Search NASA⌕ Search

SEARCH · Search NASA

Results for “Benchmark dataset”

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 OSTI2025

ON THE EFFECTIVENESS OF LLMS IN UNIT TEST GENERATION FOR STRUCTURED TEXT PROGRAMS

The reliability of industrial automation systems heavily depends on the correctness of Programmable Logic Controller (PLC) programs, which are often written in Structured Text (ST). While Large Language Models (LLMs) have shown promise in automating test generation for mainstream programming languages, their effectiveness for the syntactically strict ST language remains underexplored. This thesis presents a systematic empirical evaluation of three state-of-the-art LLMs—GPT-4o, Gemini 2.5 Pro, and Claude Sonnet 4.5—for generating ST unit tests. We examine three prompting strategies: Natural Language (NL), Code Language (CL), and Chain-of-Thought (CoT), across a curated set of 11 ST function blocks. The quality of the generated tests is assessed using Compilation Success Rate (CSR), Statement Coverage (SC), and Branch Coverage (BC). In the zero-shot setting, Claude Sonnet 4.5 achieves the highest CSR, while Gemini 2.5 Pro consistently delivers the best statement and branch coverage, particularly under CL prompts. By incorporating a one-shot CL prompt, all models exhibit substantial improvements—most notably GPT-4o, whose CSR increases from 45.45% to 90.91%, with substantial gains in both SC and BC. To further contextualize these findings, we compare GPT-4o’s one-shot results with PLCAutoTester, a state-ofthe- art ST unit test generation tool, on an additional benchmark dataset. While LLMgenerated tests approach competitive coverage levels, PLCAutoTester maintains significantly higher and more stable coverage across programs. This study provides the first comprehensive benchmark of modern LLMs for ST unit testing, highlighting their strengths, limitations, and improvements through one-shot prompting, and positioning their performance relative to specialized automated testing tools in industrial automation.

42 ENGINEERING↗
DOE OSTI2025

Integration and Quantitative Comparison of Up-Scaled Molecular Observation Network Data with Existing Soil Databases

MONet provides novel soil molecular data to the research community for understanding biogeochemical processes and complementing other soil datasets. This study assesses MONet's ability to replicate known soil patterns via a comparative analysis of soil respiration (Rs), pH, and clay content against benchmark datasets. Results show moderate agreement for pH and clay content, highlighting MONet's strengths in capturing soil biogeochemical variation in underrepresented regions like urban areas. Rs data are marked by the appropriate trends relative to other datasets, but direct comparison is impractical due to methodological differences in underlying data. Strategic sampling is recommended to improve MONet's coverage and eventual utility in bridging molecular observations with global datasets.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

OrbNet Denali: A machine learning potential for biological and organic chemistry with semi-empirical cost and DFT accuracy

We present OrbNet Denali, a machine learning model for an electronic structure that is designed as a drop-in replacement for groundstate density functional theory (DFT) energy calculations. The model is a message-passing graph neural network that uses symmetryadapted atomic orbital features from a low-cost quantum calculation to predict the energy of a molecule. OrbNet Denali is trained on a vast dataset of 2.3 × 10 6 DFT calculations on molecules and geometries. This dataset covers the most common elements in biochemistry and organic chemistry (H, Li, B, C, N, O, F, Na, Mg, Si, P, S, Cl, K, Ca, Br, and I) and charged molecules. OrbNet Denali is demonstrated on several well-established benchmark datasets, and we find that it provides accuracy that is on par with modern DFT methods while offering a speedup of up to three orders of magnitude. For the GMTKN55 benchmark set, OrbNet Denali achieves WTMAD-1 and WTMAD-2 scores of 7.19 and 9.84, on par with modern DFT functionals. For several GMTKN55 subsets, which contain chemical problems that are not present in the training set, OrbNet Denali produces a mean absolute error comparable to those of DFT methods. For the Hutchison conformer benchmark set, OrbNet Denali has a median correlation coefficient of R 2 = 0.90 compared to the reference DLPNO-CCSD(T) calculation and R 2 = 0.97 compared to the method used to generate the training data (ωB97X-D3/def2- TZVP), exceeding the performance of any other method with a similar cost. Similarly, the model reaches chemical accuracy for noncovalent interactions in the S66x10 dataset. For torsional profiles, OrbNet Denali reproduces the torsion profiles of ωB97X-D3/def2-TZVP with an average mean absolute error of 0.12 kcal/mol for the potential energy surfaces of the diverse fragments in the TorsionNet500 dataset.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Signal Processing Based Method for Real-Time Anomaly Detection in High-Performance Computing

