Training artificial neural network for optimization of nanostructured VO2-based smart window performance.

In this work, we apply for the first time a machine learning approach to design and optimize VO2 based nanostructured smart window performance. An artificial neural network was trained to find the relationship between VO2 smart window structural parameters and performance metrics-luminous transmittance (Tlum) and solar modulation (ΔTsol), calculated by first-principle electromagnetic simulations (FDTD method). Once training was accomplished, the combination of optimal Tlum and ΔTsol was found by applying classical trust region algorithm on the trained network. The proposed method allows flexibility in definition of the optimization problem and provides clear uncertainty limits for future experimental realizations.