Search NASA⌕ Search

SEARCH · Search NASA

Results for “landscape configuration”

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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Active Learning A Neural Network Model For Gold Clusters & Bulk From Sparse First Principles Training Data

Small metal clusters are of fundamental scientific interest and of tremendous significance in catalysis. These nanoscale clusters display diverse geometries and structural motifs depending on the cluster size; a knowledge of this size-dependent structural motifs and their dynamical evolution has been of longstanding interest. Given the high computational cost of first-principles calculations, molecular modeling and atomistic simulations such as molecular dynamics (MD) has proven to be an important complementary tool to aid this understanding. Classical MD typically employ predefined functional forms which limits their ability to capture such complex size-dependent structural and dynamical transformation. Neural Network (NN) based potentials represent flexible alternatives and in principle, well-trained NN potentials can provide high level of flexibility, transferability and accuracy on-par with the reference model used for training. A major challenge, however, is that NN models are interpolative and requires large quantities (similar to 10 4 or greater) of training data to ensure that the model adequately samples the energy landscape both near and far-from-equilibrium. A highly desirable goal is minimize the number of training data, especially if the underlying reference model is first-principles based and hence expensive. In this work, we introduce an active learning (AL) scheme that trains a NN model on-the-fly with minimal amount of first-principles based training data. Our AL workflow is initiated with a sparse training dataset (similar to 1 to 5 data points) and is updated on-the-fly via a Nested Ensemble Monte Carlo scheme that iteratively queries the energy landscape in regions of failure and updates the training pool to improve the network performance. Using a representative system of gold clusters, we demonstrate that our AL workflow can train a NN with similar to 500 total reference calculations. Using an extensive DFT test set of similar to 1100 configurations, we show that our AL-NN is able to accurately predict both the DFT energies and the forces for clusters of a myriad of different sizes. Our NN predictions are within 30 meV/atom and 40 meV/angstrom of the reference DFT calculations. Moreover, our AL-NN model also adequately captures the various size-dependent structural and dynamical properties of gold clusters in excellent agreement with DFT calculations and available experiments. We finally show that our AL-NN model also captures bulk properties reasonably well, even though they were not included in the training data.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Strategies to Obtain Reliable Energy Landscapes from Embedded Multireference Correlated Wavefunction Methods for Surface Reactions

Embedded correlated wavefunction (ECW) theory is a powerful tool for studying ground- and excited-state reaction mechanisms and associated energetics in heterogeneous catalysis. Several factors are important to obtaining reliable ECW energies, critically the construction of consistent active spaces (ASs) along reaction pathways when using a multireference correlated wavefunction (CW) method that relies on a subset of orbital spaces in the configuration interaction expansion to account for static electron correlation, e.g., complete AS self-consistent field theory, in addition to the adequate partitioning of the system into a cluster and environment, as well as the choice of a suitable basis set and number of states included in excited-state simulations. Here, in this work, we conducted a series of systematic studies to develop best-practice guidelines for ground- and excited-state ECW theory simulations, utilizing the decomposition of NH 3 on Pd(111) as an example. We determine that ECW theory results are relatively insensitive to cluster size, the aug-cc-pVDZ basis set provides an adequate compromise between computational complexity and accuracy, and that a fixed-clean-surface approximation holds well for the derivation of the embedding potential. Additionally, we demonstrate that a merging approach, which involves generating ASs from the molecular fragments at each configuration, is preferable to a creeping approach, which utilizes ASs from adjacent structures as an initial guess, for the generation of consistent potential energy curves involving open-d-shell metal surfaces, and, finally, we show that it is essential to include bands of excited states in their entirety when simulating excited-state reaction pathways.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Multitask Machine Learning of Collective Variables for Enhanced Sampling of Rare Events

Computing accurate reaction rates is a central challenge in computational chemistry and biology because of the high cost of free energy estimation with unbiased molecular dynamics. In this work, a data-driven machine learning algorithm is devised to learn collective variables with a multitask neural network, where a common upstream part reduces the high dimensionality of atomic configurations to a low dimensional latent space and separate downstream parts map the latent space to predictions of basin class labels and potential energies. Here, the resulting latent space is shown to be an effective low-dimensional representation, capturing the reaction progress and guiding effective umbrella sampling to obtain accurate free energy landscapes. This approach is successfully applied to model systems including a 5D Müller Brown model, a 5D three-well model, the alanine dipeptide in vacuum, and an Au(110) surface reconstruction unit reaction. It enables automated dimensionality reduction for energy controlled reactions in complex systems, offers a unified and data-efficient framework that can be trained with limited data, and outperforms single-task learning approaches, including autoencoders.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Production Operations Management System (POMS) for Fermilab Experiments

