Title

Using Artificial Intelligence to Formulate New Deep Eutectic Solvents

School Name

South Carolina Governor's School for Science and Mathematics

Grade Level

12th Grade

Presentation Topic

Computer Science

Presentation Type

Mentored

Abstract

The advances in Artificial Intelligence (AI) in the past two decades have enabled algorithms to perform daily human-like tasks such as driving cars, playing complex games, composing classical music, and even generating realistic images by using text as the input parameter. These achievements were accomplished with the implementation of Deep Neural Network (DNN) architecture along with the use of large databases, as well as the increase in computing power. This strategy has also shown promise in several sub-fields of natural sciences such as chemistry, biology, and physics through speech recognition, data analysis, and computer vision. More specifically, in chemistry, deep learning has been used to predict the properties of molecules and predict chemical reactions. To predict the properties of molecules and chemical reactions, a large database of compounds or molecules, such as Deep Eutectic Solvents (DES), must be written in a simplified text such as a Simplified Molecular Input Line Entry System (SMILES). A SMILES database is easily understood by computers, and it translates a chemical structure into a string. With the use of the SMILES database, we were able to train a model with Natural Deep Eutectic Solvents, so the AI could eventually determine if the compounds inputted with SMILES were unstable or stable.

Location

ECL 340

Start Date

3-25-2023 10:00 AM

Presentation Format

Oral Only

Group Project

No

COinS
 
Mar 25th, 10:00 AM

Using Artificial Intelligence to Formulate New Deep Eutectic Solvents

ECL 340

The advances in Artificial Intelligence (AI) in the past two decades have enabled algorithms to perform daily human-like tasks such as driving cars, playing complex games, composing classical music, and even generating realistic images by using text as the input parameter. These achievements were accomplished with the implementation of Deep Neural Network (DNN) architecture along with the use of large databases, as well as the increase in computing power. This strategy has also shown promise in several sub-fields of natural sciences such as chemistry, biology, and physics through speech recognition, data analysis, and computer vision. More specifically, in chemistry, deep learning has been used to predict the properties of molecules and predict chemical reactions. To predict the properties of molecules and chemical reactions, a large database of compounds or molecules, such as Deep Eutectic Solvents (DES), must be written in a simplified text such as a Simplified Molecular Input Line Entry System (SMILES). A SMILES database is easily understood by computers, and it translates a chemical structure into a string. With the use of the SMILES database, we were able to train a model with Natural Deep Eutectic Solvents, so the AI could eventually determine if the compounds inputted with SMILES were unstable or stable.