Search NASA⌕ Search

SEARCH · Search NASA

Results for “evaluation datasets”

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 487 records · Page 27

Characterizing uncertainty and population variability in the toxicokinetics of trichloroethylene and metabolites in mice, rats, and humans using an updated database, physiologically based pharmacokinetic (PBPK) model, and Bayesian approach

We have developed a comprehensive, Bayesian, PBPK model-based analysis of the population toxicokinetics of trichloroethylene (TCE) and its metabolites in mice, rats, and humans, considering a wider range of physiological, chemical, in vitro, and in vivo data than any previously published analysis of TCE. The toxicokinetics of the 'population average,' its population variability, and their uncertainties are characterized in an approach that strives to be maximally transparent and objective. Estimates of experimental variability and uncertainty were also included in this analysis. The experimental database was expanded to include virtually all available in vivo toxicokinetic data, which permitted, in rats and humans, the specification of separate datasets for model calibration and evaluation. The total combination of these approaches and PBPK analysis provides substantial support for the model predictions. In addition, we feel confident that the approach employed also yields an accurate characterization of the uncertainty in metabolic pathways for which available data were sparse or relatively indirect, such as GSH conjugation and respiratory tract metabolism. Key conclusions from the model predictions include the following: (1) as expected, TCE is substantially metabolized, primarily by oxidation at doses below saturation; (2) GSH conjugation and subsequent bioactivation in humans appear to be 10- to 100-fold greater than previously estimated; and (3) mice had the greatest rate of respiratory tract oxidative metabolism as compared to rats and humans. In a situation such as TCE in which there is large database of studies coupled with complex toxicokinetics, the Bayesian approach provides a systematic method of simultaneously estimating model parameters and characterizing their uncertainty and variability. However, care needs to be taken in its implementation to ensure biological consistency, transparency, and objectivity.

60 APPLIED LIFE SCIENCES↗

Converting tabular data into images for deep learning with convolutional neural networks

Abstract Convolutional neural networks (CNNs) have been successfully used in many applications where important information about data is embedded in the order of features, such as speech and imaging. However, most tabular data do not assume a spatial relationship between features, and thus are unsuitable for modeling using CNNs. To meet this challenge, we develop a novel algorithm, image generator for tabular data (IGTD), to transform tabular data into images by assigning features to pixel positions so that similar features are close to each other in the image. The algorithm searches for an optimized assignment by minimizing the difference between the ranking of distances between features and the ranking of distances between their assigned pixels in the image. We apply IGTD to transform gene expression profiles of cancer cell lines (CCLs) and molecular descriptors of drugs into their respective image representations. Compared with existing transformation methods, IGTD generates compact image representations with better preservation of feature neighborhood structure. Evaluated on benchmark drug screening datasets, CNNs trained on IGTD image representations of CCLs and drugs exhibit a better performance of predicting anti-cancer drug response than both CNNs trained on alternative image representations and prediction models trained on the original tabular data.

59 BASIC BIOLOGICAL SCIENCES↗

Graph-Based Prediction of Spatio-Temporal Vaccine Hesitancy From Insurance Claims Data

Growing vaccine hesitancy is contributing to the decline in immunization rates for highly contagious, vaccine-preventable childhood diseases. Therefore, there has been a significant interest in understanding how hesitancy is spreading at higher spatio-temporal resolutions, enabling more targeted interventions. Motivated by this, we study the problem of prediction of vaccine hesitancy at the ZIP Code level, referred to as the VaxHesitancy problem. A significant challenge for this problem is the lack of high-resolution data that indicates hesitancy. Here, we develop a hybrid VaxHesSTL framework that combines a Graph Neural Network (GNN) and a Recurrent Neural Network (RNN) to address the VaxHesitancy problem. The GNN uses a ZIP Code-level network to capture spatial signals from neighboring areas, while the RNN models the temporal dynamics present in the data. We train and evaluate VaxHesSTL using a large dataset, namely the All-Payer Claims Databases (APCD), for Virginia, consisting of insurance claims from over five million individuals for six years. We find that an aggregated contact network or graph, developed from a detailed activity-based population network, plays an important role in the performance of VaxHesSTL, compared to graph models based solely on spatial proximity. Experiments demonstrate that VaxHesSTL outperforms a range of state-of-the-art baselines, which rely solely on historical time series data without accounting for spatial relationships. Since hesitancy data at higher spatial resolution is often unavailable or hard to get, we incorporate an active learning approach with our VaxHesSTL framework to optimize the training set without compromising the prediction performance. We find that hesitancy data for only 18% of ZIP Codes selected by active learning allows us to forecast hesitancy for all the ZIP Codes in the Virginia.

