Characterising the Impact of Drought on Jowar (Sorghum spp) Crop Yield Using Bayesian Networks

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 736)

Abstract

Drought is a complex, natural hazard that affects the agricultural sector on a large scale. Although the prediction of drought can be a difficult task, understanding the patterns of drought at temporal and spatial level can help farmers to make better decisions concerning the growth of their crops and the impact of different levels of drought. This paper studied the use of Bayesian networks to characterise the impact of drought on jowar (Sorghum spp) crop in Maharashtra state on India. The study area was 25 districts on Maharashtra which were selected on the basis of data availability. Parameters such as rainfall, minimum, maximum and average temperature, potential evapotranspiration, reference crop evapotranspiration and crop yield data was obtained for the period from year 1983 to 2015. Bayes Net and Naïve Bayes classifiers were applied on the datasets using Weka analysis tool. The results obtained showed that the accuracy of Bayes net was more than the accuracy obtained by Naive Bayes method. This probabilistic model can be further used to manage and mitigate the drought conditions and hence will be useful to farmers in order to plan their cropping activities.

Keywords

Bayesian networks Classification Drought Jowar crop Prediction 

Notes

Acknowledgement

The Centre for Environmental Management and School of Science provided funding for the attendance at WICT 2017 conference.

References

  1. 1.
    Gupta, A., Tyagi, P., Sehgal, V.: Drought disaster challenges and mitigation in India: strategic appraisal. Curr. Sci. 100, 1795–1806 (2011)Google Scholar
  2. 2.
    Shewale, M., Kumar, S.: Climatological features and drought incidences in India. Meteorological Monograph, Climatology, India Meteorological Department, 21 (2005)Google Scholar
  3. 3.
    Nandakumar., T.: Manual for drought management, Department of Agriculture and Cooperation, Ministry of Agriculture, Government of India, New Delhi (2009)Google Scholar
  4. 4.
    Roy., P., Dwiwedi., R., Vijayan,. D.: Remote sensing applications. National Remote Sensing Center, ISRO, Hyderabad (2011)Google Scholar
  5. 5.
    Singh., N., Saini., R.: Contingency and compensatory agriculture plans for drought and floods in India. National Rainfed Area Authority. New Delhi (2013)Google Scholar
  6. 6.
    Keyantash, J., Dracup, J.: The quantification of drought: an evaluation of drought indices. Am. Meteorol. Soc. 83(8), 1167–1180 (2002)CrossRefGoogle Scholar
  7. 7.
    Sadoddin, A., Shahabi, M., Sheikh, V.: A Bayesian decision model for drought management in rainfed wheat farms of North East Iran. Int. J. Plant Prod. 10(4), 527–542 (2016)Google Scholar
  8. 8.
    Moradkhani, H.: Statistical-dynamical drought forecast within Bayesian networks and data assimilation: how to quantify drought recovery. Geophysical Research Abstracts 17 (2015)Google Scholar
  9. 9.
    Wankhede, S., Gandhi, N., Armstrong, L.: Role of ICTs in improving drought scenario management in India. In: Proceedings of the 9th Asian Federation for Information Technologies in Agriculture, (AFITA), Perth, pp. 521–530 (2014)Google Scholar
  10. 10.
    Tadesse, T.: Discovering associations between climatic and oceanic parameters to monitor drought in Nebraska using data-mining techniques. Am. Meteorol. Soc. 18(10), 1541–1550 (2005)Google Scholar
  11. 11.
    Rajput, A.: Impact of data mining in drought monitoring. Int. J. Comput. Sci. Issues, 8(2), 309–313 (2011)Google Scholar
  12. 12.
    Dhanya, C., Kumar, D.: Data mining for evolution of association rules for droughts and floods in India using climate inputs. J. Geophys. Res. 114, 193–209 (2009)CrossRefGoogle Scholar
  13. 13.
    Dastorani, M., Afkhami, H.: Application of artificial neural networks on drought prediction in Yazd (Central Iran). Desert 16, 39–48 (2011)Google Scholar
  14. 14.
    Belayneh, A., Adamowski, J.: Standard precipitation index drought forecasting using neural networks, wavelet neural networks, and support vector regression. Appl. Comput. Intell. Soft Comput. 2012, 1–13 (2012)CrossRefGoogle Scholar
  15. 15.
    Wambua, R.: Drought forecasting using indices and artificial neural networks for Upper Tana river basin, Kenya-a review concept. J. Civil Environ. Eng. 4(4), 1 (2014)CrossRefGoogle Scholar
  16. 16.
    Boudad, B.: Using a model hybrid based on ANN-MLP and the SPI index for drought prediction case of Inaouen basin (Northern Morocco). Int. J. Sci. Eng. Technol. 2(6), 1301–1309 (2014)Google Scholar
  17. 17.
    Lorenz, D., Otkin, J., Svoboda, M., Hain, C.: Predicting the US drought monitor using precipitation, soil moisture and evapotranspiration anomalies. Part II: intraseasonal drought intensification forecasts. Am. Meteorol. Soc. 18(7), 1963–1981 (2017)Google Scholar
  18. 18.
    Sriram, K., Suresh, K.: Machine learning perspective for predicting agricultural droughts using Naive Bayes algorithm. IIECS 24, 178–184 (2016)Google Scholar
  19. 19.
    Heaton, J.: Bayesian networks for predictive modeling. Forecast. Futurism 6–10 (2013)Google Scholar
  20. 20.
    Choudhary, K., Tahlani, P., Bisen, P., Saxena, R., Ray, S.: Assessment of drought indicators. Technical report, New Delhi (2017)Google Scholar
  21. 21.
    NIDM: Maharashtra. In: National Disaster Risk Reduction Portal, Maharashtra, pp. 1–26 (2012)Google Scholar
  22. 22.
    Shapefile India. http://www.gadm.org/country. Accessed 2 Nov 2016
  23. 23.
    Shapefile Indian Village Boundaries. https://github.com/datameet. Accessed 2 Nov 2016
  24. 24.
    Gayathri, A.: A survey on weather forecasting by data mining. IJARCCE, 5(2), 298–300 (2016)Google Scholar
  25. 25.
    Netti, K., Radhika, Y.: Minimizing loss of accuracy for seismic hazard prediction using Naive Bayes classifier. IRJET, 3(4), 75–77 (2016)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of MumbaiMumbaiIndia
  2. 2.School of ScienceEdith Cowan UniversityJoondalupAustralia

Personalised recommendations