A DATA DRIVEN FRAMEWORK FOR MATERIALS RESEARCH: EXPERIMENT DESIGN AND DATA ANALYSIS

Juejing Liu

doi:10.7273/000007254

Materials science is a field focusing on the discovery of new materials and the new usage of the existing materials. The constant development of new materials is one of the key factors promoting the evolution of humankind. Traditionally, materials science studies are time consuming, elaborate, expertise and intuition required, e.g.,, thoroughly reading a significant number of publications, relying on trial-and-error route to conduct experiments, painstakingly analyzing results from a wide range of measurement methods. The rise of machine learning (ML) and data science brings new insights into the realm of materials science and frees the materials scientists from the repetitive routine. This dissertation presents several examples about combining machine learning and materials science. I hope this dissertation will further inspire new methods to combine materials science and machine learning. Three studies will be presented in this dissertation, including a machine learning-assisted iron oxide synthesis, machine learning-based data analysis on resonant ultrasound spectroscopy (RUS) and X-ray diffraction (XRD). In the first study, I investigated the utilization of data science and machine learning on nanomaterial synthesis using iron oxide as an example. Synthesis of iron oxides with specific phases and particle sizes is a crucial challenge in various fields, including materials science, energy storage, biomedical applications, environmental science, and earth science. Despite significant advances in this area, much of the current palette of particle outcomes have been based on time-consuming trial-and-error exploration of synthesis conditions. The present study was designed to explore a very different approach to 1) predict the outcome of synthesis from specified reaction parameters based on using ML techniques, and 2) correlate sets of parameters to obtain products with desired outcomes by a newly designed recommendation algorithm. To achieve this, four ML algorithms were tested, namely random forest, logistic regression, support vector machine, and k-nearest neighbor. Among the models, random forests outperformed the others, attaining 96% and 81% accuracy when predicting the phase and size of iron oxide particles in the test dataset. Surprisingly, the permutation feature importance analysis revealed that volume, which may strongly relate to pressure, was one of the important features, along with precursor concentration, pH, temperature, and time, influencing the phase and size of iron oxide particles during synthesis. To verify the robustness of the random forest models, prediction and experimental results were compared based on 24 randomly generated methods in additive and non-additive systems not included in the datasets. The predictions of product phase and particle size from the models agreed well with the experimental results. Furthermore, a searching and ranking algorithm was developed to recommend potential synthesis parameters for obtaining iron oxide products with the desired phase and particle size from previous studies in the dataset. This study lays the foundation for a closed-loop approach in materials synthesis and preparation, beginning with suggesting potential reaction parameters from the dataset and predicting potential outcomes, followed by conducting experiments and analyses, and ultimately enriching the dataset. In the second study, we studied the deep learning-based data analysis by using the retrieval of elastic tensors from resonant ultrasound spectroscopy (RUS) data as an example. We highlighted the importance of proper data preprocessing and modulation for the generation of high-performance deep learning model. Conventionally, obtaining elastic tensors from RUS requires user intervention of published analysis codes. By strategically converting theoretical RUS spectra into their modulated fingerprints and using them as a dataset to train neural network models, we obtain deep learning models that successfully predicted both elastic moduli from theoretical test spectra of an isotropic material and from a measured steel RUS spectrum with up to 9.6% missing resonances. We further trained modulated fingerprint-based models to resolve RUS spectra from yttrium-aluminum-garnet (YAG) ceramic samples with three elastic moduli. The resulting models were capable of retrieving all three elastic moduli from spectra with a maximum of 26% missing frequencies. In summary, our modulated fingerprint method is an efficient tool to transform raw spectroscopy data and train neural network models with high accuracy and resistant to spectra distortion. In the third study, we investigated a challenging situation in deep learning-based X-ray diffraction (XRD) analysis obtaining phases information from the distorted XRD patterns. XRD data analysis can be a time-consuming and laborious task. Deep neural network (DNN) based models trained with synthetic XRD patterns have been proven to be a highly efficient, accurate, and automated method for analyzing common XRD data collected from solid samples in ambient environments. However, it remains unclear whether synthetic XRD-based models can be effective in solving micro(μ)-XRD mapping data for in-situ experiments involving liquid phases, which always have lower quality and significant artifacts. In this study, we collected μ-XRD mapping data from a LaCl3-calcite hydrothermal fluid system and trained two categories of models to analyze the experimental XRD patterns. The models trained solely with synthetic XRD patterns showed low accuracy (as low as 64%) when solving experimental μ-XRD mapping data. However, the accuracy of the DNN models significantly improved (90% or above) when we trained them with a dataset containing both synthetic and a small number of labeled experimental μ-XRD patterns. This study highlights the importance of labeled experimental patterns in training DNN models to solve μ-XRD mapping data from in-situ experiments involving liquid phases.

A DATA DRIVEN FRAMEWORK FOR MATERIALS RESEARCH: EXPERIMENT DESIGN AND DATA ANALYSIS

Files and links (1)

Abstract

Metrics

Details