Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Data bias”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

ET-AL: Entropy-targeted active learning for bias mitigation in materials data

Growing materials data and data-driven informatics drastically promote the discovery and design of materials. While there are significant advancements in data-driven models, the quality of data resources is less studied despite its huge impact on model performance. In this work, we focus on data bias arising from uneven coverage of materials families in existing knowledge. Observing different diversities among crystal systems in common materials databases, we propose an information entropy-based metric for measuring this bias. To mitigate the bias, we develop an entropy-targeted active learning (ET-AL) framework, which guides the acquisition of new data to improve the diversity of underrepresented crystal systems. We demonstrate the capability of ET-AL for bias mitigation and the resulting improvement in downstream machine learning models. This approach is broadly applicable to data-driven materials discovery, including autonomous data acquisition and dataset trimming to reduce bias, as well as data-driven informatics in other scientific domains.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Evaluation of data collection bias of third molar stages of mineralisation for age estimation in the living

Abstract Age assessment of the living is a fundamental procedure in the process of human identification, in order to guarantee fair treatment of individuals, which has ethical, civil, legal, and medical repercussions. The careful selection of the appropriate methods requires evaluation of several parameters: accuracy, precision of the method, as well as its reproducibility. The approach proposed by Mincer et al. adapted from Demirjian et al. exploring third molar mineralisation, is one of the most frequently considered for age estimation of the living. Thus, this work aims to assess potential bias in the data collection when applying the classification stages for dental mineralisation adapted by Mincer et al. A total of 102 orthopantomographs, of clinical origin, belonging to individuals aged between 12 and 25 years ($ \bar{\textit x} $ = 20.12 years, SD = 3.49 years; 65 females, 37 males, all of Portuguese nationality) were included and a retrospective analysis performed by five observers with different levels of experience (high, average, and basic). The performance and agreement between five observers were evaluated using Weighted Cohen’s Kappa and the Intraclass Correlation Coefficient. To access the influence of impaction on third molar classification, variables were tested using ordinal logistic regression Generalised Linear Model. It was observed that there were variations in the number of teeth identified among the observers, but the agreement levels ranged from moderate to substantial (0.4–0.8). Upon closer examination of the results, it was observed that although there were discernible differences between highly experienced observers and those with less experience, the gap was not as significant as initially hypothesised, and a greater disparity between the classifications of the upper (0.24–0.49) and lower third molars (>0.55) was observed. When bone superimposition is present, the classification process is not significantly influenced; however, variation in teeth angulation affects the assessment. The results suggest that with an efficient preparation, the level of experience as a factor can be overcome. Mincer and colleague's classification system can be replicated with ease and consistency, even though the classification of upper and lower third molars presents distinct challenges.

de Oliveira Santos, Inês (ORCID:0000000267324347)↗
DOE OSTI2021

Active learning strategy for high fidelity short-term data-driven building energy forecasting

The quality of a data-driven model is heavily dependent on the quality of data. Data from building operation often have data bias problems, which means that the data sample is collected in a way that some members of the intended data population are less likely to be included than others. Data-driven energy forecasting models built on such data hence are biased and could lead to large forecasting errors. Active learning—an effective method to defying data bias—is rarely studied or applied in the area of data-driven building energy forecasting modeling. This paper attempts to fill this gap and explores the application of active learning in data-driven building energy forecasting. The developed strategy in this paper efficiently generate informative training data within a time budget and uses block design to passively consider weather disturbances. The developed active learning strategy is applied and evaluated in both virtual and real-building testbeds against traditional data-driven methods. Via these virtual and real-building evaluation cases, we have demonstrated that the data bias problem typically exists in building operation data is resolved by applying the developed active learning strategy. Furthermore, building energy forecasting models trained from data generated from the active learning strategy have shown improved performances in both model accuracy and model extendibility perspectives. The effectiveness of the block design module is also validated to effectively consider the impact of weather conditions on active learning design.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2021

Data-driven building energy modeling with feature selection and active learning for data predictive control

