arXiv subjects

Daniel R. Cassar

Publications and source records attributed to Daniel R. Cassar.

11 recordsLinked to original sources

arXiv2026

Will it form a glass? Tackling glass formation using binary classification

Glass formation is one of the most important and fundamental open problems in glass science. Predicting whether a liquid can be easily frozen into a glass appears simple but is far from it. In this communication, we address glass formation in inorganic nonmetallic liquids using binary classification to predict the probability that a given liquid will form a glass under typical laboratory conditions. Using a dataset of more than 50,000 examples, we trained random forest classifiers that achieved ROC-AUC values around 0.89 and PR-AUC close to 0.95 on the holdout dataset (i.e., unseen data). A rigorous model selection routine was employed, including hyperparameter tuning with cross-validation, and four different data treatment routes were evaluated. Using SHAP values, we extracted valuable insights from the trained models that both agree with established knowledge and extend it. For example, we identified that the bandgap energy of the constituent chemical elements is positively correlated with glass formation. When glass stability parameters and Jezica were added to the dataset, no performance improvement was observed, but model complexity decreased significantly. This result is particularly relevant for composition screening, especially in inverse design problems.

cond-mat.mtrl-sci↗

arXiv2024

Evaluation of GlassNet for physics-informed machine learning of glass stability and glass-forming ability

Glasses form the basis of many modern applications and also hold great potential for future medical and environmental applications. However, their structural complexity and large composition space make design and optimization challenging for certain applications. Of particular importance for glass processing is an estimate of a given composition's glass-forming ability (GFA). However, there remain many open questions regarding the physical mechanisms of glass formation, especially in oxide glasses. It is apparent that a proxy for GFA would be highly useful in glass processing and design, but identifying such a surrogate property has proven itself to be difficult. Here, we explore the application of an open-source pre-trained NN model, GlassNet, that can predict the characteristic temperatures necessary to compute glass stability (GS) and assess the feasibility of using these physics-informed ML (PIML)-predicted GS parameters to estimate GFA. In doing so, we track the uncertainties at each step of the computation - from the original ML prediction errors, to the compounding of errors during GS estimation, and finally to the final estimation of GFA. While GlassNet exhibits reasonable accuracy on all individual properties, we observe a large compounding of error in the combination of these individual predictions for the prediction of GS, finding that random forest models offer similar accuracy to GlassNet. We also breakdown the ML performance on different glass families and find that the error in GS prediction is correlated with the error in crystallization peak temperature prediction. Lastly, we utilize this finding to assess the relationship between top-performing GS parameters and GFA for two ternary glass systems: sodium borosilicate and sodium iron phosphate glasses. We conclude that to obtain true ML predictive capability of GFA, significantly more data needs to be collected.

cond-mat.mtrl-sci↗

arXiv2023

GlassNet: a multitask deep neural network for predicting many glass properties

A multitask deep neural network model was trained on more than 218k different glass compositions. This model, called GlassNet, can predict 85 different properties (such as optical, electrical, dielectric, mechanical, and thermal properties, as well as density, viscosity/relaxation, crystallization, surface tension, and liquidus temperature) of glasses and glass-forming liquids of different chemistries (such as oxides, chalcogenides, halides, and others). The model and the data used to train it are available in the GlassPy Python module as free and open source software for the community to use and build upon. As a proof of concept, GlassNet was used with the MYEGA viscosity equation to predict the temperature dependence of viscosity and outperformed another general purpose viscosity model available in the literature (ViscNet) on unseen data. An explainable AI algorithm (SHAP) was used to extract knowledge correlating the input (physicochemical information) and output (glass properties) of the model, providing valuable insights for glass manufacturing and design. It is hoped that GlassNet, with its free and open source nature, can be used to enable faster and better computer-aided design of new technological glasses.

cond-mat.soft↗

arXiv2023

Glass Hardness: Predicting Composition and Load Effects via Symbolic Reasoning-Informed Machine Learning

Glass hardness varies in a non-linear fashion with the chemical composition and applied load, a phenomenon known as the indentation size effect (ISE), which is challenging to predict quantitatively. Here, using a curated dataset of over approx. 3000 inorganic glasses from the literature comprising the composition, indentation load, and hardness, we develop machine learning (ML) models to predict the composition and load dependence of Vickers hardness. Interestingly, when tested on new glass compositions unseen during the training, the standard data-driven ML model failed to capture the ISE. To address this gap, we combined an empirical expression (Bernhardt law) to describe the ISE with ML to develop a framework that incorporates the symbolic law representing the domain reasoning in ML, namely Symbolic Reasoning-Informed ML Procedure (SRIMP). We show that the resulting SRIMP outperforms the data-driven ML model in predicting the ISE. Finally, we interpret the SRIMP model to understand the contribution of the glass network formers and modifiers toward composition and load-dependent (ISE) and load-independent hardness. The deconvolution of the hardness into load-dependent and load-independent terms paves the way toward a holistic understanding of composition and ISE in glasses, enabling the accelerated discovery of new glass compositions with targeted hardness.