The Production Operations Management System (POMS) software allows production teams and analysis groups across multiple Fermilab experiments to launch, modify and monitor large scale campaigns of related Monte Carlo or data processing jobs, and currently manages the majority of production computing of experiments at Fermilab.POMS provides a web service interface that enables automated job submission on distributed resources according to customers’ requests, as well as subsequent monitoring of those submissions as well as recovery of failed submissions, debugging and record keeping.POMS interfaces with existing HEP data access, processing, movement and monitoring tools at Fermilab, including Jobsub (for job submission), SAM (for data management), and Landscape (for monitoring), and in combination with them handles the creation of intermediate datasets of files for multistage campaigns.POMS visualizes these campaigns with an interactive GUI interface. An important feature of POMS is a one-to-one connection between the GUI campaign visualizer and a text based representation of the complete campaign configuration. An extensible library of template campaign configurations is available. The templates are user modifiable and map cleanly to and from the GUI description of the campaign.This paper will discuss the current usage, history, and some technical details of POMS, as well as planned future extensions, particularly interfacing with Rucio as well as SAM for file movement.

Mengel, Marc↗
DOE OSTI2021

Patch selection by bumble bees navigating discontinuous landscapes

Pollen and nectar resources are unevenly distributed over space and bees must make routing decisions when navigating patchy resources. Determining the patch selection process used by bees is crucial to understanding bee foraging over discontinuous landscapes. To elucidate this process, we developed four distinct probability models of bee movement where the size and the distance to the patch determined the attractiveness of a patch. A field experiment with a center patch and four peripheral patches of two distinct sizes and distances from the center was set up in two configurations. Empirical transition probabilities from the center to each peripheral patch were obtained at two sites and two years. The best model was identified by comparing observed and predicted transition probabilities, where predicted values were obtained by incorporating the spatial dimensions of the field experiment into each model’s mathematical expression. Bumble bees used both patch size and isolation distance when selecting a patch and could assess the total amount of resources available in a patch. Bumble bees prefer large, nearby patches. This information will facilitate the development of a predictive framework to the study of bee movement and of models that predict the movement of genetically engineered pollen in bee-pollinated crops.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Enabling robust offline active learning for machine learning potentials using simple physics-based priors

Abstract Machine learning surrogate models for quantum mechanical simulations have enabled the field to efficiently and accurately study material and molecular systems. Developed models typically rely on a substantial amount of data to make reliable predictions of the potential energy landscape or careful active learning (AL) and uncertainty estimates. When starting with small datasets, convergence of AL approaches is a major outstanding challenge which has limited most demonstrations to online AL. In this work we demonstrate a Δ-machine learning (ML) approach that enables stable convergence in offline AL strategies by avoiding unphysical configurations with initial datasets as little as a single data point. We demonstrate our framework’s capabilities on a structural relaxation, transition state calculation, and molecular dynamics simulation, with the number of first principle calculations being cut down anywhere from 70%–90%. The approach is incorporated and developed alongside AMP torch , an open-source ML potential package, along with interactive Google Colab notebook examples.

