Search NASA⌕ Search

SEARCH · Search NASA

Results for “descriptor selection”

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 OSTI2018

Ethylene versus ethane: A DFT-based selectivity descriptor for efficient catalyst screening

The production of ethylene without its hydrogenation to ethane is a challenge for several catalytic processes. Here, in this study, we present a catalyst screening scheme, where the Gibbs free energy difference between the ethylene hydrogenation barrier and ethylene desorption energy is defined as a descriptor for ethylene selectivity. Using plane-wave, dispersion-corrected DFT calculations, we evaluated the descriptor values over the (111) facets of Pt, Pd, and Cu as well as a series of Pt- and Pd-based bimetallic alloys. Our predicted descriptor values indicate that the addition of a Group IB metal (Cu, Ag, or Au) to Pt or Pd improves ethylene selectivity. Ag induces the most significant improvement at 50% while Au has the strongest effect at 75% atomic composition. Pd-based alloys exhibit superior ethylene selectivity over their Pt-based counterparts. Our descriptor model offers an efficient method for the initial screening of catalysts with improved ethylene selectivity.

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

Automated descriptor selection, volcano curve generation, and active site determination using the DescMAP software

The material space for catalyst discovery is expansive. Volcano curves are traditionally employed to provide physical insights into optimal catalyst characteristics for new material selection. Their generation lies on a single descriptor picked using expert knowledge. Here we present DescMAP, a Python-based software, to automate the selection of descriptors, the generation of volcano maps, and the identification of active sites for structure-sensitive reactions. Here, we consider traditional energy-based and geometric descriptors for structure-sensitive reactions. DescMAP is integrated with the Virtual Kinetic Laboratory (VLab) to provide multiple functionalities. It inputs spreadsheets or template files for flexibility and outputs interactive graphs for post-processing. We demonstrate its features using the non-oxidative dehydrogenation of ethane to ethylene over (111) closed-packed surfaces and the methane total oxidation over various Pt facets. It can be easily applied to other complex chemistries and achieves quick screening of potential catalysts.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2019

Reactivity and selectivity descriptors of dioxygen activation routes on metal oxides

The activation of dioxygen at typically isolated two-electron reduced centers can lead to the formation of electrophilic superoxo or peroxo species, providing an essential route to form reactive O 2 -derived species in biological, organometallic, and heterogeneous catalysts. Alternatively, O 2 activation can proceed via outer sphere routes, circumventing the formation of bound peroxo (OO*) species during oxidation catalysis by forming H 2 O 2 (g), which can react with another reduced center to form H 2 O. The electronic and binding properties of metal oxides that determine the relative rates of these activation routes are assessed here by systematic theoretical treatments using density functional theory (DFT). These methods are combined with conceptual frameworks based on thermochemical cycles and crossing potential models to assess the most appropriate descriptors for the activation barriers for each route using Keggin polyoxometalates as illustrative examples. In doing so, we show that inner sphere routes, which form OO* species via O 2 activation on the O-vacancies (*) formed in the reduction part of redox cycles, are mediated by early transition states that only weakly sense the oxide binding properties. Outer sphere routes form H 2 O 2 (g) via O 2 activation on OH pairs (H/OH*) formed by dissociation of H 2 O on O-vacancies; their rates and activation barriers reflect the rates of the first H-atom transfer from H/OH* to O 2 . The activation barriers for this H-transfer step depend on the binding energy of more weakly-bound H-atom in H/OH* pairs (HAE 2 ) and on the ˙OOH-surface interaction energy at its product state ($E_{int}$ 0 ). The $E_{int}$ 0 values are similar among oxides unless a large charge-balancing cation is present and interacts with radical ˙OOH; consequently, HAE 2 acts as an appropriate descriptor of the outer sphere dynamics. HAE 2 also determines the thermodynamics of H 2 O dissociation on O-vacancies, which influence the inner and outer sphere rates by setting the relative coverage of * and H/OH*. So these results, in turn, show that HAE 2 is a complete descriptor of the reactivity and selectivity of oxides for O 2 activation; the O-atoms in more reducible oxides (more negative HAE 2 ) exhibit a greater preference for the inner sphere routes and for the formation of electrophilic OO* intermediates that mediate epoxidation and O-insertion reactions during catalytic redox cycles. Large charge-balancing cations locally modify $E_{int}$ 0 values that determine the outer sphere rates and thus can be used to alter the preference of O-atoms to either inner or outer sphere routes.

