Search NASA⌕ Search

SEARCH · Search NASA

Results for “neural operator learning”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 217 records · Page 12
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Machine Learning Algorithms for Aerosol and Cloud Detection Using CATS on the ISS

Clouds and aerosols are one of the largest uncertainties in understanding and forecasting the Earth’s changing climate system. The type and height of aerosols are important factors in determining the top-of-atmosphere (TOA) radiation budget, either direct reflection of solar radiation back to space and/or absorption of solar radiation. In addition to their impact on the Earth’s climate system, aerosols near the surface from wildfires, man-made pollution events, and dust storms are hazardous to human health. The phase and height of clouds also play a critical role in determining the role of clouds in the Earth’s climate system. Cirrus clouds in the upper troposphere can induce a significant daytime TOA warming effect, while liquid water clouds near the surface cause a large corresponding cooling effect. Lidar measurements provide accurate vertically resolved information about clouds and aerosols, including complex multi-layer scenes where passive sensors are challenged and at night, when passive sensors are unable to measure cloud and aerosol properties. The Cloud-Aerosol Transport System (CATS) is a lidar instrument that operated for 33 months on the International Space Station (ISS) at the 1064 nm wavelength to measure attenuated total backscatter and depolarization ratio. These fundamental measurements are used to derive “vertical feature mask” cloud and aerosol products, including layer top/base heights, layer geometrical thickness, aerosol type, and cloud phase. While space-based lidar systems like CATS provide cloud and aerosol vertical distributions that improve our understanding of the climate system, averaging of the daytime data from these sensors is required, at the expense of spatial resolution, to improve the daytime signal-to noise (SNR) and thus atmospheric layer detection. This presentation shows results from machine learning (ML) techniques that, when applied to CATS data: 1. improve the 1064 nm SNR 2. enable detection of atmospheric features during daytime with a horizontal resolution of 350 m or 5 km (compared to the 60 km required for standard CATS data products) 3. increase the number of atmospheric layers detected in the CATS data. A Convolutional Neural Network (CNN) trained using CATS standard data products also demonstrated the potential for improved cloud-aerosol discrimination, cloud phase, and aerosol typing compared to the operational CATS algorithms for cloud edges and complex near-surface scenes during daytime. The ML tools described in this paper can facilitate the development of smaller, low-cost lidar systems in the future and enable real-time accessibility of lidar data products from future lidar systems for monitoring and forecasting of hazardous events.

John Yorks↗
DOE OSTI2026

Detection and imaging of chemicals and hidden explosives using terahertz time-domain spectroscopy and deep learning

Detecting concealed chemicals and explosives remains a critical challenge in global security. Terahertz time-domain spectroscopy (THz-TDS) offers a promising non-invasive and stand-off detection technique owing to its ability to penetrate optically opaque materials without causing ionization damage. While many chemicals exhibit distinct spectral features in the terahertz range, conventional terahertz-based detection methods often struggle in real-world environments, where variations in sample geometry, thickness, and packaging can lead to inconsistent spectral responses. In this study, we present a chemical imaging system that integrates THz-TDS with deep learning to enable accurate pixel-level identification and classification of different explosives. Operating in reflection mode and enhanced with plasmonic nanoantenna arrays, our THz-TDS system achieves a peak dynamic range of 96 dB and a detection bandwidth of 4.5 THz, supporting practical, stand-off operation. By analyzing individual time-domain pulses with deep neural networks, the system exhibits strong resilience to environmental variations and sample inconsistencies. Blind testing across eight chemicals—including pharmaceutical excipients and explosive compounds—resulted in an average classification accuracy of 99.42% at the pixel level. Notably, the system maintained an average accuracy of 88.83% when detecting explosives concealed under opaque paper coverings, demonstrating its robust generalization capability. These results highlight the potential of combining advanced terahertz spectroscopy with neural networks for highly sensitive and specific chemical and explosive detection in diverse and operationally relevant scenarios.

