Search NASA⌕ Search

SEARCH · Search NASA

Results for “higher accuracy”

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 271 records · Page 15
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Detection of long-range entanglement in gapped quantum spin liquids by local measurements

Topological order, reflected in long-range patterns of entanglement, is quantified by the topological entanglement entropy γ. We show that for gapped quantum spin liquids it is possible to extract γ using two-spin local correlators. We demonstrate our method for the gapped Z 2 Kitaev spin liquid on a honeycomb lattice with anisotropic interactions. We show that the γ = ln⁡2 for Z 2 topological order can be simply extracted from local two-spin correlators across two different bonds that involve only Majorana fermions, with an accuracy comparable to or higher than the Kitaev-Preskill construction. This implies that even though the ground state can be factorized into the product of Majorana and gauge sectors, the different superselection sectors of Z 2 gauge theory determined by global Wilson loop operators can be reflected locally in the Majorana sector.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2024

Neural network emulation of flow in heavy-ion collisions at intermediate energies

Applications of new techniques in machine learning are speeding up progress in research in various fields. In this work, we construct and evaluate a deep neural network (DNN) to be used within a Bayesian statistical framework as a faster and more reliable alternative to the Gaussian process (GP) emulator of an isospin-dependent Boltzmann-Uehling-Uhlenbeck (IBUU) transport model simulator of heavy-ion reactions at intermediate beam energies. We found strong evidence of the DNN being able to emulate the IBUU simulator's prediction on the strengths of protons' directed and elliptical flow very efficiently even with small training datasets and with accuracy about ten times higher than the GP. Here, limitations of our present work and future improvements are also discussed.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2023

Interpolation Methods to Enable Fast and Accurate EMT Simulation of PV Inverters

In this paper, interpolation methods to enable fast simulation of photovoltaic (PV) inverters are proposed. The interpolation methods are based on the event-driven interpolating method that can be introduced in the simulation model to run the model at a higher timestep while maintaining accuracy. The proposed methods are tested on a neutral point clamp (NPC) converter and a two-level converter (2LC) that are typically used in large-scale PV plants. The interpolation methods are integrated into the NPC and 2LC simulation models in PSCAD/Fortran and RSCAD C platforms. These models are tested at different simulation timesteps in off-line and real-time simulation platforms PSCAD and RSCAD respectively.

Marthi, Phani Ratna Vanamali↗
DOE OSTI2023

Spread Spectrum Time Domain Reflectometry (SSTDR) and Frequency Domain Reflectometry (FDR) for Detection of Cable Anomalies Using Machine Learning

Cables are initially qualified for nuclear power plant use for 40 years. As plants extend their operating license to 60 and 80 years, continued use of these cables must shift to a performance-based approach since it is cost prohibitive to completely replace cables that are likely still capable of performing their design function. A variety of cable tests are available and are commonly applied during outages when the cables can be taken out of service. Frequency domain reflectometry (FDR) is one of these test methods that is being more broadly accepted and used because it not only detects anomalies along the cable with a low-voltage signal that does not stress the cable insulation, but the technique also locates the anomalies. This supports follow-up local inspection and local repair or partial replacement of a damaged cable segment. Currently, FDR testing is only applied to cables that are taken out of service since the test instrument would be damaged by operational voltages. A related technology that has found some acceptance in the aircraft and rail industry is spread spectrum time domain reflectometry (SSTDR). This technology has been implemented with a custom commercial instrument by LiveWire Innovation Inc. that is designed to operate on live cables up to 1000 volts. One of the main conclusions of a previous effort was that cable reflectometry plots can be difficult for humans to analyze due to baseline noise, low or noisy anomaly response peaks, or large responses from cable ends. Detection of cable anomalies for many of these frequencies and test conditions was challenging for manual analysis. This presented an ideal opportunity for ML analysis to distinguish undamaged cable indications from anomalous cable indications. This research discusses application of machine learning (ML) to reflectometry cable test methods. The goal was to assess feasibility to distinguish undamaged cable reflectometry responses from damaged or anomalous cable reflectometry responses. The assessment considered the 3 instruments, multiple frequency bandwidths from each instrument, multiple cable anomalies and test conditions, and both supervised and unsupervised ML approaches. Although approaches and analysis methods were not identical or directly comparable, both outputs were encouraging. The unsupervised prediction weighted accuracy was assessed by instrument and by frequency. It performed better at high frequencies with the highest prediction accuracy of 0.84 for the higher frequency FDR, 0.79 for the 48-MHz LiveWire SSTDR, and 0.77 for 300-MHz PNNL SSTDR. The initial weighted accuracy average across all frequencies for using supervised ML was 0.56 to 0.68. The supervised analysis was repeated with noisier training data removed resulting in weighted accuracies of 0.69 to 0.87. These weighted accuracies are not directly comparable due to differences in the supervised and unsupervised analysis details but do indicate an encouraging trend. Even with limited and unbalanced data, strong prediction accuracies seem encouraging for further work including more data under a wider range of conditions.