Performance anomalies can manifest as irregular execution times or abnormal execution events for many reasons, including network congestion and resource contention. Detecting such anomalies in real-time by analyzing the details of performance traces at scale is impractical due to the sheer volume of data High-Performance Computing (HPC) applications produce. In this paper, we propose formulating HPC performance anomaly detection as a signal-processing problem where anomalies can be treated as noise. We evaluate our proposed method in comparison with two other commonly used anomaly detection techniques of varying complexity based on their detection accuracy and scalability. Since real-time in-situ anomaly detection at a large scale requires lightweight methods that can handle a large volume of streaming data, we find that our proposed method provides the best trade-off. We then implement the proposed method in Chimbuko, the first online, distributed, and scalable workflow-level performance trace analysis framework. We compare our proposed signal-based anomaly detection algorithm with two other methods using a function of their accuracy, F1 score, and detection overhead. Our experiments demonstrate that our proposed approach achieves a 99% improvement for the benchmark datasets and a 93% improvement with Chimbuko traces.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2023

XploreNAS : Explore Adversarially Robust and Hardware-efficient Neural Architectures for Non-ideal Xbars

Compute In-Memory platforms such as memristive crossbars are gaining focus as they facilitate acceleration of Deep Neural Networks (DNNs) with high area and compute efficiencies. However, the intrinsic non-idealities associated with the analog nature of computing in crossbars limits the performance of the deployed DNNs. Furthermore, DNNs are shown to be vulnerable to adversarial attacks leading to severe security threats in their large-scale deployment. Thus, finding adversarially robust DNN architectures for non-ideal crossbars is critical to the safe and secure deployment of DNNs on the edge. This work proposes a two-phase algorithm-hardware co-optimization approach called XploreNAS that searches for hardware efficient and adversarially robust neural architectures for non-ideal crossbar platforms. We use the one-shot Neural Architecture Search approach to train a large Supernet with crossbar-awareness and sample adversarially robust Subnets therefrom, maintaining competitive hardware efficiency. Our experiments on crossbars with benchmark datasets (SVHN, CIFAR10, CIFAR100) show up to ~8–16% improvement in the adversarial robustness of the searched Subnets against a baseline ResNet-18 model subjected to crossbar-aware adversarial training. We benchmark our robust Subnets for Energy-Delay-Area-Products (EDAPs) using the Neurosim tool and find that with additional hardware efficiency–driven optimizations, the Subnets attain ~1.5–1.6× lower EDAPs than ResNet-18 baseline.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

A Deep Multimodal Representation Learning Framework for Accurate Molecular Properties Prediction

Drug discovery is a complex and challenging process, requiring the optimization of candidate compounds to identify those with the potential to become safe and effective drugs. Predicting molecular properties is an indispensable step in the drug discovery pipeline. Traditionally, this process is costly and time-intensive, involving multiple rounds of experiments and clinical trials, rendering it impractical for every candidate compound. Deep learning techniques have emerged as a promising approach to drug discovery to reduce the cost and time required to identify novel drugs. However, prevalent research in deep learning models focused on predicting molecular properties has primarily fixated on single-modal models, which utilize a single modality of data, neglecting the potential benefits of combining different data modalities. To overcome this limitation, we introduce MRL-Mol: a deep \textbf{M}ultimodal \textbf{R}epresentation \textbf{L}earning framework for accurate \textbf{Mol}ecular properties prediction. MRL-Mol harnesses three data modalities: sequence, graph, and image, augmenting the depth of comprehension. Leveraging a large-scale unlabeled dataset~($\sim$1M unique molecules), we pretrain MRL-Mol to extract inter- and intra-modal information. Our study demonstrates the superior performance of MRL-Mol in predicting molecular properties across six benchmark datasets, including both classification and regression tasks. Notably, MRL-Mol outperforms other state-of-the-art molecular properties prediction models. These findings suggest that by combining information from multiple data modalities, MRL-Mol can comprehend molecules better than single-modal deep learning models and identify molecular properties with better accuracy.