Imaging and sensing↗
NASA NTRSDate not supplied

Enabling Interoperability in Earth System Digital Twins (ESDT): Integrating Observations, Models, and AI for Actionable Insights Through NASA'S Intelligent Systems Technology Program

NASA’s Intelligent Systems Technology Program (IST) is driving a paradigm shift in Earth science through the development of Earth System Digital Twins (ESDT). These integrated information systems create a dynamic "digital replica" of the Earth by harmonizing continuous, multi-source observations with high-fidelity models and state-of-the-art artificial intelligence (AI) that enable “What now?”, “What next?”, and “What if?” scenario building. These scenarios are reflected in NASA IST’s series of ESDTs, from the Coastal Zone Digital Twin that integrates complex data on the current state of the Chesapeake Bay to the Terrestrial Environmental Rapid-Replication and Assimilation Hydrometeorological (TerraHydro) AI-based ESDT that forecasts water movement across Earth’s surface, to the Agriculture Land Information System (AgLIS) which can be used to assess optimal planting dates and crop yield estimates. By bridging the gap between vast data archives and actionable insights, these projects enable a system-of-systems approach to understanding complex, interacting Earth processes. This poster will highlight recent innovations and future directions from NASA’s ESDT initiatives: Continuous Data Assimilation & Multi-Source Fusion. A core requirement of the ESDT work is the transition from static models to dynamic "living" replicas. This involves creating frameworks for the continual assimilation of near-real-time data from uncoordinated, heterogeneous sources, including satellite observations and airborne assets, and ground-based Internet of Things (IoT) sensors. These systems link design, operational status, and environmental data, ensuring the digital twin accurately reflects the current state of the physical Earth system. High-Fidelity Hybrid Modeling & Computational Acceleration to enable interactive "what-if" explorations, programs are moving beyond traditional, slow physical solvers by developing fast surrogate machine learning models and Deep Generative Models (DGMs). These hybrid approaches use neural networks to emulate complex physics, such as cloud feedback or ocean dynamics, at a fraction of the original computing cost, often leveraging advanced hardware like Graphics Processing Units (GPUs) to achieve the necessary scale. Federated Ecosystems & Interoperable Frameworks rather than building isolated tools, NASA IST is moving toward federated ESDTs and reusable analytic collaborative frameworks. This theme focuses on interoperability standards and common ontologies that allow specialized digital twins to interact and share data. This system-of-systems architecture supports multi-discipline investigations, such as analyzing how upstream watershed changes impact downstream urban flooding or how wildfire emissions affect regional air quality. By leveraging these advancements, ESDTs empower researchers and decision-makers to conduct real-time analysis and run complex hypothetical scenarios, ultimately improving our understanding of Earth’s evolving systems and informing critical real-world applications.

Earth System↗
DOE OSTI2024

D2NO: Efficient handling of heterogeneous input function spaces with distributed deep neural operators

Neural operators have been applied in various scientific fields, such as solving parametric partial differential equations, dynamical systems with control, and inverse problems. However, challenges arise when dealing with input functions that exhibit heterogeneous properties, requiring multiple sensors to handle functions with minimal regularity. To address this issue, discretization-invariant neural operators have been used, allowing the sampling of diverse input functions with different sensor locations. However, existing frameworks still require an equal number of sensors for all functions. We propose a novel distributed approach to further relax the discretization requirements and solve the heterogeneous dataset challenges. Our method involves partitioning the input function space and processing individual input functions using independent and separate neural networks. A centralized neural network is used to handle shared information across all output functions. This distributed methodology reduces the number of gradient descent back-propagation steps, improving efficiency while maintaining accuracy. Here, we demonstrate that the corresponding neural network is a universal approximator of continuous nonlinear operators and present three numerical examples to validate its performance.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Introduction: Neuromorphic Materials

