Monthly rainfall time series prediction using modular fuzzy inference system with nonlinear optimization techniques
Kajornrit, J. (2012) Monthly rainfall time series prediction using modular fuzzy inference system with nonlinear optimization techniques. In: Postgraduate Electrical Engineering and Computing Symposium, Perth, Western Australia.
Download (733kB) | Preview
Accurate rainfall time series prediction is one of the important tasks in hydrological study. A conventional time series model such as autoregressive moving average or an intelligent model such as artificial neural network have been used efficiently to perform this task. However, such models are difficult to interpret by human analysts because their prediction mechanism is in the parametric form. From the hydrologist’s point of view, the accuracy of the prediction and understanding the prediction model are equally important. This study proposes the use of modular fuzzy inference system with nonlinear optimization technique to predict monthly rainfall time series. The fuzzy inference system is used to generalize the relationship of the rainfall patterns whereas nonlinear optimization method is used to capture the uncertainty in the time dimension. Eight monthly rain-fall time series selected from the northeast region of Thailand are used to evaluate the model. The experimental results showed that the proposed model could be a good alternative method to provide both accurate prediction results and human-understandable prediction mechanism.
|Publication Type:||Conference Paper|
|Murdoch Affiliation:||School of Information Technology|
|Item Control Page|
Downloads per month over past year