60 APPLIED LIFE SCIENCES↗

Deep Learning-Based Data Forgery Detection in Automatic Generation Control

Automatic Generation Control (AGC) is a key control system in the power grid. It is used to calculate the Area Control Error (ACE) based on frequency and tie-line power flow between balancing areas, and then adjust power generation to maintain the power system frequency in an acceptable range. However, attackers might inject malicious frequency or tie-line power flow measurements to mislead AGC to do false generation correction which will harm the power grid operation. Such attacks are hard to be detected since they do not violate physical power system models. In this work, we propose algorithms based on Neural Network and Fourier Transform to detect data forgery attacks in AGC. Different from the few previous work that rely on accurate load prediction to detect data forgery, our solution only uses the ACE data already available in existing AGC systems. In particular, our solution learns the normal patterns of ACE time series and detects abnormal patterns caused by artificial attacks. Evaluations on the real ACE dataset show that our methods have high detection accuracy.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Reduced carbon use efficiency and increased microbial turnover with soil warming

Global soil carbon (C) stocks are expected to decline with warming, and changes in microbial processes are key to this projection. However, warming responses of critical microbial parameters such as carbon use efficiency (CUE) and biomass turnover (rB) are not well understood. Here, we determine these parameters using a probabilistic inversion approach that integrates a microbial-enzyme model with 22 years of carbon cycling measurements at Harvard Forest. We find that increasing temperature reduces CUE but increases rB, and that two decades of soil warming increases the temperature sensitivities of CUE and rB. These temperature sensitivities, which are derived from decades-long field observations, contrast with values obtained from short-term laboratory experiments. We also show that long-term soil C flux and pool changes in response to warming are more dependent on the temperature sensitivity of CUE than that of rB. Using the inversion-derived parameters, we project that chronic soil warming at Harvard Forest over six decades will result in soil C gain of <1.0% on average (1 st and 3 rd quartiles: 3.0% loss and 10.5% gain) in the surface mineral horizon. Our results demonstrate that estimates of temperature sensitivity of microbial CUE and rB can be obtained and evaluated rigorously by integrating multidecadal datasets. This approach can potentially be applied in broader spatiotemporal scales to improve long-term projections of soil C feedbacks to climate warming.

54 ENVIRONMENTAL SCIENCES↗

DP-TwoLevel: two-stage gradient subspace learning for differentially private federated learning

Federated learning (FL) enables collaborative model training across distributed data sources without sharing raw data, but faces fundamental challenges in communication efficiency and privacy. Differentially private (DP) training mitigates information leakage but introduces noise that degrades model performance, especially in high-dimensional settings. We propose DP-TwoLevel, a hierarchical gradient projection method that improves utility under fixed DP constraints by exploiting low-dimensional structure in model updates. Our approach learns a two-level PCA-based representation of gradients and applies DP noise in a reduced-dimensional subspace, thereby lowering the effective noise magnitude while preserving dominant signal components. We evaluate the method across three datasets (MNIST, Fashion-MNIST, CIFAR-10) and three privacy regimes (ϵ∈0.5, 1.0, 2.0). Across nine experimental settings, DP-TwoLevel consistently outperforms DP-FedAvg, achieving an average accuracy improvement of 9.44%, with larger gains observed in lower ϵ(higher-noise) regimes (up to +22.31%). We further analyze scalability across models ranging from 100K to 1.49M parameters and identify a variance-based success criterion: performance remains strong when the projection preserves more than 75% of gradient variance, degrades in a marginal regime (65–75%), and fails below this threshold. Our results demonstrate that structure-aware dimensionality reduction can significantly improve the privacy–utility tradeoff in FL without modifying formal privacy guarantees. We also provide empirical evidence of scaling limitations for global projections and motivate per-layer extensions for larger models.

