From eyes to cameras: Computer vision for high-throughput liquid-liquid separation
Rama El-khawaldeh, Abhijoy Mandal, Naruki Yoshikawa, Wenyu Zhang, Ryan Corkery, Paloma L. Prieto, Alán Aspuru‐Guzik, Kourosh Darvish, Jason E. Hein
Abstract
We present a high-throughput automation platform for screening liquid-liquid extraction (LLE) processes. Our hardware platform simultaneously screens up to 12 vials and is coupled with a computer vision (CV) system for real-time monitoring of macroscopic visual cues. Our CV system, named HeinSight3.0 , leverages machine learning and image analysis to classify and quantify multivariate visual cues such as liquid level(s), turbidity, homogeneity, volume, and color. These cues, combined with process parameters such as stir rate and temperature, enable real-time analysis of key workup processes (e.g., separation time, volume ratio of layers, and emulsion presence) to aid in the optimization of separation parameters. We demonstrate our system on three case studies: impurity recovery, excess reagent removal, and Grignard workup. Our application of HeinSight3.0 to literature data also suggests a high potential for generalizability and adaptability across different platforms and contexts. Overall, our work represents a step toward autonomous LLE optimization guided by visual cues.