The explosive growth in data collection and the need to process it efficiently, as well as the desire to automate increasingly complex tasks in transportation, medical care, manufacturing, security and many other fields have motivated a growing interest in neuromorphic computing. Unlike the binary, transistorbased ON/OFF logic gates and separate logic and memory functionalities employed in digital computing, neuromorphic computing is inspired by animal brains that use interconnected synapses and neurons to perform processing, storage and transmission of information at the same location, while only consuming ~20 W or less of power. Motivated by the brain’s efficiency, adaptability, self-learning and resiliency qualities, neuromorphic computing can be broadly defined as an approach to processing and storing information using hardware and algorithms inspired by models of biological neural systems. Present research in neuromorphic computing encompasses approaches that vary significantly in their degree of neuro-inspiration, from systems that only incorporate features such as asynchronous, event-driven operation or use crossbar arrays of non-volatile memory (NVM) elements to accelerate deep neural networks (DNNs), to designs that embrace the extreme parallelism, sparsity, reconfigurability, adaptability, complexity and stochasticity observed in nervous systems. The term ‘neuromorphic’ computing is often credited to Carver Mead, who in the 1980s investigated Si-based analog electronics to replicate functions of the animal retina. Earlier important advances in this field include the work of Frank Rosenblatt, who proposed the concept of the perceptron, Bernard Widrow, who used this concept to build one of the first analog neural networks, the Adaline and many other researchers (see ref. 6 for an historical perspective on neuromorphic computing). With the recent increase in the use of artificial intelligence and large language models, and rising concerns over the associated energy costs, interest in neuromorphic hardware has expanded rapidly. According to some estimates, driven largely by the drastic growth in the training use of artificial intelligence (AI) models using the current computing architectures, the energy cost of computing is projected to reach the energy supply worldwide by 2045. Furthermore, while this is not a realistic outcome, it means that, if more efficient computing technologies are not developed -- soon -- the world will soon become one where demand for energy and market constraints limit the continued increase of societal access to AI and cloud services from data centers. Data centers used for training and use of these models consume hundreds of terawatt hours of electricity, already past 4% of the US electricity demand.

Circuits↗
DOE OSTI2024

Evaluating the Use of Foundational Chemical Language Models in Multimodal Graph Fusion

Rapid and accurate prediction of the physicochemical properties of molecules given their structures remains a key challenge in cheminformatics. Machine learning approaches offer high-throughput options, but the optimality of inductive biases and data representations are up for debate. For example, BERT-based masked language models (MLMs) can be trained in a self-supervised way on hundreds of millions to billions of readily available SMILES strings. Another option is graph neural networks (GNNs), which can operate directly on molecular structures. Yet, generating accurate molecular geometry is computationally expensive, leading to a relative scarcity in data compared to SMILES strings. It is attractive to combine these two paradigms by pre-training an LM on a large corpus of SMILES strings and embedding these representation into a geometric graph neural network. Despite the promise of such an approach, and contrary to previous studies, we find mixed results with the combination of the LMs and GNNs on several molecule datasets. In particular, we found evidence for improvement on the FreeSolv and QM7 benchmarks, but degraded performance on the ESOL, LIPO and QM9 datasets compared to a GNN baseline.

Francel, Collin [University of Alabama]↗
DOE OSTI2025

Deep-learning-enhanced assessment of wellbore barrier effectiveness in geologic storage systems with intermediate aquifers

For geologic systems where carbon dioxide (CO 2 ) is injected underground, existing wells represent potential pathways for fluid migration. Here, this study introduces a novel deep learning model to quantify the likelihood and potential magnitude of fluid migration through wellbores at sites with intermediate aquifers or thief zones between the injection units and underground drinking water sources. Synthetic datasets, generated using reservoir simulations, captured a wide range of subsurface conditions, well attributes, operational parameters, and fluid migration scenarios. Among the regression models developed to predict brine and CO 2 leakage rates and CO 2 saturations along leaky wellbores, convolutional neural network (CNN) outperformed both Light Gradient Boosting Machine and deep neural network. Additionally, a CNN-based classification model was created to predict whether brine and CO 2 would leak along a wellbore, further improving performance over regression alone. The best models were integrated into the National Risk Assessment Partnership Open-source Integrated Assessment Model for rapid, stochastic assessment of storage system containment and leakage risks. A case study demonstrated the model’s ability to simulate fluid migration through existing wells with multiple intermediate aquifers. This computationally efficient wellbore model offers value in support of site performance evaluation and risk-informed decision making by stakeholders.

