Deep learning neural network: A machine learning approach for monthly rainfall forecast, case study in eastern region of Thailand

  • Uruya Weesakul Department of Civil Engineering, Faculty of Engineering, Thammasat University, Pathum Thani 12120, Thailand
  • Phisan Kaewprapha Department of Electrical and Computer Engineering, Faculty of Engineering, Thammasat University, Pathum Thani 12120, Thailand
  • Kitinan Boonyuen Department of Electrical and Computer Engineering, Faculty of Engineering, Thammasat University, Pathum Thani 12120, Thailand
  • Ole Mark DHI, Agern Alle 5, 2970 HORSHOM Horshom, Denmark
Keywords: Rainfall forecast model, Deep learning neural network, Eastern River Basin of Thailand

Abstract

Accurate monthly rainfall forecasting is essential for efficient watershed management, particularly for the current situation with high variation of rainfall due to global climate change. A variety of researchers attempted to develop more sophisticated models to enhance model capability to capture uncertainty due to high variation in rainfall both in time and space. The objective of this study is to investigate capability of a Deep Learning Neural Network (DNN) in forecasting monthly rainfall. A river basin in eastern region of Thailand, where a high increase in water demand is expected in next 20 years due to the national development plan, is selected as the study area. In this study LAV with different atmospheric layers, such as air temperature, geopotential height, meridonal wind, omega, outgoing longwave radiation, relative humidity, specific humidity, sea level pressure, sea surface temperature, zonal wind, precipitation rate and precipitable water, were selected as inputs to the DNN model. Monthly rainfall at Pluak Deang station from 1991 to 2010 were used for the training process in the DNN model. Monthly rainfall from 2011 to 2016 were used for model validation. Results of forecasting revealed that DNN is able to predict monthly rainfall from one month up to 12 months in the future, however, accuracy of forecasting decreases when the forecast time horizon increases. The most practical time of forecast is one month into the future yielding a forecast where around 70% of the forecasted values are within the range of one standard deviation from the observed values.

Downloads

Download data is not yet available.

Author Biographies

Uruya Weesakul, Department of Civil Engineering, Faculty of Engineering, Thammasat University, Pathum Thani 12120, Thailand

Associate Professor, Faculty of Engineering, Thammasat University, Pathum Thani, 12120, Thailand

Phisan Kaewprapha, Department of Electrical and Computer Engineering, Faculty of Engineering, Thammasat University, Pathum Thani 12120, Thailand

Assistant Professor, Faculty of Engineering, Thammasat University, Pathum Thani, 12120, Thailand

Kitinan Boonyuen, Department of Electrical and Computer Engineering, Faculty of Engineering, Thammasat University, Pathum Thani 12120, Thailand

Master Student, Faculty of Engineering, Thammasat University, Pathum Thani, 12120, Thailand

Ole Mark, DHI, Agern Alle 5, 2970 HORSHOM Horshom, Denmark

DHI, Agern Alle 5, 2970 HORSHOM Horshom, Denmark

References

[1] Weesakul U, Singhrattna N, Viwat H. Identification of large-scale atmospheric predictors for rainfall forecasting of Nan River Basin. Proceedings of the 5th National Water Resources Engineering Symposium; 2013 Sep 5-6; Chiengrai, Thailand.

[2] Weesakul U, Singhrattna N, Luangdilok N. Identification of large-scale atmospheric predictors for rainfall forecasting of Chi River Basin. Proceedings of the 5th National Water Resources Engineering Symposium; 2013 Sep 5-6; Chiengrai, Thailand.

[3] Weesakul U, Singhrattna N, Yodpongpiput P. Statistical relationships between large-scale atmospheric variables and rainfall in Mun River Basin. Proceedings of the 5th National Water Resources Engineering Symposium; 2013 Sep 5-6; Chiengrai, Thailand.

[4] Weesakul U, Singhrattna N, Khetped N. Large-scale atmospheric variables influencing on rainfall in Tapee River Basin. Proceedings of the 5th National Water Resources Engineering Symposium; 2013 Sep 5-6; Chiengrai, Thailand.