42 ENGINEERING↗
DOE OSTI2021

Vertical-Axis Wind Turbine Steady and Unsteady Aerodynamics for Curved Deforming Blades

Vertical-axis wind turbines’ simpler design and low center of gravity make them ideal for floating wind applications. However, efficient design optimization of floating systems requires fast and accurate models. Low-fidelity vertical-axis turbine aerodynamic models, including double multiple streamtube and actuator cylinder theory, were created during the 1980s. Commercial development of vertical-axis turbines all but ceased in the 1990s until around 2010 when interest resurged for floating applications. Despite the age of these models, the original assumptions (2-D, rigid, steady, straight bladed) have not been revisited in full. When the current low-fidelity formulations are applied to modern turbines in the unsteady domain, aerodynamic load errors nearing 50% are found, consistent with prior literature. However, a set of steady and unsteady modifications that remove the majority of error is identified, limiting it near 5%. This paper shows how to reformulate the steady models to allow for unsteady inputs including turbulence, deforming blades, and variable rotational speed. A new unsteady approximation that increases numerical speed by 5–10× is also presented. Combined, these modifications enable full-turbine unsteady simulations with accuracy comparable to higher-fidelity vortex methods, but over 5000× faster.

17 WIND ENERGY↗
DOE OSTI2023

Milestone 1.2.15: Feasibility of In Situ Accelerated Aluminum Coupon Radiolysis by Synchrotron X-Rays

Extended dry storage of aluminum-clad spent nuclear fuel (ASNF) requires an assessment of the radiolytic generation of molecular hydrogen gas (H2) from the ASNF’s corrosion layers. H2 accumulation can potentially lead to storage canister embrittlement/rupture and the accumulation of flammable gas mixtures in accident scenarios. To date, computational models have been developed for the prediction of radiolytic H2 generation from samples exposed to lower absorbed dose regimes (up to ~3 MGy). However, greater accuracy is needed for higher absorbed doses (> 25 MGy) where the concentration of H2 ultimately reaches a steady-state. Data in this area is limited due to the amount of time taken (months) to accumulate such high gamma doses. Furthermore, a recent study observed radiation-induced damage to the surface of pre-corroded aluminum alloy coupons at high absorbed gamma doses. Despite this observation and its implications, there is currently no computational connection between the radiolytic formation of H2 and changes in the composition and morphology of the cladding’s corrosion layers with absorbed dose. To develop a better understanding of the processes and effects described above, the present study aimed to evaluate the feasibility of leveraging synchrotron x-ray capabilities for coupled accelerated irradiation and in situ surface characterization of ASNF alloys. To that end, National Synchrotron Light Source II (NSLS-II) beamtime was secured and a series of aluminum alloy 1100 (AA1100) wires, prepared under a variety of conditions, were interrogated using ex situ x-ray diffraction (XRD) and scanning electron microscopy (SEM) techniques at Idaho National Laboratory (INL) and ex situ and in situ XRD capabilities at the NSLS-II x-ray powder diffraction (XPD) beamline. Results indicated that performing synchrotron XRD using the available XPD beamline configuration can provide sufficient radiation dose but cannot discern changes in the composition and morphology of sample corrosion layers. Additionally, ex situ XRD and SEM data from Idaho National Laboratory (INL) indicated that the pre-corrosion of AA1100 wires did not generate an appreciably thick corrosion layer, as compared with previous aluminum coupon studies. These thinner surface corrosion layers were not sufficient for detection by both ex situ and in situ synchrotron XRD, specifically under consideration of the NSLS-II XPD beamline’s configuration primarily capturing information from the sample’s bulk material, i.e., aluminum metal. In summary, the use of the NSLS-II XPD beamline for promoting accelerated radiolysis and in situ surface characterization is not appropriate for this program’s goals.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗
DOE OSTI2020