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

Machine-learning-guided descriptor selection for predicting corrosion resistance in multi-principal element alloys

More than $270 billion is spent on combatting corrosion annually in the USA alone. As such, we present a machine-learning (ML) approach to down select corrosion-resistant alloys. Our focus is on a non-traditional class of alloys called multi-principal element alloys (MPEAs). Given the vast search space due to the variety of compositions and descriptors to be considered, and based upon existing corrosion data for MPEAs, we demonstrate descriptor optimization to predict corrosion resistance of any given MPEA. Our ML model with descriptor optimization predicts the corrosion resistance of a given MPEA in the presence of an aqueous environment by down selecting two environmental descriptors (pH of the medium and halide concentration), one chemical composition descriptor (atomic % of element with minimum reduction potential), and two atomic descriptors (difference in lattice constant (Δa) and average reduction potential). Our findings show that, while it is possible to down select corrosion-resistant MPEAs by using ML from a large search space, a larger dataset and higher quality data are needed to accurately predict the corrosion rate of MPEAs. This study shows both the promise and the perils of ML when applied to a complex chemical phenomenon like corrosion of alloys.

36 MATERIALS SCIENCE↗
DOE OSTI2022

A systematic method for selecting molecular descriptors as features when training models for predicting physiochemical properties

Machine learning has proven to be a powerful tool for accelerating biofuel development. Although numerous models are available to predict a range of properties using chemical descriptors, there is a trade-off between interpretability and performance. Neural networks provide predictive models with high accuracy at the expense of some interpretability, while simpler models such as linear regression often lack in accuracy. In addition to model architecture, feature selection is also critical for developing interpretable and accurate predictive models. We present a method for systematically selecting molecular descriptor features and developing interpretable machine learning models without sacrificing accuracy. Our method simplifies the process of selecting features by reducing feature multicollinearity and enables discoveries of new relationships between global properties and molecular descriptors. To demonstrate our approach, we developed models for predicting melting point, boiling point, flash point, yield sooting index, and net heat of combustion with the help of the Tree-based Pipeline Optimization Tool (TPOT). For training, we used publicly available experimental data for up to 8351 molecules. Our models accurately predict various molecular properties for organic molecules (mean absolute percent error (MAPE) ranges from 3.3% to 10.5%) and provide a set of features that are well-correlated to the property. This method enables researchers to explore sets of features that significantly contribute to the prediction of the property, offering new scientific insights. To help accelerate early stage biofuel research and development, we also integrated the data and models into a open-source, interactive web tool.

09 BIOMASS FUELS↗
DOE OSTI2024

Prediction of Dielectric Constant in Series of Polymers by Quantitative Structure-Property Relationship (QSPR)

This work is devoted to the investigation of dielectric permittivity which is influenced by electronic, ionic, and dipolar polarization mechanisms, contributing to the material’s capacity to store electrical energy. In this study, an extended dataset of 86 polymers was analyzed, and two quantitative structure–property relationship (QSPR) models were developed to predict dielectric permittivity. From an initial set of 1273 descriptors, the most relevant ones were selected using a genetic algorithm, and machine learning models were built using the Gradient Boosting Regressor (GBR). In contrast to Multiple Linear Regression (MLR)- and Partial Least Squares (PLS)-based models, the gradient boosting models excel in handling nonlinear relationships and multicollinearity, iteratively optimizing decision trees to improve accuracy without overfitting. The developed GBR models showed high R2 coefficients of 0.938 and 0.822, for the training and test sets, respectively. An Accumulated Local Effect (ALE) technique was applied to assess the relationship between the selected descriptors—eight for the GB_A model and six for the GB_B model, and their impact on target property. ALE analysis revealed that descriptors such as TDB09m had a strong positive effect on permittivity, while MLOGP2 showed a negative effect. These results highlight the effectiveness of the GBR approach in predicting the dielectric properties of polymers, offering improved accuracy and interpretability.

