The Experts below are selected from a list of 47403 Experts worldwide ranked by ideXlab platform
John M Gregoire - One of the best experts on this subject based on the ideXlab platform.
-
materials representation and transfer learning for multi Property prediction
Applied physics reviews, 2021Co-Authors: Shufeng Kong, Dan Guevarra, Carla P Gomes, John M GregoireAbstract:The adoption of machine learning in materials science has rapidly transformed materials Property prediction. Hurdles limiting full capitalization of recent advancements in machine learning include the limited development of methods to learn the underlying interactions of multiple elements as well as the relationships among multiple properties to facilitate Property prediction in new Composition spaces. To address these issues, we introduce the Hierarchical Correlation Learning for Multi-Property Prediction (H-CLMP) framework that seamlessly integrates: (i) prediction using only a material's Composition, (ii) learning and exploitation of correlations among target properties in multi-target regression, and (iii) leveraging training data from tangential domains via generative transfer learning. The model is demonstrated for prediction of spectral optical absorption of complex metal oxides spanning 69 three-cation metal oxide Composition spaces. H-CLMP accurately predicts non-linear Composition-Property relationships in Composition spaces for which no training data are available, which broadens the purview of machine learning to the discovery of materials with exceptional properties. This achievement results from the principled integration of latent embedding learning, Property correlation learning, generative transfer learning, and attention models. The best performance is obtained using H-CLMP with transfer learning [H-CLMP(T)] wherein a generative adversarial network is trained on computational density of states data and deployed in the target domain to augment prediction of optical absorption from Composition. H-CLMP(T) aggregates multiple knowledge sources with a framework that is well suited for multi-target regression across the physical sciences.
-
materials representation and transfer learning for multi Property prediction
arXiv: Learning, 2021Co-Authors: Shufeng Kong, Dan Guevarra, Carla P Gomes, John M GregoireAbstract:The adoption of machine learning in materials science has rapidly transformed materials Property prediction. Hurdles limiting full capitalization of recent advancements in machine learning include the limited development of methods to learn the underlying interactions of multiple elements, as well as the relationships among multiple properties, to facilitate Property prediction in new Composition spaces. To address these issues, we introduce the Hierarchical Correlation Learning for Multi-Property Prediction (H-CLMP) framework that seamlessly integrates (i) prediction using only a material's Composition, (ii) learning and exploitation of correlations among target properties in multi-target regression, and (iii) leveraging training data from tangential domains via generative transfer learning. The model is demonstrated for prediction of spectral optical absorption of complex metal oxides spanning 69 3-cation metal oxide Composition spaces. H-CLMP accurately predicts non-linear Composition-Property relationships in Composition spaces for which no training data is available, which broadens the purview of machine learning to the discovery of materials with exceptional properties. This achievement results from the principled integration of latent embedding learning, Property correlation learning, generative transfer learning, and attention models. The best performance is obtained using H-CLMP with Transfer learning (H-CLMP(T)) wherein a generative adversarial network is trained on computational density of states data and deployed in the target domain to augment prediction of optical absorption from Composition. H-CLMP(T) aggregates multiple knowledge sources with a framework that is well-suited for multi-target regression across the physical sciences.
-
generating information rich high throughput experimental materials genomes using functional clustering via multitree genetic programming and information theory
ACS Combinatorial Science, 2015Co-Authors: Santosh K Suram, Joel A Haber, Jian Jin, John M GregoireAbstract:High-throughput experimental methodologies are capable of synthesizing, screening and characterizing vast arrays of combinatorial material libraries at a very rapid rate. These methodologies strategically employ tiered screening wherein the number of Compositions screened decreases as the complexity, and very often the scientific information obtained from a screening experiment, increases. The algorithm used for down-selection of samples from higher throughput screening experiment to a lower throughput screening experiment is vital in achieving information-rich experimental materials genomes. The fundamental science of material discovery lies in the establishment of Composition–structure–Property relationships, motivating the development of advanced down-selection algorithms which consider the information value of the selected Compositions, as opposed to simply selecting the best performing Compositions from a high throughput experiment. Identification of Property fields (Composition regions with distinct Composition-Property relationships) in high throughput data enables down-selection algorithms to employ advanced selection strategies, such as the selection of representative Compositions from each field or selection of Compositions that span the Composition space of the highest performing field. Such strategies would greatly enhance the generation of data-driven discoveries. We introduce an informatics-based clustering of Composition-Property functional relationships using a combination of information theory and multitree genetic programming concepts for identification of Property fields in a Composition library. We demonstrate our approach using a complex synthetic Composition-Property map for a 5 at. % step ternary library consisting of four distinct Property fields and finally explore the application of this methodology for capturing relationships between Composition and catalytic activity for the oxygen evolution reaction for 5429 catalyst Compositions in a (Ni–Fe–Co–Ce)O_x library.
