Search NASA⌕ Search

SEARCH · Search NASA

Results for “NETWORK TECHNOLOGY”

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 1,081 records · Page 60

LDMS-GPU: Lightweight Distributed Metric Service (LDMS) for NVIDIA GPGPUs

GPUs are now a fundamental accelerator for many high-performance computing applications. They are viewed by many as a technology facilitator for the surge in fields like machine learning and Convolutional Neural Networks. To deliver the best performance on a GPU, we need to create monitoring tools to ensure that we optimize the code to get the most performance and efficiency out of a GPU. Since NVIDIA GPUs are currently the most commonly implemented in HPC applications and systems, NVIDIA tools are the solution for performance monitoring. The Light-Weight Distributed Metric System (LDMS) at Sandia is an infrastructure widely adopted for large-scale systems and application monitoring. Sandia has developed CPU application monitoring capability within LDMS. Therefore, we chose to develop a GPU monitoring capability within the same framework. In this report, we discuss the current limitations in the NVIDIA monitoring tools, how we overcame such limitations, and present an overview of the tool we built to monitor GPU performance in LDMS and its capabilities. Also, we discuss our current validation results. Most of the performance counter results are the same in both vendor tools and our tool when using LDMS to collect these results. Furthermore, our tool provides these statistics during the entire runtime of the tool as a time series and not just aggregate statistics at the end of the application run. This allows the user to see the progress of the behavior of the applications during their lifetime.

97 MATHEMATICS AND COMPUTING↗

A Comparison between Invariant and Equivariant Classical and Quantum Graph Neural Networks

Machine learning algorithms are heavily relied on to understand the vast amounts of data from high-energy particle collisions at the CERN Large Hadron Collider (LHC). The data from such collision events can naturally be represented with graph structures. Therefore, deep geometric methods, such as graph neural networks (GNNs), have been leveraged for various data analysis tasks in high-energy physics. One typical task is jet tagging, where jets are viewed as point clouds with distinct features and edge connections between their constituent particles. The increasing size and complexity of the LHC particle datasets, as well as the computational models used for their analysis, have greatly motivated the development of alternative fast and efficient computational paradigms such as quantum computation. In addition, to enhance the validity and robustness of deep networks, we can leverage the fundamental symmetries present in the data through the use of invariant inputs and equivariant layers. In this paper, we provide a fair and comprehensive comparison of classical graph neural networks (GNNs) and equivariant graph neural networks (EGNNs) and their quantum counterparts: quantum graph neural networks (QGNNs) and equivariant quantum graph neural networks (EQGNN). The four architectures were benchmarked on a binary classification task to classify the parton-level particle initiating the jet. Based on their area under the curve (AUC) scores, the quantum networks were found to outperform the classical networks. However, seeing the computational advantage of quantum networks in practice may have to wait for the further development of quantum technology and its associated application programming interfaces (APIs).

Forestano, Roy T. (ORCID:0000000203552076)↗

A Role for Industry in Promoting Nuclear Security and Nonproliferation

Industry has a unique opportunity and critical role to play in strengthening governmental efforts to prevent the spread of nuclear, radiological, and dual-use materials and technologies that could be used in a nuclear or radiological weapon. Governmental regulations and policies are in effect at both the national and international levels to inhibit access to such materials and technologies by illegitimate end-users. However, the discovery of an illegal nuclear network, spearheaded by Pakistani scientist A Q Khan, increased international concern about what more could be done to prevent proliferation. Industry is well-poised and has a strong incentive to take a more proactive role to complement existing governmental efforts. Companies can be a tremendous help in ensuring that illicit diversions do not occur by increasing their oversight over the supply chain.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗

Impact of DER Communication Delay in AGC: Cyber-Physical Dynamic Co-Simulation: Preprint

Distributed energy resource (DER) frequency regulations are promising technologies for future grid operation. Unlike conventional generators, DERs might require open communication networks to exchange signals with control centers, possibly through DER aggregators; therefore, the impacts of the communication variations including the latency on the system frequency stability need to be investigated. This paper develops a cyber-physical dynamic simulation (CPDS) model based on the Hierarchical Engine for Large-Scale Co-Simulation (HELICS) to evaluate the impact of the communication variations, such as delays in DER frequency regulations. The feasible delay range can be obtained under different AGC parameter settings. The results show that the risk of instability generally increases with the communication delay and that the difference of AGC provided from DER and conventional generation units should be recognized when designing frequency regulation controllers.

