Chemical Engineering is a field with high availability of data and computational resources, which should be conducive to AI-based research. However, efforts in recent years to introduce machine learning to chemical engineering have sometimes failed to meet expectations; often chemical engineers will have had limited training in computer science and data analysis, leading to inappropriate or inadequate use. AI must take advantage of data from industrial processes or complex systems, which often have characteristics such as uncertain, noisy, or incomplete observations, and present concrete and reliable solutions for a sustainable world. This book demonstrates the recent advances in the various software, methodologies, examples, and applications of machine learning in the field of Chemical Engineering, seeking to better acquaint the reader with applied ML techniques and methodologies and build a better foundational understanding of their usage and potential, which offers significant advantages (such as accuracy, speed of execution, and flexibility) over traditional modelling and optimization techniques. Through developing methodologies and applications, students and professionals will learn applied AI using explicitly chemical engineering focused examples. The book provides a precedent for applied AI, but one that goes beyond purely data-centric ML. It is firmly grounded in the philosophies of knowledge modelling, knowledge representation, search and inference, and knowledge extraction and management. Machine Learning Tools for Chemical Engineering addresses an underexplored area of opportunity for chemical engineers. It is written primarily for graduate and upper undergraduate students, early career researchers and teachers, and professional/industry-based decision-makers focused on developing AI for the field. However, the interdisciplinary nature of the field means it will likely be of use to those in the adjacent and overlapping fields such as energy, mechanical engineering, materials science, and industrial engineering.

• Outlines the current and potential future contribution of machine learning, the use of data science and ultimately how to correctly use machine learning tools specifically in chemical engineering
• Devoted to the correct application and interpretation of results in various phases of the development of decision support systems: data collection, model development, training, and testing, as well as application in chemical engineering
• Examines chemical engineering specific challenges and problems including noise, manufacturing equipment, and domain-specific solutions such as physical knowledge using relevant case study examples