SOURCE-LINKED INTELLIGENCE

INtelligent System for Processing Intensive Reaction Electrochemistry

CORDIS · observation · Publication date unknown

gs are vital intermediates in organic synthesis, yet their scalable production via green and efficient methods remains underdeveloped. This study aims to optimize EC cyclopropanation with the aid of machine learning algorithms (e.g., Bayesian optimization) to refine reaction conditions and minimize electrode passivation. The key objectives include: (i) optimizing reaction parameters to maximize yields, conversion rates, and selectivity, (ii) implementing advanced machine learning tools to address and mitigate fouling—a major barrier to EC process scalability—and, (iii) developing robust numerical models to enable the scaling up of EC reactions. The integration of machine learning with EC flow synthesis is expected to enhance reaction efficiency and reproducibility, creating a framework for the systematic screening of reactions and mechanisms, thus reducing the manual experimental time required by traditional optimization methods. The EC microreactor, implemented within automated continuous-flow platforms, will facilitate dataset generation, real-time control over reaction dynamics,

Read original source ↗ Open in workspace

recordType

award

status

SIGNED

region

EU

value

232916.16

unit

EUR