Daniel Boyd - One of the best experts on this subject based on the ideXlab platform.
-
modulation of strontium release from a tertiary borate glass through substitution of alkali for alkali earth oxide
Journal of Non-crystalline Solids, 2016Co-Authors: Kathleen Macdonald, Margaret A Hanson, Daniel BoydAbstract:Abstract The effect of the substitution of Na2O for SrO in a series of nine borate glasses was studied to understand the effect of alkali for alkali earth oxide substitution in the boron transition range. Glasses were analyzed for post-firing Composition, density, glass transition, 11B MAS-NMR and ion release in a simulated physiological condition (immersion in PBS at 37 °C over time points of 1, 7, 30 and 60 days). Post-Compositional analysis revealed decreases in boron and sodium content during glass firing, and allowed for improvements in Composition Property relationships. Increased substitution of sodium resulted in decreases in glass density, glass transition, and non-bridging oxygen fraction in the glass. Strontium ion release kinetics were governed by Fickian diffusion and were not altered by the substitution of sodium for strontium in the glass. Boron ion release varied from pure Fickian diffusion controlled to a parabolic release demonstrating precipitation with high sodium contents.
-
methotrexate loaded glass ionomer cements for drug release in the skeleton an examination of Composition Property relationships
Journal of Biomaterials Applications, 2016Co-Authors: Lauren Kiri, M J Filiaggi, Daniel BoydAbstract:Chemotherapeutic-loaded bone cement may be an effective method of drug delivery for the management of cancer-related vertebral fractures that require cement injection for pain relief. Recent advancements in the development of aluminum-free glass ionomer cements (GICs) have rendered this class of biomaterials clinically viable for such applications. To expand the therapeutic benefits of these materials, this study examined, for the first time, their drug delivery potential. Through incrementally loading the GIC with methotrexate (MTX) by up to 10-wt%, Composition–Property relationships were established, correlating MTX loading with working time and setting time, as well as compressive strength, drug release, and cytotoxic effect over 31 days. The most significant finding of this study was that MTX was readily released from the GIC, while maintaining cytotoxic activity. Release correlated linearly with initial loading and appeared to be diffusion mediated, delivering a total of 1–2% of the incorporated drug...
-
Composition Property relationships for radiopaque composite materials pre loaded drug eluting beads for transarterial chemoembolization
Journal of Biomaterials Applications, 2015Co-Authors: Nancy Kilcup, Daniel Boyd, Elena Tonkopi, Robert J Abraham, S KehoeAbstract:The purpose of this study was to synthesize and optimize intrinsically radiopaque composite embolic microspheres for sustained release of doxorubicin in drug-eluting bead transarterial chemoembolization. Using a design of experiments approach, 12 radiopaque composites composed of polylactic-co-glycolic acid and a radiopaque glass (ORP5) were screened over a range of Compositions and examined for radiopacity (computed tomography) and density. In vitro cell viability was determined using an extract assay derived from each Composition against the human hepatocellular carcinoma cell line, HepG2. Mathematical models based on a D-Optimal response surface methodology were used to determine the preferred radiopaque composite. The resulting radiopaque composite was validated and subsequently loaded with doxorubicin between 0 and 1.4% (wt% of polylactic-co-glycolic acid) to yield radiopaque composite drug-eluting beads. Thereafter, the radiopaque composite drug-eluting beads were subjected to an elution study (up t...
Robert E Synovec - One of the best experts on this subject based on the ideXlab platform.