Shuaibi, Muhammed↗
DOE OSTI2024

Shifting Between Compute and Memory Bounds: A Compression-Enabled Roofline Model

In the evolving landscape of high-performance computing, especially to fight the end of Moore’s Law and Dennard’s Scaling, the ability to shift between compute-bound and memory-bound states is critical for enhancing adaptability and flexibility to diverse system and domain-specific architectures. Such capability is vital for optimizing performance across distinguished hardware configurations, such as accelerators, memory hierarchies, and cache systems. Despite that ad hoc optimization techniques, such as compressed/approximate computation, have been enabled for compute-/data-intensive computing for improved performance in distinct hardware settings, there lacks an understanding of 1) the rational behind performance improvement; 2) capability of different optimizations; 3) what optimization to respond to specific computational and memory demands. This work proposes a compression-enabled roofline model to facilitate this adaptability with data compression techniques to balance and transform between computational and memory demands. This model enables applications to adjust in response to the specific strengths and limitations of the underlying hardware and system to optimize resource utilization. The effectiveness of this approach is demonstrated with matrix multiplication kernels on different input sizes, with turning on/off various compression techniques, including 1) low-precision floating point; 2) sparse matrix formulation; and 3) compressed arrays with ZFP. By reducing memory transfer volumes and cache misses and increasing data locality and computational intensity through compression, the specific roofline model can transform between compute and memory bounds to align more efficiently with system capabilities. This advancement not only improves overall performance but also maximizes adaptability in diverse computing environments.

Naraparaju, Ramasoumya [University of Washington]↗
DOE OSTI2026

A two-stage optical fusion framework for wildfire severity mapping across the conterminous United States

Accurate wildfire severity mapping (WSM) is essential for post-fire recovery planning, erosion risk assessment, ecosystem monitoring, and disaster risk reduction. Although Landsat and Sentinel optical imagery have been widely used for burn severity assessment, the added value of fusing multiple optical sensors has not been sufficiently quantified across diverse fire events, particularly since the launch of Landsat-9. This study evaluates whether multisensor optical fusion improves wildfire severity mapping relative to single-sensor baselines using Sentinel-2, Landsat-8, and Landsat-9 imagery across 40 wildfire events in the conterminous United States. We tested a two-stage fusion framework that combines feature-level fusion with pixel-level dimensionality reduction. First, feature-level fused datasets were created through early fusion by combining standardized post-fire bands from each sensor into a single predictor stack. Both raw reflectance bands and pairwise spectral transforms were retained to capture within- and cross-sensor spectral interactions. Second, Linear Discriminant Analysis was applied to both single-sensor and fused datasets to produce comparable low-dimensional feature spaces. Six machine-learning classifiers were then used to benchmark model performance with repeated spatially buffered train–test splits. Results show that Landsat-9 was the strongest single-sensor baseline. Among the fusion strategies, Sentinel-2 + Landsat-9 produced the most consistent improvement and reduced performance variability. Landscape-condition analysis further showed that this fusion was most beneficial in shrubland-dominated and high-terrain fires, where it achieved the highest overall mean accuracy and the fewest failures. In contrast, its benefits were less reliable in evergreen forests, mixed vegetation, and low- to moderate-elevation terrain. In operational settings, the Sentinel-2 + Landsat-9 configuration offers a practical solution for post-fire recovery planning, erosion-risk assessment, watershed management, and ecological monitoring when field observations are available and timely satellite-based information is needed.

Landsat↗
DOE OSTI2025

Integrating Characteristic Arctic Vegetation in a Land Surface Model Improves Representation of Carbon Dynamics Across a Tundra Landscape: Modeling Archive

This modeling archive is in support of the Next-Generation Ecosystem Experiments in the Arctic (NGEE Arctic) publication "Integrating Characteristic Arctic Vegetation in a Land Surface Model Improves Representation of Carbon Dynamics Across a Tundra Landscape", by Murphy et al. (2025). This archive contains model input files and outputs from landscape-scale simulations conducted using ELM, the land model component of the Department of Energy’s Energy Exascale Earth System Model (E3SM), at the Council NGEE Arctic field site (Council Road mile marker 71) on Alaska’s Seward Peninsula. Input data and model output from two sets of ELM simulations are provided. The first set of simulations were conducted with the two default ELM Arctic plant functional types (PFTs; broadleaf deciduous boreal shrub and a C3 grass) and the second set of simulations were conducted with a set of nine Arctic-specific PFTs including nonvascular mosses and lichens, graminoids, forbs, evergreen dwarf shrubs, three height classes of deciduous shrubs (dwarf, low, and low to tall), and deciduous alder shrubs (Sulman et al., 2021). Parameter names and major parameter changes in the Arctic-specific PFT configuration are described in Sulman et al. (2021) and archived in the Sulman et al. (2021) dataset (see below). Simulations were spatially explicit, covering an approximately 6.4X3.3 km domain at the Council site with a spatial resolution of 100 m for a total of 2,112 simulated grid cells under each ELM PFT configuration. The modeling archive contains meteorological forcing (seven *.nc files and one *.txt file), a domain definition file (one *.nc files), land surface configuration files (two *.nc files), parameter files (two *.nc files), annual ELM output files spanning 1980-2014 (68 *.nc files), and a User’s Guide (*pdf file). Additional information on the provided files is in the “Modeling Archive Contents” section of the User’s Guide. Model outputs are aggregated to the column scale (i.e. PFT-specific outputs are not provided here).

