficients for 3D, 2D, and 2D/3D interface cases. With these equations, we are able to demonstrate that when species react faster than they diffuse they can react orders of magnitude faster than predicted by Smoluchowski theory, through what we term “the reactive transport effect”. We validate the derived steady-state equations against particle Monte Carlo (PMC) simulations, KMC simulations, and non-steady-state solutions. Furthermore, using PMC and KMC simulations, we propose corrections that agree with all limits and the computed data for the 2D and 2D/3D interface steady-state equations, accounting for unique limitations in the associated derived equations. Additionally, we derive equations to handle couplings between diffusion-limited rate coefficients in reaction networks. We believe these equations should make it possible to run much more accurate mean-field simulations of liquids, surfaces, and liquid–surface interfaces accounting for diffusion limitations and the reactive transport effect.

Johnson, Matthew Sean↗
DOE OSTI2026

Low-Rate Cycling Regeneration Sustains NMC811–Graphite Battery Performance through Extreme Ultrafast Charging

Urban air mobility (UAM) systems, such as electric vertical takeoff and landing (eVTOL) aircraft, require batteries capable of extreme ultrafast charging to support high-frequency operations. Here, in this work, we evaluate the electrochemical stability of NMC811–graphite full cells using a complex mixed-modal protocol designed to simulate the aggressive turnaround demands of UAM missions. We demonstrate that incorporating a periodic low-rate (0.3C) “regeneration” cycle enables cells to maintain 96% capacity retention over 900 cycles, despite repeated exposure to ultrafast pulses. To validate the efficacy of this regeneration mechanism, we performed simplified control experiments comparing continuous 10C charging against a 10C–0.3C interleaved protocol. Advanced characterization reveals that while mechanical particle fracture is pervasive at these rates, the regeneration cycles decelerate the electrochemical degradation by resolving spatially heterogeneous Ni oxidation states and relaxing lithium-ion concentration gradients. These findings provide a vital mechanistic framework for battery operation, proving that restorative charging can effectively delay and mitigate failure in demanding UAM applications.

batteries↗
DOE OSTI2025

From Nonclassical to Classical: Crystallization Seeds Reshape Nucleation Mechanisms

Crystalline seeds are widely employed in crystallization to accelerate nucleation and control product polymorphs; yet, their impact on nucleation mechanisms remains poorly understood. While homogeneous nucleation of crystals from solution often proceeds through nonclassical pathways involving amorphous intermediates, it is unclear how seeds that promote heterogeneous nucleation reshape these mechanisms and govern polymorph selection. Here, in this study, we provide the first direct evidence that crystalline seeds can bypass the need for amorphous intermediates as nucleation sites, converting nonclassical nucleation mechanisms into classical, monomer-by-monomer crystallization pathways. Using molecular dynamics simulations of zeolite synthesis, we uncover a complex reaction network of competing nucleation processes mediated by intermediate interfacial polymorphs. The interplay between thermodynamic stability and kinetic favorability of these interfacial polymorphs dictates nucleation outcomes, creating a dynamic balance between the interfacial polymorph stability and crystallization rates. Furthermore, we show that the synthesis environment-whether monomers or aggregates serve as reactants-profoundly impacts these pathways. At moderate supersaturation, seeds eliminate amorphous intermediates and promote classical nucleation, whereas high supersaturation or aggregate-based reactants favor nonclassical pathways, even in the presence of seeds. These findings establish a general framework for understanding how seeds govern crystallization mechanisms, with broad implications for controlling nucleation kinetics, polymorph selection, and material properties. While focused on zeolites, this work reveals insights that may be applicable to biominerals, pharmaceuticals, functional materials, and catalysts, providing a basis for engineering crystallization pathways in diverse applications.

Chu-Jon, Carlos [Univ. of Utah, Salt Lake City, UT↗
DOE OSTI2025

Accelerating detector simulations with Celeritas: Profiling and performance optimizations

Celeritas is a GPU-optimized Monte Carlo (MC) particle transport code designed to meet the growing computational demands of next-generation high energy physics (HEP) experiments. It provides efficient simulation of electromagnetic (EM) physics processes in complex geometries with magnetic fields, detector hit scoring, and seamless integration into Geant4-driven applications to offload EM physics to GPUs. Recent efforts have focused on performance optimizations and expanding profiling capabilities. This paper presents some key advancements, including the integration of the Perfetto system profiling tool for detailed performance analysis and the development of track-sorting methods to improve computational efficiency.

