CACHE Awards Three New Seed Grants for Development of Computational-Based Tools and Modules for Chemical Engineering Education

CACHE funds 12-month long projects that focus on the development of novel computational-based educational modules or tools. These modules/tools can be linked to existing courses or they can be used to broaden and support interest in a chemical engineering education beyond students traditionally interested in this field. Submitting PIs need to be in departments affiliated with CACHE: https://cache.org/members

The proposals summarized below were recently selected for funding this year:

Integrating Machine Learning based Sustainability Evaluation for Chemicals and Processes in the Undergraduate Curriculum
Kirti M. Yenkie and Aditya Dilip Lele (Rowan)

Design and evaluation of new chemicals and processes is a key skill for Chemical Engineers. Traditional process design and sustainability evaluation tools are proficient in evaluating systems that are well-known and have all the information about physicochemical, thermodynamic, and structural properties, as well as operating conditions. However, with the research advancements in materials and product design, new technologies, pharmaceuticals, and bio-based options, the exact information needed for design and sustainability evaluation is limited. To this end, teaching our students to leverage new tools such as Machine Learning (ML) for molecular design and property identification, as well as life cycle inventory (LCI) and emissions factor identification, can play a key role in developing advanced computational skills that will equip them with the technical know-how to handle emerging problems in Chemical Engineering Product and Process Design. To overcome the above challenges, we aim to develop 2 Educational Modules: 1) ML-assisted property estimation for novel chemicals; 2) ML-assisted life cycle analysis (LCA) of chemicals/processes.

The Industrially-Situated Redox Flow Battery Virtual Laboratory
Milo Koretsky and Graham Leverick (Tufts)

Supported by an internal Tufts University grant, we have developed a preliminary version of the industrially-situated Redox Flow Battery Virtual Laboratory (RFBVL). This technology tool was used as part of the delivery in the inaugural 2025 Tufts’ Battery Research Summer
School (BRSS) – a four-day intensive workshop designed to equip participants with foundational knowledge and hands-on experience in battery science. With the support of CACHE funding, we will make this virtual laboratory instructionally self-sufficient so that it can be used in a variety of chemical engineering classroom contexts to support the learning of electrochemical engineering and of dealing with authentic, messy real-world problems.

Preparing Chemical Engineering Faculty for Rapid Instructional Interventions using AI-Generated Resources
David L. Silverstein (Mississippi)

The purpose of this project is to develop a faculty guide for rapid development of AI generated interventions to address faculty-identified student misconceptions and misunderstandings. The form of these interventions are anticipated to be primarily simulation-based and would be accompanied by guided inquiry activities. Additional resource formats include illustrations, animations, podcasts, games, and quizzes. These activities would be generated using AI tools considered most effective for the intended product, with the primary product being an electronic guide for developing effective prompts and using the resulting products, and the outcomes-driven resources a secondary product.