-
correlation of rocket propulsion fuel properties with chemical Composition using comprehensive two dimensional gas chromatography with time of flight mass spectrometry followed by partial least squares regression analysis
Journal of Chromatography A, 2014Co-Authors: Benjamin Kehimkar, Jamin C Hoggard, Luke C Marney, Matthew C Billingsley, Carlos G Fraga, Thomas J Bruno, Robert E SynovecAbstract:Abstract There is an increased need to more fully assess and control the Composition of kerosene-based rocket propulsion fuels such as RP-1. In particular, it is critical to make better quantitative connections among the following three attributes: fuel performance (thermal stability, sooting propensity, engine specific impulse, etc.), fuel properties (such as flash point, density, kinematic viscosity, net heat of combustion, and hydrogen content), and the chemical Composition of a given fuel, i.e., amounts of specific chemical compounds and compound classes present in a fuel as a result of feedstock blending and/or processing. Recent efforts in predicting fuel chemical and physical behavior through modeling put greater emphasis on attaining detailed and accurate fuel properties and fuel Composition information. Often, one-dimensional gas chromatography (GC) combined with mass spectrometry (MS) is employed to provide chemical Composition information. Building on approaches that used GC–MS, but to glean substantially more chemical information from these complex fuels, we recently studied the use of comprehensive two dimensional (2D) gas chromatography combined with time-of-flight mass spectrometry (GC × GC–TOFMS) using a “reversed column” format: RTX-wax column for the first dimension, and a RTX-1 column for the second dimension. In this report, by applying chemometric data analysis, specifically partial least-squares (PLS) regression analysis, we are able to readily model (and correlate) the chemical Compositional information provided by use of GC × GC–TOFMS to RP-1 fuel Property information such as density, kinematic viscosity, net heat of combustion, and so on. Furthermore, we readily identified compounds that contribute significantly to measured differences in fuel properties based on results from the PLS models. We anticipate this new chemical analysis strategy will have broad implications for the development of high fidelity Composition-Property models, leading to an improved approach to fuel formulation and specification for advanced engine cycles.
Krishnan N. M. Anoop - One of the best experts on this subject based on the ideXlab platform.
-
Unveiling the Glass Veil: Elucidating the Optical Properties in Glasses with Interpretable Machine Learning
2021Co-Authors: Zaki Mohd, Bishnoi Suresh, Ravinder R., Venugopal Vineeth, Singh, Sourabh Kumar, Allu, Amarnath R., Krishnan N. M. AnoopAbstract:Due to their excellent optical properties, glasses are used for various applications ranging from smartphone screens to telescopes. Developing Compositions with tailored Abbe number (Vd) and refractive index (nd), two crucial optical properties, is a major challenge. To this extent, machine learning (ML) approaches have been successfully used to develop Composition-Property models. However, these models are essentially black-box in nature and suffer from the lack of interpretability. In this paper, we demonstrate the use of ML models to predict the Composition-dependent variations of Vd and n at 587.6 nm (nd). Further, using Shapely Additive exPlanations (SHAP), we interpret the ML models to identify the contribution of each of the input components toward a target prediction. We observe that the glass formers such as SiO2, B2O3, and P2O5, and intermediates like TiO2, PbO, and Bi2O3 play a significant role in controlling the optical properties. Interestingly, components that contribute toward increasing the nd are found to decrease the Vd and vice-versa. Finally, we develop the Abbe diagram, also known as the "glass veil", using the ML models, allowing accelerated discovery of new glasses for optical properties beyond the experimental pareto front. Overall, employing explainable ML, we discover the hidden Compositional control on the optical properties of oxide glasses.Comment: 13 pages, 5 figure
-
Revealing the Compositional Control of Electrical, Mechanical, Optical, and Physical Properties of Inorganic Glasses