Ascencio-Medina, Estefania↗
DOE OSTI2016

Theory-Guided Machine Learning in Materials Science

Materials scientists are increasingly adopting the use of machine learning tools to discover hidden trends in data and make predictions. Applying concepts from data science without foreknowledge of their limitations and the unique qualities of materials data, however, could lead to errant conclusions. The differences that exist between various kinds of experimental and calculated data require careful choices of data processing and machine learning methods. Here, we outline potential pitfalls involved in using machine learning without robust protocols. We address some problems of overfitting to training data using decision trees as an example, rational descriptor selection in the field of perovskites, and preserving physical interpretability in the application of dimensionality reducing techniques such as principal component analysis. We show how proceeding without the guidance of domain knowledge can lead to both quantitatively and qualitatively incorrect predictive models.

36 MATERIALS SCIENCE↗
DOE OSTI2020

A Deep Neural Network for Accurate and Robust Prediction of the Glass Transition Temperature of Polyhydroxyalkanoate Homo- and Copolymers

The purpose of this study was to develop a data-driven machine learning model to predict the performance properties of polyhydroxyalkanoates (PHAs), a group of biosourced polyesters featuring excellent performance, to guide future design and synthesis experiments. A deep neural network (DNN) machine learning model was built for predicting the glass transition temperature, Tg, of PHA homo- and copolymers. Molecular fingerprints were used to capture the structural and atomic information of PHA monomers. The other input variables included the molecular weight, the polydispersity index, and the percentage of each monomer in the homo- and copolymers. The results indicate that the DNN model achieves high accuracy in estimation of the glass transition temperature of PHAs. In addition, the symmetry of the DNN model is ensured by incorporating symmetry data in the training process. The DNN model achieved better performance than the support vector machine (SVD), a nonlinear ML model and least absolute shrinkage and selection operator (LASSO), a sparse linear regression model. The relative importance of factors affecting the DNN model prediction were analyzed. Sensitivity of the DNN model, including strategies to deal with missing data, were also investigated. Compared with commonly used machine learning models incorporating quantitative structure–property (QSPR) relationships, it does not require an explicit descriptor selection step but shows a comparable performance. The machine learning model framework can be readily extended to predict other properties.

quantitative structure–property relationship (QSPR↗
DOE OSTI2022

A general strategy and a consolidated mechanism for low-methane hydrogenolysis of polyethylene over ruthenium

Polyethylene (PE) is one of the most environment-threatening plastic waste. Its Ru-catalyzed hydrogenolysis is rapid but produces too much methane. Here, in this study, low-density PE hydrogenolysis is performed at mild conditions and short times over Ru-doped zirconia catalysts (Ru-XZr, X = Ti, Nb, Ce, W, V, Mo, Fe) to determine low-methane catalysts. Methane is produced via direct terminal C-C scission and surface cascade of consecutive C-C scissions, with the latter sensitive to hydrogen availability and dominant in hydrogen-lean conditions. Reactivity studies, characterization and theory reveal that the most effective dopant oxides (W, V, and Mo) are intermediately reducible, as they store and supply extra hydrogen to Ru via reverse hydrogen spillover. This hydrogen readily hydrogenates and desorbs long alkyl surface intermediates that would otherwise produce cascade methane. Our proposed mechanism reconciles the low methane production achieved by increasing the hydrogen pressure or reducing the particle size and exposes the key selectivity descriptors.

