Modeling of Relative Humidity Using Artificial Neural Network
View Abstract View PDF Download PDF

Keywords

Relative humidity, Metrological variables prediction, ANN

How to Cite

AlSadi, S. ., & Khatib, T. . (2012). Modeling of Relative Humidity Using Artificial Neural Network. Journal of Asian Scientific Research, 2(2), 81–86. Retrieved from https://archive.aessweb.com/index.php/5003/article/view/3329

Abstract

This paper presents a relative humidity predictions using feedforward artificial neural network (FFNN). Relative humidity values obtained from weather records for Malaysia are used in training the FFNNs. The prediction of the relative humidity is in terms of Sun shine ration and cloud cover. However, three statistical parameters, namely, mean absolute percentage error, MAPE, mean bias error, MBE, and root mean square error, RMSE are used to evaluate the neural networks. Based on results, the proposed neural network gives accurate prediction of hourly relative humidity whereas the MAPE, RMSE and MBE values in predicting hourly relative humidity are 5.08%, 5.8 and -0.041, respectively. While the MAPE values for the daily and monthly predicted values are 2.66% and 0.57%.

View Abstract View PDF Download PDF

Downloads

Download data is not yet available.