The projects will be organized in the following matrix between the areas of chemical engineering and machine learning tasks. Data, models, and methods will be shared among all participants of the priority programme in an internal platform. Matrix outlining the fields of investigation of this priority program is shown below. The columns organize the areas of chemical engineering, while the rows structure machine learning.
We identified six areas of collaborative research for this Priority Programme, which open up new methods for chemical engineering, formulate new types of problems for machine learning, and will jointly generate advances for methods in both machine learning and chemical engineering. These areas are #1 optimal decision making, #2 introducing/enforcing physical laws in machine learning models, #3 heterogeneity of data, #4 information and knowledge representation, #5 safety and trust in machine learning applications, and #6 creativity. Under the umbrella of these areas/topics, the priority program will have collaborative projects between groups from chemical engineering and machine learning, which promise progress regarding process synthesis (especially regarding feedstock transformation), process flexibility, material selection, generation of alternatives, and uncovering hidden information. This priority program can hence make a large contribution towards readying Germany’s chemical industry for a sustainable future.
We expect projects to address at least one chemical engineering area and one machine learning area, i.e., one of the 9 collaboration fields in the matrix (A to I), and clearly state why it does, and how it will achieve progress in one of the areas #1 to #6