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

Thermochemical Data Fusion Using Graph Representation Learning

Large databases are required for “Big Data” applications in catalysis and materials science. Thermochemical databases can be created by combining data from various sources and by correcting low-fidelity datasets to higher accuracy with minimal computation. To achieve this “data fusion”, thermochemical quantities of interest, calculated at various levels of density functional theory (DFT), need to be mapped to the same, high levels of theory. In this work, a graph theoretical, statistical framework is proposed for such tasks. Subgraph frequencies are shown to provide a natural representation for learning these fusion maps. The maps are linear and are learnt with automated descriptor selection. Using a dataset of as few as ~1% from the QM9 database of 133,885 molecules, these models can predict multiple thermochemical quantities at a higher level of theory with an accuracy of 1 kcal/mol. Here, the method is explainable, generalizable, and provides a diagnostic tool for outlier identification

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Density functional theory studies of transition metal carbides and nitrides as electrocatalysts

Transition metal carbides and nitrides are interesting non-precious materials that have been shown to replace or reduce the loading of precious metals for catalyzing several important electrochemical reactions. The purpose of this review is to summarize density functional theory (DFT) studies, describe reaction pathways, identify activity and selectivity descriptors, and present a future outlook in designing carbide and nitride catalysts for the hydrogen evolution reaction (HER), oxygen evolution reaction (OER), oxygen reduction reaction (ORR), nitrogen reduction reaction (N 2 RR), CO 2 reduction reaction (CO 2 RR) and alcohol oxidation reactions. Furthermore, this topic is of high interest to scientific communities working in the field of electrocatalysis and this review should provide theoretical guidance for the rational design of improved carbide and nitride electrocatalysts.

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

From electricity to fuels: Descriptors for C 1 selectivity in electrochemical CO 2 reduction

Electrochemical reduction of carbon dioxide (CO 2 RR) over transition metals follows a complex reaction network. Here, we combine observations from experimental literature with a theoretical analysis of energetics to rationalize that not all intermediates in the reduction of CO 2 are formed through direct protonation steps. We derive a selectivity map for two-electron products (carbon monoxide (CO) and formate) on pure metal surfaces using only the CO and OH binding energies as descriptors. For the pure metals that are selective towards CO formation, the variation of the CO binding energy is sufficient to further subdivide the map into domains that predominantly form H 2 , CO, and more reduced products. Our analysis rationalizes experimentally observed product distributions in CO 2 RR across pure metal systems. Overall, we highlight the need for additional material screening descriptors for CO 2 R and the importance of considering competition from the elementary steps of the hydrogen evolution reaction.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2026

Hofmann Stability Charts Revisited for PIP-II: From Classical Theory to Assumption-Free and ML-Driven Maps

The Hofmann stability chart remains a standard for visualizing parametric resonances in space-charge–dominated linacs, but its use typically relies on non-oscillatory Vlasov dispersion relations with simplifying assumptions (continuous focusing, KV phase space, linear optics, limited transverse–longitudinal coupling). We revisit the chart for the PIP-II linac along three tracks. (1) We reproduce the conventional maps in the (νz/νx, νx/ν0x) plane for relevant εz/εx, providing a validated reference. (2) We remove key assumptions by deriving stability surfaces directly from multi-particle tracking with realistic lattice discreteness, RF defocusing, solenoid/quad optics, and bunched-beam dynamics; local tunes and early-time growth rates are estimated from envelope oscillations and projected to the same coordinates. These assumption-reduced maps recover the canonical stopbands while revealing shifts and broadenings driven by tune modulation, non-KV distributions, and transverse–longitudinal coupling at PIP-II intensities. (3) We train a compact machine-learning surrogate that emulates the growth surface from zero-current optics, tune depression, emittance ratio, bunching factor, and selected lattice descriptors, enabling rapid scans and online working-point selection. We compare the three representations on representative PIP-II sections and discuss implications for commissioning guard bands, resonance avoidance, and routine operations.

Pathak, Abhishek [Fermilab] (ORCID:000000021704208↗
DOE OSTI2024

Phase Selection Rules of Multi‐Principal Element Alloys

Abstract Computational prediction of phase stability of multi‐principal element alloys (MPEAs) holds a lot of promise for rapid exploration of the enormous design space and autonomous discovery of superior structural and functional properties. Regardless of many plausible works that rely on phenomenological theory and machine learning, precise prediction is still limited by insufficient data and the lack of interpretability of some machine learning algorithms, e.g., convolutional neural network. In this work, a comprehensive approach is presented, encompassing the development of a complete dataset that contains 72 387 density functional theory calculations, as well as a predictive global phenomenological descriptor. The phase selection descriptor, based on atomic electronegativity and valence electron concentration, significantly outperforms the widely used valence electron concentration, excelling in both accuracy (with an f1 score of 63% compared to 47%) and its ability to predict the HCP phase (0.48 recall compared to 0). The comprehensive data mining on the global design space of 61 425 quaternary MPEAs made from 28 possible metals, together with the phenomenological theory and physical interpretation, will set up a solid computational science foundation for data‐driven exploration of MPEAs.

