Prediction of tubular solar still performance by machine learning integrated with Bayesian optimization algorithm

Abstract

Presented is a new generation prediction model of a tubular solar still (TSS) productivity utilizing two machine learning (ML) techniques, namely:Random forest (RF) and Artificial neural network (ANN). Prediction models were conducted based on experimental data recorded under Egyptian climate. Meteorological and operational thermal parameters were utilized as input layers. Moreover, Bayesian optimization algorithm (BOA) was used to obtain the optimal performance of RF and ANN models. In addition, these models results were compared to those of a multilinear regression (MLR) model. As resulted, experimentally, the average value accumulated productivity was 4.3 L/(m2day). For models results, RF was less sensitive to hyper parameters than ANN as ANN performance could be significantly improved by BOA more than RF. In addition, RF achieved better prediction performance of TSS on the current dataset. The determination coefficients (R2) of RF and ANN were 0.9964 and 0.9977, respectively, which were much higher than MLR models, 0.9431. Based on the robustness performance and high accuracy, RF is recommended as a stable method for predicting the productivity of TSS.