SUSSOL-Using Artificial Intelligence for Greener Solvent Selection and Substitution

Area of Science:

• Green Chemistry
• Computational Chemistry
• Chemical Engineering

Background:

• Selecting appropriate solvents for specific applications is complex.
• Identifying environmentally benign alternatives to hazardous solvents presents significant challenges.
• Current methods for solvent substitution often lack systematic approaches.

Purpose of the Study:

• To develop and present a novel methodology for solvent selection and substitution.
• To leverage Artificial Intelligence (AI) for clustering solvents based on physical properties.
• To introduce user-friendly software (SUSSOL) for exploring sustainable solvent options.

Main Methods:

• Utilized Artificial Intelligence (AI) software, specifically a neural network (Self-organizing Map of Kohonen), to cluster a comprehensive solvent database.
• Processed solvents based on their physical properties to generate a 2D map of clusters.
• Validated chemical and statistical clusters and presented them via user-friendly visualizations in the SUSSOL software.

Main Results:

• Developed the SUSSOL software, which provides intuitive visualizations of solvent clusters.
• Enabled users to explore the solvent space and generate ranked lists of potential solvent alternatives.
• Alternatives are ranked based on crucial safety, health, and environmental (SHE) scores, confirming literature findings in case studies.

Conclusions:

• The SUSSOL software offers a robust and intuitive platform for identifying sustainable solvent candidates.
• The AI-driven approach facilitates the discovery and evaluation of greener solvent alternatives.
• This methodology significantly aids researchers and industry professionals in the transition towards more environmentally responsible solvent usage.