Lund, Amanda [Argonne National Laboratory (ANL)]↗
DOE OSTI2024

The Simons Observatory: Combining cross-spectral foreground cleaning with multitracer B -mode delensing for improved constraints on inflation

The Simons Observatory (SO), due to start full science operations in early 2025, aims to set tight constraints on inflationary physics by inferring the tensor-to-scalar ratio r from measurements of cosmic microwave background (CMB) polarization B-modes. Its nominal design including three small-aperture telescopes (SATs) targets a precision σ⁡(r = 0) ≤ 0.003 without delensing. Achieving this goal and further reducing uncertainties requires a thorough understanding and mitigation of other large-scale B-mode sources such as Galactic foregrounds and weak gravitational lensing. We present an analysis pipeline aiming to estimate r by including delensing within a cross-spectral likelihood, and demonstrate it for the first time on SO-like simulations accounting for various levels of foreground complexity, inhomogeneous noise and partial sky coverage. As introduced in an earlier SO delensing paper, lensing B-modes are synthesized using internal CMB lensing reconstructions as well as Planck-like cosmic infrared background maps and LSST-like galaxy density maps. We then extend SO’s power-spectrum-based foreground-cleaning algorithm to include all auto- and cross-spectra between the lensing template and the SAT B-modes in the likelihood function. This allows us to constrain r and the parameters of our foreground model simultaneously. Within this framework, we demonstrate the equivalence of map-based and cross-spectral delensing and use it to motivate an optimized pixel-weighting scheme for power spectrum estimation. We start by validating our pipeline in the simplistic case of uniform foreground spectral energy distributions. In the absence of primordial B-modes, we find that the 1⁢σ statistical uncertainty on r, σ⁡(r), decreases by 37% as a result of delensing. Tensor modes at the level of r = 0.01 are successfully detected by our pipeline. Even when using more realistic foreground models including spatial variations in the dust and synchrotron spectral properties, we obtain unbiased estimates of r both with and without delensing by employing the moment-expansion method. In this case, uncertainties are increased due to the higher number of model parameters, and delensing-related improvements range between 27% and 31%. These results constitute the first realistic assessment of the delensing performance at SO’s nominal sensitivity level.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Identifying Climate Patterns Using Clustering Autoencoder Techniques

Abstract The complexity of growing spatiotemporal resolution of climate simulations produces a variety of climate patterns under different projection scenarios. This paper proposes a new data-driven climate classification workflow via an unsupervised deep learning technique that can dimensionally reduce the vast volume of spatiotemporal numerical climate projection data into a compact representation. We aim to identify distinct zones that capture multiple climate variables as well as their future changes under different climate change scenarios. Our approach leverages convolutional autoencoders combined with k -means clustering (standard autoencoder) and online clustering based on the Sinkhorn–Knopp algorithm (clustering autoencoder) across the conterminous United States (CONUS) to capture unique climate patterns in a data-driven fashion from the Geophysical Fluid Dynamics Laboratory Earth System Model with GOLD component (GFDL-ESM2G). The developed approach compresses 70 years of GFDL-ESM2G simulation at 0.125° spatial resolution across the CONUS under multiple warming scenarios to a lower-dimensional space by a factor of 660 000 and then tested on 150 years of GFDL-ESM2G simulation data. The results show that five climate clusters capture physically reasonable and spatially stable climatological patterns matched to known climate classes defined by human experts. Results also show that using a clustering autoencoder can reduce the computational time for clustering by up to 9.2 times when compared to using a standard autoencoder. Our five unique climate patterns resulting from the deep learning–based clustering of the lower-dimensional space thereby enable us to provide insights on hydrometeorology and its spatial heterogeneity across the conterminous United States immediately without downloading large climate datasets. Significance Statement This paper presents a data-driven climate classification approach using unsupervised deep learning to dimensionally reduce climate model outputs and to identify distinct climate regions for their future changes. Our approach compresses climate information for 70 years of Geophysical Fluid Dynamics Laboratory Earth System Model data across the conterminous United States (CONUS) at 0.125° spatial resolution. The results reveal that five climate clusters capture reasonable and stable climatological patterns matched to known climate patterns. The embedded clustering process in deep learning provides ×9.2 times faster execution than the k -means clustering technique. These results give us insight about climate spatial patterns and heterogeneity of hydrological patterns across the conterminous United States without downloading large climate datasets.

Kurihana, Takuya↗
DOE OSTI2024

High-Fidelity and High-Performance Computational Simulations for Rapid Design Optimization of Sulfur Thermal Energy Storage (CRADA Report)

NREL and Element 16 collaborated on sulfur thermal energy storage modeling using NREL’s high performance computing (HPC) resources to assist its application in industrial processes. Industrial process heat (IPH) accounts for ~70% of US manufacturing energy use and is primarily produced by fossil fuel combustion. Approximately, 1500 TWht (~60% Terawatt hour thermal) of IPH demand is in the temperature range of 100-300°C. Industrial applications in this temperature range include drying, hydrothermal processing, thermal enhanced oil recovery, food and beverage, bioethanol production, etc. Cost-effective thermal energy storage (TES) that increases the utilization of waste and renewable heat (solar, geothermal, etc.) could provide significant energy savings and reliable heat sources, decrease emissions, and increase US manufacturing competitiveness through reductions in fuel consumption. This HPC4EI project facilitated Element 16’s development of low-cost and high-impact molten sulfur TES for dispatchable IPH. The development of a high-fidelity model validated by experimental data and HPC simulations enabled the successful resolution of the complex interplay between fluid dynamics and heat transfer processes during transient operation of sulfur TES, overcoming the numerical challenges posed by the non-linear temperature-dependent physical properties of sulfur. The project helped accelerate Element 16’s molten sulfur TES product design and support its broad applications.

