Accelerating Development of Materials for Industrial and High-Tech Applications with Data-Driven Analysis and Simulation
- PDF / 1,960,594 Bytes
- 15 Pages / 432 x 648 pts Page_size
- 6 Downloads / 146 Views
MRS Advances © 2020 Materials Research Society DOI: 10.1557/adv.2020.189
Accelerating Development of Materials for Industrial and High-Tech Applications with DataDriven Analysis and Simulations Sergey V. Barabash Intermolecular Inc., 3011 N. First St., San Jose, CA 95134, U.S.A.
ABSTRACT
We describe how the development of advanced materials via high-throughput experimentation at Intermolecular® is accelerated using guidance from modelling, machine learning (ML) and other data-driven approaches. Focusing on rapid development of materials for the semiconductor industry at a reasonable cost, we review the strengths and the limitations of data-driven methods. ML applied to the experimental data accelerates the development of record-breaking materials, but needs a supply of physically meaningful descriptors to succeed in a practical setting. Theoretical materials design greatly benefits from the external modelling ecosystems that have arisen over the last decade, enabling a rapid theoretical screening of materials, including additional material layers introduced to improve the performance of the material stack as a whole, “dopants” to stabilize a given phase of a polymorphic material, etc. We discuss the relative importance of different approaches, and note that the success rates for seemingly similar problems can be drastically different. We then discuss the methods that assist experimentation by providing better phase identification. Finally, we compare the strengths of different approaches, using as an example the problem of identifying regions of thermodynamic stability in multicomponent systems.
INTRODUCTION The rapid proliferation of data-centric methods has enabled new ways to advance materials development[1]. The biggest advantage is offered by workflows that synergistically combine data-driven tools with other simulations methods to drive experimentation within a feedback loop. At the same time, the benefits and the scope of applications for individual data-centric approaches are often restricted by practical considerations in commercial research and development (R&D), e.g. in development of new materials within the semiconductor device industry sector. Here, we overview both
Downloaded from https://www.cambridge.org/core. Rice University, on 17 May 2020 at 03:56:37, subject to the Cambridge Core terms of use, available at https://www.cambridge.org/core/terms. https://doi.org/10.1557/adv.2020.189
the strengths and the limitations of such approaches, using as a case study the acceleration of materials development at Intermolecular. Note that in this review, we focus on methods and rarely disclose material details, due to a proprietary nature of data. For the benefit of the reader, before proceeding we first describe the nature of the business that forms the perspective for the subsequent discussion. Intermolecular focuses on rapid development of thin film materials via high-throughput experimentation. In practice, a customer needs an improved performance of a material inside the final device – i.e. not on
Data Loading...