Three gaps impede the development of cost-effective and accurate data-driven building energy modeling/models (DBEM) for energy forecasting and predictive control strategies. Gap 1: data bias is common in building operation data, but this topic is hardly studied in DBEM; Gap 2: high data dimensionality is common in DBEM, but a systematic and scalable methodology is lacking to solve the problem; Gap 3: the interactions between data bias and high dimensionality have not been systematically studied for DBEM and predictive control in buildings. In this work, to address the three gaps mentioned above, we develop a framework that integrates active learning and feature selection for DBEM used for whole building data predictive control (or DPC, which is a branch of model predictive control). The framework provides a systematic methodology and automatic workflow that starts with raw data from building automation systems to the establishment of data-driven energy models for DPC controllers. The developed strategies and framework are evaluated in a virtual testbed based on EnergyPlus and BCVTB. Improved performance and reduced computational complexity are observed from the DBEM built with the developed framework, as well as the DPC controller based on that DBEM, indicating the effectiveness of the developed framework.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

How close are urban scale building simulations to measured data? Examining bias derived from building metadata in urban building energy modeling

Residential and commercial buildings in the United States accounted for 40% of total energy in 2020. Building energy modeling (BEM) is a useful tool that allows individuals, researchers, companies, or utilities to save energy by optimizing buildings through estimation of building technology savings and performance projection of building energy under various environmental conditions. Urban building energy modeling (UBEM) expands the scope beyond individual buildings to the buildings in a neighborhood, city, utility and more. Yet there is a knowledge gap in the literature as to how these models compare to measured data on an individual and aggregated basis. As UBEM data and methods continue to develop, it is important to consider the accuracy, bias, and limitations of the models. Here, nation-scale data and UBEM software suite named Automatic Building Energy Modeling (AutoBEM) was used to model 50,843 buildings in Chattanooga, Tennessee. The uncalibrated simulation results were compared to aggregated 15-minute electricity data for the year 2019 with visualizations highlighting sources of bias in building data and the AutoBEM framework while considering how they relate to other UBEM methods. Estimation of building type and year of constructions are found to be the major sources of bias. Accounting for the amount of conditioned area per building significantly improves the overall fit of the simulated energy use intensity. it was found that inherent variation in building energy use contributes to R 2 values between 0.008 and 0.095 across building types but slope values near 1 for the total number of buildings. This indicates the need for building aggregation for representative building energy modeling with data sources available at an urban scale while illustrating the need for additional individual building data and model improvement beyond the originally produced UBEM models for individual building analysis.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

Case studies in bias reduction and inference for electronic health record data with selection bias and phenotype misclassification

Electronic health records (EHR) are not designed for population‐based research, but they provide easy and quick access to longitudinal health information for a large number of individuals. Many statistical methods have been proposed to account for selection bias, missing data, phenotyping errors, or other problems that arise in EHR data analysis. However, addressing multiple sources of bias simultaneously is challenging. We developed a methodological framework (R package, SAMBA ) for jointly handling both selection bias and phenotype misclassification in the EHR setting that leverages external data sources. These methods assume factors related to selection and misclassification are fully observed, but these factors may be poorly understood and partially observed in practice. As a follow‐up to the methodological work, we demonstrate how to apply these methods for two real‐world case studies, and we evaluate their performance. In both examples, we use individual patient‐level data collected through the University of Michigan Health System and various external population‐based data sources. In case study (a), we explore the impact of these methods on estimated associations between gender and cancer diagnosis. In case study (b), we compare corrected associations between previously identified genetic loci and age‐related macular degeneration with gold standard external summary estimates. These case studies illustrate how to utilize diverse auxiliary information to achieve less biased inference in EHR‐based research.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

Inclusive J /$\psi$ production at midrapidity in pp collisions at $\sqrt{s}$ = 13 TeV