cond-mat.mtrl-sci↗

arXiv2021

Machine learning unveils composition-property relationships in chalcogenide glasses

Due to their unique optical and electronic functionalities, chalcogenide glasses are materials of choice for numerous microelectronic and photonic devices. However, to extend the range of compositions and applications, profound knowledge about composition-property relationships is necessary. To this end, we collected a large quantity of composition-property data on chalcogenide glasses from SciGlass database regarding glass transition temperature ($T_g$), Young's modulus ($E$), coefficient of thermal expansion (CTE), and refractive index ($n_D$). With these data, we induced predictive models using three machine learning algorithms: Random Forest, K-nearest Neighbors, and Classification and Regression Trees. Finally, the induced models were interpreted by computing the SHAP (SHapley Additive exPlanations) values of the chemical features, which revealed the key elements that significantly impacted the tested properties and quantified their impact. For instance, Ge and Ga increase $T_g$ and $E$ and decrease CTE (three properties that depend on bond strength), whereas Se has the opposite effect. Te, As, Tl, and Sb increase $n_D$ (which strongly depends on polarizability), whereas S, Ge, and P diminish it. Knowledge about the effect of each element on the glass properties is precious for semi-empirical compositional development trials or simulation-driven formulations. The induced models can be used to design novel chalcogenide glasses with required combinations of properties.

cond-mat.mtrl-sci↗

arXiv2021

Predicting and interpreting oxide glass properties by machine learning using large datasets

With the advent of powerful computer simulation techniques, it is time to move from the widely used knowledge-guided empirical methods to approaches driven by data science, mainly machine learning algorithms. We investigated the predictive performance of three machine learning algorithms for six different glass properties. For such, we used an extensive dataset of about 150,000 oxide glasses, which was segmented into smaller datasets for each property investigated. Using the decision tree induction, k-nearest neighbors, and random forest algorithms, selected from a previous study of six algorithms, we induced predictive models for glass transition temperature, liquidus temperature, elastic modulus, thermal expansion coefficient, refractive index, and Abbe number. Moreover, each model was induced with default and tuned hyperparameter values. We demonstrate that, apart from the elastic modulus (which had the smallest training dataset), the induced predictive models for the other five properties yield a comparable uncertainty to the usual data spread. However, for glasses with extremely low or high values of these properties, the prediction uncertainty is significantly higher. Finally, as expected, glasses containing chemical elements that are poorly represented in the training set yielded higher prediction errors. The method developed here calls attention to the success and possible pitfalls of machine learning algorithms. The analysis of the SHAP values indicated the key elements that increase or decrease the value of the modeled properties. It also estimated the maximum possible increase or decrease. Insights gained by this analysis can help empirical compositional tuning and computer-aided inverse design of glass formulations.

cond-mat.mtrl-sci↗

arXiv2021

ViscNet: Neural network for predicting the fragility index and the temperature-dependency of viscosity

Viscosity ($η$) is one of the most important properties of disordered matter. The temperature-dependence of viscosity is used to adjust process variables for glass-making, from melting to annealing. The aim of this work was to develop a physics-informed machine learning model capable of predicting $η(T)$ of oxide liquids. Instead of predicting the viscosity itself, the NN predicts the parameters of the MYEGA viscosity equation: the liquid's fragility index, the glass transition temperature, and the asymptotic viscosity. With these parameters, $η$ can be computed at any temperature of interest, with the advantage of good extrapolation capabilities inherent to the MYEGA equation. The dataset was collected from the SciGlass database; only oxide liquids with enough data points in the high and low viscosity regions were selected, resulting in a final dataset with 17,584 data points containing 847 different liquids. About 600 features were engineered from the liquids' chemical composition and 35 of these features were selected using a feature selection protocol. The hyperparameter (HP) tuning of the NN was performed in a set of experiments using both random search and Bayesian strategies, where a total of 700 HP sets were tested. The most successful HP sets were further tested using 10-fold cross-validation, and the one with the lowest average validation loss was selected as the best set. The final trained NN was tested with a test dataset of 85 liquids with different compositions than those used for training and validating the NN. The $R^2$ for the test dataset's prediction was 0.97. This work introduces three advantages: the model can predict viscosity as well as the liquids' glass transition temperature and fragility index; the model is designed and trained with a focus on extrapolation; finally, the model is available as free and open-source software licensed under the GPL3.

