Comparison of Machine Learning Models For Rainfall Forecasting
作者： Nazli Bin Mohd Khairudin , Norwati Binti Mustapha , Teh Noranis Binti Mohd Aris , Maslina Binti Zolkepli , None
DOI: 10.1109/ICOSICA49951.2020.9243275
关键词: Mean squared error 、 Random forest 、 Machine learning 、 Predictor variable 、 Decision tree 、 Support vector machine 、 Flood myth 、 Artificial intelligence 、 Artificial neural network 、 Mean absolute error 、 Mathematics
摘要: Extreme rainfall can lead to a flood occurrence that give devastating impact on human lives including the agriculture sectors. Accurate forecasting is crucial in minimizing consequences derived from flood. In this study, forecast estimated using 5 different machine learning models which are Artificial Neural Network (ANN), Support Vector Regression (SVR), Decision Tree (DT), Random Forest Algorithm (RFA), and Long Short-Term Memory (LSTM). Average weekly data of Kuala Krai station have been used as predictor variable for study. The performances modelling approaches evaluated by statistical score metrics root mean squared error (RMSE) absolute (MAE). results shown LSTM performed best among other station.
sci-hub.st 参考文章(38)
Honey Badrzadeh, Ranjan Sarukkalige, A.W. Jayawardena, Hourly runoff forecasting for flood risk management: Application of various computational intelligence models Journal of Hydrology. ,vol. 529, pp. 1633- 1643 ,(2015) , 10.1016/J.JHYDROL.2015.07.057
Mark A. Hall, Ian H. Witten, Eibe Frank, Data Mining: Practical Machine Learning Tools and Techniques ,(1999)
M.E. Moeletsi, E.A.R. Mellaart, N.S. Mpandeli, H. Hamandawana, The Use of Rainfall Forecasts as a Decision Guide for Small-Scale Farming in Limpopo Province, South Africa. The Journal of Agricultural Education and Extension. ,vol. 19, pp. 133- 145 ,(2013) , 10.1080/1389224X.2012.734253
Ajay Kalra, Sajjad Ahmad, Anurag Nayak, None, Increasing streamflow forecast lead time for snowmelt-driven catchment based on large-scale climate patterns Advances in Water Resources. ,vol. 53, pp. 150- 162 ,(2013) , 10.1016/J.ADVWATRES.2012.11.003
Warren S. McCulloch, Walter Pitts, A logical calculus of the ideas immanent in nervous activity Bulletin of Mathematical Biology. ,vol. 52, pp. 99- 115 ,(1990) , 10.1007/BF02478259
Ming Zhang, John Fulcher, Roderick A. Scofield, Rainfall estimation using artificial neural network group Neurocomputing. ,vol. 16, pp. 97- 115 ,(1997) , 10.1016/S0925-2312(96)00022-7
Victor Rodriguez-Galiano, Maria Paula Mendes, Maria Jose Garcia-Soldado, Mario Chica-Olmo, Luis Ribeiro, Predictive modeling of groundwater nitrate pollution using Random Forest and multisource variables related to intrinsic and specific vulnerability: a case study in an agricultural setting (Southern Spain). Science of The Total Environment. ,vol. 476, pp. 189- 206 ,(2014) , 10.1016/J.SCITOTENV.2014.01.001
Vahid Nourani, Aida Hosseini Baghanam, Jan Adamowski, Ozgur Kisi, Applications of hybrid wavelet–Artificial Intelligence models in hydrology: A review Journal of Hydrology. ,vol. 514, pp. 358- 377 ,(2014) , 10.1016/J.JHYDROL.2014.03.057
Sepp Hochreiter, Jürgen Schmidhuber, Long short-term memory Neural Computation. ,vol. 9, pp. 1735- 1780 ,(1997) , 10.1162/NECO.1997.9.8.1735
D.J. Booker, R.A. Woods, Comparing and combining physically-based and empirically-based approaches for estimating the hydrology of ungauged catchments Journal of Hydrology. ,vol. 508, pp. 227- 239 ,(2014) , 10.1016/J.JHYDROL.2013.11.007