Yang, Yuxin↗
DOE OSTI2023

Towards deep computer vision for in-line defect detection in polymer electrolyte membrane fuel cell materials

Polymer Electrolyte Membrane (PEM) fuel cells are a promising source of alternative energy. However, their production is limited by a lack of well-established methods for quality control of their constituent materials like the membrane-electrode assembly during roll-to-roll manufacturing. One potential solution is the implementation of deep learning methods to detect unwanted defects through their detection in scanned images. Here we explore the detection of defects like scratches, pinholes, and scuffs in a sample dataset of PEM optical images using two deep learning algorithms: Patch Distribution Modeling (PaDiM) for unsupervised anomaly detection and Faster-RCNN for supervised object detection. Both methods achieve scores on performance metrics (ROC-AUC and PRO-AUC for PaDiM and AP for Faster-RCNN) that are comparable to their scores on benchmark datasets. These methods also have the potential to detect a wider range of defects compared to IR thermography and previous optical inspection methods. Overall, deep learning shows promise at detecting relevant defects of interest and has the potential to achieve real-time defect detection.

30 DIRECT ENERGY CONVERSION↗
DOE OSTI2025

PyCMG-based Simulation of Volumetric Concrete Microstructure

Concrete is a complex, heterogeneous material with a microstructure composed of aggregates, cement paste, and pores spanning multiple length scales. Understanding this microstructure is critical for advancing the performance, durability, and modeling of concrete-based systems. While experimental imaging such as X-ray computed tomography (XCT) provides valuable insights, generating large datasets with detailed ground truth annotations is both costly and labor-intensive due to challenges in segmenting similar phases, such as aggregates and cement paste, that often share similar attenuation properties. To address this, we developed a pipeline to simulate realistic 3D concrete microstructures using the open-source Python package PyCMG. This simulation effort focuses on generating high-fidelity, annotated microstructures that can serve as training or benchmarking datasets for image analysis, segmentation algorithms, and machine learning models, particularly in scenarios where experimental data is scarce.

Ziabari, Amir [Oak Ridge National Laboratory; ORNL↗
DOE OSTI2023

Digital Rocks Portal (Digital Porous Media): Connecting data, simulation and community

Digital Rocks Portal (DRP, https://www.digitalrocksportal.org) organizes and preserves imaged datasets and experimental measurements of porous materials in subsurface, and beyond, with the mission to connect them to simulation and analysis, as well as educate the research community. We have over 150 projects represented in more than 200 publications, and an active community that reuses the data, most recently in multiple machine learning applications for automating image analysis as well as the prediction of transport. Such automation is crucial for performing formation evaluation tasks in near-real time. We present benchmark datasets that have played a role in recent machine learning prediction successes in the field. We further discuss the vision for further research advances, educational materials, as well as growth and sustainability plan of this digital rock physics community resource. In particular, we are in the process of expanding into a broader repository of engineered porous materials, specifically those for energy storage and the portal will transition to Digital Porous Media (DPM) in near future.

