Meteorology and Atmospheric Physics

, Volume 128, Issue 5, pp 613–628 | Cite as

Autoencoder-based identification of predictors of Indian monsoon

  • Moumita SahaEmail author
  • Pabitra Mitra
  • Ravi S. Nanjundiah
Original Paper


Prediction of Indian summer monsoon uses a number of climatic variables that are historically known to provide a high skill. However, relationships between predictors and predictand could be complex and also change with time. The present work attempts to use a machine learning technique to identify new predictors for forecasting the Indian monsoon. A neural network-based non-linear dimensionality reduction technique, namely, the sparse autoencoder is used for this purpose. It extracts a number of new predictors that have prediction skills higher than the existing ones. Two non-linear ensemble prediction models of regression tree and bagged decision tree are designed with identified monsoon predictors and are shown to be superior in terms of prediction accuracy. Proposed model shows mean absolute error of 4.5 % in predicting the Indian summer monsoon rainfall. Lastly, geographical distribution of the new monsoon predictors and their characteristics are discussed.


Hide Node Indian Summer Monsoon Indian Monsoon India Meteorological Department Forecast Skill 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. Baldi P (2012) Autoencoders, unsupervised learning, and deep architectures. ICML Unsupervised Transf Learn 27:37–50Google Scholar
  2. Blanford HF (1884) On the connexion of the Himalaya snowfall with dry winds and seasons of drought in India. Proc R Soc Lond 37(232–234):3–22CrossRefGoogle Scholar
  3. Boriah S, Simon G, Naorem M, Steinbach M, Kumar V, Klooster S, Potter C (2004) Predicting land temperature using ocean data. In: Proceedings of the knowledge discovery in databases KDD, CiteseerGoogle Scholar
  4. Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140Google Scholar
  5. Cherchi A, Navarra A (2013) Influence of ENSO and of the Indian ocean dipole on the Indian summer monsoon variability. Clim Dyn 41(1):81–103CrossRefGoogle Scholar
  6. Compo G, Whitaker J, Sardeshmukh P, Matsui N, Allan R, Yin X, Gleason B, Vose R, Rutledge G, Bessemoulin P, Bronnimann S, Brunet M, Crouthamel R, Grant A, Groisman P, Jones P, Kruk M, Kruger A, Marshall G, Maugeri M, Mok H, Nordli O, Ross T, Trigo R, Wang X, Woodruff S, Worley S (2011) The twentieth century reanalysis project. Q J R Meteor Soc 137(654):1–28CrossRefGoogle Scholar
  7. DelSole T, Shukla J (2002) Linear prediction of Indian monsoon rainfall. J Clim 15:3645–3658CrossRefGoogle Scholar
  8. DelSole T, Shukla J (2012) Climate models produce skillful predictions of Indian summer monsoon rainfall. Geophys Res Lett 39(9):L09–703CrossRefGoogle Scholar
  9. Gadgil S, Vinayachandran P, Francis P, Gadgil S (2004) Extremes of the Indian summer monsoon rainfall, ENSO and equatorial Indian ocean oscillation. Geophys Res Lett 31(12):L12213CrossRefGoogle Scholar
  10. Gadgil S, Rajeevan M, Nanjundiah R (2005) Monsoon prediction-Why yet another failure? Curr Sci 88(9):1389–1400Google Scholar
  11. Goswami BN, Ajayamohan R (2001) Intraseasonal oscillations and interannual variability of the Indian summer monsoon. J Clim 14(6):1180–1198CrossRefGoogle Scholar
  12. Gowariker V, Thapliyal V, Kulshrestha SM, Mandal GS, Sen Roy N, Sikka DR (1991) A power regression model for long range forecast of southwest monsoon rainfall over India. Mausam 42(2):125–130Google Scholar
  13. Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504–507CrossRefGoogle Scholar
  14. Hong YT, Hong B, Lin QH, Zhu YX, Shibata Y, Hirota M, Uchida M, Leng XT, Jiang HB, Xu H (2003) Correlation between Indian ocean summer monsoon and North Atlantic climate during the Holocene. Earth Planet Sci Lett 211(3):371–380CrossRefGoogle Scholar