61 RADIATION PROTECTION AND DOSIMETRY↗

Resilient, Rural, and Revolutionary: Salisbury Square's Direct-Current Affordable Microgrid Community: Preprint

The technology to interconnect buildings with a dedicated direct-current (DC) power distribution network is in place today; what is missing is a turnkey approach to designing a DC microgrid - and the business models allowing such systems to be deployed, owned, and operated at scale. To close this gap, the Salisbury Square Development Team, comprising clean-energy experts, has engineered a resilient community DC microgrid for an affordable housing community in Randolph, Vermont. Ten single-family, occupant-owned residences and 12 multifamily rental units will share locally generated and stored solar energy via a DC power distribution bus capable of operating during extended grid outages. With a DC power distribution network in place, each home will be equipped with high-efficiency DC lighting and appliances, operating alongside alternating current (AC) appliances, even during an islanded mode of operation. To obtain a comprehensive understanding of what is possible and achievable, the Team collaborated with the local utility, regulatory agencies, a national laboratory, energy-as-service providers, and vendors. The collaborators evaluated microgrid typologies, business models, and energy modeling, and analyzed electrification and resilience. Further, the Team applied the URBANoptTM (Urban Renewable Building and Neighborhood optimization, NREL 2022) software development kit (SDK) to Salisbury Square's single-family and multifamily buildings to validate workflows and identify needs for advanced capability. This paper addresses the barriers to entry, scalability, and impact on residents and system ownership. It also examines the analysis that informed the design and engineering of the DC microgrid and the opportunities to streamline the process.

DER↗

Cyber security using multi-threaded architecture data diode at the NBSR - 114

Ongoing upgrades for the control room of the National Bureau of Standards Reactor (NBSR) located at the National Institute of Standards and Technology (NIST) require the ability to collect sensor data from the secured reactor network and transfer to the outside network for trend analysis, while maintaining the security of the reactor network. To accomplish this, a data diode was created to provide a physical barrier that prevents any outside data from reaching the secured reactor network. The hardware of the data diode consists of two embedded computers, running Unix based operating systems, connected by three DB-9 serial cables. The serial cables have been modified so that only two wires, a ground and a transmission line, provide connection between the computers. The data diode relies on a multi-threaded architecture to collect and simultaneously transfer data over three serial connections. A software program, implemented in Java, has been written to request data from the digital recorders installed to monitor the NBSR process instrumentation and transfer that data across the serial connections. The data diode can collect over 1200 data points from multiple digital recorders each second. The collected data can then be stored in a relational database for later analysis. The source codes for the software are available open source on GitHub. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Inverse Design of Photonic Surfaces via High throughput Femtosecond Laser Processing and Tandem Neural Networks

Abstract This work demonstrates a method to design photonic surfaces by combining femtosecond laser processing with the inverse design capabilities of tandem neural networks that directly link laser fabrication parameters to their resulting textured substrate optical properties. High throughput fabrication and characterization platforms are developed that generate a dataset comprising 35280 unique microtextured surfaces on stainless steel with corresponding measured spectral emissivities. The trained model utilizes the nonlinear one‐to‐many mapping between spectral emissivity and laser parameters. Consequently, it generates predominantly novel designs, which reproduce the full range of spectral emissivities (average root‐mean‐squared‐error < 2.5%) using only a compact region of laser parameter space 25 times smaller than what is represented in the training data. Finally, the inverse design model is experimentally validated on a thermophotovoltaic emitter design application. By synergizing laser‐matter interactions with neural network capabilities, the approach offers insights into accelerating the discovery of photonic surfaces, advancing energy harvesting technologies.

