Department of Electrical and Electronics Engineering2024-12-2920242041-172310.1038/s41467-024-45846-32-s2.0-85185260503https://doi.org/10.1038/s41467-024-45846-3https://hdl.handle.net/20.500.14288/22881Expanding applications in optical communications, computing, and sensing continue to drive the need for high-performance integrated photonic components. Designing these on-chip systems with arbitrary functionality requires beyond what is possible with physical intuition, for which machine learning-based methods have recently become popular. However, computational demands for physically accurate device simulations present critical challenges, significantly limiting scalability and design flexibility of these methods. Here, we present a highly-scalable, physics-informed design platform for on-chip optical systems with arbitrary functionality, based on deep photonic networks of custom-designed Mach-Zehnder interferometers. Leveraging this platform, we demonstrate ultra-broadband power splitters and a spectral duplexer, each designed within two minutes. The devices exhibit state-of-the-art experimental performance with insertion losses below 0.66 dB, and 1-dB bandwidths exceeding 120 nm. This platform provides a tractable path towards systematic, large-scale photonic system design, enabling custom power, phase, and dispersion profiles for high-throughput communications, quantum information processing, and medical/biological sensing applications. An efficient and physically accurate platform is required to rapidly design high-performance integrated photonic devices. Here, the authors present a scalable framework for creating on-chip optical systems with complex and arbitrary functionality. Optical electronics and engineeringSilicon photonicsJournal article2041-1723 1164810100016Q141014