Abstract
Forecasting the monsoon temporally is a major scientific issue in the field of monsoon meteorology. The ensemble of statistics and mathematics has increased the accuracy of forecasting of Indian summer monsoon rainfall (ISMR) up to some extent. But due to the nonlinear nature of ISMR, its forecasting accuracy is still below the satisfactory level. Mathematical and statistical models require complex computing power. Therefore, many researchers have paid attention to apply artificial neural network in ISMR forecasting. In this study, we have used feed-forward back-propagation neural network algorithm for ISMR forecasting. Based on this algorithm, we have proposed the five neural network architectures designated as BP1, BP2, \(\ldots, \) BP5 using three layers of neurons (one input layer, one hidden layer and one output layer). Detail architecture of the neural networks is provided in this article. Time series data set of ISMR is obtained from Pathasarathy et al. (Theor Appl Climatol 49:217–224 1994) (1871–1994) and IITM (http://www.tropmet.res.in/, 2012) (1995–2010) for the period 1871–2010, for the months of June, July, August and September individually, and for the monsoon season (sum of June, July, August and September). The data set is trained and tested separately for each of the neural network architecture, viz., BP1–BP5. The forecasted results obtained for the training and testing data are then compared with existing model. Results clearly exhibit superiority of our model over the considered existing model. The seasonal rainfall values over India for next 5 years have also been predicted.
Similar content being viewed by others
References
Aksoy H, Dahamsheh A (2008) Artificial neural network models for forecasting monthly precipitation in Jordan. Stoch Environ Res Risk Assess 23:917–931
Annamalai H (1995) Intrinsic problems in the seasonal prediction of the Indian summer monsoon rainfall. Meteorol Atmos Phys 55:61–76
Bacanli UG, Firat M, Dikbas F (2009) Adaptive neuro-fuzzy inference system for drought forecasting. Stoch Environ Res Risk Assess 23:1143–1154
Barnston AG, Li S, Mason SJ, DeWitt DG, Goddard L, Gong X (2010) Verification of the first 11 years of IRIŠs seasonal climate forecasts. J Appl Meteorol Climatol 49:493–520
Basu S, Andharia HI (1992) The chaotic time-series of Indian monsoon rainfall and its prediction. Proc Ind Acad Sci (Earth Planet Sci) 101:27–34
Beale MH, Hagan MT, Demuth HB (2010) Neural network toolbox 7. The MathWorks, Inc., Natick
Bishop CM (1994) Neural networks and their applications. Rev Sci Instrum 65(6):1803–1832
Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, Oxford
Blanford HF (1884) On the connection of the Himalayan snow with dry winds and seasons of droughts in India. Proc R Soc Lond 37:3–22
Bose NK, Liang P (1998) Neural network fundamentals with graphs, algorithms, and applications. Tata McGraw-Hill, New Delhi
Bryson AE, Ho YC (1969) Applied optimal control: optimization, estimation, and control. Blaisdell Publishing Company or Xerox College Publishing, Waltham
Cannon AJ, Mckendry IG (1999) Forecasting all-india summer monsoon rainfall using regional circulation principal components: a comparision between neural network and multiple regression models. Int J Climatol 19:1561–1578
Carpenter WC, Barthelemy JF (1994) Common misconceptions about neural networks as approximators. ASCE J Comput Civil Eng 8:345–358
Chakraverty S, Gupta P (2007) Comparison of neural network configurations in the long-range forecast of southwest monsoon rainfall over India. Neural Comput Appl 17:187–192
Chakraverty S, Gupta P (2008) Comparison of neural network configurations in the long-range forecast of southwest monsoon rainfall over India. Neural Comput Appl 17:187–192
Chattopadhyay S, Chattopadhyay G (2001) Identification of the best hidden layer size for threelayered neural net in predicting monsoon rainfall in India. J Hydroinform 10(2):181–188
Chong Y, Sundaraj K (2009) A study of back-propagation and radial basis neural network on EMG signal classification. In: 6th International symposium on mechatronics and its applications. ISMA, Sharjah, p 1–6