  15. Krishnamurti TN, Bhalme H (1976) Oscillations of a monsoon system. Part I. Observational aspects. J Atmos Sci 33(10):1937–1954CrossRefGoogle Scholar
  16. Kucharski F, Bracco A, Yoo JH, Molteni F (2008) Atlantic forced component of the Indian monsoon interannual variability. Geophys Res Lett 35(4):L04706CrossRefGoogle Scholar
  17. Kumar N, Nasser M, Sarker SC (2011) A new singular value decomposition based robust graphical clustering technique and its application in climatic data. J Geogr Geol 3(1):227–238Google Scholar
  18. Li S, Lu J, Huang G, Hu K (2008) Tropical Indian Ocean basin warming and East Asian summer monsoon: a multiple AGCM study. J Clim 21(22):6080–6088CrossRefGoogle Scholar
  19. Li Y, Yang R (2013) A hybrid algorithm combining auto-encoder network with sparse Bayesian regression optimized by artificial bee colony for short-term wind power forecasting. Przeglkad Elektrotechniczny 89(2a):223–228Google Scholar
  20. Liaw A, Wiener M (2002) Classification and regression by random forest. R News 2(3):18–22Google Scholar
  21. Liu JNK, Hu Y, He Y, Chan PW, Lai L (2015) Deep neural network modeling for big data weather forecasting. In: Information granularity, big data, and computational intelligence, Springer, pp 389–408Google Scholar
  22. Loh WY (2008) Classification and regression tree methods. Encyclo of statistics in quality and reliability, pp 315–323Google Scholar
  23. MATLAB (2012) Statistics and machine learning toolbox. MATLAB version 2012b, The MathWorks Inc., Natick, Massachusetts, USGoogle Scholar
  24. Nanjundiah RS, Francis P, Ved M, Gadgil S (2013) Predicting the extremes of Indian summer monsoon rainfall with coupled ocean-atmosphere models. Curr Sci 104(10):1380–1393Google Scholar
  25. 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(3):422–431Google Scholar
  26. Rajeevan M, Pai DS, Kumar RA, Lal B (2007) New statistical models for long-range forecasting of southwest monsoon rainfall over India. Clim Dyn 28(7–8):813–828CrossRefGoogle Scholar
  27. Sap MNM, Awan AM (2005) Finding spatio-temporal patterns in climate data using clustering. In: Proceedings of the 2005 international conference cyberworlds, IEEE, pp 8–15Google Scholar
  28. Schott FA, Xie SP, McCreary JP (2009) Indian Ocean circulation and climate variability. Rev Geophys 47(1):RG1002CrossRefGoogle Scholar
  29. Smith TM, Reynolds R, Peterson T, Lawrimore J (2008) Improvements to NOAA’s historical merged land-ocean surface temperature analysis (1880-2006). J Clim 21(10):2283–2296CrossRefGoogle Scholar
  30. Song C, Liu F, Huang Y, Wang L, Tan T (2013) Auto-encoder based data clustering. In: Progress in pattern recognition, image analysis, computer vision and applied, Springer, pp 117–124Google Scholar
  31. Steinbach M, Tan PN, Kumar V, Klooster S, Potter C (2003) Discovery of climate indices using clustering. Proceedings of ACM, ACM SIGKDD, pp 446–455Google Scholar
  32. Thapliyal V, Kulshrestha S (1992) Recent models for long range forecasting of south-west monsoon rainfall in India. Mausam 43(3):239–248Google Scholar
  33. Walker G (1924) Correlation in seasonal variations of weather-IV, a further study of world weather. Mem India Meteorol Dept 24:275–332Google Scholar
  34. Wang B, Xiang B, Li J, Webster PJ, Rajeevan MN, Liu J, Ha KJ (2015) Rethinking Indian monsoon rainfall prediction in the context of recent global warming. Nature 6:7154Google Scholar
  35. Xue Y, Smith T, Reynolds R (2003) Interdecadal changes of 30-yr SST normals during 1871–2000. J Climate 16:1601–1612CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Wien 2016

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringIndian Institute of Technology KharagpurKharagpurIndia
  2. 2.Centre for Atmospheric and Oceanic Sciences, Divecha Centre for Climate ChangeIndian Institute of ScienceBangaloreIndia

Personalised recommendations