Abstract

In the civil engineering designs and water resources management projects, various methods have been proposed to prevent the evaporation of water storage tanks and pools, including the use of physical materials. The use of MDF sheets is an evaporation reduction method using physical elements, which can be useful in controlling evaporation. The present study investigates water evaporation reduction from a standard Colorado Sunken evaporation pan using 50 mm-thick MDF sheets covering 100% of the evaporation pan. The least-square support vector machine (LSSVM) and an artificial neural network (ANN) were used to estimate evaporation reduction. The efficiency of the intelligent methods was evaluated by the root mean square error (RMSE), coefficient of determination (R2), and mean absolute error (MAE). The R2, RMSE, and MAE values were attained for the LSSVM method in the test stage 0.8755, 1.6517, and 2.2042, and for the ANN model 0.7714, 2.112 and 1.6732 respectively which shows the LSSVM model has better performance than ANN model. The evaporation correlation, according to the Pearson test for sheet cover, MDF with minimum temperature, maximum temperature, sunny hours, is positive. It has 0.442, 0.362, and 0.387 values, respectively, and with minimum damp, maximum damp, pressure is negative and has -0.313, -0.350, and -0.319 values, respectively. The results reveal that MDF had satisfactory performance in controlling evaporation and lead to higher water resource storage. Performing tests for three months indicate that MDF sheets can result in an approximately 91% reduction in evaporation on average.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call