CO2 leakage↗
DOE OSTI2024

Comparative study of machine learning techniques for post-combustion carbon capture systems

Computational analysis of countercurrent flows in packed absorption columns, often used in solvent-based post-combustion carbon capture systems (CCSs), is challenging. Typically, computational fluid dynamics (CFD) approaches are used to simulate the interactions between a solvent, gas, and column's packing geometry while accounting for the thermodynamics, kinetics, heat, and mass transfer effects of the absorption process. These simulations can then be used explain a column's hydrodynamic characteristics and evaluate its CO 2 -capture efficiency. However, these approaches are computationally expensive, making it difficult to evaluate numerous designs and operating conditions to improve efficiency at industrial scales. In this work, we comprehensively explore the application of statistical ML methods, convolutional neural networks (CNNs), and graph neural networks (GNNs) to aid and accelerate the scale-up and design optimization of solvent-based post-combustion CCSs. We apply these methods to CFD datasets of countercurrent flows in absorption columns with structured packings characterized by several geometric parameters. We train models to use these parameters, inlet velocity conditions, and other model-specific representations of the column to estimate key determinants of CO 2 -capture efficiency without having to simulate additional CFD datasets. We also evaluate the impact of different input types on the accuracy and generalizability of each model. We discuss the strengths and limitations of each approach to further elucidate the role of CNNs, GNNs, and other machine learning approaches for CO 2 -capture property prediction and design optimization.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1991

Fuzzy logic in autonomous orbital operations

Fuzzy logic can be used advantageously in autonomous orbital operations that require the capability of handling imprecise measurements from sensors. Several applications are underway to investigate fuzzy logic approaches and develop guidance and control algorithms for autonomous orbital operations. Translational as well as rotational control of a spacecraft have been demonstrated using space shuttle simulations. An approach to a camera tracking system has been developed to support proximity operations and traffic management around the Space Station Freedom. Pattern recognition and object identification algorithms currently under development will become part of this camera system at an appropriate level in the future. A concept to control environment and life support systems for large Lunar based crew quarters is also under development. Investigations in the area of reinforcement learning, utilizing neural networks, combined with a fuzzy logic controller, are planned as a joint project with the Ames Research Center.

Lea, Robert N.↗
NASA NTRS1992

A reinforcement learning-based architecture for fuzzy logic control

This paper introduces a new method for learning to refine a rule-based fuzzy logic controller. A reinforcement learning technique is used in conjunction with a multilayer neural network model of a fuzzy controller. The approximate reasoning based intelligent control (ARIC) architecture proposed here learns by updating its prediction of the physical system's behavior and fine tunes a control knowledge base. Its theory is related to Sutton's temporal difference (TD) method. Because ARIC has the advantage of using the control knowledge of an experienced operator and fine tuning it through the process of learning, it learns faster than systems that train networks from scratch. The approach is applied to a cart-pole balancing system.

Berenji, Hamid R.↗
NASA NTRS2003

Motor System Development Depends on Experience: A Microgravity Study of Rats

Animals move about their environment by sensing their surroundings and making adjustments according to need. All animals take the force of gravity into account when the brain and spinal cord undertake the planning and execution of movements. To what extent must animals learn to factor in the force of gravity when making neural calculations about movement? Are animals born knowing how to respond to gravity, or must the young nervous system learn to enter gravity into the equation? To study this issue, young rats were reared in two different gravitational environments (the one-G of Earth and the microgravity of low Earth orbit) that necessitated two different types of motor operations (movements) for optimal behavior. We inquired whether those portions of the young nervous system involved in movement, the motor system, can adapt to different gravitational levels and, if so, the cellular basis for this phenomenon. We studied two groups of rats that had been raised for 16 days in microgravity (eight or 14 days old at launch) and compared their walking and righting (ability to go from upside down to upright) and brain structure to those of control rats that developed on Earth. Flight rats were easily distinguished from the age-matched ground control rats in terms of both motor function and central nervous system structure. Mature surface righting predominated in control rats on the day of landing (R+O), while immature righting predominated in the flight rats on landing day and 30 days after landing. Some of these changes appear to be permanent. Several conclusions can be drawn from these studies: (1) Many aspects of motor behavior are preprogrammed into the young nervous system. In addition, several aspects of motor behavior are acquired as a function of the interaction of the developing organism and the rearing environment; (2) Widespread neuroanatomical differences between one-G- and microgravity-reared rats indicate that there is a structural basis for the adaptation to the rearing environment. These observations provide support for the idea that an animal's motor system adapts for optimal function within the environment experienced during a critical period in early postnatal life.

