Optimum Neural Network Architecture for Precipitation Prediction of Myanmar
Nowadays, precipitation prediction is required for proper planning and management of water resources. Prediction with neural network models has received increasing interest in various research and application domains. However, it is difficult to determine the best neural network architecture for prediction since it is not immediately obvious how many input or hidden nodes are used in the model. In this paper, neural network model is used as a forecasting tool. The major aim is to evaluate a suitable neural network model for monthly precipitation mapping of Myanmar. Using 3-layerd neural network models, 100 cases are tested by changing the number of input and hidden nodes from 1 to 10 nodes, respectively, and only one outputnode used. The optimum model with the suitable number of nodes is selected in accordance with the minimum forecast error. In measuring network performance using Root Mean Square Error (RMSE), experimental results significantly show that 3 inputs-10 hiddens-1 output architecture model gives the best prediction result for monthly precipitation in Myanmar.
[1] A free Neural Network engine; www.tek271.com/free/nuExpert.html
[2] BackPropagation Neural Network model;
http://ieee.uow.edu.au/~daniel/software/libneural/BPN_tutorial/BPN_En
glish/BPN_English/node8.html
[3] B.Cannas, A. Fanni, , "River flow forecasting using neural networks and
wavelet analysis", Electric and Electronic Engineering Department,
University of Cagliari, Italy, Geophysical Research Abstracts, Vol. 7,
08651, 2005
[4] C. Marzban, G.J.Stumpf, "A Neural Network for Tornado Prediction
Based on Doppler Radar-derived Attributes", National Severe Storms
Laboratory, Norman, OK 73069, 1998.
[5] F.Yerong, et.al, " A Short-Range Quantitative Precipitation Forecast
Algorithm Using Back-Propagation Neural Network Approach",
ADVANCES In ATMOSPHERIC SCIENCES, VOL. 23, NO. 3,
Department of Atmospheric Science, Zhongshan University, Guangzhou
510275, 2006, pp. 405-414.
[6] J. McCullagh, et.al, "A Neural Network Model for Rainfall Estimation",
IEEE Transactions on Neural Networks, Department of Information
Technology, Lafrobe University Bendigo, 2005.
[7] K.Figueiredo, et.al, "Neural Networks for Inflow Forecasting Using
Precipitation Information", Springerm , Electrical and
Telecommunications Engineering Department, Brazil, 2007, pp.552-
561.
[8] M.Adya, F.Collopy, "How Effective are Neural Networks at Forecasting
and Prediction? A Review and Evaluation", Journal of Forecasting,
University of Maryland at Baltimore County, USA, 1998. pp.481-482.
[9] Myanmar; "Myanmar Country Report: Flood Forecasting And Warning
In Myanmar", 4th Annual Mekong Flood Forum, Siem Reap, Cambodia,
18-19 May 2006, pp. 142-144.
[10] N.Chantasut, C.Charoenjit, l, "Predictive Mining of Rainfall Predictions
Using Artificial Neural Networks for Chao Phraya River", In
Proceedings of Joint Conference The 4th International Conference of
The Asian Federation of Information Technology in Agriculture and The
2nd World Congress on Computers in Agriculture and Natural
Resources, August 9-12, 2004, Bangkok, Thailand, pp. 117-122.
[11] Neural Network Model; http://leenissen.dk/fann/report/node4.html
[12] N. J. de Vos and T. H. M. Rientjes, "Constraints of artificial neural
networks for rainfall-runoff modelling: trade-offs in hydrological state
representation and model evaluation", Hydrology and Earth System
Sciences, 9, 111-126, Water Resources Section, Delft University of
Technology, Delft, The Netherlands, 2005
[13] S.Chattopadhyay, , "A Soft Computing Technique in rainfall
forecasting", In Proceedings of International Conference on IT, HIT,
Pailan College of Management and Technology, Kolkata - 700 104,
2007, pp. 523-525.
[14] S.Kalogirou, C.Neocleous, , "Wind Speed Prediction Using Artificial
Neural Networks", Higher Technical Institute Department of
Mechanical Engineering, Cyprus.