Chemistry↗
DOE OSTI2018

Prediction of Adsorption Energies for Chemical Species on Metal Catalyst Surfaces Using Machine Learning

Computational catalyst screening has the potential to significantly accelerate heterogeneous catalyst discovery. Typically, this involves developing microkinetic reactor models that are based on parameters obtained from density functional theory and transition-state theory. To reduce the large computational cost involved in computing various adsorption and transition-state energies of all possible surface states on a large number of catalyst models, linear scaling relations for surface intermediates and transition states have been developed that only depend on a few, typically one or two descriptors, such as the carbon atom adsorption energy. As a result, only the descriptor values have to be computed for various active site models to generate volcano curves in activity or selectivity. Unfortunately, for more complex chemistries the predictability of linear scaling relations is unknown. Also, the selection of descriptors is essentially a trial and error process. Here, using a database of adsorption energies of the surface species involved in the decarboxylation and decarbonylation of propionic acid over eight monometalic transition-metal catalyst surfaces (Ni, Pt, Pd, Ru, Rh, Re, Cu, Ag), we tested if nonlinear machine learning (ML) models can outperform the linear scaling relations in prediction accuracy when predicting the adsorption energy for various species on a metal surface based on data from the rest of the metal surfaces. We found linear scaling relations to hold well for predictions across metals with a mean-absolute error of 0.12 eV, and ML methods being unable to outperform linear scaling relations when the training dataset contains a complete set of energies for all of the species on various metal surfaces. Only when the training dataset is incomplete, namely, contains a random subset of species’ energies for each metal, a currently unlikely scenario for catalyst screening, do kernel-based ML models significantly outperform linear scaling relations. We also found that simple coordinate-free species descriptors, such as bond counts, achieve as good results as sophisticated coordinate-based descriptors. Finally, we propose an approach for automatic discovery of appropriate metal descriptors using principal component analysis.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2015

Local curvature analysis for classifying breast tumors: Preliminary analysis in dedicated breast CT

Purpose: The purpose of this study is to measure the effectiveness of local curvature measures as novel image features for classifying breast tumors. Methods: A total of 119 breast lesions from 104 noncontrast dedicated breast computed tomography images of women were used in this study. Volumetric segmentation was done using a seed-based segmentation algorithm and then a triangulated surface was extracted from the resulting segmentation. Total, mean, and Gaussian curvatures were then computed. Normalized curvatures were used as classification features. In addition, traditional image features were also extracted and a forward feature selection scheme was used to select the optimal feature set. Logistic regression was used as a classifier and leave-one-out cross-validation was utilized to evaluate the classification performances of the features. The area under the receiver operating characteristic curve (AUC, area under curve) was used as a figure of merit. Results: Among curvature measures, the normalized total curvature (C{sub T}) showed the best classification performance (AUC of 0.74), while the others showed no classification power individually. Five traditional image features (two shape, two margin, and one texture descriptors) were selected via the feature selection scheme and its resulting classifier achieved an AUC of 0.83. Among those five features, the radial gradient index (RGI), which is a margin descriptor, showed the best classification performance (AUC of 0.73). A classifier combining RGI and C{sub T} yielded an AUC of 0.81, which showed similar performance (i.e., no statistically significant difference) to the classifier with the above five traditional image features. Additional comparisons in AUC values between classifiers using different combinations of traditional image features and C{sub T} were conducted. The results showed that C{sub T} was able to replace the other four image features for the classification task. Conclusions: The normalized curvature measure contains useful information in classifying breast tumors. Using this, one can reduce the number of features in a classifier, which may result in more robust classifiers for different datasets.

60 APPLIED LIFE SCIENCES↗