Low Level Calibration of Liquid Scintillation Counting

Liquid Scintillation Counting (LSC) is an analytical laboratory method that quantifies the concentrations of alpha and beta emitting isotopes. The LSC method can be utilized for the detection of tritium, both environmentally and at nuclear facilities. Most LSC samples are aqueous-based and prepared as a radioactive sample dissolved or suspended in a high efficiency scintillation cocktail that converts radioactive energy into light pulses. When placed in counting vials, the liquid scintillation cocktail allows for optical coupling in which energy is released from the samples radioactive decay, and transferred to the scintillator. That energy is then absorbed to produce excited electrons that fall back to their ground-state and emit a pulse of light that is detected by the liquid scintillation analyzers photomultiplier tubes. Quench is a signal attenuation due to physical, chemical, or color interferences. To compensate for quench, quench standards of a known concentration are implemented at increasing increments of quench per vial to create a quench curve. Quench standards can be purchased pre-made or customized from the manufacturer, however, there are several issues that arise from purchasing the pre-made quench standards. The main issues with ordering pre-made quench standards is that they use higher count values, between 30,000 and 250,000 disintegrations per minute (dpm) of tritium per vial and only come in glass vials. Using higher counting standards in glass vials makes it hard to see lower concentrations in plastic vials. Additionally, when using higher energy standards the accuracy of the calibration readings tend to be lower. On the other hand, making a set of quench standards in-house allows for the customization of the dpm concentration to roughly 1,500-3,000 and preparation in plastic vials. This allows for lower activity readings that results in closer precision of the samples' true concentration. Technical Objectives: Create a quench curve and calibrate the LSA for tritium. Verify the calibration of the quench curve prior to cross sample runs. Check calibration against Quality Control (QC) reference value. Conclusion: a tritium quench curve calibration was performed using a scintillation cocktail with ultima gold (AB and AB/F), acetone (only with AB), and water (only with AB/F). By performing the tritium quench curve calibration, the counting efficiency was correlated to various levels of quench. Calibration checks with quality control standards were also performed to verify that the calibration was correct. The observed results provided acceptable values that matched the quality control standard reference values with an acceptable uncertainty. The next step will be fine tuning and cross comparison checks with legacy instrumentation.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

Investigating lab-scaled offshore wind aerodynamic testing failure and developing solutions for early anomaly detections

As offshore wind systems become more complex, the risk of human error or equipment malfunction increases during experimental testing. This study investigates a lab-scale incident involving a 1 : 50 scale 5 MW wind turbine, where a generator failure led to rotor overspeed and a blade–tower strike. To improve early fault detection, we propose a data-driven method based on multivariate long short-term memory (LSTM) models. High-frequency measurements are projected onto principal components, and anomalies are identified using reconstruction error and its time derivative. Two models are trained on different healthy datasets and tested using single- and multi-principal component (1PC and MPC) variations. Results show that combining both error and error derivative improves detection accuracy. The 1PC model detects faults faster, has a higher recall rate, and achieves a 43 % improvement in anomaly detection accuracy, while the MPC model yields higher precision. This approach provides a simple and effective tool for early anomaly detection in lab-scale experiments, helping to reduce the risk of future failures during the testing of new technologies.

17 WIND ENERGY↗
DOE OSTI2025

Prediction of carbon nanostructure mechanical properties and the role of defects using machine learning

Graphene-based nanostructures hold immense potential as strong and lightweight materials, however, their mechanical properties such as modulus and strength are difficult to fully exploit due to challenges in atomic-scale engineering. This study presents a database of over 2,000 pristine and defective nanoscale CNT bundles and other graphitic assemblies, inspired by microscopy, with associated stress–strain curves from reactive molecular dynamics (MD) simulations using the reactive INTERFACE force field (IFF-R). These 3D structures, containing up to 80,000 atoms, enable detailed analyses of structure-stiffness-failure relationships. By leveraging the database and physics- and chemistry-informed machine learning (ML), accurate predictions of elastic moduli and tensile strength are demonstrated at speeds 1,000 to 10,000 times faster than efficient MD simulations. Hierarchical Graph Neural Networks with Spatial Information (HS-GNNs) are introduced, which integrate chemistry knowledge. HS-GNNs as well as extreme gradient boosted trees (XGBoost) achieve forecasts of mechanical properties of arbitrary carbon nanostructures with only 3 to 6% mean relative error. The reliability equals experimental accuracy and is up to 20 times higher than other ML methods. Predictions maintain 8 to 18% accuracy for large CNT bundles, CNT junctions, and carbon fiber cross-sections outside the training distribution. The physics- and chemistry-informed HS-GNN works remarkably well for data outside the training range while XGBoost works well with limited training data inside the training range. The carbon nanostructure database is designed for integration with multimodal experimental and simulation data, scalable beyond 100 nm size, and extendable to chemically similar compounds and broader property ranges. The ML approaches have potential for applications in structural materials, nanoelectronics, and carbon-based catalysts.