[5] Weesakul U, Yodpongpipu P. Interannual variability of monsoon rainfall in Thailand: an inconsistent effect of climate change over south East Asian region. American Transactions on Engineering and Applied Sciences. 2015;4(4):251-60.

[6] Weesakul U, Singhrattna N, Luangdilok N. Effects of climate change on Thailand rainfall variability. The 3rd International Engineering Symposium on Engineering, Energy and Environments; 2013 Nov 17-20; Bangkok, Thailand.

[7] Weesakul U, Singhrattna N, Luangdilok N. Rainfall forecast in northeast of Thailand using modified k-nearest neighbor. KKU Eng J. 2014;41(1):1-10.

[8] Weesakul U, Singhrattna N, Yodpongpiput P. Seasonal rainfall forecast for cropping pattern planning using a modified k-nearest neighbor model. KKU Eng J. 2016;43(3):156-61.

[9] Toth E, Brath A, Montanari A. Comparison of short term rainfall prediction models for real-time flood forecasting. J Hydrol. 2000;239:132-47.

[10] Terzi O, Cevik E. Rainfall estimation using artificial neural network method. SDU International Journal of Technological Science. 2012;4(1):10-9.

[11] Chantasut N, Charoenjit C, Tanprasert C. Predictive mining of rainfall predictions using artificial neural networks for Chao Phraya River. Proceedings of 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; 2004 Aug 9-12; Bangkok, Thailand.

[12] Rangsiwanichpong P, Ekkawatpanit C, Kositgittiwong D. Seasonal rainfall forecasting in the Chao Phraya River Basin using artificial neural networks. In Proceeding of the 20th National Convention on Civil Engineering; 2015 July 8-10; Chonburi, Thailand.

[13] Mislan, Haviluddin, Hardwinarto S, Sumaryono, Aipassa M. Rainfall monthly prediction based on artificial neural network: a case study in Tenggarong station, east Kalimantan-Indonesia. Procedia Comput Sci. 2015;59:142-51.

[14] Thammakul P, Kaewprapha P. Rainfall forecasting using artificial neural networks in eastern river basin of Thailand. The 40th Electrical Engineering Conference; 2017 Nov 15 -17; Chonburi, Thailand.

[15] Hochreiter S, Schmidhuber J. Long short-term memory. Neural Computation. 1997;9(8):1735-80.

[16] Graves A. Generating sequences with recurrent neural networks. arXiv. 2014; arXiv:1308.0850.

[17] Cho K, Merrienboer B van, Gulcehre C, Bahdanau D, Bougares F, Schwenle H, et al. Learning phrase representation using RNN encoder-decoder of statistical machine translation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP); 2014 Oct 25-29; Doha, Qatar; 2014. p. 1724-34.

[18] Donahue J, Hendricks LA, Guadarrama S, Rohrbach M, Venugopalan S, Saenko K, et al. Long-term recurrent convolutional network for visual recognition and description. IEEE Trans Pattern Anal Mach Intell. 2017;39(4):677-91.

[19] Suiskever I, Vinyals O, Le Q V. Sequence to sequence learning with neural network. Proceedings of the 27th International Conference on Neural Information Processing Systems; 2014 Dec 8-13; Montreal, Canada; 2014. p. 3104-12.

[20] Karpathy A, Fei-Fei L. Deep visual-semantic alignments for generating image descriptions. IEEE Trans Pattern Anal Mach Intell. 2017;39(4):664-76.

[21] Ranzato M, Szlam A, Bruna J, Mathieu M, Collobert R, Chopra S. Video(language) modeling: a baseline for generative models of natural videos. arXiv. 2014; arXiv:142.6604.

[22] Srivastava N, Mansimov E, Salakhuidinov R. Unsupervised learning of video representation using lstms. Proceedings of the 32nd International Conference on International Conference on Machine Learning; 2015 Jul 6-11; Lille, France; 2015. p. 843-52.

[23] Xu K, Ba J, Kiros R, Cho K, Courville A, Salakhuidinov R, et al. Show, attend and tell: neural image caption generation with visual attention. Proceedings of the 32nd International Conference on International Conference on Machine Learning; 2015 Jul 6-11; Lille, France; 2015. p. 2048-57.