Kotevska, Olivera [ORNL] (ORCID:0000000316772243)↗

Microaneurysms detection with the radon cliff operator in retinal fundus images

Diabetic Retinopathy (DR) is one of the leading causes of blindness in the industrialized world. Early detection is the key in providing effective treatment. However, the current number of trained eye care specialists is inadequate to screen the increasing number of diabetic patients. In recent years, automated and semi-automated systems to detect DR with color fundus images have been developed with encouraging, but not fully satisfactory results. In this study we present the initial results of a new technique for the detection and localization of microaneurysms, an early sign of DR. The algorithm is based on three steps: candidates selection, the actual microaneurysms detection and a final probability evaluation. We introduce the new Radon Cliff operator which is our main contribution to the field. Making use of the Radon transform, the operator is able to detect single noisy Gaussian-like circular structures regardless of their size or strength. The advantages over existing microaneurysms detectors are manifold: the size of the lesions can be unknown, it automatically distinguishes lesions from the vasculature and it provides a fair approach to microaneurysm localization even without post-processing the candidates with machine learning techniques, facilitating the training phase. The algorithm is evaluated on a publicly available dataset from the Retinopathy Online Challenge.

60 APPLIED LIFE SCIENCES↗

Fast automatic 3D liver segmentation based on a three-level AdaBoost-guided active shape model

Purpose: A robust, automatic, and rapid method for liver delineation is urgently needed for the diagnosis and treatment of liver disorders. Until now, the high variability in liver shape, local image artifacts, and the presence of tumors have complicated the development of automatic 3D liver segmentation. In this study, an automatic three-level AdaBoost-guided active shape model (ASM) is proposed for the segmentation of the liver based on enhanced computed tomography images in a robust and fast manner, with an emphasis on the detection of tumors. Methods: The AdaBoost voxel classifier and AdaBoost profile classifier were used to automatically guide three-level active shape modeling. In the first level of model initialization, fast automatic liver segmentation by an AdaBoost voxel classifier method is proposed. A shape model is then initialized by registration with the resulting rough segmentation. In the second level of active shape model fitting, a prior model based on the two-class AdaBoost profile classifier is proposed to identify the optimal surface. In the third level, a deformable simplex mesh with profile probability and curvature constraint as the external force is used to refine the shape fitting result. In total, three registration methods—3D similarity registration, probability atlas B-spline, and their proposed deformable closest point registration—are used to establish shape correspondence. Results: The proposed method was evaluated using three public challenge datasets: 3Dircadb1, SLIVER07, and Visceral Anatomy3. The results showed that our approach performs with promising efficiency, with an average of 35 s, and accuracy, with an average Dice similarity coefficient (DSC) of 0.94 ± 0.02, 0.96 ± 0.01, and 0.94 ± 0.02 for the 3Dircadb1, SLIVER07, and Anatomy3 training datasets, respectively. The DSC of the SLIVER07 testing and Anatomy3 unseen testing datasets were 0.964 and 0.933, respectively. Conclusions: The proposed automatic approach achieves robust, accurate, and fast liver segmentation for 3D CTce datasets. The AdaBoost voxel classifier can detect liver area quickly without errors and provides sufficient liver shape information for model initialization. The AdaBoost profile classifier achieves sufficient accuracy and greatly decreases segmentation time. These results show that the proposed segmentation method achieves a level of accuracy comparable to that of state-of-the-art automatic methods based on ASM.

60 APPLIED LIFE SCIENCES↗

MO-DE-207B-08: Radiomic CT Features Complement Semantic Annotations to Predict EGFR Mutations in Lung Adenocarcinomas

Purpose: To compare the complementary value of quantitative radiomic features to that of radiologist-annotated semantic features in predicting EGFR mutations in lung adenocarcinomas. Methods: Pre-operative CT images of 258 lung adenocarcinoma patients were available. Tumors were segmented using the sing-click ensemble segmentation algorithm. A set of radiomic features was extracted using 3D-Slicer. Test-retest reproducibility and unsupervised dimensionality reduction were applied to select a subset of reproducible and independent radiomic features. Twenty semantic annotations were scored by an expert radiologist, describing the tumor, surrounding tissue and associated findings. Minimum-redundancy-maximum-relevance (MRMR) was used to identify the most informative radiomic and semantic features in 172 patients (training-set, temporal split). Radiomic, semantic and combined radiomic-semantic logistic regression models to predict EGFR mutations were evaluated in and independent validation dataset of 86 patients using the area under the receiver operating curve (AUC). Results: EGFR mutations were found in 77/172 (45%) and 39/86 (45%) of the training and validation sets, respectively. Univariate AUCs showed a similar range for both feature types: radiomics median AUC = 0.57 (range: 0.50 – 0.62); semantic median AUC = 0.53 (range: 0.50 – 0.64, Wilcoxon p = 0.55). After MRMR feature selection, the best-performing radiomic, semantic, and radiomic-semantic logistic regression models, for EGFR mutations, showed a validation AUC of 0.56 (p = 0.29), 0.63 (p = 0.063) and 0.67 (p = 0.004), respectively. Conclusion: Quantitative volumetric and textural Radiomic features complement the qualitative and semi-quantitative radiologist annotations. The prognostic value of informative qualitative semantic features such as cavitation and lobulation is increased with the addition of quantitative textural features from the tumor region.

