The Potential of Fuzzy Multi-objective Model for Rainfall Forecasting from Typhoons

This study applies the fuzzy multi-objective approach to forecast short-term (around 24 h) typhoon rainfall, which can be implemented without much background meteorological knowledge. The physical characteristics of 40 typhoons, including route, central pressure, central velocity and cyclonic radius, were used as the data set. The fuzzy multi-objective method ‘mined’ information from the database to forecast both the depth and pattern of rainfall, which were then combined to estimate a cumulative rainfall curve. The results of calibration with reference to 40 historical typhoon events and the results of validation using another five typhoon events indicate that the proposed model has the potential to forecast short-term cumulative rainfall curves if more variables can be included and more historical typhoon events can be collected to enlarge the database.

[1]  Francesco Masulli,et al.  Application of an ensemble technique based on singular spectrum analysis to daily rainfall forecasting , 2003, Neural Networks.

[2]  Shyi-Ming Chen,et al.  Handling multicriteria fuzzy decision-making problems based on vague set theory , 1994 .

[3]  Hans-Jürgen Zimmermann,et al.  Fuzzy Set Theory - and Its Applications , 1985 .

[4]  Jose D. Salas,et al.  On parameter estimation of temporal rainfall models , 1987 .

[5]  Pao-Shan Yu,et al.  Application of Gray and Fuzzy Methods for Rainfall Forecasting , 2000 .

[6]  L. Bodri,et al.  Prediction of extreme precipitation using a neural network: application to summer flood occurence in Moravia , 2000 .

[7]  Upmanu Lall,et al.  Seasonal to interannual rainfall probabilistic forecasts for improved water supply management : Part 2 - Predictor identification of quarterly rainfall using ocean-atmosphere information , 2000 .

[8]  Konstantine P. Georgakakos,et al.  A hydrologically useful station precipitation model: 1. Formulation , 1984 .

[9]  Witold F. Krajewski,et al.  Rainfall forecasting in space and time using a neural network , 1992 .

[10]  George J. Klir,et al.  Fuzzy sets and fuzzy logic - theory and applications , 1995 .

[11]  P. Brémaud,et al.  Forecasting heavy rainfall from rain cell motion using radar data , 1993 .

[12]  Floyd A. Huff,et al.  Time distribution of rainfall in heavy storms , 1967 .

[13]  E. Toth,et al.  Comparison of short-term rainfall prediction models for real-time flood forecasting , 2000 .

[14]  Holger R. Maier,et al.  Neural networks for the prediction and forecasting of water resource variables: a review of modelling issues and applications , 2000, Environ. Model. Softw..

[15]  John W. Labadie,et al.  Worth of short‐term rainfall forecasting for combined sewer overflow control , 1981 .

[16]  Konstantine P. Georgakakos,et al.  A hydrologically useful station precipitation model: 2. Case studies , 1984 .

[17]  Francesco Masulli,et al.  Daily rainfall forecasting using an ensemble technique based on singular spectrum analysis , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[18]  Jean-Dominique Creutin,et al.  Evaluation of a simplified dynamical rainfall forecasting model from rain events simulated using a meteorological model , 1999 .

[19]  J. Salas,et al.  Forecasting of short-term rainfall using ARMA models , 1993 .

[20]  Ashish Sharma,et al.  An application of artificial neural networks for rainfall forecasting , 2001 .

[21]  Ashish Sharma,et al.  Seasonal to interannual rainfall probabilistic forecasts for improved water supply management: Part 1 — A strategy for system predictor identification , 2000 .