CMI Project 4.1.2 Automated and artificial intelligence (AI)-accelerated separation of critical materials Research Highlights

Autonomous titration system fully operational

CMI researchers at Lawrence Livermore National Laboratory, University of Arizona, Ames National Laboratory and Oak Ridge National Laboratory conducted the activity for this highlight

Figure: Depiction of pKaScope software workflow (top) and automated titration system showing (A) titration vessel, (B) Rxn Rover operating software, (C) solutions for titrations, (E) syringe pumps, and (D) waste container

A comprehensive model to predict metal ion binding constants

CMI researchers from Ames National Laboratory conducted the activity for this highlight

Molecular design improved through machine learning

CMI researchers from Ames National Laboratory conducted the activity for this highlight

A) Parity plot comparing predicted and experimental log K values with mean error (ME = 0.032) lower than experimental accuracy and root mean squared error (RMSE = 0.629) approaching experimental errors. B) The top ranked ligands generated by linking pyridines and amides (blue functional groups).

Accelerating process development by synthesis, auto extraction

CMI researchers from Ames National Laboratory and Purdue University conducted the activity for this highlight

spider diagram shows life cycle assessment of new DGA synthesis pathway comparing to prior art method.