(8g) Machine Learning Accelerated Scale-up for Microporous Materials

Microporous materials such as zeolites and MOFs play a crucial role in producing energy and energy products at scale. Traditional approaches for materials development and scale-up are time consuming and involve a lot of trial and error. Two key questions need to be addressed including (1) what the critical variables are that impact the synthesis (2) and how the material properties can be controlled and optimized. This presentation provides an overview of machine learning approaches to build quantitative synthesis-property relationships (QSPR). These methods provide a highly efficient path to optimize synthesis parameters towards target(s) such as purity, crystal size and surface area, and enable us to enable us to significantly speed up our materials workflow.

Our workflow combines design of experiments, machine learning and deep learning, and high-throughput experimentation (HTE). In order to build QSPR, we featurized the characterization data using machine learning and deep learning approaches. For example, we quantified crystal purity using peak deconvolution of powder XRD pattern. We used a deep learning model to calculate crystal size and aspect ratio from scanning electron microscopy (SEM). We also performed functional principal component analysis to ensure the surface area calculated from the linear region of Brunauer-Emmett-Teller (BET) adsorption curve selected using Rouquerol rule explains a substantial fraction of variance. Since the synthesis parameter space for microporous materials is large and complex, we combined Bayesian Optimization and HTE to further accelerate the workflow. After optimization, we used feed-forward neural network models to summarize QSPR for extended investigation at different scales.

We validated the accelerated workflow with a known zeolite. Without referring to historical data, we used the workflow to systematically probe a large and complex synthesis parameter space and obtain small pure crystals of the material. The new workflow demonstrated a significant reduction in the number of experiments needed to meet the same goals as past experiments.