Posts in category: News

Dr. Maria Chan delivered an A3MD Distinguished Seminar entitled: “All of the above – combining modeling, characterization, and AI/ML to understand and design materials”.

In materials and chemical science, the combination of high throughput computational modeling and experimentation has given rise to significant challenges and opportunities. Data science techniques such as machine learning, artificial intelligence, and computer vision have made a significant impact in the ease, scope, and speed of understanding of known materials and discovery of new ones. In this talk, we will discuss how we use data science approaches in conjunction with theory-based modeling to interpret experimental characterization data (such as x-ray scattering, spectroscopy, scanning probe microscopy, and electron microscopy) and carry out materials design (such as in the space of classic zinc blende and hybrid perovskite optoelectronic materials). The role of computer vision and pattern recognition in the analysis of microscopy data will also be discussed. 

Prof. Miguel Modestino delivered an A3MD Distinguished Seminar entitled: “Accelerating the Development of Electrochemical Technologies for Sustainable Chemical Manufacturing”.

The chemical industry produces more than 70,000 products (1.2 billion tons in total) via thermal processes powered by fossil fuel combustion, accounting for ~5% of the US energy utilization and >30% of the US energy-derived industrial CO2 emissions. Amongst these processes, the production of organic chemical commodities accounts for most of the energy utilization (>1200 TBTU/y), and the electrification of these processes via the implementation of electro-organic reactions could enable the integration of renewable electricity sources with chemical plants and accelerate the decarbonization of the chemical industry. Currently, however, two major challenges prevent the deployment of electro-organic reactions at scale: their low selectivity and their low production rates. To circumvent these barriers, my group combines electrochemical reaction engineering principles and machine-learning methods to accelerate the development of high-performing electro-organic reaction processes.  

In this presentation, I will discuss our work on understanding and improving the production of adiponitrile (ADN), a precursor to Nylon 6,6, via the electrohydrodimerization of acrylonitrile (AN). This is the largest and most successful electro-organic reaction deployed in industry and serves as a test case for the development of large-scale organic electrochemical processes. Our investigations on ADN are aimed at uncovering the relationship between the electrochemical environment at and near the electrical double layer (EDL) and reaction performance metrics (i.e., selectivity, efficiency, and productivity). I will discuss general guidelines for electrolyte formulation and provide insights into the role of different electrolyte species (e.g., buffer ions, chelating ions, selectivity-directing ions, and supporting ions) in achieving conversions of AN to ADN with selectivity as high as 83%. I will also present how carefully controlling pulsed electrosynthesis conditions guided by active machine learning can help mitigate mass transport limitations, control the concentration of AN near the EDL and enhance the production rate of ADN by >30%. Our learnings on ADN electrosynthesis helped us to also engineer the electrocatalytic hydrogenation of ADN to hexamethylenediamine (a Nylon 6,6 monomer), achieving the highest reported selectivity to date for this reaction (>95%). To further accelerate the development of high-performing electro-organic processes, my group has recently developed new machine-learning methods for rapid reactor outflow analysis using inexpensive spectroscopic tools and Bayesian optimization methods that leverage physical models to maximize process performance. These new tools are critical components of future autonomous workflows that will help us accelerate the electrification of petrochemical processes with large carbon footprints.

Prof. Vladan Stevanovic delivered an A3MD Distinguished Seminar entitled: “Toward Accelerated Discovery and Design of Metastable Materials”

