Advances in machine learning-based design for high-volume manufacturing of planar lightwave circuits

The increasing functionality and associated complexity of planar lightwave circuits demand novel approaches to the design and simulation of photonic chips. In high-volume manufacturing, it is critical that photonic circuits are designed in ways that can withstand inevitable process variations. We discuss our use of machine learning and deep neural networks to advance the design and fabrication of optical chips in a high-volume production environment. We also describe the capabilities of our silica-on-silicon planar lightwave circuit platform and its exceptional characteristics that make it essential for the realization of key building blocks in LiDAR and optical coherence tomography systems.