(628g) Machine Learning Predictions for Evaluating Organic Acid Separation Technologies

The separation of organic acids is a critical process in various key industrial applications, including pharmaceuticals, food production, and biofuel manufacturing. Accurate process simulation relies on robust physical property data and models, which are essential for the efficient design and selection of materials and separation technologies. This study examines the use of machine learning (ML) techniques to predict and optimize the performance of organic acid separation technologies.

In this talk, we evaluate the performance of ML models for membrane and adsorption separation technologies using both experimental datasets and literature datasets. By integrating insights from thermodynamic modeling and developing thermodynamic-informed neural networks, we have created ML models that can make accurate predictions for the experimental datasets.