Search

The prediction of freshwater production from the condenser of an agricultural seawater greenhouse is important for designing the greenhouse process. Two models, namely, Artificial Neural Network and multilinear regression (denoted as ANN and RA, respectively), were developed and tested to predict the freshwater production rate considering ambient solar intensity, condenser inlet moist-air temperature, humidity ratio and mass flowrate, and inlet coolant temperature. Statistical analysis indicated that all parameters significantly affected the prediction (p < 0.05). The accuracy of the ANN and RA models was then compared to two models previously developed by Yetilmezsoy and Abdul-Wahab and Al-Ismaili et al. (denoted as Yetilmezsoy model and Al-Ismaili model, respectively). The ANN model showed the best prediction when seven statistical criteria were considered. The Pearson correlations for ANN, RA, Yetilmezsoy, and Al-Ismaili models were observed as 1.00, 0.98, 0.88, and 0.96, respectively, while mean absolute percentage errors (MAPE) were 17.84, 79.72, 63.24, and 80.50%, respectively. Hence it could be recommended to use ANN model for the prediction of freshwater production rate, however other three simple models could also be used with lower accuracy in the cases of unavailability of the ANN model. [ABSTRACT FROM AUTHOR]

Seawater greenhouses (SWGH) utilize seawater or saline/brackish groundwater for cooling the microclimate and providing freshwater for irrigation through a humidification-dehumidification desalination process. The overall effectiveness of the SWGH greatly depends on the effectiveness of its condenser. The present study provides a good review on the available simulation models of the SWGH condenser and proposes a multiple linear regression model to predict the dehumidification rate of the condenser in the Oman SWGH. Four climatic and operational input variables were considered, including solar irradiance, inlet moist air temperature, inlet humidity ratio, and inlet air mass flow rate. The results showed that the model accurately predicts the dehumidification rate when compared against experimental values [a mean predictive error (PE) = −0.127 kg/h and root mean square error (RMSE) = 4.691 kg/h]. The model also outperformed some other model in several accuracy indicators such as PE, mean absolute predictive error, RMSE, R2, index of agreement and fractional variance. [ABSTRACT FROM AUTHOR]