60 APPLIED LIFE SCIENCES↗

Machine Learning Toolkit for Extreme Scale

Support Vector Machines (SVM) is a popular machine learning technique, which has been applied to a wide range of domains such as science, finance, and social networks for supervised learning. MaTEx undertakes the challenge of designing a scalable parallel SVM training algorithm for large scale systems, which includes commodity multi-core machines, tightly connected supercomputers and cloud computing systems. Several techniques are proposed for improved speed and memory space usage including adaptive and aggressive elimination of samples for faster convergence , and sparse format representation of data samples. Several heuristics for earliest possible to lazy elimination of non-contributing samples are considered in MaTEx. In many cases, where an early sample elimination might result in a false positive, low overhead mechanisms for reconstruction of key data structures are proposed. The proposed algorithm and heuristics are implemented and evaluated on various publicly available datasets

Source record↗

Berkeley Efficient Long-Read to Long-Read Aligner and Overlapper (BELLA) v1.0

BELLA is a long-read overlapper and read-to-read aligner that exploits novel approaches for selecting reliable k-mer seeds for filtering and for detecting overlapping read pairs to reconstruct the whole genome. BELLA uses a sparse matrix-matrix multiplication for high-performance overlap detection and then performs pairwise alignment on the overlapping read pairs. BELLA can be built with different pre-existing aligners to use on each read pair, so precision rates are determined by those aligners. Our evaluations include real and synthetic datasets with varying size and complexity and include recall, precision, and running time. BELLA's overlap detection retains nearly all true alignments, with recall rates that exceed other aligners, yet it filters enough read pairs that the running time, including pairwise alignments, is closer to tools that only perform overlapping and is significantly faster than tools that also perform alignment

Guidi, Giulia↗

Graphene U-Net v1

Graphene U-Net is a library that provides a simplified platform for training deep neural networks for the task of microscopy image segmentation. It contains functions and classes that make the process of training a neural network simple such that non-ML experts can train and evaluate models on their own datasets. It uses Pytorch as a backend and can run on both CUDA-enable GPUs and CPUs. It contains the main library file Microscopy_Unet.py as well as unet.py which contains the UNET model used for this software. This can be replaced with any other fully convolutional deep learning architecture with relative ease.

Sadre, Robbie↗

Explainable Neural Architecture Search (XNAS)

Code for the paper Learning Interpretable Models Through Multi-Objective Neural Architecture Search by Zachariah Carmichael, Tim Moon, and Sam Ade Jacobs. Monumental advances in deep learning have led to unprecedented achievements across a multitude of domains. While the performance of deep neural networks is indubitable, the architectural design and interpretability of such models are nontrivial. Research has been introduced to automate the design of neural network architectures through neural architecture search (NAS). Recent progress has made these methods more pragmatic by exploiting distributed computation and novel optimization algorithms. However, there is little work in optimizing architectures for interpretability. To this end, we propose a multiobjective distributed NAS framework that optimizes for both task performance and introspection. We leverage the non-dominated sorting genetic algorithm (NSGA-II) and explainable AI (XAI) techniques to reward architectures that can be better comprehended by humans. The framework is evaluated on several image classification datasets. We demonstrate that jointly optimizing for introspection ability and task error leads to more disentangled architectures that perform within tolerable error.

Carmichael, ZachariahJ↗

CLIP Representation Enhanced Predicate Estimation

This software provides functions to perform visual predicate estimation by leveraging the pre-trained vision-language model CLIP. In addition to training the prediction estimator with a labeled dataset, it also performs performance evaluation and visualization of results.

