Martin Seifrid
Bio
Our group designs organic materials with precisely controlled structures and functions through synthesis and processing. To accelerate materials design, we develop self-driving labs – automated experiments guided by machine learning.
We are a multidisciplinary group whose expertise spans materials informatics, machine learning, automation, synthesis, and characterization.
Our current focus is a new class of materials with applications in sensing, energy storage, healthcare, and neuromorphic computing: organic mixed ionic-electronic conductors.
Education
Ph.D. Chemistry University of California, Santa Barbara 2019
B.S. Chemistry University of Southern California, Los Angeles 2014
Publications
- Artificial Coater: A Self-Driving Lab Maps Thin Film Processing Windows and Reveals Failure Mechanisms in Hybrid Perovskites , ChemRxiv (2026)
- Metadata Analysis to Reveal Environmental Effects in Large-Area Molecular Tunneling Junctions , ChemRxiv (2026)
- On the Need for Autonomous Science Instruments: A Call to Action , ChemRxiv (2026)
- Robust learning from literature data: Model generalizability and uncertainty for predicting conjugated polymer solution conformation , APL Machine Learning (2026)
- Stoichiometry-Driven Magnetic Frustration in Triangular Lattice Complexes , ChemRxiv (2026)
- Robust Learning from Literature Data: Model Generalizability and Uncertainty for Predicting Conjugated Polymer Solution Conformation , ChemRxiv (2025)
- Robust Learning from Literature Data: Model Generalizability and Uncertainty for Predicting Conjugated Polymer Solution Conformation , ChemRxiv (2025)
- Science acceleration and accessibility with self-driving labs , Nature Communications (2025)
- Chemspyd : an open-source python interface for Chemspeed robotic chemistry and materials platforms , Digital Discovery (2024)
- Beyond Molecular Structure: Critically Assessing Machine Learning for Designing Organic Photovoltaic Materials and Devices , ChemRxiv (2024)