We report on the inclusive J/ψ production cross section measured at the CERN Large Hadron Collider in proton–proton collisions at a center-of-mass energy $\sqrt{s}$ = 13 TeV. The J/ψ mesons are reconstructed in the e + e - decay channel and the measurements are performed at midrapidity (|y|<0.9) in the transverse-momentum interval 0 < p T < 40 GeV/c, using a minimum-bias data sample corresponding to an integrated luminosity L int =32.2 nb -1 and an Electromagnetic Calorimeter triggered data sample with L int =8.3 pb -1 . The p T -integrated J/ψ production cross section at midrapidity, computed using the minimum-bias data sample, is dσ/dy| y = 0 = 8.97±0.24 (stat)±0.48 (syst)±0.15 (lumi) μb. An approximate logarithmic dependence with the collision energy is suggested by these results and available world data, in agreement with model predictions. The integrated and p T -differential measurements are compared with measurements in pp collisions at lower energies and with several recent phenomenological calculations based on the non-relativistic QCD and Color Evaporation models.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

Exploring Data Set Bias and Decision Support with Predictive Uncertainty Through Bayesian Approximations and Convolutional Neural Networks

Individual seismic catalogs can contain multiscale observations from fault level to global scales and associated waveforms from discrete events reflect crustal structure across many different scales and locations. Seismic network aperture, geographic location, and observation distance may not provide informative guidance or intuition on how different catalogs will behave across models trained under different conditions. We rely on uncertainty to provide guardrails for when to trust model decisions, but understanding when our uncertainty is trustworthy is an open challenge. Here, in this work, we explore Bayesian approximation methods for assigning predictive uncertainty in seismic event classification problems. We find that computationally expensive Bayesian approximations do not outperform simple ensemble methods. We also find that when exploiting multiple seismic event catalogs, joint training with data from all the catalogs combined with Bayesian approximations and supervised training for classification can obscure bias and result in less robust uncertainty while also not providing substantial performance benefits compared to training individual models for each catalog.

58 GEOSCIENCES↗
DOE OSTI2022

Suppressing simulation bias in multi-modal data using transfer learning

Abstract Many problems in science and engineering require making predictions based on few observations. To build a robust predictive model, these sparse data may need to be augmented with simulated data, especially when the design space is multi-dimensional. Simulations, however, often suffer from an inherent bias. Estimation of this bias may be poorly constrained not only because of data sparsity, but also because traditional predictive models fit only one type of observed outputs, such as scalars or images, instead of all available output data modalities, which might have been acquired and simulated at great cost. To break this limitation and open up the path for multi-modal calibration, we propose to combine a novel, transfer learning technique for suppressing the bias with recent developments in deep learning, which allow building predictive models with multi-modal outputs. First, we train an initial neural network model on simulated data to learn important correlations between different output modalities and between simulation inputs and outputs. Then, the model is partially retrained, or transfer learned, to fit the experiments; a method that has never been implemented in this type of architecture. Using fewer than 10 inertial confinement fusion experiments for training, transfer learning systematically improves the simulation predictions while a simple output calibration, which we design as a baseline, makes the predictions worse. We also offer extensive cross-validation with real and carefully designed synthetic data. The method described in this paper can be applied to a wide range of problems that require transferring knowledge from simulations to the domain of experiments.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Californium-252 production at the High Flux Isotope Reactor - I: Validation study using campaign data

This paper presents a series of 252 Cf production validation and code-to-code comparison studies performed based on data from the production campaigns at the High Flux Isotope Reactor (HFIR). These studies support efforts to convert HFIR from using highly enriched uranium (HEU) fuel to low-enriched uranium (LEU) fuel. HFIR must maintain its world-class performance and missions following this conversion, and because 252 Cf is a vital neutron-emitting radioisotope used for a variety of high-impact applications (e.g., reactor startup, cancer treatment), the ability to efficiently produce 252 Cf must be preserved. In this work, the HFIRCON, Shift, ORIGEN, and TCOMP codes were deployed, and several sets of data libraries were investigated to better understand the calculation codes and the data biases. As-loaded target composition data, as-run irradiation history data, and post-irradiation measurements from recent multi-cycle irradiation campaigns of the HEU core were used to validate and determine methodology biases. Further, the findings demonstrated a good agreement, with results falling within 3 standard deviations of measurements. This paper lays the ground work for the second paper, which evaluates and compares 252 Cf production and safety metrics with the HEU core and a proposed LEU core.

