期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2013
卷号：56
期号：1
出版社：Journal of Theoretical and Applied
摘要：Groundwater level in the tidal lowlands fluctuates according to space and time. It is influenced by local rainfall or tidal. Tidal lowlands development for agriculture particularly food crops requires proper water management strategies so that the productivity of land and the production of food crops can be optimized. Proper water management must be supported by an accurate prediction system. This research aims to apply extreme learning machine (ELM) which can be used to make a prediction system of groundwater level in tidal lowlands. ELM is a feed forward artificial neural network with a single hidden layer or commonly referred to as single hidden layer feed forward neural networks (SLFNs). ELM has the advantage in learning speed. The result of the ground water level prediction using ELM was better than that using BPANN. Based on these results, the ELM can be used to predict the ground water level in order to assist decision makers in determining water management strategies and the determination of appropriate cropping patterns in the tidal lowlands reclamation.
关键词：Prediction; Ground Water Level; Back Propagation; Artificial Neural Network; Extreme Learning Machine
