DEVELOPMENT OF A NEURAL NETWORK BASED SOIL EVAPORATION PREDICTION MODEL
Publication Date : 01/02/2009
Meteorological conditions have a great impact on the amount of energy available in the natural world and as such play a great role in regulating evaporation from the vegetation. This work is aimed at developing a Neural Net based soil evaporation prediction model by considering the effect of such meteorological conditions as solar radiation (sunshine hours), wind speed, temperature and relative humidity (over an eleven year period from 1993 to 2003) on the ET process using Zaria as a case study. One of the signs of a good model is that the training set performance and that of the test set are fairly similar with respect to the key performance indicators. The model also performed well on the validation data. The model was then tested on the data for 2003, which was previously not used and the results obtained can be regarded as acceptable.
No. of Downloads :