Murphy, Bailey [ORNL] (ORCID:0000000203995221)↗
DOE OSTI2022

Water Network Shape-Dependence of Local Interactions with the Microhydrated –NO 2 – and –CO 2 – Anionic Head Groups by Cold Ion Vibrational Spectroscopy

We report the structural evolutions of water networks and solvatochromic response of the CH 3 NO 2 – radical anion in the OH and CH stretching regions by analysis of the vibrational spectra displayed by cryogenically cooled CH 3 NO 2 – ·(H 2 O) n=1–6 clusters. The OH stretching bands evolve with a surprisingly large discontinuity at n = 6, which features the emergence of an intense, strongly red-shifted band along with a weaker feature that appears in the region assigned to a free OH fundamental. Very similar behavior is displayed by the perdeuterated carboxylate clusters, RCO 2 – ·(H 2 O) n=5–7 (R = CD 3 CD 2 ), indicating that this behavior is a general feature in the microhydration of the triatomic anionic domain and not associated with CH oscillators. Electronic structure calculations trace this behavior to the formation of a “book” isomer of the water hexamer that adopts a configuration in which one of the water molecules resides in an acceptor–acceptor–donor (AAD) (A = acceptor, D = donor) H-bonding site. Excitation of the bound OH in the AAD site explores the local network topology best suited to stabilize an incipient –XO 2 H–OH–(H 2 O) 2 intracluster proton-transfer reaction. These systems thus provide particularly clear examples where the network shape controls the potential energy landscape that governs water network-mediated, intracluster proton transfer. The CH stretching bands of the CH 3 NO 2 – ·(H 2 O) n=1–6 clusters also exhibit strong solvatochromic shifts, but in this case, they smoothly blue-shift with increasing hydration with no discontinuity at n = 6. Furthermore, this behavior is analyzed in the context of the solute-ion polarizability response and partial charge transfer to the water networks.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Free-Energy Landscapes and Surface Dynamics in Methane Activation on Ni(511) via Machine Learning and Enhanced Sampling

Methane activation on stepped Ni(511) surfaces involves the rearrangement of surface atoms as the chemical reaction proceeds. This process is particularly sensitive to temperature. Using machine-learned interatomic potentials (MLIPs) coupled with enhanced sampling techniques, we investigate the activation of methane under realistic operando conditions. Our analysis reveals that methane dissociation occurs predominantly at step-edge nickel atoms. As CH x (where x = 3 or 4) species bind to additional surface nickel atoms, their reduced mobility leads to entropic penalties that suppress certain configurations and transition states. This is reflected in the underlying free energy surfaces, where configurations such as methyl binding to hollow sites and activation routes involving two nickel atoms become unfavorable as temperature increases. At elevated temperatures, methane activation extends from step-edge sites to terrace regions because of reduced free-energy barriers and enhanced surface dynamics. By decomposing the free-energy into enthalpic and entropic contributions, we uncover temperature-dependent shifts in the preferences of methane for the relevant active sites and arrive at a detailed molecular picture of methane activation.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Dual Channel Dual Staging: Hierarchical and Portable Staging for GPU-Based In-Situ Workflow

