Table 3 Optimization results for the DNN model trained with 1566 data set. \({\tilde{\alpha }}_{sol}\) is the solar absorptance predicted by DNN. \({\alpha }_{sol}\) is the solar absorptance calculated by RCWA for validation. \({\sigma }_{sol}\) is the standard deviation of the distributed \({\tilde{\alpha }}_{sol}\) due to fabrication uncertainty of each dimensional variables.

From: Design of a Broadband Solar Thermal Absorber Using a Deep Neural Network and Experimental Demonstration of Its Performance