Machine learning driven inverse design of devices and components for optical communication and sensing systems: a comprehensive review

We discuss recent progress in using machine-learning (ML)-enabled inverse design techniques applied to photonic devices and components. Specifically, we highlight the design of optical sources, including fiber and semiconductor lasers, as well as Raman and semiconductor optical amplifiers. Although inverse design approaches for optical detectors remain relatively underexplored, we examine optical layers, particularly metamaterial absorbers, as promising candidates for high-performance optical detection. In addition, we underscore advancements in inverse designing passive optical components, including beam splitters, gratings, and optical fibers. These optical blocks are fundamental in developing next-generation standalone optical communication systems and optical sensing networks, including integrated sensing and communication technologies. While categorizing various reported deep learning architectures across five paradigms, we offer a paradigm-based perspective that reveals how different ML techniques function within modern inverse design methods and enable fast, data-driven solutions that significantly reduce design time and computational demands compared with traditional optimization methods.