In-situ workflows have emerged as an attractive approach for addressing data movement challenges at very large scales. Since GPU-based architectures dominate the HPC landscapes, porting these in-situ workflows, and, specifically, the inter-application data exchange, to GPU-based systems can be challenging. Technologies such as GPUDirect RDMA (GDR), which is typically used for I/O in GPU applications as an optimization that circumvents the CPU overhead, can be leveraged to support bulk data exchanges between GPU applications. However, current GDR design often lacks performance portability across HPC clusters built with different hardware configurations. Furthermore, the local CPU may also be effectively used as an auxiliary communication mechanism to offload data exchanges. In this paper, we present a dual channel dual staging approach for efficient, scalable, and performance-portable inter-application data exchange for in-situ workflows. This approach exploits the data access pattern within in-situ workflows along with the inherent execution asynchrony to accelerate data exchanges and, at the same time, improve performance portability. Specifically, the dual channel dual staging method leverages both the local CPU and the remote data staging server to build a hierarchical joint staging area and uses this staging area to transform blocking inter-application bulk data exchanges into best-effort local data movements between GPU and CPU. The dual channel dual staging is implemented as a portability extension of the Dataspaces-GPU staging framework. We present an experimental evaluation of its performance, portability, and scalability using this implementation on three leadership GPU clusters. The evaluation results demonstrate that the dual channel dual staging method saves up to 75% in data-exchange time compared to host-based, GDR, and alternate portable designs, while maintaining scalability (up to 512 GPUs) and performance portability across the three platforms.

Zhang, Bo [University of Utah]↗
DOE OSTI2022

Geometrically stabilized skyrmionic vortex in FeGe tetrahedral nanoparticles

The concept of topology has dramatically expanded the research landscape of magnetism, leading to the discovery of numerous magnetic textures with intriguing topological properties. A magnetic skyrmion is an emergent topological magnetic texture with a string-like structure in three dimensions and a disk-like structure in one and two dimensions. Skyrmions in zero dimensions have remained elusive due to challenges from many competing orders. Here, by combining electron holography and micromagnetic simulations, we uncover the real-space magnetic configurations of a skyrmionic vortex structure confined in a B20-type FeGe tetrahedral nanoparticle. An isolated skyrmionic vortex forms at the ground state and this texture shows excellent robustness against temperature without applying a magnetic field. Furthermore, our findings shed light on zero-dimensional geometrical confinement as a route to engineer and manipulate individual skyrmionic metastructures.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Formation of phosphorus monoxide through the $$\mathbf {P}(^{4}S)+\mathbf {O}_{\mathbf {2}}(^{3}\Sigma ^{-})\rightarrow \mathbf {O}(^{3}P)+\mathbf {PO}(^{2}\Pi )$$ reaction

Phosphorus is a key and vital element for a diverse set of important biological molecules, being indispensable for life as we know. A deeper comprehension of its role in astrochemistry and atmospheric chemistry may aid in finding answers to how this element became available on Earth. The PO molecule is one of the main reservoirs of phosphorus in the interstellar medium (ISM), and a better understanding of the mechanisms and rate coefficients for its formation in the ISM is important for modelling its abundances. Here in this work, we perform multireference configuration interaction calculations on the formation of PO via the P( 4 S) + O 2 (3 Σ - ) reaction, analyzing its potential energy surface and rate coefficients for the global reaction on both doublet and quartet states. We also perform DFT (M06-2X) and CCSD(T) calculations, in order to compare the results. We found that the OPO system possesses a high multiconfigurational character, making DFT and CCSD methodologies not suitable for its potential energy landscape calculation. The rate coefficients have been calculated using the master equation system solver (MESS) package, and the results compared to recent experimental data. It is shown that the quartet state contributes for temperatures higher than 700K. The computed rate coefficient can be described by a modified Arrhenius equation [α(T/300) β exp (-γ/T)] with α = 1.44 x 10 -12 cm 3 s -1 , β= -1.66 and γ= 704 K.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Continental rift evolution and drainage reorganization along the Dead Sea rift since the Miocene

The Dead Sea fault is a section of the Arabian-African plate boundary. Widespread field relations indicate that three major drainage systems (stages) occupied the landscape west of the Dead Sea fault since its initiation at ca. 20 Ma. Specifically, (1) an early to middle Miocene drainage system, only minorly reconfigured by the fault (all sediments of this system belong to the Hazeva Formation); (2) a late Miocene to early Pleistocene fault-parallel drainage system named Paran-Neqarot (all sediments of this system belong to the Arava and Zehiha Formations; and (3) the early Pleistocene to present drainage configuration. The temporal and spatial frameworks of drainage stage 1 are generally constrained by radiometric dating of interfingering volcanic units, and the onset and temporal and spatial frameworks of drainage stage 3 are well constrained by cosmogenic 10 Be surface exposure ages. The timing and longevity of the rift-parallel drainage (stage 2) have until now been evasive to direct dating. The overall time gap between stages 1 and 3 is ~12–13 million years. Thus, an early age (within this time gap) of stage 2 would imply an immediate response of drainage reorganization to rift tectonics, while a later age of this drainage system would imply a delayed response. We present 11 10 Be- 26 Al cosmogenic burial ages of alluvial and colluvial units related to the fault-parallel drainage system (stage 2), which collectively constrain the time of deposition of the Arava Formation sediments in the central Negev to ca. 8 Ma. The general lack of stratigraphic order, together with the large dispersion of ages both across and within the sampling sites, attests to significant recycling of sediments from drainage stage 1 into the Arava Formation deposits. The termination of Arava and Zehiha Formation sediment deposition at ca. 1.8 Ma was determined previously using cosmogenic exposure ages of desert pavements that cover the formations. Combining the previously published data with our new data, we established the longevity and character of the Paran-Neqarot drainage system. In conlcusion, this framework highlights the temporal aspect of drainage system build-up and collapse as it responded to transform and extensional plate boundary tectonics during the Neogene.