Metastable materials, including both crystalline and amorphous systems, are invaluable in our daily lives. Classic examples include diamond, amorphous SiO2 (glass) or solid chocolate. However, despite the relevance of metastable materials and despite a rather extensive knowledge of the phenomenology of metastability, our ability to rationally discover and design metastable forms of matter is rather limited. In this talk I will present our recent attempts to resolving some of the issues hindering rational discovery and design of metastable phases with the particular focus on covalent and partially ionic (semiconducting/insulating) systems. More specifically, I will discuss the experimental realizability (synthesizability) of metastable crystalline phases (polymorphs) in connection to specific features of the potential energy surface  leading to an effective methodology to identifying realizable metastable states. Next, I will talk about our efforts in developing computational methods to enable large-scale assessment of the kinetics of polymorphic transformations (i.e., polymorph lifetimes). ,  These are predicated on the novel solution to the problem of finding an optimal atom-to-atom mapping between infinitely periodic systems. Lastly, an alternative description of covalent and ionic glassy solids as statistical ensembles of crystalline local minima on the potential energy surface  will be discussed, opening the door to fully predictive approaches to modeling glasses without the need for experimental inputs. In all of these areas our recent works offer quantitative predictions of relevant properties, which, in turn, can help construct more rational and reliable searches for useful metastable materials. This work is supported by the NSF-DMR Career program.

Dr. Alpha Lee delivered an A3MD Distinguished Seminar entitled: “Accelerating the materials design-make-test cycle with machine learning and coarse graining”

Unlike molecular chemistry, where valance-bond theory provides a robust framework to represent molecules as a graph, representing inorganic materials is significantly more intricate. On the one hand, representing a material using composition alone removes the possibility of identifying polymorphs. On the other hand, a representation based on distances between atoms is challenging to deploy in a computational high throughput screening workflow for novel materials because it is a priori unclear whether a particular composition/structure is thermodynamically stable. In my talk, I will discuss our journey in applying concepts in coarse graining to devise machine learning models for materials properties prediction and materials synthesis prediction. I will first discuss the lowest level of coarse graining – stoichiometry – and discuss a representation learning framework that predicts materials properties using stoichiometry as input. I will then show how this framework can be extended to predict the outcomes of materials synthesis, whilst also providing an interpretable “reaction similarity” metric that enables rapid search for literature precedents in materials synthesis. Finally, I will move up the coarse graining ladder and discuss how we can incorporate structure, albeit in a coarse-grained way, using the concept of Wyckoff representation. This approach allows us to effectively amortise crystal structure searching, turning an infinite search space into a combinatorially enumerable search problem.

Professor John Gregoire delivered an A3MD Distinguished Seminar entitled: “Accelerating discovery of solar fuels materials with high throughput experiments and artificial intelligence”

The large data flux of high throughput experiments naturally presents opportunities for data science. Addressing the most pressing materials discovery challenges with these techniques requires design of experiments and algorithms in the context of the materials physics and chemistry that are pertinent to the target technology. The corresponding quest for materials that harvest solar energy to generate chemical fuels has led to research problems that challenge the state of the art in artificial intelligence. The ensuing efforts to generate new algorithms and modalities of research include 1) the development of deep reasoning networks that incorporate physics rules in machine learning, which is critical for automating crystal structure phase mapping; 2) the incorporation of hierarchical correlation learning in multi-property prediction, which conditions models to facilitate prediction in never-before-seen composition spaces; and 3) probabilistic modeling of data in high order composition spaces, which identifies materials most likely to exhibit exceptional properties for any target technology. While these efforts arose from specific research challenges, the methods and concepts are intended to be generally applicable for accelerating scientific discovery via adaption and improvement by the research community.

Professor Laura Gagliardi delivered an A3MD Distinguished Seminar entitled: “Theoretical and Computational Challenges in Modeling MOF-Based Catalysis and Water Harvesting”

Metal-organic frameworks (MOFs) are versatile platforms with tunable properties ranging from high selectivity in gas separations, to catalytic activity for complex reactions, to unique magnetic properties. In collaboration with experimentalists, we try to understand the activity of MOF-based catalysts for reactions related to natural gas conversion, e.g., catalytic oligomerization of abundant C1, C2, and C3 hydrocarbons to longer congeners, or their selective oxidation to alcohols or other fuel molecules. Modeling these species poses enormous challenges from a theoretical and computational perspective. I will describe our latest results in modeling light-alkane hydroxylation over Fe-based MOFs. I will also describe our combined computational and data-science approach to explore MOFs quantum-chemical properties.