# Molecular Machine Learning in Chemical Process Design

## TL;DR

This paper reviews the application of molecular machine learning in chemical process engineering, highlighting recent advances, potential future directions, and the integration of ML models into process design and optimization.

## Contribution

It provides a comprehensive overview of current molecular ML models, discusses future research directions, and emphasizes the importance of benchmarks and industry collaboration for validation.

## Key findings

- Molecular ML models achieve high accuracy in property prediction.
- Graph neural networks and transformers are key methods.
- Integration into process design can accelerate molecule discovery.

## Abstract

We present a perspective on molecular machine learning (ML) in the field of chemical process engineering. Recently, molecular ML has demonstrated great potential in (i) providing highly accurate predictions for properties of pure components and their mixtures, and (ii) exploring the chemical space for new molecular structures. We review current state-of-the-art molecular ML models and discuss research directions that promise further advancements. This includes ML methods, such as graph neural networks and transformers, which can be further advanced through the incorporation of physicochemical knowledge in a hybrid or physics-informed fashion. Then, we consider leveraging molecular ML at the chemical process scale, which is highly desirable yet rather unexplored. We discuss how molecular ML can be integrated into process design and optimization formulations, promising to accelerate the identification of novel molecules and processes. To this end, it will be essential to create molecule and process design benchmarks and practically validate proposed candidates, possibly in collaboration with the chemical industry.