2021Co-Authors: Ravinder R., Bishnoi Suresh, Zaki Mohd, Krishnan N. M. AnoopAbstract:Inorganic glasses, produced by the melt-quenching of a concoction of minerals, compounds, and elements, can possess unique optical and elastic properties along with excellent chemical, and thermal durability. Despite the ubiquitous use of glasses for critical applications such as touchscreen panels, windshields, bioactive implants, optical fibers and sensors, kitchen and laboratory glassware, thermal insulators, nuclear waste immobilization, optical lenses, and solid electrolytes, their Composition-structure-Property relationships remain poorly understood. Here, exploiting largescale experimental data on inorganic glasses and explainable machine learning algorithms, we develop Composition-Property models for twenty-five properties, which are in agreement with experimental observations. These models are further interpreted using a game-theoretic concept namely, Shapley additive explanations, to understand the role of glass components in controlling the final Property. The analysis reveals that the components present in the glass, such as network formers, modifiers, and the intermediates, play distinct roles in governing each of the optical, physical, electrical, and mechanical properties of glasses. Additionally, these components exhibit interdependence, the magnitude of which is different for different properties. While the physical origins of some of these interdependencies could be attributed to known phenomena such as "boron anomaly", "mixed modifier effect", and the "Loewenstein rule", the majority of the remaining ones requires further experimental and computational analysis of the glass structure. Thus, our work paves the way for decoding the "glass genome", which can provide the recipe for discovery of novel glasses, while also shedding light into the fundamental factors governing the Composition-structure-Property relationships
-
Scalable Gaussian Processes for Predicting the Properties of Inorganic Glasses with Large Datasets
2020Co-Authors: Bishnoi Suresh, Ravinder R., Singh Hargun, Kodamana Hariprasad, Krishnan N. M. AnoopAbstract:Gaussian process regression (GPR) is a useful technique to predict Composition--Property relationships in glasses as the method inherently provides the standard deviation of the predictions. However, the technique remains restricted to small datasets due to the substantial computational cost associated with it. Here, using a scalable GPR algorithm, namely, kernel interpolation for scalable structured Gaussian processes (KISS-GP) along with massively scalable GP (MSGP), we develop Composition--Property models for inorganic glasses based on a large dataset with more than 100,000 glass Compositions, 37 components, and nine important properties, namely, density, Young's, shear, and bulk moduli, thermal expansion coefficient, Vickers' hardness, refractive index, glass transition temperature, and liquidus temperature. Finally, to accelerate glass design, the models developed here are shared publicly as part of a package, namely, Python for Glass Genomics (PyGGi)
-
Realistic atomic structure of fly ash-based geopolymer gels: Insights from molecular dynamics simulations
DigitalCommons@URI, 2019Co-Authors: Lyngdoh, Gideon A, Krishnan N. M. Anoop, Kumar Rajesh, Das SumantaAbstract:Geopolymers, synthesized through alkaline activation of aluminosilicates, have emerged as a sustainable alternative for traditional ordinary Portland cement. In spite of the satisfactory mechanical performance and sustainability-related benefits, the large scale acceptance of geopolymers in the construction industry is still limited due to poor understanding of the Composition-Property relationships. Molecular simulation is a powerful tool to develop such relationships, provided that the adopted molecular structure represents the experimental data effectively. Toward this end, this paper presents a new molecular structure of sodium aluminosilicate hydrate geopolymer gels, inspired from the traditional calcium silicate hydrates gel. In contrast to the existing model—where water is uniformly distributed in the structure—we present a layered-but-disordered structure. This new structure incorporates water in the interlayer space of the aluminosilicate network. The structural features of the new proposed molecular structure are evaluated in terms of both short- and medium-range order features such as pair distribution functions, bond angle distributions, and structure factor. The structural features of the newly proposed molecular structure with interlayer water show better correlation with the experimental observations as compared to the existing traditional structure signifying an increased plausibility of the proposed structure. The proposed structure can be adopted as a starting point toward the realistic multiscale simulation-based design and development of geopolymers
Manfred Aigner - One of the best experts on this subject based on the ideXlab platform.
-
predictive capability assessment of probabilistic machine learning models for density prediction of conventional and synthetic jet fuels
Energy & Fuels, 2021Co-Authors: Clemens Hall, Bastian Rauch, Uwe Bauder, Patrick Le Clercq, Manfred AignerAbstract:Machine Learning (ML) models are increasingly applied in the field of jet fuel Property predictions due to their ability of modeling a high number of complex Composition–Property relationships dire...