58 GEOSCIENCES↗
DOE OSTI2020

A neural network for determination of latent dimensionality in Nonnegative Matrix Factorization

Non-negative Matrix Factorization (NMF) has proven to be a powerful unsupervised learning method for uncovering hidden features in complex and noisy datasets with applications in data mining, text recognition, dimension reduction, face recognition, anomaly detection, blind source separation, and many other fields. An important input for NMF is the latent dimensionality of the data, that is, the number of hidden features, K, present in the explored dataset. Unfortunately, and this quantity is rarely known a priori. The existing methods for determining latent dimensionality, such as Automatic Relevance Determination (ARD), are mostly heuristic and utilize different characteristics to estimate the number of hidden features. However, all of them require human presence to make a final determination of K. Here we utilize a supervised machine learning approach in combination with a recent method for model determination, called NMFk, to determine the number of hidden features automatically. NMFk performs a set of NMF simulations on an ensemble of matrices, obtained by bootstrapping the initial dataset, and estimates which K produces stable groups of latent features that reconstruct the initial dataset well. We then train a Multi-Layter Perceptron (MLP) classifier network to determine the correct number of latent features utilizing the statistics and characteristics of the NMF solution, obtained from NMFk. In order to train the MLP classifier, a training set of 58,660 matrices with predetermined latent features were factorized with NMFk. The MLP classifier in conjunction with NMFk maintains a greater than 95% success rate when applied to a held out test set. Additionally, when applied to two well-known benchmark datasets, the swimmer and MIT face data, NMFk/MLP correctly recovers the established number of hidden features. Finally, we compare the accuracy of our method to the ARD, AIC and Stability-based methods.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Training a Quantum Annealing Based Restricted Boltzmann Machine on Cybersecurity Data

A restricted Boltzmann machine (RBM) is a generative model that could be used in effectively balancing a cybersecurity dataset because the synthetic data a RBM generates follows the probability distribution of the training data. RBM training can be performed using contrastive divergence (CD) and quantum annealing (QA). QA-based RBM training is fundamentally different from CD and requires samples from a quantum computer. We present a real-world application that uses a quantum computer. Specifically, we train a RBM using QA for cybersecurity applications. The D-Wave 2000Q has been used to implement QA. RBMs are trained on the ISCX data, which is a benchmark dataset for cybersecurity. For comparison, RBMs are also trained using CD. CD is a commonly used method for RBM training. Our analysis of the ISCX data shows that the dataset is imbalanced. We present two different schemes to balance the training dataset before feeding it to a classifier. The first scheme is based on the undersampling of benign instances. The imbalanced training dataset is divided into five sub-datasets that are trained separately. A majority voting is then performed to get the result. Our results show the majority vote increases the classification accuracy up from 90.24% to 95.68%, in the case of CD. For the case of QA, the classification accuracy increases from 74.14% to 80.04%. In the second scheme, a RBM is used to generate synthetic data to balance the training dataset. We show that both QA and CD-trained RBM can be used to generate useful synthetic data. Balanced training data is used to evaluate several classifiers. Among the classifiers investigated, K-Nearest Neighbor (KNN) and Neural Network (NN) perform better than other classifiers. They both show an accuracy of 93%. Our results show a proof-of-concept that a QA-based RBM can be trained on a 64-bit binary dataset. The illustrative example suggests the possibility to migrate many practical classification problems to QA-based techniques. Further, we show that synthetic data generated from a RBM can be used to balance the original dataset.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Global 1 km land surface parameters for kilometer-scale Earth system modeling