Winetrout, Jordan J.↗
DOE OSTI2025

Leveraging Large Language Models for Real-World Data Evidence: A Framework for Automated Treatment Extraction and Data Harmonization

Background: The ability to comprehensively collect treatment information from cancer patient medical records would enable studies to evaluate real-world benefits and risks tied to specific treatments. Currently, it is difficult to system- atically collect high-quality treatment information because it is often stored in unstructured text. Manually extracting and standardizing drug and regimen data is time-intensive. Recent advances in large language models (LLMs) offer a potential solution for automated extraction of structured treatment information from clinical text. Objective: This study systematically evaluates the utility of four LLMs from the Llama family for automated extraction of oncology treatment information from clinical text. This information can guide researchers using cancer registry data to provide insights into cancer care and outcomes beyond clinical trials. Methods: Four instruction-tuned Llama models with varying parameter counts (1B, 3B, 8B, and 70B) were evaluated for their ability to extract treatment information from clinical documents. A unified oncology knowledge base integrating seven major public data sources was developed to standardize and normalize extracted entities—a critical step for harmonizing data from diverse sources. Extracted treatment data were compared against expert-annotated ground truth. Model performance was assessed using accuracy metrics (Precision, Recall, F1-Score) and opera- tional feasibility metrics, including processing speed and structural compliance of the output. Results: A strong positive correlation was observed between model size and extraction accuracy. F1-score improved from 0.609 for the 1B model to 0.710 (3B), 0.807 (8B), and 0.828 (70B). While larger models demonstrated superior accuracy and compliance, they incurred higher computational costs. The modest performance difference between 8B and 70B suggests diminishing returns with increasing model size. Conclusions: LLMs represent a viable technology for automating oncology treatment extraction. The 8B-parameter model emerged as a highly effective option, balancing high accuracy and computational efficiency. Selecting an appropriate LLM for deployment in cancer registries involves a trade-off between desired accuracy and available operational resources. Harmonizing extracted entities with the oncology knowledge base facilitates standardized integration into common data models, enhancing data quality for real-world evidence analyses.

artificial intelligence↗
DOE OSTI2022

Supervised learning of a chemistry functional with damped dispersion

Abstract Kohn–Sham density functional theory is widely used in chemistry, but no functional can accurately predict the whole range of chemical properties, although recent progress by some doubly hybrid functionals comes close. Here, we optimized a singly hybrid functional called CF22D with higher across-the-board accuracy for chemistry than most of the existing non-doubly hybrid functionals by using a flexible functional form that combines a global hybrid meta-nonseparable gradient approximation that depends on density and occupied orbitals with a damped dispersion term that depends on geometry. We optimized this energy functional by using a large database and performance-triggered iterative supervised training. We combined several databases to create a very large, combined database whose use demonstrated the good performance of CF22D on barrier heights, isomerization energies, thermochemistry, noncovalent interactions, radical and nonradical chemistry, small and large systems, simple and complex systems and transition-metal chemistry.

Liu, Yiwei (ORCID:0000000288126163)↗
DOE OSTI2025

Time Alignment of the CMS Hadron Calorimeter

The Hadron Calorimeter (HCAL) in the Compact Muon Solenoid (CMS) experiment at the Large Hadron Collider (LHC) was recently upgraded for Run 3 (2022-2025) to introduce depth segmentation and online timing measurements. With increased segmentation and readout channels, the HCAL provides new timing capabilities for jets and hadronic tau decays with nearly 4π coverage and sensitivity to highly displaced decays within the calorimeter volume. Recent HCAL timing scans provide a valuable look at artificially delayed jets in collision data and are crucial to improving the detector’s performance. Online timing is utilized for detector alignment based on positioning the pulse rising edge, achieving an alignment accuracy of 0.5 ns, considerably higher than previous energy-weighting based approaches. Using precision arrival time measurements, significant advances have been made in understanding the propagation of hadronic showers throughout the calorimeter.

