She will discuss their efforts to use machine learning (ML) to accelerate the computational tailoring and design of transition metal complexes and metal-organic framework (MOF) materials for outstanding challenges in resource utilization, including catalysis, separations, and energy storage.
One limitation in a challenging materials space such as open shell, 3d transition metal chemistry is that ML models and ML-accelerated high-throughput screening traditionally rely on density functional theory (DFT) for data generation, but DFT is both computationally demanding and prone to errors that limit its accuracy in predicting new materials.
Audacity of huge: machine learning for the discovery of transition metal catalysts and materials.
She will describe three ways they've overcome these limitations:
- i) through efficient global optimization to minimize the numbers of calculations carried out to obtain design rules in weeks instead of decades while satisfying multiple objectives,
- ii) through machine-learned consensus from a family of dozens of functionals to more robustly uncover new materials,
- iii) by the use of natural language processing to extract, learn, and directly predict experimental measures of stability on heterogeneous MOF materials.
Contact: Mikaël Kepenekian, mikael [dot] kepenekianuniv-rennes1 [dot] fr