Comparative study of grammatical evolution and adaptive neuro-fuzzy inference system on rainfall forecasting in Bandung

Rainfall is a very crucial weather parameter. The information on rainfall is also used for certain fields including farming, transportation, and flood early warning system. The significant fluctuation of rainfall in Bandung recently causes the difficulty in rainfall forecasting. The study analyzes and implements Soft Computing algorithm for rainfall forecasting in Bandung Regency. The algorithms belong to SC method are Fuzzy Logic, Neural Network, and Evolutionary Algorithms (EAs). The study compares the performance of the forecasting from two algorithms, Grammatical Evolution (GE) and Adaptive Neuro-Fuzzy Inference System (ANFIS). For GE algorithm, the comparison between two survivor selection methods is conducted, namely between generational replacement and steady state. The experiment used the rainfall data for Bandung regency obtained from Indonesian Agency for Meteorology Climatology and Geophysics (BMKG) for the current 10 years (2003-2012). The experiment shows the performance of forecasting result of 70.76% for GE that uses the generational replacement, 74.35% for GE that uses the steady state and 80% for ANFIS.

[1]  F. Nhita,et al.  Forecasting Indonesian Weather through Evolving Neural Network (ENN) based on Genetic Algorithm , 2014 .

[2]  Adiwijaya,et al.  Rainfall prediction in Kemayoran Jakarta using Hybrid Genetic Algorithm (GA) and Partially Connected Feedforward Neural Network (PCFNN) , 2014, 2014 2nd International Conference on Information and Communication Technology (ICoICT).

[3]  Rashedur M. Rahman,et al.  Comparative study of ANFIS and ARIMA model for weather forecasting in Dhaka , 2013, 2013 International Conference on Informatics, Electronics and Vision (ICIEV).

[4]  Adiwijaya,et al.  A rainfall forecasting using fuzzy system based on genetic algorithm , 2013, 2013 International Conference of Information and Communication Technology (ICoICT).

[5]  Helio J. C. Barbosa,et al.  Evaluating the feasibility of grammar-based GP in combining meteorological forecast models , 2013, 2013 IEEE Congress on Evolutionary Computation.

[6]  Adiwijaya,et al.  PLANTING CALENDAR FORECASTING SYSTEM USING EVOLVING NEURAL NETWORK , 2015 .

[7]  Suyanto.  Soft Computing Membangun Mesin ber-IQ tinggi Edisi Cetakan Pertama , 2011 .

[8]  L. Pazvakawambwa,et al.  Forecasting methods and applications. , 2013 .

[9]  Thee Houw Liong,et al.  Prediction of malaria incidence in Banggai Regency using Evolving Neural Network , 2013, 2013 International Conference on Technology, Informatics, Management, Engineering and Environment.