physics.comp-ph↗

arXiv2021

Designing optical glasses by machine learning coupled with a genetic algorithm

Engineering new glass compositions have experienced a sturdy tendency to move forward from (educated) trial-and-error to data- and simulation-driven strategies. In this work, we developed a computer program that combines data-driven predictive models (in this case, neural networks) with a genetic algorithm to design glass compositions with desired combinations of properties. First, we induced predictive models for the glass transition temperature ($T_g$) using a dataset of 45,302 compositions with 39 different chemical elements, and for the refractive index ($n_d$) using a dataset of 41,225 compositions with 38 different chemical elements. Then, we searched for relevant glass compositions using a genetic algorithm informed by a design trend of glasses having high $n_d$ (1.7 or more) and low $T_g$ (500 °C or less). Two candidate compositions suggested by the combined algorithms were selected and produced in the laboratory. These compositions are significantly different from those in the datasets used to induce the predictive models, showing that the used method is indeed capable of exploration. Both glasses met the constraints of the work, which supports the proposed framework. Therefore, this new tool can be immediately used for accelerating the design of new glasses. These results are a stepping stone in the pathway of machine learning-guided design of novel glasses.

cond-mat.mtrl-sci↗

arXiv2021

Is the Structural Relaxation of Glasses Controlled by Equilibrium Shear Viscosity?

Knowledge of relaxation processes is fundamental in glass science and technology because relaxation is intrinsically related to vitrification, tempering as well as to annealing and sev-eral applications of glasses. However, there are conflicting reports -- summarized here for different glasses -- on whether the structural relaxation time of glass can be calculated using the Maxwell equation, which relates relaxation time with shear viscosity and shear modulus. Hence, this study aimed to verify whether these two relaxation times are comparable. The structural relaxation kinetics of a lead metasilicate glass were studied by measuring the re-fractive index variation over time at temperatures between 5 and 25 K below the fictive temperature, which was initially set 5 K below the glass transition temperature. Equilibrium shear viscosity was measured above and below the glass transition range, expanding the current knowledge by one order of magnitude. The Kohlrausch equation described very well the experimental structural relaxation kinetics throughout the investigated temperature range and the Kohlrausch exponent increased with temperature, in agreement with studies on other glasses. The experimental average structural relaxation times were much longer than the values computed from isostructural viscosity, as expected. Still, they were less than one order of magnitude higher than the average relaxation time computed through the Maxwell equation, which relies on equilibrium shear viscosity. Thus, these results demon-strate that the structural relaxation process is not controlled by isostructural viscosity, and that equilibrium shear viscosity only provides a lower boundary for structural relaxation kinetics.

cond-mat.soft↗

arXiv2020

Which glass stability parameters can assess the glass-forming ability of oxide systems?

Glass forming ability (GFA) is a property of utmost importance in glass science and technology. In this paper, we used a statistical methodology---involving bootstrap sampling and the Wilcoxon test---to find out which glass stability parameters can better predict the glass forming ability. We collected or measured the necessary data for twelve stoichiometric oxide glasses that underwent predominant heterogeneous nucleation (the most common case). We found that some GS parameters could predict the GFA of these oxide glasses quite well, whereas others perform poorly. Parameter $K_w$ was the top ranked, closely followed by the $K_H$, $γ$, $H^{'}$, $ΔT_{rg}$, and $K_{cr}$. Our results corroborate previous reports carried out using a smaller number of glasses, much less GS parameters, and less rigorous statistics. We also found that using $T_c$ instead of $T_x$ improved the predictive power of these parameters. Finally, the Jezica, the only parameter considered here that predicts the GFA without requiring the production of a glass piece (i.e., without relying on any crystallization information), ranked reasonably well in our analysis.

cond-mat.soft↗

arXiv2019

Solving the Classical Nucleation Theory with respect to the surface energy

An essential parameter of the Classical Nucleation Theory (CNT) is the surface energy between a critical-size nucleus and the ambient phase, $σ$. In condensed matter, this parameter cannot be experimentally determined independently of CNT. A common practice to obtain $σ$ is to assume a model for its temperature-dependence and perform a regression of the CNT equation against experimental nucleation data. The drawback of this practice is that assuming the temperature-dependence of $σ$ adds a bias to the analysis. Nonetheless, this practice is common because an analytical solution of the Classical Nucleation Theory with respect to $σ$ is not possible considering common expressions of this theory. In this article, a general numerical solution to this problem using the Lambert $W$ function is proposed, tested, and compared with typical regression methods. The major advantage of the proposed method is that there is no need to assume a model for the temperature-dependence of $σ$.

cond-mat.soft↗