IMSA-Title: Accelerated Discovery of PME Water Electrolyzers Anode Catalysts: A Closed-Loop Machine Learning and High-Throughput Approach chez Argonne

Background:

The production of green hydrogen through water electrolysis is a cornerstone of a sustainable energy economy and the global decarbonization efforts. A significant bottleneck in Proton Exchange Membrane (PME) water electrolyzers is the sluggish oxygen evolution reaction (OER) at the anode, which relies on scarce and expensive catalysts like iridium

To accelerate the transition to a hydrogen-based economy, the discovery of highly active and durable anode materials is imperative. This project will bypass traditional, slow, trial-and-error research methods by implementing a 'closed-loop' approach that integrates high-throughput (HT) experimentation with machine learning (ML) to rapidly identify promising new catalysts.

Description of Student Internship:

This internship is designed to equip the student with foundational skills in modern materials research, focusing on two critical, non-experimental areas. The training will encompass: 1) Systematic Literature Analysis: The student will be trained to perform comprehensive literature surveys using scientific databases (e.g., Web of Science, Scopus) to identify state-of-the-art developments in PEMWE anode catalysts. This involves mapping the existing materials landscape and identifying knowledge gaps. 2) Scientific Data Analysis: The student will gain experience in methodologies for processing, analyzing, and visualizing complex scientific datasets. The focus will be on extracting meaningful insights and understanding trends from existing research data.