25 ENERGY STORAGE↗
DOE OSTI2025

Replace Human Intelligence with Fast and Smart Geometric Reasoning and Graph Neural Network to Accelerate Next Gen ModSim Workflows

We present an agent-guided approach to CAD geometry decomposition that automates hex/hybrid meshing with graph neural networks (GNNs) to accelerate next-generation ModSim workflows. Our end-to-end pipeline (i) reduces 3D boundary-representation (B-Rep) models to a 2D chordal axis skeleton (CAT) and then to a 1D bipartite graph of surface and curve nodes, (ii) assigns per node labels as Cubit® WebCut actions, (iii) trains a multi-action GNN under supervised learning, and (iv) predicts five surface-node and three curve-node actions on out-of-distribution test geometries. Each graph node carries geometric, topological, and meshing attributes drawn from the B-Rep “skin” and CAT “skeleton,” with two-way mappings across 3D↔2D↔1D representations to maintain traceability back to 3D CAD. The supervised learning model exhibits stable convergence of the binary cross-entropy loss and achieves 98.7% accuracy on unseen lattice models. To operationalize decision-making, we rank predicted commands by geometric significance and prototyped the agent-guided workflow through the Cubit® Meshing PowerTool GUI. As a stretch goal, we explore reinforcement learning (RL) to reduce or remove label requirements and to learn policies for action sequences that maximize total reward (e.g., size of hex-meshable regions and resulting hex mesh quality). When all-hex meshing is not feasible, the agent assists in producing hybrid meshes—prioritizing hex in critical regions and transitioning to tetrahedral elements (tets) elsewhere—maintaining fidelity while ensuring robustness. The overarching objective is to replace manual, heuristics-based decomposition with data-driven, reproducible automation, cutting meshing turnaround time by orders of magnitude. We anticipate direct impact on simulation workflows through intelligent, scalable decomposition of complex CAD models into hex-meshable subdomains.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Evaluation of Best Practices in Mitigating Startup Costs on Leadership-Class Supercomputers

Supercomputers at Department of Energy (DOE) National Laboratories face a widening range of workloads, from traditional modeling and simulation to Artificial Intelligence model training or complex multi-stage workflows, and beyond. At DOE Leadership Computing Facilities like the Oak Ridge Leadership Computing Facility (OLCF), these workloads demand concurrent access to large portions of the supercomputer’s resources. Launching a job across massive supercomputers is challenging from the start; the file system struggles with a large backlog of metadata requests as tens of thousands of processes read thousands of the same files, and the compute job cannot start until this is completed. There are multiple existing approaches to calm this metadata storm, ranging from vendor-developed tools like sbcast to National Laboratory-developed tools like Spindle and Copper. In this paper, we benchmark and discuss three common approaches to improving compute job launch latencies on Frontier: Slurm’s sbcast tool, Spindle, and Copper. We evaluate these tools by measuring the launch latencies of four workloads: OSU Microbenchmark’s osu_init, Pynamic, Python import mpi4py, and Python import torch. We provide discussion of the results, highlighting data that meet expectations and that do not meet expectations.

Hagerty, Nick [ORNL] (ORCID:0000000330014414)↗
DOE OSTI2025

Latent space mapping: Revolutionizing predictive models for divertor plasma detachment control

The inherent complexity of boundary plasma, characterized by multi-scale and multi-physics challenges, has historically restricted high-fidelity simulations to scientific research due to their intensive computational demands. Consequently, routine applications such as discharge control and scenario development have relied on faster but less accurate empirical methods. This work introduces DivControlNN, a novel machine-learning-based surrogate model designed to address these limitations by enabling quasi-real-time predictions (i.e., ~ 0.2 ms) of boundary and divertor plasma behavior. Trained on over 70,000 2D UEDGE simulations from KSTAR tokamak equilibria, DivControlNN employs latent space mapping to efficiently represent complex divertor plasma states, achieving a computational speed-up of over 10 8 compared to traditional simulations while maintaining a relative error below 20% for key plasma property predictions. During the 2024 KSTAR experimental campaign, a prototype detachment control system powered by DivControlNN successfully demonstrated detachment control on its first attempt, even for a new tungsten divertor configuration and without any fine-tuning. These results highlight the transformative potential of DivControlNN in overcoming diagnostic challenges in future fusion reactors by providing fast, robust, and reliable predictions for advanced integrated control systems.

Artificial neural networks↗