Mapping the global design space of nanophotonic components using machine learning pattern recognition

• Published in: Nature communications Vol. 10; no. 1; pp. 4775 - 9
• Main Authors: Melati, Daniele, Grinberg, Yuri, Kamandar Dezfouli, Mohsen, Janz, Siegfried, Cheben, Pavel, Schmid, Jens H., Sánchez-Postigo, Alejandro, Xu, Dan-Xia
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 21.10.2019; Nature Publishing Group; Nature Portfolio
• Subjects: Algorithms; Complexity; Design; Design parameters; Humanities and Social Sciences; Learning algorithms; Machine learning; Mapping; multidisciplinary; Optimization; Pattern recognition; Science; Science (multidisciplinary)
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-019-12698-1

Nanophotonics finds ever broadening applications requiring complex components with many parameters to be simultaneously designed. Recent methodologies employing optimization algorithms commonly focus on a single performance objective, provide isolated designs, and do not describe how the design parameters influence the device behaviour. Here we propose and demonstrate a machine-learning-based approach to map and characterize the multi-parameter design space of nanophotonic components. Pattern recognition is used to reveal the relationship between an initial sparse set of optimized designs through a significant reduction in the number of characterizing parameters. This defines a design sub-space of lower dimensionality that can be mapped faster by orders of magnitude than the original design space. The behavior for multiple performance criteria is visualized, revealing the interplay of the design parameters, highlighting performance and structural limitations, and inspiring new design ideas. This global perspective on high-dimensional design problems represents a major shift in modern nanophotonic design and provides a powerful tool to explore complexity in next-generation devices. Machine learning is increasingly used in nanophotonics for designing novel classes of complex devices but the general parameter behavior is often neglected. Here, the authors report a new methodology to discover and visualize optimal design spaces with respect to multiple performance objectives.