Chowdhury A, Abhyankar VP (1984) On some climatological aspects of droughts in India. Mausam 35(3):375–378
Chowdhury A, Dandekar MM, Raut PS (1989) Variability of drought incidence over India: astatistical approach. Mausam 40(2):207–214
Demuth H, Beale M, Hagan M (2008a) Neural network toolbox 6 user’s guide. In: Backpropagation. The Mathworks, Natick, p 156–227
Demuth H, Beale M, Hagan M (2008b) Neural network toolbox 6 user’s guide. In: Radial basis networks. The Mathworks, Natick, p 293–307
Donaldson RG, Kamstra M (1996) Forecast combining with neural networks. J Forecast 15(1):49–61
Dracup JA, Lee KS, Paulson EG (1980) On the statistical characteristics of drought events. Water Resour Res 16:289–296
Firat M, Güngör M (2010) Monthly total sediment forecasting using adaptive neuro fuzzy inference system. Stoch Environ Res Risk Assess 24:259–270
Gadgil S, Srinivasan J, Nanjundiah RS, Kumar KK, Munot AA, Kumar KR (2002) On forecasting the Indian summer monsoon: the intriguing season of 2002. Curr Sci 83(4):394–403
Gadgil S, Rajeevan M, Nanjundiah R (2005) Monsoon prediction: why yet another failure? Curr Sci 88(9):1389–1400
Gaume E, Gosset R (2003) Over-parameterisation, a major obstacle to the use of artificial neural networks in hydrology? Hydrol Earth Syst Sci 7(5):693–706
Gevrey M, Dimopoulos I, Lek S (2003) Review and comparison of methods to study the contribution of variables in artificial neural network models. Ecol Model 160(3):249–264
Gore PG, Ray KS (2002a) Droughts and aridity over districts of Gujarat. J Agrometeorol 4(1):75–85
Gore PG, Ray KS (2002b) Variability of drought incidence over districts of Maharashtra. Mausam 53(4):533–538
Goswami P, Kumar P (1997) Experimental annual forecast of all-India mean summer monsoon rainfall for 1997 using a neural network model. Curr Sci 72:781–782
Goswami P, Srividya (1996) A novel neural network design for long range prediction of rainfall pattern. Curr Sci 70:447–457
Guhathakurta P (2006) Long-range monsoon rainfall prediction of 2005 for the districts and sub-division kerala with artificial neural network. Curr Sci 90:773–779
Guhathakurta P, Rajeevan M, Thapliyal V (1999) Long range forecasting indian summer monsoon rainfall by a hybrid principal component neural network model. Meteorol Atmos Phys 71:255–266
Han J, Kamber M (2001) Data mining: concepts and techniques, 1st edn. Morgan Kaufmann Publishers, San Francisco
Hastenrath S (1988) Prediction of Indian monsoon rainfall: further exploration. J Clim 1:298–304
Hastenrath S, Greischar L (1993) Changing predictability of Indian monsoon rainfall anomalies? Earth Planet Sci 102:35–47
Hayes MJ, Svoboda MD, Wilhite DA, Vanyarkho OV (1999) Monitoring the 1996 drought using the standardized precipitation index. Bull Am Meteorol Soc 80(3):429–438
Haykin S (1999) Neural networks, a comprehensive foundation. Macmillan College Publishing Co., New York
Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366
IFAS (1998) Extreme heat and drought: the disaster handbook. University of Florida, Orlando
IITM (2012) Homogeneous Indian monthly rainfall data sets. http://www.tropmet.res.in/
IMD (2011) Long range forecast for 2011 south-west monsoon season rainfall. Technical report. India Meteorological Department, National Climate Centre, Pune
IMD (2012) 2012 Southwest monsoon end of-season report. Technical report. India Meteorological Department, National Climate Centre, Pune
Indro DC, Jiang CX, Patuwo BE, Zhang GP (1999) Predicting mutual fund performance using artificial neural networks. Omega 27(3):373–380
Iyengar RN, Raghukanth STG (2003) Empirical modelling and forecasting of Indian monsoon rainfall. Curr Sci 85(8):1189–1201
Jain A, Kumar AM (2007) Hybrid neural network models for hydrologic time series forecasting. Appl Soft Comput 7:585–592
Jeong D, Kim Y (2005) Rainfall-runoff models using artificial neural networks for ensemble streamflow prediction. Hydrol Process 19(19):3819–3835
Johnson RA, Wichern DW (1992) Applied multivariate statistical analysis, 5th edn. Prentice-Hall, Englewood Cliffs