36 MATERIALS SCIENCE↗

Neural network approximation of Bayesian models for the inference of ion and electron temperature profiles at W7-X

Here, we describe a method for training a neural network (NN) to approximate the full model Bayesian inference of plasma profiles from x-ray imaging diagnostic measurements. The modeling is carried out within the Minerva Bayesian modeling framework where models are defined as a set of assumptions, prior beliefs on parameter values and physics knowledge. The goal is to use NNs for fast ion and electron temperature profile inversion from measured image data. The NN is trained solely on artificial data generated by sampling from the joint distribution of the free parameters and model predictions. The training is carried out in such a way that the mapping learned by the network constitutes an approximation of the full model Bayesian inference. The analysis is carried out on images constituted of 20 × 195 pixels corresponding to binned lines of sight and spectral channels, respectively. Through the full model inference, it is possible to infer electron and ion temperature profiles as well as impurity density profiles. When the network is utilized for the inference of the temperature profiles, the analysis time can be reduced down to a few tens of microseconds for a single time point, which is a drastic improvement if compared to the ≈4 h long Bayesian inference. The procedure developed for the generation of the training set does not rely on diagnostic-specific features, and therefore it is in principle applicable to any other model developed within the Minerva framework. The trained NN has been tested on data collected during the first operational campaign at W7-X, and compared to the full model Bayesian inference results.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Exploring the mobility and energy implications of shared versus private autonomous vehicles

The prevailing trend toward greater automation and connectivity requires modeling and analysis tools to explore connectivity, automation, decision science and other future mobility issues at multiple scales. This paper describes various modeling efforts in order to model the mobility and energy impact of autonomous and connected technologies; design of scenarios under different technological, behavioral, and socioeconomic assumptions; and finally, key findings from the scenario runs enabled by the advanced models developed. The integrated ABM-DTA software POLARIS has been extended to include transit, intra-household vehicle sharing, transportation network company (TNC) operations along with updates to the mesoscopic traffic models and value of time adjustments due to new technologies affecting the mode, destination, and route choice. The three scenarios are summarized as high sharing - low automation, high sharing - high automation, and low sharing - high automation, with VMT changes ranging from -13% to 42%.

Multi-autonomous Vehicle Studies, Models, Techniqu↗

Design and Challenges of Edge Computing ASICs on Front-End Electronics

In situ or hardware-embedded data processing of raw signals, close to their source, in radiation detectors is expected to provide dramatic improvements in data quality and volumes. However, the implementation of artificial neural networks (ANNs) in the front-end electronics, and the design of custom integrated circuits (ASICs), comes with challenges. In addition, detectors have to operate with limited power budget and implement complex functionalities in a very dense space. They often are exposed to extreme conditions as they work in high-radiation environments and/or cryogenic temperatures. This paper presents examples of applications and design methodologies for in-situ ANNs, along with the challenges of retaining the fidelity of the trained networks. For illustration, we use the problem of estimating the energy deposited by the radiation from digitized waveforms. The proposed implementation starts with an ML algorithm trained in Qkeras and eventually leads to an equivalent ASIC implementation. The associated design challenges in realizing energy and area efficient implementations in CMOS processes are reviewed. Novel approaches that employ hybrid technologies (combination of CMOS with memristors), in-memory computing models, and bio-inspired spiking neural networks are also highlighted

47 OTHER INSTRUMENTATION↗

Deterministic Discrete Fracture Network (DFN) Model for the EGS Collab Project on the 4850 Level of the Sanford Underground Research Facility (SURF)

The EGS Collab is conducting hydraulic fracture stimulation and fluid circulation experiments in the Sanford Underground Research Facility (SURF) located in Lead, South Dakota. A total of eight ~60m-long subhorizontal boreholes were drilled from the 4850 Level (~1.5 km below the ground surface) into the crystalline rock of this former mine. Six of these holes are used for geophysical monitoring, one is used for hydraulic fracture stimulation, and the remaining hole was designed as a production borehole that receives water from the injection well via the induced and natural fracture system. The primary goal of creating the discrete fracture network model is to show that these modeling methods are critical for the development of enhanced geothermal systems (EGS). This includes the prediction of rock behavior during fracturing and during an extended period of water flow between the parallel injection and production boreholes. Understanding the results from the induced fracturing and flow is complicated by the presence of significant natural fractures that interact with the stimulation and/or flow pathways. The delineation and characterization of natural fractures is thus an important part of the project, and therefore a model of the Discrete Fracture Network (DFN) was developed on a deterministic basis. The DFN was populated using observations and interpretations integrated from drift (horizontal passageways that allow access in the underground) fracture mapping, analysis of core recovered from the eight boreholes, borehole televiewer logs and videos, and observations of flow between and within boreholes and in the drift. The natural fracture system is dominated by a pervasive northwest-trending, steeply dipping shear system that is identifiable in the drifts and the core. Hydraulic fracture stimulation, flow/tracer circulation tests, and geophysical monitoring revealed that the behavior of the injected water, and perhaps the growth of induced fractures, has been significantly influenced by the existing fractures identified in the DFN.