58 GEOSCIENCES↗
DOE OSTI2026

A unifying equation for fermentation sustainability across the titer-rate-yield landscape

Industrial fermentation is central to the sustainable production of fuels and chemicals, yet commercial viability of emerging technologies hinges on improving fermentation titer, rate, and yield (TRY). How these metrics shape system cost remains difficult to generalize due to complex interactions among feedstocks, fermentation, separations, catalytic upgrading, waste management, and facility design. Here, we systematically map theoretical fermentation performance spaces (formed by all potential TRY combinations) for 32 representative biomanufacturing facilities—spanning distinct choices for feedstocks, fermentation regimes and products, separations, and catalytic upgrading—by simulating and evaluating them (via techno-economic analysis, TEA) under uncertainty (600,000 Monte Carlo simulations) and across TRY combinations (7500 TRY combinations for each of 32 configurations). Across this wide design and thermodynamic simulation space, we find the relationship between fermentation TRY and system cost is captured by a simple, generalizable mathematical equation (R 2 of 0.992 − 1.000 across our simulations; 0.954 − 1.000 when validated against prior studies that used different tools). We use this equation to elucidate key drivers that shape cost sensitivity to fermentation performance, generating widely applicable insights. By demonstrating a unifying relationship governs the impact of fermentation on biomanufacturing economics, this work establishes a foundation for agile, holistically predictive, resource-efficient strategies to prioritize fermentation research and development needs and accelerate commercialization of emerging biomanufacturing technologies.

applied mathematics↗
DOE OSTI2023

Autonomous System Inference, Trojan, and Adversarial Reprogramming Attack and Defense (Final)