Jayaraman Thiagarajan, Jayaraman↗

Spectral Peak Enhancement by Combining Trusted Response Elements via Machine Learning (SPECTRE-ML) v0.8.0

SPECTRE-ML (Spectral Peak Enhancement by Combining Trusted Response Elements via Machine Learning) is a machine learning based program for finding optimal clusters of radiation detector segments (i.e., pixels or voxels) in order to improve spectral performance. It provides facilities for pre-processing and analyzing training datasets, running ML algorithms, and evaluating and visualizing outputs. SPECTRE-ML outperforms simpler ad-hoc segmentation methods such as uniform depth clusters, learning detector performance trends such as dead layers, edge effects, and gain shifts. Although extensible to arbitrary highly-segmented spectroscopic radiation detectors, SPECTRE-ML currently focuses on improving spectral performance in highly-segmented CdZnTe (CZT) detectors for International Atomic Energy Agency (IAEA) non-destructive assay (NDA) safeguards tasks.

Vavrek, Jayson↗

Spatio-temporal Fourier Transformer for Long-term Dynamics Prediction (StFT) v1.0

We propose a novel machine learning model spatio-temporal Fourier transformer (StFT) to emulate long-term dynamics of multi-scale and multi-physics systems. Our method StFT overcomes the limitations of rapid error accumulation, particularly in long-term forecasting of systems characterized by complex and coupled dynamics. StFT achieves outstanding accuracy and computational efficiency by effectively capturing multi-scale interactions, and quantify the uncertainties inherent in the predictions. Our model leverages a structured hierarchy of StFT blocks, and explicitly captures dynamics across both macro- and micro- spatial scales. Evaluations conducted on three benchmark datasets (plasma, fluid, and atmospheric dynamics) demonstrate the advantages of our approach over state-of-the-art ML methods.

Bai, Zhe [Lawrence Berkeley National Laboratory (L↗

Validation of Noah-simulated Soil Temperature in the North American Land Data Assimilation System Phase 2

Soil temperature can exhibit considerable memory from weather and climate signals and is among the most important initial conditions in numerical weather and climate models. Consequently, a more accurate long-term land surface soil temperature dataset is needed to improve weather and climate simulation and prediction, and is also important for the simulation of agricultural crop yield and ecological processes. The North-American Land Data Assimilation (NLDAS) Phase 2 (NLDAS-2) has generated 31-years (1979-2009) of simulated hourly soil temperature data with a spatial resolution of 1/8o. This dataset has not been comprehensively evaluated to date. Thus, the ultimate purpose of the present work is to assess Noah-simulated soil temperature for different soil depths and timescales. We used long-term (1979-2001) observed monthly mean soil temperatures from 137 cooperative stations over the United States to evaluate simulated soil temperature for three soil layers (0-10 cm, 10-40 cm, 40-100 cm) for annual and monthly timescales. We used short-term (1997-1999) observed soil temperature from 72 Oklahoma Mesonet stations to validate simulated soil temperatures for three soil layers and for daily and hourly timescales. The results showed that the Noah land surface model (Noah LSM) generally matches observed soil temperature well for different soil layers and timescales. At greater depths, the simulation skill (anomaly correlation) decreased for all time scales. The monthly mean diurnal cycle difference between simulated and observed soil temperature revealed large midnight biases in the cold season due to small downward longwave radiation and issues related to model parameters.

land↗

PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space

Background Protein language models (PLMs) have revolutionized protein fitness prediction, yet their application to rapidly evolving viral pathogens is often confounded by extreme sequence homology. This homology leads to “data leakage” in standard random validation splits, yielding inflated performance metrics that fail to translate into real-world biosurveillance utility. Results We present Protein Representation Inference for Mutation Evaluation (PRIME), a framework that integrates domain-specific fine-tuning with a rigorous position-stratified validation protocol to evaluate viral threats. Using a dataset of 347,432 SARS-CoV-2 receptor binding domain (RBD) sequences, we demonstrate that while random training data split yields deceptive R 2 values (> 0.90), they fail to generalize to novel mutational sites. By benchmarking models up to 650 M parameters, we show that domain-specific fine-tuning of the ESM-C 600 M model with correctly stratified data provides an initial demonstration of predictive signal for binding affinity and expression at unseen mutational sites of binding affinity and expression on unseen sites (R 2 ~0.23), a significant advancement over base foundation models which exhibit no predictive power (R 2 <0). PRIME’s embedding-based clustering identified 3.03% of bat coronavirus sequences as candidates for further experimental prioritization based on their functional similarity to human-infective strains in embedding space, offering a perspective complementary to traditional phylogenetic methods. Conclusion PRIME establishes a new benchmark for the application of PLMs in pathogen surveillance. Our findings demonstrate that state-of-the-art models and fine-tuning, when paired with stratified validation, provide biologically meaningful insights into pathogen evolution and zoonotic risk.

59 BASIC BIOLOGICAL SCIENCES↗