Productivity forecasting of solar distiller integrated with evacuated tubes and external condenser using artificial intelligence model and moth-flame optimizer

This paper aims at developing an artificial intelligence model to forecast the water yield of a modified solar distiller integrated with evacuated tubes and external condenser. The consists hybrid long short-term memory (LSTM) optimized by moth-flame optimizer (MFO) used as subroutine obtain optimal internal parameters LSTM that maximize forecasting accuracy. performance was compared standalone model. Both developed models were trained tested using experimental data conventional distiller. thermal both distillers is also in this article. maximum daily distillate output achieved for 3920 l/m 2 . forecasted several statistical measures. For all measurements, LSTM-MFO outperformed LSTM. determination coefficient reached high value 0.999 distillers.