Kopp, Gillian [Princeton Univ., NJ (United States)↗
DOE OSTI2023

Vibrational heat-bath configuration interaction with semistochastic perturbation theory using harmonic oscillator or VSCF modals

Vibrational heat-bath configuration interaction (VHCI)—a selected configuration interaction technique for vibrational structure theory—has recently been developed in two independent works [J. H. Fetherolf and T. C. Berkelbach, J. Chem. Phys. 154, 074104 (2021); A. U. Bhatty and K. R. Brorsen, Mol. Phys. 119, e1936250 (2021)], where it was shown to provide accuracy on par with the most accurate vibrational structure methods with a low computational cost. Here, we eliminate the memory bottleneck of the second-order perturbation theory correction using the same (semi)stochastic approach developed previously for electronic structure theory. This allows us to treat, in an unbiased manner, much larger perturbative spaces, which are necessary for high accuracy in large systems. Stochastic errors are easily controlled to be less than 1 cm−1. We also report two other developments: (i) we propose a new heat-bath criterion and an associated exact implicit sorting algorithm for potential energy surfaces expressible as a sum of products of one-dimensional potentials; (ii) we formulate VHCI to use a vibrational self-consistent field (VSCF) reference, as opposed to the harmonic oscillator reference configuration used in previous reports. Our tests are done with quartic and sextic force fields, for which we find that with VSCF, the minor improvements to accuracy are outweighed by the higher computational cost associated the matrix element evaluations. We expect VSCF-based VHCI to be important for more general potential representations, for which the harmonic oscillator basis function integrals are no longer analytic.

Chemistry↗
DOE OSTI2026

Role of electron correlation on the adenine dimer interaction for non-equilibrium geometries: a benchmark Quantum Monte Carlo study

The accurate description of non-covalent interactions is critical for understanding the structure, dynamics, and eventual function of biomolecules. The adenine dimer serves as a benchmark system for computational methods due to its role in nucleic acid structures and its rich conformational landscape. In this study, we employ benchmark diffusion quantum Monte Carlo (DMC) methods to investigate the relative energies and role of electron correlation on a set of adenine dimer conformations generated via a search of the potential energy landscape using the global optimizer algorithm. Relative DMC energies are compared against a wide range of density functional theory (DFT) approximation results. We find that although most of the DFT functionals perform well for low-energy structures, their accuracy varies significantly for higher-energy conformations, including stacked and T-shaped structures. A large fraction of the variation is due to the treatment of the van der Waals interaction. BLYP, B3LYP, and PBE0 significantly improve with added D4 dispersion, while the recent r2SCAN-D4 and ωB97M-V functionals show the least scatter and closest agreement with the DMC. These findings highlight the delicate nature of these interactions in biomolecular systems and provide guidance for simulations of their structure and dynamics and for the development of machine learned interatomic potentials.

Washburn, Laurel [ORNL] (ORCID:0000000324179335)↗
DOE OSTI2023

Performance of methods for SARS-CoV-2 variant detection and abundance estimation within mixed population samples

The accurate identification of SARS-CoV-2 (SC2) variants and estimation of their abundance in mixed population samples (e.g., air or wastewater) is imperative for successful surveillance of community level trends. Assessing the performance of SC2 variant composition estimators (VCEs) should improve our confidence in public health decision making. Here, we introduce a linear regression based VCE and compare its performance to four other VCEs: two re-purposed DNA sequence read classifiers (Kallisto and Kraken2), a maximum-likelihood based method (Lineage deComposition for Sars-Cov-2 pooled samples (LCS)), and a regression based method (Freyja). We simulated DNA sequence datasets of known variant composition from both Illumina and Oxford Nanopore Technologies (ONT) platforms and assessed the performance of each VCE. We also evaluated VCEs performance using publicly available empirical wastewater samples collected for SC2 surveillance efforts. Bioinformatic analyses were performed with a custom NextFlow workflow (C-WAP, CFSAN Wastewater Analysis Pipeline). Relative root mean squared error (RRMSE) was used as a measure of performance with respect to the known abundance and concordance correlation coefficient (CCC) was used to measure agreement between pairs of estimators. Based on our results from simulated data, Kallisto was the most accurate estimator as it had the lowest RRMSE, followed by Freyja. Kallisto and Freyja had the most similar predictions, reflected by the highest CCC metrics. We also found that accuracy was platform and amplicon panel dependent. For example, the accuracy of Freyja was significantly higher with Illumina data compared to ONT data; performance of Kallisto was best with ARTICv4. However, when analyzing empirical data there was poor agreement among methods and variations in the number of variants detected (e.g., Freyja ARTICv4 had a mean of 2.2 variants while Kallisto ARTICv4 had a mean of 10.1 variants). This work provides an understanding of the differences in performance of a number of VCEs and how accurate they are in capturing the relative abundance of SC2 variants within a mixed sample (e.g., wastewater). Such information should help officials gauge the confidence they can have in such data for informing public health decisions.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Adaptive Client Selection in Federated Learning: A Network Anomaly Detection Use Case

