CATALYTIC APPLICATION TESTING FOR ACCELERATED LEARNING CHEMISTRIES VIA HIGH-THROUGHPUT EXPERIMENTATION AND MODELING EFFICIENTLY (CATALCHEM-E)

The Catalytic Application Testing for Accelerated Learning Chemistries via High-Throughput Experimentation and Modeling Efficiently (CATALCHEM-E) program aims to disrupt and accelerate the design and development cycle for heterogeneous catalyst R&D workflows by coupling the latest advancements in artificial intelligence (AI) and machine learning (ML) with high-throughput experimentation (HTE). The program will span from rational material discovery to synthesis and final reactor testing, and will use these new tools to discover and optimize catalytic chemistries relevant to ARPA-E's goals, ultimately helping to advance the objective of net-zero carbon emissions by 2050. • The program involves the development of novel workflows that strategically remove bottlenecks and time-consuming tasks, resulting in significant acceleration compared to traditional workflows. • The program uses reference chemistries for workflow validation, which have been proven at the commercial scale and are relevant to ARPA-E's goals and the U.S. goal of net-zero carbon emissions by 2050. • The program generates high-quality data via HTE, which is used to train and validate AI/ML models, and creates AI/ML-ready catalysis databases and informatics. • The program involves transformational multi-scale, multi-modal modeling using AI/ML, and surrogate AI/ML-assisted computational modeling and simulations.