[24] LeCun Y, Battou L, Bengio Y and Haffner P. Gradient-based learning applied to document recognition. Proc IEEE. 1998;86(11):2278-324.

[25] Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Proceedings of the 25th International Conference on Neural Information Processing Systems; 2012 Dec 3-6; Lake Tahoe, Nevada; 2012. p. 1097-105.

[26] Ciresan DC, Giusti A, Gambaradella LM, Schmidhuber J. Mitosis detection in breast cancer histology images with deep neural networks. Med Image Comput Comput Assist Interv. 2013;16 (Pt 2):411-8.

[27] Sermant P, Eigen D, Zhang X, Mathien M, Fergus R, Lecun Y. Overfeat: integrated recognition, localization and detection using convolutional networks. arXiv. 2013; arXiv:1312.6229.

[28] Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. Going deeper with convolutions. arXiv. 2014; arXiv:1409.4842.

[29] Taigman Y, Yang M, Ranzato M, Wolf L. Deepface: closing the gap to human-level performance in face verification. 2014 IEEE Conference on Computer Vision and Pattern Recognition; 2014 Jun 23-28; Ohio, USA. USA: IEEE; 2014. p. 1701-8.

[30] Farabet C, Couprie C, Najman L, Lecun Y. Learning hierarchical feature for scene labeling. IEEE Trans Pattern Anal Mach Intell. 2013;35(8):1915-29.

[31] Klein B, Wolf L, Afek Y. Dynamic convolutional layer for short rangeweather prediction. IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2015 Jun 7-12; Boston, USA. USA: IEEE; 2015. p. 4840-8.

[32] Shi X, Chen Z, Wang H, Yeung DY. Convolutional LSTM network: a machine learning approach for precipitation nowcasting. arXiv. 2015; arXiv:1506.04214.

[33] Nabilah FMR, Andi P, Zalinda O, Azuraliza AB, Abdul RH. Comparative study-three artificial intelligence techniques for rain domain in precipitation forecast. Int J Comput Inform Eng. 2013;7(12):930-5.

[34] Bing L, Guishan Y, Rongrong W, Xue D, Yanhui Z. Comparison of random forests and other statistical methods for the prediction of lake water level: a case study of the Poyang lake in China. Hydrology Research. 2016;47(S1):69-83.

[35] Hristos T, Georgia P. Variable selection in time series forecasting using random forests. Algorithm. 2017;10(4)1:1-25.

[36] Phanida P, Asaad YS. The use of stochastic gradient boosting method for multi-model combination of rainfall-runoff models. International Conference on Innovations in Engineering and Technology (ICIET ‘2013); 2013 Dec 25-26; Bangkok, Thailand.

[37] Binghong C, Cong L, Ke Z, Xing S, Xiaoguang W, Minghui Q, et al. Non-linear machine learning approach to short-term precipitation forecast. World Meteorological Organization [Internet]. 2017 [cited 2018 Jul]:1-11. Available from: https://pac.base.shuju. aliyun.com.

[38] Plaut DC, Nowlan SJ, Hinton GE. Experiments on learning by back propagation. USA: Carnegie-Mellon University; 1986.

[39] Anchal G, Ganatra A, Kosta YP, Panchal D. Behaviour analysis of multilayer perceptrons with multiple hidden neurons and hidden layers. International Journal of Computer Theory and Engineering. 2011;3(2):332-7.

[40] Hinton GE, Osindero S, The YW. A fast learning algorithm for deep belief nets. Neural Comput. 2006;18(7):1527-54.

[41] Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, et al. TensorFlow: a system for large-scale machine learning. 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI ’16); 2016 Nov 2-4; Savannah, USA; 2016. p. 265-83.
Published
2018-09-14
How to Cite
Weesakul, U., Kaewprapha, P., Boonyuen, K., & Mark, O. (2018). Deep learning neural network: A machine learning approach for monthly rainfall forecast, case study in eastern region of Thailand. Engineering and Applied Science Research, 45(3), 203-211. Retrieved from https://ph01.tci-thaijo.org/index.php/easr/article/view/127733
Section
ORIGINAL RESEARCH

Most read articles by the same author(s)