07 ISOTOPE AND RADIATION SOURCES↗
DOE OSTI2020

Comparison of four learning-based methods for predicting groundwater redox status

Knowing the location where groundwater denitrification occurs, or by proxy the groundwater redox status (oxic, mixed, and anoxic), is valuable information for assessing and managing potential agricultural land-use impacts on freshwater quality. We compare the efficacy of supervised (Linear Discriminant Analysis LDA; Boosted Regression Trees, BRT; and Random Forest, RF) and unsupervised (Modified Self-Organizing Map, MSOM) learning-based methods to predict groundwater redox status in the agriculturally dominated Tasman, Waikato, and Wellington regions of New Zealand. Thresholds applied to regional groundwater-quality samples provide redox status variables and learn heuristics constrained by these variables and applied to spatial factors (climate, elevation, geologic, hydrology soils, and well depth) identify optimal sets of regional predictor variables. A split-sample approach is used to train and test the learning methods ability to predict redox status using the optimal predictor variables. Overall, the supervised methods demonstrate a prediction bias toward oxic conditions and inability to perform statistically well when using independent regional data; for example, consider kappa statistics for BRT (Tasman: 0.42, Waikato: 0.38, Wellington: 0.17), RF (Tasman: 0.42, Waikato: 0.47, Wellington: 0.17 and LDA (Tasman: 0.46, Waikato: 0.32, Wellington: 0.17). By contrast, the unsupervised method performs statistically well when predicting oxic, mixed, and anoxic conditions and corresponding depths when using independent regional data; for example, consider MSOM kappa statistics for Tasman: 0.78, Waikato: 0.80, Wellington: 0.76. The unsupervised learning method provides the added benefits of being (1) able to combine predictions into 3D regional anoxic probability plots for interpreting the spatial influence of paleosols and groundwater flowpaths on redox status, and (2) readily extended to map 3D redox status across New Zealand and other countries despite data bias and sparsity.

machine learning algorithms, Random Forest, booste↗
DOE OSTI2025

Challenges in predicting protein-protein interactions of understudied viruses: Arenavirus-human interactions

Understanding protein-protein interactions (PPIs) between viruses and host organisms is crucial for uncovering infection mechanisms and identifying potential therapeutic targets. The ability to generalize PPI predictive models across understudied viruses presents a significant challenge. In this work, we use arenavirus-human PPIs to illustrate the difficulties associated with model generalization, which are compounded by a lack of both positive and negative data. We employ a Transfer Learning approach to investigate arenavirus-human PPIs by utilizing models trained on better-studied virus-human and human-human PPIs. Additionally, we curate and assess four types of negative sampling datasets to evaluate their impact on model performance. Despite the overall high accuracies (93–99 %) and AUPRC scores (0.8–0.9) appearing promising, further analysis indicates that these performance metrics can be misleading due to data leakage, data bias, and overfitting, especially concerning under-represented viral proteins. We reveal these gaps and assess the impact of data imbalance using standard k-fold cross-validation and Independent Blind Testing with a Balanced Dataset, resulting in a drop in accuracy below 50 %. We propose a viral protein-specific evaluation framework that categorizes viral proteins into majority and minority classes based on their representation in the dataset, enabling comparison of model performance across these groups using balanced accuracies. This framework offers a more robust evaluation of model generalizability, addressing biases inherent in standard evaluation techniques and paving the way for more reliable PPI prediction models for understudied viruses.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Photometric redshift estimation with convolutional neural networks and galaxy images: Case study of resolving biases in data-driven methods

