Title :
Modelling harbour sedimentation using ANN and M5 model trees
Author :
Bhattacharya, B. ; Solomatine, D.P.
Author_Institution :
Inst. for Water Educ., UNESCO-IHE, Delft, Netherlands
fDate :
July 31 2005-Aug. 4 2005
Abstract :
The paper presents machine learning (ML) models that predict sedimentation in the harbour basin of the Port of Rotterdam. The important factors affecting the sedimentation process such as waves, wind, tides, surge, river discharge, etc. are studied, the corresponding time series data is analysed and the most important variables behind the process are chosen as the inputs. Two ML methods are used: MLP ANN and M5 model tree. The latter is a collection of piece-wise linear regression models, each being an expert for a particular region of the input space. The models are trained on the data collected during 1992-1998 and tested by the data of 1999-2000. The predictive accuracy of the models is found to be adequate for the potential use in the operational decision making.
Keywords :
decision trees; ecology; learning (artificial intelligence); neural nets; regression analysis; sedimentation; time series; M5 model trees; artificial neural networks; harbour sedimentation; machine learning models; piece-wise linear regression models; time series data; Accuracy; Data analysis; Machine learning; Piecewise linear techniques; Predictive models; Rivers; Surges; Testing; Tides; Time series analysis;
Conference_Titel :
Neural Networks, 2005. IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on
Conference_Location :
Montreal, Que.
Print_ISBN :
0-7803-9048-2
DOI :
10.1109/IJCNN.2005.1556320