40 EE - Geothermal Technologies Office (EE-4G)↗

Data-driven profile prediction for DIII-D

A new, fully data-driven algorithm has been developed that uses neural networks to predict plasma pro les on a scale of τ E into the future given actuators and the present plasma state. The model was trained and tested on DIII-D data from the 2013-2018 experimental campaigns. The model is accurate on average, with q predictions the worst and pressure predictions the best. The model can run in milliseconds and is very simple to use. This makes it a potentially useful tool for operators and physicists when planning plasma scenarios. It also is a candidate for doing phase-space exploration without going through the DIIID database or complicated and computationally expensive simulation codes. Here, a reduced model using only realtime diagnostics has also been developed and formed the basis for a model-predictive control algorithm implemented and successfully tested on DIII-D.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Development of Thermoacoustic Sensors for Sodium-cooled Fast Reactors

This Final Report refers to the project “Development of Thermoacoustic Sensors for Sodium-cooled Fast Reactor Systems”, which was led by Westinghouse Electric Company (Westinghouse) and carried out in collaboration with Argonne National Laboratory (ANL) and University of Pittsburgh. Thermo-acoustic Power Sensors (TAPS) are self-powered, wireless sensors envisioned for measuring key parameters, such as local temperature and neutron flux, in a nuclear reactor core. This project was intended to specifically investigate their applicability to Sodium-cooled Fast Reactors (SFR). TAPS are non-invasive (wireless) and passive (self-powered) devices. The passivity derives from their ability to use conditions that “naturally” exist in a nuclear reactor, such as gamma and neutron flux, as power sources. They generate oscillating pressure waves (i.e., sound waves) which, with a frequency and amplitude dependent upon these conditions, can travel through the core and associated structures, and reach the outside of the reactor vessel where a properly designed network of receivers can detect and interpret them. These receivers require a very small amount of power which, during loss of power events, can be provided for example by harvesting gamma radiation energy, thus resulting in a monitoring system that can function both during normal operation and during loss of power events. The project aimed at TAPS development through a series of tasks which are listed and briefly discussed as follows. TASK 1 – Sensor hardware design Subtask 1a: Assessment of sensor applications to SFRs Subtask 1b: Development of sensor functional requirements Subtask 1c: Definition of sensor hardware design specifications Task description: TAPS design was informed by considerations on their application (Subtask 1a), both the ultimate one in an SFR and the actual one in the ANL testing facilities that was intended to be used in support of the project. Considerations were made to identify optimum sensor design features that optimize the sensor size, materials, and output signal, for installation inside an SFR core. These considerations led to the development of Functional Requirements (Subtask 1b) and Design Requirements (Subtask 1c). TASK 2 – Sensor Hardware Manufacture Subtask 2a: Sensor hardware construction drawing development Subtask 2b: Sensor manufacture and assembly Task description: TAPS technical drawings were developed (Subtask 2a) using the Design Requirements established under Task 1. Subsequently, in spite of some problems which ultimately caused the program to be delayed, TAPS manufacturing was completed based on drawings (Subtask 2b). TASK 3 – Development of TAPS Signal Measurement System and TAPS Testing in Water Subtask 3a: Design, assembly and testing of signal measurement system, and TAPS testing in water Subtask 3b: Signal prediction-correction methodology development Task description: An assessment was performed on the techniques that can potentially be used to detect the signals emitted by the TAPS, e.g. a fiber-optic based acoustic signal measurement system, a laser vibrometer system, or an accelerometer-based system. The most suited technology, i.e. the accelerometer-based system, was developed further, and tested in water (Subtask 3a). Moreover, efforts were made to develop the methodology required to determine the actual system temperature and neutron flux distribution using differences between the measured and predicted TAPS responses (Subtask 3b). TASK 4 – Sensor System Testing in Sodium Subtask 4a: Test plan development Subtask 4b: Design, assembly and testing in small-scale sodium facility Subtask 4c: Design, assembly and testing in large-scale sodium and structures facility Task description: Upon proper test plan development (Subtask 4a), the fabricated TAPS was planned to be tested in sodium, by using two sodium facilities at ANL having different size and different purpose. The Under Sodium Viewing (USV) small-scale facility was intended to be used to investigate the effect of sodium on the sensor and its performance (Subtask 4b). The Mechanism Engineering Test Loop (METL) large-scale facility was instead intended to be used to assess the additional effect of prototypical SFR structures, such as fuel assembly mockup or parts of the core restrain structure, on sensor performance (Subtask 4c). As discussed in Section 3.2.2.7, unexpected issues during the TAPS manufacturing process resulted in some activities being delayed, with the TAPS and USV facility developed to the point to be ready for testing in sodium, however without the possibility to actually perform such testing (including the testing in METL) due to the end of the program’s performance period. Overall, through the development and testing (in water only) of two TAPS devices (a First-Generation TAPS followed by an optimized Second-Generation TAPS), the project confirmed the capability of this technology to generate acoustic signals proportional to temperature, which can be detected through a network of accelerometers identified as the best-suited type of receivers for acoustic signal detection. Moreover, the project also developed a computational model to predict the characteristics of the acoustic signals being generated, which combines thermal analysis of the TAPS with Finite Element Modeling (FEM)-aided acoustic characterization of the system. This model was benchmarked against experimental data collected during the project and, although general agreement was obtained, some limitations of the modeling methods were identified, which require additional development. Additional testing is needed in order to assess the effect, on TAPS operation and performance, of environmental changes resulting from the transition from water to liquid sodium. Such testing, which is suggested to be performed in the future, should look specifically at 1) both the effect resulting from the different thermoacoustic behavior of sodium (relative to water) and the effects of higher temperature on TAPS performance, and 2) the performance of the sensor-receiver system when multiple TAPS are used simultaneously and prototypical reactor structures are positioned in the testing environment. The latter testing is needed to assess the effects that potential signal attenuation/ distortion phenomena, as well as potential interference between signals emitted simultaneously, have on the performance of the technology for ultimate application in a nuclear reactor.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Development of a neural network technique for KSTAR Thomson scattering diagnostics

