Using machine learning to design extractants for improved - PowerPoint PPT Presentation

Using machine learning to design extractants for improved separations Marilu G. Perez In collaboration with: Federico Zahariev, Theresa L. Windus, Benjamin Hay 1

Purpose • Critical Materials Institute • keep the U.S. competitive in energy technology by securing “critical” materials • Collaboration with industry is important • Industry is practical – but can open up new avenues of research • Social Science Example: Crisis Text Line (crisistextline.org) • Correlation between high-risk users and words “Advil” and “ibuprofen” over intuitive words such as “die” or “suicide” • Result more important than reason for outcome 2

Collaboration Experimental Computer Science Chemistry Data Science Project Federico Marilu Zahariev Perez Computational/Theoretical Chemistry 3

Goal • Determine metal-ligand complex equilibrium constants, K • Identify system descriptors – properties that may correlate to K values • Use supervised learning • Relatively limited amount of data • Some knowledge of the system exists • Ultimately – predict distribution coefficients/separation factors 4

Predicting Value of Interest Training Set • Descriptors Sample Descriptors Values 1 2 … n Known 1 D₁₁ D₂₂ … D nn V₁ . . . … . . • Considerations m D₁ m D₂ m … D nm V m Test Set Sample Descriptors Values • Challenges 1 2 … n Known Predicted 1 D₁₁ D₂₂ … D nn V₁ V₁ . . . … . . . m D₁ D₂ m … D nm V m V m m 5

Future Outlook Experimental Computer Science Chemistry • Open access data Data Science • Experimental conditions • Experimental analysis • Raw data • Incorporating “failed” experiments • More collaboration Computational/Theoretical Chemistry 6