Advertisement

Deep Learning Based LSTM and SeqToSeq Models to Detect Monsoon Spells of India

  • Saicharan Viswanath
  • Moumita SahaEmail author
  • Pabitra Mitra
  • Ravi S. Nanjundiah
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11537)

Abstract

Monsoon spells are important climatic phenomenon modulating the quality and quantity of monsoon over a year. India being an agricultural country, identification of monsoon spells is extremely important to plan agricultural policies following the phases of monsoon to attain maximum productivity. Monsoon spells’ detection involve analyzing and predicting monsoon at daily levels which make it more challenging as daily-variability is higher as compared to monsoon over a month or an year. In this article, deep-learning based long short-term memory and sequence-to-sequence models are utilized to classify monsoon days, which are finally assembled to detect the spells. Dry and wet days are classified with precision of 0.95 and 0.87, respectively. Break spells are observed to be forecast with higher accuracy than the active spells. Additionally, sequence-to-sequence model is noted to perform superior to that of long-short term memory model. The proposed models also outperform traditional classification models for monsoon spell detection.

Keywords

Active spell Break spell Long short term memory Sequence-to-sequence model Attention mechanism Classification Spells’ detection 

References

  1. 1.
    Abhilash, S., Sahai, A., Pattnaik, S., Goswami, B., Kumar, A.: Extended range prediction of active-break spells of Indian summer monsoon rainfall using an ensemble prediction system in ncep climate forecast system. Int. J. Climatol. 34(1), 98–113 (2014)CrossRefGoogle Scholar
  2. 2.
    Bahdanau, D., Cho, k., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: International Conference on Learning Representations. (2015). arXiv:1409.0473
  3. 3.
    Chattopadhyay, S., Chattopadhyay, G.: Comparative study among different neural net learning algorithms applied to rainfall time series. Meteorol. Appl. 15(2), 273–280 (2008)CrossRefGoogle Scholar
  4. 4.
    Fan, K., Liu, Y., Chen, H.: Improving the prediction of the East Asian summer monsoon: new approaches. Weather Forecast. 27(4), 1017–1030 (2012)CrossRefGoogle Scholar
  5. 5.
    Gadgil, S., Joseph, P.V.: On breaks of the Indian monsoon. J. Earth Syst. Sci. 112(4), 529–558 (2003)CrossRefGoogle Scholar
  6. 6.
    Gadgil, S., Rajeevan, M., Nanjundiah, R.S.: Monsoon prediction - why yet another failure? Curr. Sci. 88(9), 1389–1400 (2005)Google Scholar
  7. 7.
    Hong, W.C.: Rainfall forecasting by technological machine learning models. Appl. Math. Comput. 200(1), 41–57 (2008)MathSciNetzbMATHGoogle Scholar
  8. 8.
    Kalnay, E., et al.: The NCEP/NCAR 40-year reanalysis project. Bull. Am. Meteorol. Soc. 77(3), 437–471 (1996)CrossRefGoogle Scholar
  9. 9.
    Kiran, V.R., Rajeevan, M., Rao, S.V.B., Rao, N.P.: Analysis of variations of cloud and aerosol properties associated with active and break spells of Indian summer monsoon using MODIS data. Geophys. Res. Lett. 36(9), L09706 (2009).  https://doi.org/10.1029/2008GL037135CrossRefGoogle Scholar
  10. 10.
    Kripalani, R.H., Kulkarni, A.: Rainfall variability over South-East Asia-connections with Indian monsoon and ENSO extremes: new perspectives. Int. J. Climatol. 17(11), 1155–1168 (1997)CrossRefGoogle Scholar
  11. 11.
    Kucharski, F., Bracco, A., Yoo, J.H., Molteni, F.: Atlantic forced component of the Indian monsoon interannual variability. Geophys. Res. Lett. 35(4), L04706 (2008).  https://doi.org/10.1029/2007GL033037CrossRefGoogle Scholar
  12. 12.
    Kumar, K.K., Rajagopalan, B., Hoerling, M., Bates, G., Cane, M.: Unraveling the mystery of Indian monsoon failure during El Niño. Science 314(5796), 115–119 (2006)CrossRefGoogle Scholar
  13. 13.