Walton, Kerry D.↗
NASA NTRSDate not supplied

Artificial Neural Network (ANN) Surface Longwave and Shortwave Fluxes Trained on CERES Observations

The Clouds and Earth’s Radiant Energy System (CERES) project provides satellite-based observations of the radiative fluxes and clouds systems. CERES climate quality data products typically take several months of calibration and validation before release to the public. The Fast Longwave and Shortwave Radiative Flux (FLASHFlux) data product was developed to provide key data for the applied sciences and educational users within a week of observation. FLASHFlux achieves this by using simplified calibration, an operational meteorological product from Global Modeling and Assimilation Office (GMAO), and its own surface parameterizations model. The CERES FLASHFlux provides two data products: 1) an hourly Level 2 Single Scanner Footprint (SSF) data separately for Terra and NOAA-20 observations, and 2) a daily Level 3 Time Interpolated and Spatially Averaged (TISA) 1o x 1o gridded data that combines Terra and NOAA-20 observations. Currently, FLASHFlux uses the Langley Parameterized Shortwave Algorithm (LPSA) and Langley Parameterized Longwave Algorithm (LPLA) to derive its surface fluxes (Kratz et al., 2010; Gupta et al, 2001). A new Machine Learning (ML) based approach using Artificial Neural Networks to derive Surface Longwave (LW) & Shortwave (SW) fluxes based on training data from the CERES Clouds Radiative Swath (CRS) product is being investigated to replace LPSA and LPLA in the SSF surface flux products. One of the biggest hurdles in training ML model is model fitting. To overcome the problem of overfitting we use feature engineering that helps in finding the important feature and remove features that are irrelevant to the model. In our training we employed the Leave-One-Feature-Out Importance (LOFO) to evaluate the significance of each feature in our training. We intercompare ANN fluxes against surface fluxes produced from the Fu-Liou model in CRS and the LPSA/LPLA in FLASHFlux SSF. Furthermore, we validated ANN derived fluxes to the Baseline Surface Radiation Network (BSRN).

P C Sawaengphokhai↗
DOE OSTI2025

ReSpike: A Co-Design Framework for Evaluating SNNs on ReRAM-Based Neuromorphic Processors

With Moore’s law approaching its end, traditional von Neumann architectures are struggling to keep up with the exceeding performance and memory requirements of artificial intelligence and machine learning algorithms. Unconventional computing approaches such as neuromorphic computing that leverage spiking neural networks (SNNs) to perform computation are gaining traction and seek the paradigm shift necessary to sustain the increasing demands of modern applications. Novel memory technologies, such as resistive RAM (ReRAM), employ a crossbar architecture that possesses the inherent capability of efficiently computing vector-matrix multiplication—a dominant operation in SNNs. The prospect of naturally mapping SNNs to the crossbar structures provides a unique opportunity for achieving a high-performance, power-efficient neuromorphic system. In this work, we present ReSpike, which is a new framework, behavioral simulator, and architectural design based on ReRAM crossbar architectures, enabling modeling and co-design to achieve efficient execution of SNNs. We drive this co-design forward by quantifying the impact that ReRAM cell nonidealities have on the corresponding accuracy of an SNN application.

Asifuzzaman, Kazi [ORNL] (ORCID:0000000240044791)↗
NASA NTRS2005

Upper Torso Control for HOAP-2 Using Neural Networks

Humanoid robots have similar physical builds and motion patterns as humans. Not only does this provide a suitable operating environment for the humanoid but it also opens up many research doors on how humans function. The overall objective is replacing humans operating in unsafe environments. A first target application is assembly of structures for future lunar-planetary bases. The initial development platform is a Fujitsu HOAP-2 humanoid robot. The goal for the project is to demonstrate the capability of a HOAP-2 to autonomously construct a cubic frame using provided tubes and joints. This task will require the robot to identify several items, pick them up, transport them to the build location, then properly assemble the structure. The ability to grasp and assemble the pieces will require improved motor control and the addition of tactile feedback sensors. In recent years, learning-based control is becoming more and more popular; for implementing this method we will be using the Adaptive Neural Fuzzy Inference System (ANFIS). When using neural networks for control, no complex models of the system must be constructed in advance-only input/output relationships are required to model the system.