Kang IS, Lee JY, Park CK (2004) Potential predictability of summer mean precipitation in a dynamical seasonal prediction system with systematic error correction. J Clim 17:834–844
Kasiviswanathan K, Sudheer K (2012) Quantification of the predictive uncertainty of artificial neural network based river flow forecast models. Stoch Environ Res Risk Assess :1–10. doi:10.1007/s00477-012-0600-2
Khan MR, Ondrusek C (2000) Short-term electric demand prognosis using artificial neural networks. J Electr Eng 51:296–300
Kishtawal CM, Basu S, Patadia F, Thapliyal PK (2003) Forecasting summer rainfall over india using genetic algorithm. Geophys Res Lett 30(23):2203
Krishna KK, Soman MK, Kumar KR (1995) Seasonal forecasting of Indian summer monsoon rainfall: a review. Weather 50:449–467
Krishna YSR, Sastri ASRSA, Rao GGSN, Rao BVR (1984) On prediction of droughts in the Indian arid region. Mausam 35(3):349–354
Krishnamurti TN, Bedi HS, Subramaniam M (1990) The summer monsoon of 1988. Meteorol Atmos Phys 42:19–37
Kuligowski RJ, Barros AP (1998) Experiments in short-term precipitation forecasting using artificial neural networks. Mon Weather Rev 126:470–482
Kumar A, Mitra AK, Bohra AK, Iyengar GR, Durai VR (2012) Multi-model ensemble (MME) prediction of rainfall using neural networks during monsoon season in India. Meteorol Appl 19(2):161–169. doi:10.1002/met.254
Kumar ARS, Sudheer KP, Jain SK, Agarwal PK (2005) Rainfall-runoff modelling using artificial neural networks: comparison of network types. Hydrol Process 19(6):1277–1291
Kumar K, Bhattacharya S (2006) Artificial neural network vs. linear discriminant analysis in credit ratings forecast: a comparative study of prediction performances. Rev Account Finance 5(3):216–227
Kumar KK, Rajagopalan B, Cane MA (1999) On the weakening relationship between the indian monsoon and enso. Sci Agric 284(5423):2156–2159
Kumar S (2011) Neural networks. Tata McGraw-Hill, New Delhi
Lattin JM, Carroll J, Green P (2003) Analyzing multivariate data: Duxbury applied series. Thomson Brooks/Cole, Belmont
Law R (2000) Back-propagation learning in improving the accuracy of neural network-based tourism demand forecasting. Tour Manag 21(4):331–340
Lippmann PR (1989) Pattern classification using neural networks. IEEE Commun Mag 11:47–54
Liu Y, Yao X, Higuchi T (2000) Evolutionary ensembles with negative correlation learning. IEEE Trans Evol Comput 4(4):380–387
Liu Y, Starzyk JA, Zhu Z (2008) Optimized approximation algorithm in neural networks without overfitting. IEEE Trans Neural Netw 19(6):983–995
Maqsood I, Khan MR, Abraham A (2004) An ensemble of neural networks for weather forecasting. Neural Comput Appl 13:112–122
Masters T (1993) Practical neural network recipes in C++. Academic Press, New York
MATALB (2011) The mathworks. http://www.mathworks.com/
Mishra AK, Singh VP (2011) Drought modeling : areview. J Hydrol 403(1–2):157–175
Mishra AK, Singh VP, Desai V (2008) Drought characterization: a probabilistic approach. Stoch Environ Res Risk Assess 23(1):41–55
Mooley D, Munot AA (1993) Variation in the relationship of the Indian summer monsoon with global factors. Earth Planet Sci 102:89–104
Mooley DA, Parthasarathy B (1984) Fluctuations in All-India summer monsoon rainfall during 1871–1978. Clim Change 6:287–301
Morid S, Smakhtin V, Bagherzadeh K (2007) Drought forecasting using artificial neural networks and time series of drought indices. Int J Climatol 27:2103–2111
Muller B, Reinhardt J (1991) Neural networks: an introduction, vol 2. Springer, Berlin
Navone HD, Ceccatto HA (1994) Predicting Indian monsoon rainfall:a neural network approach. Clim Dyn 10:305–312
Nicholson SE, Davenport ML, Malo AR (1990) A comparison of the vegetation response to rainfall in the Sahel and East Africa, using normalized difference vegetation index from NOAA AVHRR. Clim Change 17:209–241
Pandya AS, Macy RB (1996) Pattern recognition with neural networks in C++. CRC Press, Inc., Boca Raton
Paruelo JM, Tomasel F (1997) Prediction of functional characteristics of ecosystems: a comparison of artificial neural networks and regression models. Ecol Model 98(2–3):173–186