Earth system models (ESMs) are progressively advancing towards the kilometer scale (“k-scale”). However, the surface parameters for land surface models (LSMs) within ESMs running at the k-scale are typically derived from coarse-resolution and outdated datasets. This study aims to develop a new set of global land surface parameters with a resolution of 1 km for multiple years from 2001 to 2020, utilizing the latest and most accurate available datasets. Specifically, the datasets consist of parameters related to land use and land cover, vegetation, soil, and topography. Differences between the newly developed 1 km land surface parameters and conventional parameters emphasize their potential for higher accuracy due to the incorporation of the most advanced and latest data sources. To demonstrate the capability of these new parameters, we conducted 1 km resolution simulations using the E3SM Land Model version 2 (ELM2) over the contiguous United States. Our results demonstrate that land surface parameters contribute to significant spatial heterogeneity in ELM2 simulations of soil moisture, latent heat, emitted longwave radiation, and absorbed shortwave radiation. On average, about 31 % to 54 % of spatial information is lost by upscaling the 1 km ELM2 simulations to a 12 km resolution. Using eXplainable Machine Learning (XML) methods, the influential factors driving the spatial variability and spatial information loss of ELM2 simulations were identified, highlighting the substantial impact of the spatial variability and information loss of various land surface parameters, as well as the mean climate conditions. The comparison against four benchmark datasets indicates that ELM generally performs well in simulating soil moisture and surface energy fluxes. The new land surface parameters are tailored to meet the emerging needs of k-scale LSM and ESM modeling with significant implications for advancing our understanding of water, carbon, and energy cycles under global change. The 1 km land surface parameters are publicly available at https://doi.org/10.5281/zenodo.10815170 (Li et al., 2024).

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Model Assumptions and Data Characteristics: Impacts on Domain Adaptation in Building Segmentation

Studies on domain adaptation (DA) for remote sensing (RS) imagery analysis lack consistency in selection and description of evaluation scenarios. Without properly characterizing datasets, model assumptions, and evaluation scenarios, it is difficult to objectively compare DA methods and reach conclusions about their suitability across different applications. With this motivation, this work seeks to empirically assess to which extent the interaction between data characteristics and model assumptions influences the effectiveness of DA methods. Using the widely explored task of building footprint segmentation as a case study, we perform a large-scale study across over 200 DA scenarios that include variations across view angles, areas observed, and sensors used for data acquisition. Rather than adopting different model architectures or optimization criteria, we contrast the performances of two DA methods based on adversarial learning that differ only in their assumptions about source and target domains. Informed by metadata and data characteristics unveiled using traditional computer vision (CV) techniques as well as pretrained deep models, we provide a detailed meta-analysis of experiments highlighting the importance of accurately considering data assumptions for DA in RS segmentation tasks. As demonstrated by a “cherry-picking” exercise, different claims regarding which model is best could be made by selecting different subsets of evaluation scenarios. While well-calibrated assumptions can be beneficial, mismatching assumptions can lead to negative biases in DA applications. Furthermore, this study intends to motivate the community toward more consistent evaluation protocols while providing recommendations and insights toward creating novel benchmark datasets, documenting data characteristics, application-specific knowledge, and model assumptions.

42 ENGINEERING↗
DOE OSTI2025

Adiabatic quantum support vector machines

Adiabatic quantum computers can solve difficult optimization problems (e.g., the quadratic unconstrained binary optimization problem), and they seem well suited to train machine learning models. In this paper, we describe an adiabatic quantum approach for training support vector machines. We show that the time complexity of our quantum approach is an order of magnitude better than the classical approach. Next, we compare the test accuracy of our quantum approach against a classical approach that uses the Scikit-learn library in Python across five benchmark datasets (Iris, Wisconsin Breast Cancer (WBC), Wine, Digits, and Lambeq). We show that our quantum approach obtains accuracies on par with the classical approach. Finally, we perform a scalability study in which we compute the total training times of the quantum approach and the classical approach with an increasing number of features and an increasing number of data points in the training dataset. In conclusion, our scalability results show that the quantum approach obtains a 3.5–4.5x speedup over the classical approach on datasets with many (millions of) features.

Computational Complexity↗
DOE OSTI2021

A scalable algorithm for the optimization of neural network architectures

In this work, we propose a new scalable method to optimize the architecture of an artificial neural network. The proposed algorithm, called Greedy Search for Neural Network Architecture, aims to determine a neural network with minimal number of layers that is at least as performant as neural networks of the same structure identified by other hyperparameter search algorithms in terms of accuracy and computational cost. Numerical results performed on benchmark datasets show that, for these datasets, our method outperforms state-of-the-art hyperparameter optimization algorithms in terms of attainable predictive performance by the selected neural network architecture, and time-to-solution for the hyperparameter optimization to complete.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Sensitivity evaluation of the Kudryavtsev permafrost model

