Source-linked AI summary

Accelerating Materials Development via Automation, Machine Learning, and High-Performance Computing

Juan Pablo Correa-Baena, Kedar Hippalgaonkar, Jeroen van Duren, Shaffiq Jaffer, Vijay R. Chandrasekhar, Vladan Stevanovic, Cyrus Wadia, Supratik Guha, Tonio Buonassisi

arXiv:1803.11246v1cs.CYcond-mat.mtrl-sci

TL;DR

Novel materials development is constrained by mismatched time constants. The paper describes state-of-the-art approaches and resource gaps for combining automation, computing, and machine learning, with >10x faster synthesis among the reported outcomes.

  • Problem

    Novel materials development has long been stymied by a mismatch of time constants.

  • Method

    The paper describes state-of-the-art attempts to address materials-methods challenges, including down-selecting appropriate approaches and considering environmental factors in synthesis routes.

  • Results

    >10x faster synthesis is identified among the outcomes associated with new tools in materials research.

  • Takeaways & Limitations

    Reducing communication barriers and strengthening expertise in supporting fields will be important as new tools become part of the scientific process.

  • Takeaways & Limitations

    The learning curve for becoming even a generalist across the relevant domains remains very steep.

Abstract

from arXiv · show

Successful materials innovations can transform society. However, materials research often involves long timelines and low success probabilities, dissuading investors who have expectations of shorter times from bench to business. A combination of emergent technologies could accelerate the pace of novel materials development by 10x or more, aligning the timelines of stakeholders (investors and researchers), markets, and the environment, while increasing return-on-investment. First, tool automation enables rapid experimental testing of candidate materials. Second, high-throughput computing (HPC) concentrates experimental bandwidth on promising compounds by predicting and inferring bulk, interface, and defect-related properties. Third, machine learning connects the former two, where experimental outputs automatically refine theory and help define next experiments. We describe state-of-the-art attempts to realize this vision and identify resource gaps. We posit that over the coming decade, this combination of tools will transform the way we perform materials research. There are considerable first-mover advantages at stake, especially for grand challenges in energy and related fields, including computing, healthcare, urbanization, water, food, and the environment.

Loading 1803.11246v1…