Pathasarathy B, Munot AA, Kothawale DR (1994) All India monthly and seasonal rainfall series: 1871-1993. Theor Appl Climatol 49:217–224
Parthasarathy B, Rupakumar DRKK (1992) Indian summer monsoon ramfall indices: 1871–1990. Meteorol Mag 12:174–186
Perrone MP, Cooper LN (1993) When networks disagree: ensemble methods for hybrid neural networks. Chapman and Hall, London, p 126–142
Pickup G (1998) Desertification and climate change: the Australian perspective. Climate Res 11:51–63
Piotrowski AP, Napiorkowski JJ (2012) A comparison of methods to avoid overfitting in neural networks training in the case of catchment runoff modelling. J Hydrol. doi:10.1016/j.jhydrol.2012.10.019
Prasad K, Dash SK, Mohanty UC (2010) A logistic regression approach for monthly rainfall forecasts in meteorological subdivisions of India based on DEMETER retrospective forecasts. Int J Climatol 30(10):1577–1588
Preethi B, Revadekar JV, Kripalani RH (2011) Anomalous behaviour of the indian summer monsoon 2009. J Earth Syst Sci 120(5):783–794
Rajeevan M, Pai DS, Dikshit SK, Kelkar RR (2004) IMD’s new operational models for long-range forecast of southwest monsoon rainfall over India and their verification for 2003. Curr Sci 86:422–431
Rajurkarand M, Kothyari U, Chaube U (2004) Modeling of the daily rainfall-runoff relationship with artificial neural network. J Hydrol 285(1–4):96–113
Rumelhart ED, Hinton EG, Williams JR (1986) Learning representations by back-propagating errors. Nat Biotechnol 323:533–536
Sahai AK, Soman MK, Satyan V (2000) All India summer monsoon rainfall prediction using an artificial neural network. Clim Dyn 16:291–302
Satyan V (1988) Is there an attractor for the Indian summer monsoon? Proc Ind Acad Sci (Earth Planet Sci) 97:49–52
Sharkey AJ (ed) (1999) Combining artificial neural nets: ensemble and modular multi-net systems. Springer, Berlin
Shewale MP, Ray KCS (2001) Probability of occurrence of drought in various sub divisions of India. Mausam 52(3):541–546
Shimshoni Y, Intrator N (1998) Classification of seismic signals by integrating ensembles of neural networks. IEEE Trans Signal Process 46(5):1194–1201
Shukla J, Mooley DA (1987) Empirical prediction of the summer monsoon rainfall over India. Mon Weather Rev 115:695–703
Singh A, Kulkarni MA, Mohanty UC, Kar SC, Robertson AW, Mishra G (2012a) Prediction of Indian summer monsoon rainfall (ISMR) using canonical correlation analysis of global circulation model products. Meteorol Appl 19(2):179–188. doi:10.1002/met.1333
Sinha P, Mohanty UC, Kar SC, Dash SK, Robertson AW, Tippett MK (2012b) Seasonal prediction of the Indian summer monsoon rainfall using canonical correlation analysis of the NCMRWF global model products. Int J Climatol. doi:10.1002/joc.3536
Sivanandam SN, Deepa SN (2007) Principles of soft computing. Wiley India (P) Ltd., New Delhi
Sivanandam SN, Sumathi S, Deepa SN (2012) Introduction to Neural Networks using Matlab 6.0. Tata McGraw-Hill, New Delhi
Swaminathan MS (1998) Padma Bhusan Prof. P. Koteswaram first memorial lecture, 23rd March 1998. In: Climate and sustainable food security, vol 28. Vayu Mandal, p 3–10
Tan PN, Steinbach M, Kumar V (2009) Introduction to data mining, 4th edn. Dorling Kindersley Publishing, Inc., Noida
Taylor JW, Buizza R (2002) Neural network load forecasting with weather ensemble predictions. IEEE Trans Power Syst 17:626–632
Travis WR, Karl T, Changnon SA (1991) Drought and natural resources management in the United States: impacts and implications of the 1987–89 drought. Westview Press, Boulder
Tyagi A, Pai DS (2012) Monsoon 2011. Techinal report. India Meteorological Department, National Climate Centre, Pune
Venkatesan C, Raskar SD, Tambe SS, Kulkarni BD, Keshavamurty RN (1997) Prediction of all India summer monsoon rainfall using error-back-propagation neural networks. Meteorol Atmos Phys 62:225–240
Walker GT (1908) Correlation in seasonal variation of climate. Mem Ind Meteorol Dep 20:117–124
Walker GT (1910) On the meteorological evidence for supposed changes of climate in India. Mem Ind Meteorol Dep 21:1–21