[1] A free Neural Network engine; www.tek271.com/free/nuExpert.html
[2] BackPropagation Neural Network model;
http://ieee.uow.edu.au/~daniel/software/libneural/BPN_tutorial/BPN_En
glish/BPN_English/node8.html
[3] B.Cannas, A. Fanni, , "River flow forecasting using neural networks and
wavelet analysis", Electric and Electronic Engineering Department,
University of Cagliari, Italy, Geophysical Research Abstracts, Vol. 7,
08651, 2005
[4] C. Marzban, G.J.Stumpf, "A Neural Network for Tornado Prediction
Based on Doppler Radar-derived Attributes", National Severe Storms
Laboratory, Norman, OK 73069, 1998.
[5] F.Yerong, et.al, " A Short-Range Quantitative Precipitation Forecast
Algorithm Using Back-Propagation Neural Network Approach",
ADVANCES In ATMOSPHERIC SCIENCES, VOL. 23, NO. 3,
Department of Atmospheric Science, Zhongshan University, Guangzhou
510275, 2006, pp. 405-414.
[6] J. McCullagh, et.al, "A Neural Network Model for Rainfall Estimation",
IEEE Transactions on Neural Networks, Department of Information
Technology, Lafrobe University Bendigo, 2005.
[7] K.Figueiredo, et.al, "Neural Networks for Inflow Forecasting Using
Precipitation Information", Springerm , Electrical and
Telecommunications Engineering Department, Brazil, 2007, pp.552-
561.
[8] M.Adya, F.Collopy, "How Effective are Neural Networks at Forecasting
and Prediction? A Review and Evaluation", Journal of Forecasting,
University of Maryland at Baltimore County, USA, 1998. pp.481-482.
[9] Myanmar; "Myanmar Country Report: Flood Forecasting And Warning
In Myanmar", 4th Annual Mekong Flood Forum, Siem Reap, Cambodia,
18-19 May 2006, pp. 142-144.
[10] N.Chantasut, C.Charoenjit, l, "Predictive Mining of Rainfall Predictions
Using Artificial Neural Networks for Chao Phraya River", In
Proceedings of Joint Conference The 4th International Conference of
The Asian Federation of Information Technology in Agriculture and The
2nd World Congress on Computers in Agriculture and Natural
Resources, August 9-12, 2004, Bangkok, Thailand, pp. 117-122.
[11] Neural Network Model; http://leenissen.dk/fann/report/node4.html
[12] N. J. de Vos and T. H. M. Rientjes, "Constraints of artificial neural
networks for rainfall-runoff modelling: trade-offs in hydrological state
representation and model evaluation", Hydrology and Earth System
Sciences, 9, 111-126, Water Resources Section, Delft University of
Technology, Delft, The Netherlands, 2005
[13] S.Chattopadhyay, , "A Soft Computing Technique in rainfall
forecasting", In Proceedings of International Conference on IT, HIT,
Pailan College of Management and Technology, Kolkata - 700 104,
2007, pp. 523-525.
[14] S.Kalogirou, C.Neocleous, , "Wind Speed Prediction Using Artificial
Neural Networks", Higher Technical Institute Department of
Mechanical Engineering, Cyprus.
@article{"International Journal of Earth, Energy and Environmental Sciences:62867", author = "Khaing Win Mar and Thinn Thu Naing", title = "Optimum Neural Network Architecture for Precipitation Prediction of Myanmar", abstract = "Nowadays, precipitation prediction is required for proper planning and management of water resources. Prediction with neural network models has received increasing interest in various research and application domains. However, it is difficult to determine the best neural network architecture for prediction since it is not immediately obvious how many input or hidden nodes are used in the model. In this paper, neural network model is used as a forecasting tool. The major aim is to evaluate a suitable neural network model for monthly precipitation mapping of Myanmar. Using 3-layerd neural network models, 100 cases are tested by changing the number of input and hidden nodes from 1 to 10 nodes, respectively, and only one outputnode used. The optimum model with the suitable number of nodes is selected in accordance with the minimum forecast error. In measuring network performance using Root Mean Square Error (RMSE), experimental results significantly show that 3 inputs-10 hiddens-1 output architecture model gives the best prediction result for monthly precipitation in Myanmar.
", keywords = "Precipitation prediction, monthly precipitation,neural network models, Myanmar.", volume = "2", number = "12", pages = "160-5", }