Modeling is an important way to assess current and future permafrost spatial distribution and dynamics, especially in data poor areas like the Arctic region. Here, we evaluate a physics-based analytical model, Kudryavtsev's active layer model, which is widely used because it has relatively few data requirements. This model was recently incorporated into a component modeling toolbox, allowing for coupled modeling of permafrost and geomorphic processes over geological timescales. However, systematic quantitative assessment of the influence of its controlling parameters on permafrost temperature and active layer thickness predictions has not been undertaken before. In this work, we investigate the sensitivity of the Kudryavtsev's active layer model by Monte Carlo simulations to generate probability distributions for input parameters and compare predictions with a comprehensive benchmark dataset of in-situ permafrost observations over entire Alaska. Predicted permafrost surface temperature is highly dependent on mean annual air temperature (r = 0.78 on average), annual temperature amplitude (–0.41), and winter-averaged snow thickness (0.30). Uncertainty of predicted permafrost temperature is relatively small (RMSE = 1 °C), when air temperature and snow depth are well constrained. Similarly, RMSE between simulated and observed ALT at stations is ~0.08 m. However, under given air temperature and snow conditions, soil water content bias can significantly affect modeled active layer thickness (RMSE = 0.1 m or 40% of the observed active layer thickness). If soil water content has a large bias, improvements in other parameters may not significantly improve the active layer predictions of the Kudryavtsev's model.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Score-based denoising for atomic structure identification

We propose an effective method for removing thermal vibrations that complicate the task of analyzing complex dynamics in atomistic simulation of condensed matter. Our method iteratively subtracts thermal noises or perturbations in atomic positions using a denoising score function trained on synthetically noised but otherwise perfect crystal lattices. The resulting denoised structures clearly reveal underlying crystal order while retaining disorder associated with crystal defects. Purely geometric, agnostic to interatomic potentials, and trained without inputs from explicit simulations, our denoiser can be applied to simulation data generated from vastly different interatomic interactions. The denoiser is shown to improve existing classification methods, such as common neighbor analysis and polyhedral template matching, reaching perfect classification accuracy on a recent benchmark dataset of thermally perturbed structures up to the melting point. Demonstrated here in a wide variety of atomistic simulation contexts, the denoiser is general, robust, and readily extendable to delineate order from disorder in structurally and chemically complex materials.

36 MATERIALS SCIENCE↗
DOE OSTI2023

AI-accelerated protein-ligand docking for SARS-CoV-2 is 100-fold faster with no significant change in detection

Protein-ligand docking is a computational method for identifying drug leads. The method is capable of narrowing a vast library of compounds down to a tractable size for downstream simulation or experimental testing and is widely used in drug discovery. While there has been progress in accelerating scoring of compounds with artificial intelligence, few works have bridged these successes back to the virtual screening community in terms of utility and forward-looking development. We demonstrate the power of high-speed ML models by scoring 1 billion molecules in under a day (50 k predictions per GPU seconds). We showcase a workflow for docking utilizing surrogate AI-based models as a pre-filter to a standard docking workflow. Our workflow is ten times faster at screening a library of compounds than the standard technique, with an error rate less than 0.01% of detecting the underlying best scoring 0.1% of compounds. Our analysis of the speedup explains that another order of magnitude speedup must come from model accuracy rather than computing speed. In order to drive another order of magnitude of acceleration, we share a benchmark dataset consisting of 200 million 3D complex structures and 2D structure scores across a consistent set of 13 million “in-stock” molecules over 15 receptors, or binding sites, across the SARS-CoV-2 proteome. We believe this is strong evidence for the community to begin focusing on improving the accuracy of surrogate models to improve the ability to screen massive compound libraries 100 × or even 1000 × faster than current techniques and reduce missing top hits. The technique outlined aims to be a fast drop-in replacement for docking for screening billion-scale molecular libraries.

59 BASIC BIOLOGICAL SCIENCES↗