Sandoval, Steven P.↗
DOE OSTI2024

Initial testing of Alfvén eigenmode feedback control with machine-learning observers on DIII-D

A first of its kind fully data-driven system has been developed and implemented into the DIII-D plasma control system to detect and control Alfvén eigenmodes (AE) in real-time. Susceptibility to fast ion-induced AE is a challenge in fully non-inductive tokamak operation, which significantly reduces fast-particle confinement and results in degraded fusion gain. Controlling AEs in real-time to improve fast-ion confinement is, hence, important for future advanced tokamak fusion reactors. The models were implemented and tested in experiments which showed that neural networks (NN) are highly effective in detecting 5 types of AE (BAE, EAE, LFM, RSAE, TAE) using high resolution ECE. To estimate the neutron deficit, a NN has been trained that outputs the classical neutron rate using similar inputs to NUBEAM. Also a preliminary ML-based proportional control has been designed and gone through initial testing in experiment to use feedback-control on the neutral beam power to achieve desired amplitude of AE modes and neutron deficits. The effect of AEs on fast-ion confinement is measured by analysing the gap in classical neutron rate from the proposed NN-based NUBEAM and the measured neutron rate.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRSDate not supplied

A Machine Learning Approach for the Remote Sensing Retrieval of Oil Spills from Polarimetric Measurements

The Fresnel laws of specular reflection directly connect remote sensing observations of light polarization within the sunglint region to the ocean surface refractive index. This parameter is instrumental to identify areas affected by oil, or any other floating substance capable of modifying the refractive index of pure seawater. In preparation for the NASA Plankton, Aerosol, ocean Ecosystem (PACE) mission, we are developing an advanced retrieval scheme that exploits such measurements to deliver the refractive index as an operational product. The original method was developed based on observations of the airborne Research Scanning Polarimeter. Here we present several aspects related to the extension of this technique to the PACE HARP-2 sensor (especially regarding the projected accuracy), and discuss preliminary results obtained by applying neural-network trainings to look-up tables produced with the forward radiative transfer code, with the goal of improving the computational performance. Success in the final implementation will guarantee a version of the retrieval algorithm suitable to fast-response needs and disaster management.

machine learning↗
DOE OSTI2025

Next-Level Energy Management in Manufacturing: Facility-Level Energy Digital Twin Framework Based on Machine Learning and Automated Data Collection

This research introduces an energy prediction framework at the facility level supported by automated data collection and machine learning models. It investigates whether reducing the prediction time scale allows for applying more complex machine learning techniques and if those techniques improve the prediction accuracy. The primary advantages of this framework lie in its automation of the energy prediction process and its provision of real-time energy data suitable for use in energy dashboards or digital twins. A sitewide dataset was created by combining 15 min energy and daily production data of five shops—assembly, battery, body (electric), body (gas), and paint—from a globally recognized electric vehicle manufacturer. Various machine learning models were evaluated on daily, weekly, and monthly datasets, including, in increasingly complex order: naïve, simple linear regression, net regularized generalized linear regression, principal component regression, k-nearest neighbor, random forest, and Bayesian regularized neural network. Compared to the current state-of-the-art energy consumption prediction for the industrial facility level, this research investigates more complex models and smaller time intervals for higher accuracy. The findings revealed that the more complex monthly models require a minimum of a year and a half of data to operate, while weekly models demand a year of data to achieve improved accuracy. Daily models can operate with only six months of data but exhibit poor performance due to reduced prediction accuracy of production. Key challenges identified include access to reliable, high-quality energy and production data and the initial demand for human labor.

digital twin↗
DOE OSTI2026

HydraGNN_OPF_GFM_2026 - Ensemble of predictive graph foundation models for power grid applications

This dataset supports research on graph foundation models for optimal power flow (OPF) on electric grids using HydraGNN. It contains heterogeneous graph representations of PGLib-OPF cases spanning systems from 14 to 13,659 buses, together with packed HDF5 datasets for pretraining, feasibility classification, and N-1 contingency analysis. The release includes OPF solution data, downstream fine-tuning datasets, pretrained HeteroSAGE and HeteroHEAT model checkpoints, hyperparameter-optimization summaries across multiple heterogeneous GNN architectures, and aggregated fine-tuning results for sample-efficiency studies. The dataset is designed to enable scalable training, evaluation, and transfer-learning studies for OPF surrogate modeling, including node-level AC-OPF solution prediction, graph-level prediction, feasibility classification, operating-condition generalization, and contingency-response tasks.

24 POWER TRANSMISSION AND DISTRIBUTION↗