Neural networks provide powerful approaches of dealing with nonlinear data and have been successfully applied to fusion plasma diagnostics and control systems. Controlling tokamak plasmas in real time is essential to measure the plasma parameters in situ. However, the χ{sup 2} method traditionally used in Thomson scattering diagnostics hampers real-time measurement due to the complexity of the calculations involved. In this study, we applied a neural network approach to Thomson scattering diagnostics in order to calculate the electron temperature, comparing the results to those obtained with the χ{sup 2} method. The best results were obtained for 10{sup 3} training cycles and eight nodes in the hidden layer. Our neural network approach shows good agreement with the χ{sup 2} method and performs the calculation twenty times faster.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DeepShadows: Separating low surface brightness galaxies from artifacts using deep learning

Searches for low-surface-brightness galaxies (LSBGs) in galaxy surveys are plagued by the presence of a large number of artifacts (e.g., objects blended in the diffuse light from stars and galaxies, Galactic cirrus, star-forming regions in the arms of spiral galaxies, etc.) that have to be rejected through time consuming visual inspection. In future surveys, which are expected to collect hundreds of petabytes of data and detect billions of objects, such an approach will not be feasible. We investigate the use of convolutional neural networks (CNNs) for the problem of separating LSBGs from artifacts in survey images. We take advantage of the fact that we have available a large number of labeled LSBGs and artifacts from the Dark Energy Survey, that we use to train, validate, and test a CNN model. That model, which we call DeepShadows , achieves a test accuracy of 92.0%, a significant improvement relative to feature-based machine learning models. We also study the ability to use transfer learning to adapt this model to classify objects from the deeper Hyper-Suprime-Cam survey, and we show that after the model is retrained on a very small sample from the new survey, it can reach an accuracy of 87.6%. Finally, these results demonstrate that CNNs offer a very promising path in the quest to study the low-surface-brightness universe.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Decoupling Power Quality Issues in Grid-Microgrid Network Using Microgrid Building Blocks