Federated Learning (FL) has become a ubiquitous approach for training machine learning models on decentralized data, addressing the myriad privacy concerns inherent in traditional centralized methods. However, the efficiency of FL depends on effective client selection and robust privacy preservation mechanisms. Inadequate client selection may lead to suboptimal model performance, while insufficient privacy measures risk exposing sensitive data. This paper proposes a client selection framework for FL that integrates differential privacy and fault tolerance. Our adaptive approach dynamically adjusts the number of selected clients based on model performance and system constraints, ensuring privacy through calibrated noise addition. We evaluate our method on a network anomaly detection use case using the UNSW-NB15 and ROAD datasets. Results show up to a 7% increase in accuracy and a 25% reduction in training time compared to FedL2P. Moreover, we highlight the trade-offs between privacy budgets and model performance, with higher privacy budgets reducing noise and improving accuracy. Our fault tolerance mechanism, while causing a slight performance drop, enhances robustness to client failures. Statistical validation using Mann-Whitney U tests confirms the significance of these improvements (p < 0.05).

Marfo, William [University of Texas at El Paso,Dep↗
DOE OSTI2025

SPIKANs: separable physics-informed Kolmogorov–Arnold networks

Physics-Informed Neural Networks (PINNs) have emerged as a promising method for solving partial differential equations (PDEs) in scientific computing. While PINNs typically use multilayer perceptrons (MLPs) as their underlying architecture, recent advancements have explored alternative neural network structures. One such innovation is the Kolmogorov–Arnold Network (KAN), which has demonstrated benefits over traditional MLPs, including faster neural scaling and better interpretability. The application of KANs to physics-informed learning has led to the development of Physics-Informed KANs (PIKANs), enabling the use of KANs to solve PDEs. However, despite their advantages, KANs often suffer from slower training speeds, particularly in higher-dimensional problems where the number of collocation points grows exponentially with the dimensionality of the system. To address this challenge, we introduce Separable Physics-Informed Kolmogorov–Arnold Networks (SPIKANs). This novel architecture applies the principle of separation of variables to PIKANs, decomposing the problem such that each dimension is handled by an individual KAN. This approach drastically reduces the computational complexity of training without sacrificing accuracy, facilitating their application to higher-dimensional PDEs. Through a series of benchmark problems, we demonstrate the effectiveness of SPIKANs, showcasing their superior scalability and performance compared to PIKANs and highlighting their potential for solving complex, high-dimensional PDEs in scientific computing.

Kolmogorov-Arnold networks↗
DOE OSTI2025

Higher-order factorization machine for accurate surrogate modeling in material design

Efficient and robust optimization is important in material science for identifying optimal structural parameters and enhancing material performance. Surrogate-based active learning algorithms have recently gained great attention for their ability to efficiently navigate large, high-dimensional design spaces. Among surrogate models, 2 nd -order factorization machine (FM) models are widely employed as the surrogate model in active learning algorithms due to their balance between simplicity and effectiveness. However, their quadratic nature limits their capacity to capture complex, higher-order interactions among variables, often leading to suboptimal solutions. To overcome this limitation, we propose an active learning scheme integrating a 3 rd -order FM model, capable of modeling three-variable interactions and more intricate relationships in material systems. We comprehensively evaluate the surrogate modeling performance of the 3 rd -order FM case using various objective functions. Furthermore, we examine the optimization reliability and efficiency of the 3 rd -order FM-based active learning in a real-world material design task (e.g., nanophotonic structures for transparent radiative cooling). Our study shows that the 3 rd -order FM outperforms the 2 nd -order model in both surrogate accuracy and optimization performance, highlighting higher-order models’ promises for material design and optimization problems.

Factorization machine↗