    Kumar, M.R.R., Dessai, U.R.P.: A new criterion for identifying breaks in monsoon conditions over the Indian subcontinent. Geophys. Res. Lett. 31(18), L18201 (2004)CrossRefGoogle Scholar
  14. 14.
    Mandke, S.K., Sahai, A.K., Shinde, M.A., Joseph, S., Chattopadhyay, R.: Simulated changes in active/break spells during the Indian summer monsoon due to enhanced CO2 concentrations: assessment from selected coupled atmosphere-ocean global climate models. Int. J. Climatol. 27(7), 837–859 (2007)CrossRefGoogle Scholar
  15. 15.
    Mekanik, F., Imteaz, M.A., Gato-Trinidad, S., Elmahdi, A.: Multiple regression and artificial neural network for long-term rainfall forecasting using large scale climate modes. J. Hydrol. 503, 11–21 (2013)CrossRefGoogle Scholar
  16. 16.
    Prasad, V.S., Hayashi, T.: Active, weak and break spells in the Indian summer monsoon. Meteorol. Atmos. Phys. 95(1–2), 53–61 (2007)CrossRefGoogle Scholar
  17. 17.
    Rajeevan, M., Bhate, J., Kale, J.D., Lal, B.: High resolution daily gridded rainfall data for the Indian region: analysis of break and active monsoon spells. Curr. Sci. 91(3), 296–306 (2006)Google Scholar
  18. 18.
    Rajeevan, M., Gadgil, S., Bhate, J.: Active and break spells of the Indian summer monsoon. J. Earth Syst. Sci. 119(3), 229–247 (2010)CrossRefGoogle Scholar
  19. 19.
    Ramamurthy, K.: Monsoon of India: some aspects of the break in the Indian southwest monsoon during July and August. Forecast. Manual 18.3, pp. 1–57 (1969). IMD PoonaGoogle Scholar
  20. 20.
    Rao, T.N., Saikranthi, K., Radhakrishna, B., Rao, S.V.B.: Differences in the climatological characteristics of precipitation between active and break spells of the Indian summer monsoon. J. Clim. 29(21), 7797–7814 (2016)CrossRefGoogle Scholar
  21. 21.
    Saha, M., Chakraborty, A., Mitra, P.: Predictor-year subspace clustering based ensemble prediction of Indian summer monsoon. Adv. Meteorol. 2016(9031625), 1–12 (2016)CrossRefGoogle Scholar
  22. 22.
    Saha, M., Mitra, P.: Identification of Indian monsoon predictors using climate network and density-based spatial clustering. Meteorol. Atmos. Phys. 128(5), 1–14 (2018)Google Scholar
  23. 23.
    Saha, M., Mitra, P., Chakraborty, A.: Fuzzy clustering-based ensemble approach to predicting Indian monsoon. Adv. Meteorol. 2015(32835), 1–12 (2015)CrossRefGoogle Scholar
  24. 24.
    Saha, M., Mitra, P., Nanjundiah, R.S.: Autoencoder-basedidentification of predictors of Indian monsoon. Meteorol. Atmos. Phys. 128, 613–628 (2016).  https://doi.org/10.1007/s00703-018-0637-yCrossRefGoogle Scholar
  25. 25.
    Saha, M., Mitra, P., Nanjundiah, R.S.: Prediction of active and break spells of Indian summer monsoon using linear discriminant analysis. In: International Conference on Advances in Pattern Recognition, pp. 1–6 (2017)Google Scholar
  26. 26.
    Saha, M., Mitra, P., Nanjundiah, R.: Predictor discovery for early-late Indian summer monsoon using stacked autoencoder. Proc. Comput. Sci. 80, 565–576 (2016)CrossRefGoogle Scholar
  27. 27.
    Saha, M., Mitra, P., Nanjundiah, R.: Deep learning for predicting the monsoon over the homogeneous regions of India. J. Earth Syst. Sci. 126(4), 1–18 (2017)CrossRefGoogle Scholar
  28. 28.
    Sudeepkumar, B.L., Babu, C.A., Varikoden, H.: Future projections of active-break spells of Indian summer monsoon in a climate change perspective. Glob. Planet. Change 161, 222–230 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Saicharan Viswanath
    • 1
  • Moumita Saha
    • 2
    Email author
  • Pabitra Mitra
    • 3
  • Ravi S. Nanjundiah
    • 2
    • 4
    • 5
  1. 1.National Institute of Technology KarnatakaSurathkalIndia
  2. 2.Centre for Atmospheric and Oceanic SciencesIndian Institute of ScienceBangaloreIndia
  3. 3.Indian Institute of Technology KharagpurKharagpurIndia
  4. 4.Divecha Centre for Climate ChangeIndian Institute of ScienceBangaloreIndia
  5. 5.Indian Institute of Tropical MeteorologyPuneIndia

Personalised recommendations