Microgrids are evolving as promising options to enhance reliability of the connected transmission and distribution systems. Traditional design and deployment of microgrids require significant engineering analysis. However, Microgrid Building Blocks (MBB), consisting of modular blocks that integrate seamlessly to form effective microgrids, are promising technologies to enable faster and broader adoption of microgrids. Back-to-Back converter placed at the point of common coupling of microgrid is an integral part of MBB. This paper presents applications of MBB to decouple power quality issues in grid-microgrid network serving power quality sensitive critical loads such as data centers, new grid-edge technologies such as vehicle-to-grid generation, and emergency condition loads such as electric vehicle charging loads during evacuation prior disaster events. Simulation results show that MBB effectively decouple the power quality issues across networks and allow network with low power quality to transfer high-power quality power to connected networks during emergency conditions.

Acharya, Samrat S. [BATTELLE (PACIFIC NW LAB)]↗

Advanced Solar and Load Forecasting Incorporating HD Sky Imaging (Phase III)

Due to rapidly changing sky conditions, the available solar irradiance for energy generation is subject to wide swings in amplitude. As the market penetration of solar energy continues to increase rapidly, these variations in solar power generation are beginning to have an impact on grid stability and increased wear on power switches. Solar power forecasting plays a critical role in operations for Independent System Operators (ISOs) and utilities. Accurate forecasts help maintain grid reliability, optimize generation from renewables, and reduce operating costs. Of particular interest to the ISOs and utilities are sudden changes in solar irradiance, termed “ramp events,” due to the movement of clouds. One significant impact of ramp events on the grid is additional ancillary service requirements necessary to manage such variability. Ramp events can also cause voltage fluctuations in the distribution grids and trigger actions of automated line equipment (e.g., tap changers), leading to additional maintenance costs. In high penetration solar regions, forecasts must be made for both transmission-connected and distribution-connected resources – either behind the meter or in front of it. Particularly for distributed solar energy resources, forecasting can be a challenge due to the lack of visibility of the energy resource. Brookhaven National Laboratory (BNL) has been working towards nowcasting Global Horizontal Irradiance (GHI) using low-cost technologies for several years now. The Solar NowCasting technology being developed by BNL is a 0 – 30 min solar “nowcasting” technology applicable to a scale covering both large generating facilities and residential, distributed solar installations that relies on a network of ground-based high-definition (HD) cameras and surface pyranometers. GHI forecasts are being produced for both regions using 8 ground-based HD cameras and at least 2 surface pyranometers. When stitched together, the camera images can be used to forecast the impact of clouds on available solar irradiance over a domain of ~50 km 2 . Phase I of the project was the engineering scale up conceptual design stage. Phase II was the initial field test and demonstration, in which the technology was scaled up by a factor of 20 times and successfully demonstrated in eastern Long Island. In Phase III, an additional forecasting network was added in upstate NY and both networks are currently being operated until at least a full year of data is gathered by the Albany network to allow for the collection of sufficient data to evaluate performance against the persistence and smart persistence models using the Solar Arbiter.

14 SOLAR ENERGY↗

EFIT-Prime: Probabilistic and physics-constrained reduced-order neural network model for equilibrium reconstruction in DIII-D

We introduce EFIT-Prime, a novel machine learning surrogate model for EFIT (Equilibrium FIT) that integrates probabilistic and physics-informed methodologies to overcome typical limitations associated with deterministic and ad hoc neural network architectures. EFIT-Prime utilizes a neural architecture search-based deep ensemble for robust uncertainty quantification, providing scalable and efficient neural architectures that comprehensively quantify both data and model uncertainties. Physically informed by the Grad–Shafranov equation, EFIT-Prime applies a constraint on the current density J tor and a smoothness constraint on the first derivative of the poloidal flux, ensuring physically plausible solutions. Furthermore, the spatial location of the diagnostics is explicitly incorporated in the inputs to account for their spatial correlation. Extensive evaluations demonstrate EFIT-Prime's accuracy and robustness across diverse scenarios, most notably showing good generalization on negative-triangularity discharges that were excluded from training. Timing studies indicate an ensemble inference time of 15 ms for predicting a new equilibrium, offering the possibility of plasma control in real-time, if the model is optimized for speed.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