Walker GT (1933) Seasonal weather and its prediction. Br Assoc Adv Sci 103:25–44
Wang B, Ding Q, Fu X, Kang IS, Jin K, Shukla J, Doblas-Reyes F (2005) Fundamental challenge in simulation and prediction of summer monsoon rainfall. Geophys Res Lett 32: L15711. doi:10.1029/2005GL022734
Weigend A (1994) An overfitting and the effective number of hidden units. In: Mozer MC, Smolensky P, Weigend AS (eds) Proceedings of the 1993 connectionist models summer school. Lawrence Erlbaum Associates, Hillsdale, p 335–342
Wilhite DA (1996) A methodology for drought preparedness. Nat Hazards 13:229–252
Wilks DS (1995) Statistical methods in atmospheric sciences. Academic Press, New York
Wu JD, Li N, juan Yang H, hua Li C (2008) Risk evaluation of heavy snow disasters using BP artificial neural network: the case of Xilingol in Inner Mongolia. Stoch Environ Res Risk Assess 22:719–725
Acknowledgements
We are thankful to H. A. Ahmed, Research Fellow of the Department of Computer Science and Engineering, Tezpur University, Tezpur (India), for encouragement, valuable suggestions and discussions. Constructive comments by three anonymous reviewers helped to improve the revised manuscript.
Author information
Authors and Affiliations
Corresponding author
Appendices
Appendix 1
The training process of the neural networks, which comprises of 8 steps, is presented next.
- Step 1:
-
Each input node \(I_i ( i=1, 2, \ldots, n)\) receive the input data X i and transmit to the hidden layer nodes \(Y_i (i=1, 2, \ldots, n). \)
- Step 2:
-
The net input to each hidden node \(Y_{input_j} (j=1, 2, \ldots, n)\) is calculated as:
$$ Y_{input_j}= b_{oj}+\sum_{i}X_ib_{ij}, $$where b oj is the bias on jth hidden node, and b ij is the bias on connecting the ith input layer node to the jth node of the hidden layer.
- Step 3:
-
Compute the output of the hidden node by using the AF as:
$$ Y_j=AF(Y_{input_j}), $$and, this signal is sent to the output layer node from the hidden layer nodes.
- Step 4:
-
For output node O, the net input is calculated as:
$$ O_{input_k}=d_{oj}+\sum_{j}Y_jd_{jk}, $$where d oj is the bias on jth output node, and d jk is the bias on connecting the jth hidden layer node to the kth node of the output layer.
- Step 5:
-
Compute the output information by applying the AF as:
$$ O_k=AF(O_{input_k}) $$ - Step 6:
-
Adjust the weight d jk for error correction that is occurred due to output node O k . This information is back-propagated to the hidden layer nodes \(Y_{input_j} (j=1, 2, \ldots, 6)\) that provide again information on output layer node O k .
- Step 7:
-
Due to back-propagation of error to the hidden layer nodes \(Y_{input_j} (j=1, 2, \ldots, 6)\) which may be large or small in amount, adjust the weight b ij for error correction repeatedly until the error is minimized.
- Step 8:
-
When the calculated output is equal to the desired output, stop the whole steps of training process.
Appendix 2
The testing process of the neural networks, which comprises of 3 steps, is presented next.
- Step 1:
-
Use the weights for testing process, which are obtained just after the neural network is completely trained.
- Step 2:
-
The net input to each hidden node \(Y_{input_j} (j=1, 2, \ldots, n)\) is:
$$ Y_{input_j}= b_{oj}+\sum_{i}X_ib_{ij}, $$where b oj is the bias on jth hidden node, and b ij is the bias on connecting the ith input layer node to the jth node of the hidden layer, and the output of the hidden node is:
$$ Y_j=AF(Y_{input_j}) $$ - Step 3:
-
For output node O, the net input is:
$$ O_{input_k}=d_{oj}+\sum_{j}Y_jd_{jk}, $$where d oj is the bias on jth output node, and d jk is the bias on connecting the jth hidden layer node to the kth node of the output layer, and the output information is:
$$ O_k=AF(O_{input_k}) $$
Rights and permissions
About this article
Cite this article
Singh, P., Borah, B. Indian summer monsoon rainfall prediction using artificial neural network. Stoch Environ Res Risk Assess 27, 1585–1599 (2013). https://doi.org/10.1007/s00477-013-0695-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00477-013-0695-0