Open AccessArtificial neural network models for forecasting intermittent monthly precipitation in arid regions
Author(s) -
Dahamsheh Ahmad,
Aksoy Hafzullah
Publication year - 2009
Publication title -
meteorological applications
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.672
H-Index - 59
eISSN - 1469-8080
pISSN - 1350-4827
DOI - 10.1002/met.127
Subject(s) - precipitation , artificial neural network , standard deviation , environmental science , mean squared error , linear regression , arid , markov chain , meteorology , statistics , computer science , mathematics , geography , machine learning , geology , paleontology
Forecasting monthly precipitation in arid regions is investigated by means of feed forward back propagation (FFBP) artificial neural networks (ANNs) and compared to the linear regression technique with multiple inputs (MLR). Four meteorological stations from different geographical regions in Jordan are selected. The ANNs and MLR processes are analysed based on the mean square error, relative/absolute error, determination coefficient as well as the central statistical moments such as mean, standard deviation, and minimum and maximum values. It is found that whilst on one hand the ANNs are slightly better than the MLR in forecasting the monthly total precipitation, on the other hand, both are found with to have limitations which should be improved by means of either changing the type and architecture of the ANNs or incorporating modelling tools such as Markov chains into the forecast model. Copyright © 2009 Royal Meteorological Society