Deep-learning models have been increasingly exploited in astrophysical studies, but these data-driven algorithms are prone to producing biased outputs that are detrimental for subsequent analyses. In this work, we investigate two main forms of biases: class-dependent residuals, and mode collapse. We do this in a case study, in which we estimate photometric redshift as a classification problem using convolutional neural networks (CNNs) trained with galaxy images and associated spectroscopic redshifts. We focus on point estimates and propose a set of consecutive steps for resolving the two biases based on CNN models, involving representation learning with multichannel outputs, balancing the training data, and leveraging soft labels. The residuals can be viewed as a function of spectroscopic redshift or photometric redshift, and the biases with respect to these two definitions are incompatible and should be treated individually. We suggest that a prerequisite for resolving biases in photometric space is resolving biases in spectroscopic space. Experiments show that our methods can better control biases than benchmark methods, and they are robust in various implementing and training conditions with high-quality data. Our methods hold promises for future cosmological surveys that require a good constraint of biases, and they may be applied to regression problems and other studies that make use of data-driven models. Nonetheless, the bias-variance tradeoff and the requirement of sufficient statistics suggest that we need better methods and optimized data usage strategies.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Optimal adjustment sets for causal query estimation in partially observed biomolecular networks

Abstract Causal query estimation in biomolecular networks commonly selects a ‘valid adjustment set’, i.e. a subset of network variables that eliminates the bias of the estimator. A same query may have multiple valid adjustment sets, each with a different variance. When networks are partially observed, current methods use graph-based criteria to find an adjustment set that minimizes asymptotic variance. Unfortunately, many models that share the same graph topology, and therefore same functional dependencies, may differ in the processes that generate the observational data. In these cases, the topology-based criteria fail to distinguish the variances of the adjustment sets. This deficiency can lead to sub-optimal adjustment sets, and to miss-characterization of the effect of the intervention. We propose an approach for deriving ‘optimal adjustment sets’ that takes into account the nature of the data, bias and finite-sample variance of the estimator, and cost. It empirically learns the data generating processes from historical experimental data, and characterizes the properties of the estimators by simulation. We demonstrate the utility of the proposed approach in four biomolecular Case studies with different topologies and different data generation processes. The implementation and reproducible Case studies are at https://github.com/srtaheri/OptimalAdjustmentSet.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Development and validation of HERWIG 7 tunes from CMS underlying-event measurements

This paper presents new sets of parameters (“tunes”) for the underlying-event model of the ${\textsc {herwig}} \,7$ event generator. These parameters control the description of multiple-parton interactions (MPI) and colour reconnection in ${\textsc {herwig}} \,7$, and are obtained from a fit to minimum-bias data collected by the CMS experiment at $\sqrt{s}=0.9$, 7, and $13 \,\text {Te}\text {V} $. The tunes are based on the NNPDF 3.1 next-to-next-to-leading-order parton distribution function (PDF) set for the parton shower, and either a leading-order or next-to-next-to-leading-order PDF set for the simulation of MPI and the beam remnants. Predictions utilizing the tunes are produced for event shape observables in electron-positron collisions, and for minimum-bias, inclusive jet, top quark pair, and Z and W boson events in proton-proton collisions, and are compared with data. Each of the new tunes describes the data at a reasonable level, and the tunes using a leading-order PDF for the simulation of MPI provide the best description of the data.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2026

Ten questions concerning Large Language Models (LLMs) for building applications

Large Language Models (LLMs) are emerging as powerful AI tools capable of transforming how building information is collected, processed, analyzed, and applied across diverse research areas. Their capabilities can help building operators, facility managers and other stakeholders such as designers, architects and engineers by providing actionable insights for decision-making across planning, construction, operations, and maintenance of buildings and facilities. This paper explores ten key questions concerning the role of LLMs in shaping sustainable, intelligent, and human-centric buildings. From fundamental definitions to advanced applications, we examine how LLMs facilitate decision-making across the life cycle of buildings and energy systems. LLMs can enhance life cycle assessments (LCA), building energy simulations, and real-time data integration, empowering more efficient and adaptive human-AI environments. They can also contribute to streamlining regulatory compliance, improving post-occupancy evaluations, and fostering more inclusive and participatory design processes. Additionally, this paper addresses the ethical challenges posed by LLMs, such as bias, data privacy, and environmental impacts, and explores their potentials in advancing intelligent digital twins (DT) for ongoing building operations and maintenance. Built upon our applied research using LLMs and the review of tools, datasets, and research gaps, we provide a forward-looking perspective on how LLMs can drive innovation, collaboration, and productivity in the built environment while supporting ethical and effective implementation.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