Inverse Design of Microresonators Using Machine Learning

The rapidly increasing number of ways to fabricate integrated microresonators have led to a demand for optimization of such structures based on the desired optical properties. Tweaking the geometry of photonic structures can alter their dispersion profiles, which can counter optical nonlinearities and influence the intracavity optical dynamics. The parameter $D_{\text{int}}$ describes the integrated dispersion which can be written as,