In the world of ever-advancing technology, Autonomous Systems (AS) find extensive application, bolstering functionalities of critical infrastructures such as nuclear power plants. These systems, however, are increasingly becoming a target for nefarious activities, namely through inference attacks, trojan attacks, and adversarial reprogramming. This paper delves into a comprehensive exploration of machine learning (ML)-driven autonomous control systems within advanced nuclear reactor designs, revealing the vulnerabilities and proposing strategies for defense against potential cyber-attacks. Advanced cyber-attacks against critical infrastructure and the energy sector are becoming more common. With the invention of autonomous control systems (ACS) within advanced nuclear reactor designs, system designers, reactor operators, and regulators must consider cybersecurity during the design and operational phases. This article provides a cyber threat assessment of machine learning (ML)- based digital twinning (DT) technologies in the context of advanced reactor ACS. A cyber-physical testbed was created to emulate nuclear reactor digital instrumentation and controls (I&C) and act as a basis for the ACS. The ACS was designed as two plant-level DTs predicting reactor malfunctions and determining control actions and two component-level DTs responsible for classifying component states and forecasting component inputs and outputs (I/O). Two duplicate ACS designs– one using a traditional ML framework and one using an automated ML (AutoML) framework– were created and tested against cyber-attacks on training data, real-time process data, and ML model architectures to determine their respective qualitative cyber-risk in terms of likelihood and impact. Both frameworks showed similar cyber-resilience against training, real-time, and ML architecture attacks, proving that neither is inherently more secure. Recommended safeguard and security measures are posed to system designers, reactor operators, and regulators to maintain the cybersecurity of ML-based DT technologies such as ACS, prompting a holistic view of shared responsibility for maintaining cyber-secure ML-based systems. As global reliance on generation III reactors begins to be critically assessed, the evolution towards advanced reactor systems utilizing digital instrumentation and controls (I&C) becomes not merely preferable, but essential. The integration of semi and fully autonomous control systems (ACS), powered by digital I&C and machine learning (ML)-based digital twinning (DT) technologies, emerges as a potent strategy to mitigate operations and maintenance costs, thereby enhancing the economic feasibility of novel reactor designs. However, with a staggering 500% and 380% increase in cyber-attacks reported against the energy sector by the United States Department of Energy (DoE) and the European Union respectively, a surge in cyber vulnerabilities specifically targeting the nuclear industry has been 2 markedly observed. Notable incidents, such as the W32.Ramnit spyware infiltration at the Gundremmingen nuclear power plant in Germany and the Dtrack spyware intrusion at the Kudankulam nuclear power plant in India, while not directly compromising core industrial control systems (ICS), underscore a compelling necessity to fortify cybersecurity protocols in safeguarding reactor systems against increasingly adept digital adversaries. In light of this, our investigation extends beyond conventional cybersecurity parameters, diving into the intricate web of potential vulnerabilities woven into ML-based DTs and ACS in advanced reactor systems. A crafted cyber-physical testbed and preliminary ACS were devised to act as a mirror, reflecting potential configurations of advanced reactor control designs. Moreover, this study is intertwined with a scrutinization of ML models, developed either through conventional, manually tuned methodologies or via automated means through AutoML, probing into their cyber-risk profiles within operational technology (OT) environments. Expanding on this, two distinct ACS blueprints were forged – one navigating through the corridors of traditional ML and the other traversing the path of AutoML – in an effort to holistically encapsulate the considerations pivotal to ML-based DT control system design. Employing the SANS Institute Industrial Control System (ICS) Kill Chain and the MITRE ATT&CK Tactics, Techniques, and Procedures (TTP) framework, a structured analysis was conducted, launching three targeted attacks against the training dataset, real-time dataset, and ML models, therein dissecting the potential cyber-attack implications against both ML frameworks within an ACS milieu. It is essential to note that three distinct categories of attacks were conducted against both ACS configurations, each encompassing three distinct ML-based DTs, cumulating in a total of 18 varied attacks. This exploration extends into the realms of Autonomous System Inference, Trojan, and Adversarial Reprogramming Attack and Defense, unraveling vulnerabilities, and opportunities for fortified defenses against such intrusions, particularly where ML-driven technologies, and by extension, ACS, are deployed. Final recommendations, articulated through a lens of security, safeguard, and implementation considerations, are presented for both traditional and AutoML models, anchoring upon the existing knowledge landscape and ML-based DT modeling for ACS, and are offered as a beacon to guide the nuclear industry through the intricate cybersecurity challenges that lie ahead.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2024

Effective optimization of atomic decoration in giant and superstructurally ordered crystals with machine learning

Crystals with complicated geometry are often observed with mixed chemical occupancy among Wyckoff sites, presenting a unique challenge for accurate atomic modeling. Similar systems possessing exact occupancy on all the sites can exhibit superstructural ordering, dramatically inflating the unit cell size. In this work, a crystal graph convolutional neural network (CGCNN) is used to predict optimal atomic decorations on fixed crystalline geometries. This is achieved with a site permutation search (SPS) optimization algorithm based on Monte Carlo moves combined with simulated annealing and basin-hopping techniques. Our approach relies on the evidence that, for a given chemical composition, a CGCNN estimates the correct energetic ordering of different atomic decorations, as predicted by electronic structure calculations. This provides a suitable energy landscape that can be optimized according to site occupation, allowing the prediction of chemical decoration in crystals exhibiting mixed or disordered occupancy, or superstructural ordering. Verification of the procedure is carried out on several known compounds, including the superstructurally ordered clathrate compound Rb8Ga27Sb16 and vacancy-ordered perovskite Cs2SnI6, neither of which was previously seen during the neural network training. In addition, the critical temperature of an order–disorder phase transition in solid solution CuZn is probed with our SPS routines by sampling site configuration trajectories in the canonical ensemble. This strategy provides an accurate method for determining favorable decoration in complex crystals and analyzing site occupation at unprecedented speed and scale.

Chemistry↗