Applicability of machine learning models for drought prediction using SPI in Kalahandi, Odisha

Authors

  • AMIT PRASAD The Graduate School, IARI, ICAR-Central Institute of Agricultural Engineering (Outreach campus of IARI), Bhopal (CIAE), Madhya Pradesh-462038, India
  • R.K. SINGH ICAR-Central Institute of Agricultural Engineering (Outreach campus of IARI), Bhopal (CIAE), Madhya Pradesh-462038, India
  • K V RAMANA RAO ICAR-Central Institute of Agricultural Engineering (Outreach campus of IARI), Bhopal (CIAE), Madhya Pradesh-462038, India
  • C. K. SAXENA ICAR-Central Institute of Agricultural Engineering (Outreach campus of IARI), Bhopal (CIAE), Madhya Pradesh-462038, India

DOI:

https://doi.org/10.54386/jam.v27i2.2906

Keywords:

ARIMA, SPI, ELM, SVM, ANN

Abstract

This study assesses the performance of auto-regressive integrated moving average (ARIMA), artificial neural network (ANN), support vector machine (SVM) and extreme learning machine (ELM), in predicting meteorological drought with Standardized Precipitation Index (SPI-6 and SPI-12) for Kalahandi district, Odisha. Mann-Kendall tests showed no significant trend in SPI value for both shorter and longer scales. Model performance was evaluated using correlation coefficient (CC), root mean square error (RMSE), Nash-Sutcliffe efficiency (NSE), and mean absolute error (MAE) during the training as well as testing phases. For SPI-6, ARIMA performed well during training (NSE = 0.66, RMSE = 0.60) but showed a decline in testing (NSE = 0.25). Machine learning models, including ELM, SVM and ANN exhibited better consistency, with NSE values ranging from 0.45 to 0.47. For SPI-12, ANN delivered the highest accuracy with NSE values of 0.91 and 0.89 and RMSE values of 0.31 and 0.29 in training and testing, respectively. Graphical analysis further demonstrated that ANN and SVM outperformed ARIMA by effectively capturing nonlinear trends and extreme fluctuations. Overall, machine learning models, particularly ANN and SVM, proved to be superior for predicting both long-term (SPI-12) and short-term (SPI-6) precipitation indices, highlighting their effectiveness for accurate drought forecasting.

References

Deo, R.C., and Şahin, M. (2015). Application of the extreme learning machine algorithm for the prediction of monthly effective drought index in eastern Australia. Atmos. Res., 153: 512-525.

Hao, Z., Singh, V.P., and Xia, Y. (2018). Seasonal drought prediction: Advances, challenges, and future prospects. Rev. Geophys., 56: 108-141.

Kanthavel, P., Saxena, C.K., and Singh, R.K. (2023). Risk analysis of meteorological, agricultural, and hydrological drought events and study of drought propagation features: A case study in the upper Tapti River sub-basin, Central India. J. Water Clim. Change., 14(6): 1912-1923.

Khan, U., Khalil, A., and Jan, S. (2024). Drought assessment in Kabul River basin using machine learnings. J. Agrometeorol.,, 26(3), 349-355. https://doi.org/10.54386/jam.v26i3.2674

Lalika, C., Mujahid, A. U. H., James, M., and Lalika, M. C. (2024). Machine learning algorithms for the prediction of drought conditions in the Wami River sub-catchment, Tanzania. J. Hydrol.: Regional Studies, 53: 101794.

Lee, Seung Kyu and Truong An, Dang. (2018). Evaluating drought events under influence of El-Nino phenomenon: A case study of Mekong delta area, Vietnam. J. Agrometeorol., 20(4): 275–279. https://doi.org/10.54386/jam.v20i4.565

McKee, T.B., Doesken, N.J., and Kleist, J. (1993). The relationship of drought frequency and duration to time scales. Eighth Conference on Applied Climatology, California.

OSDMA (2016). Annual report on natural calamities. Special Relief Commissioner, Revenue Department, Odisha State Disaster Mitigation Authority, Government of Odisha.

Panda, R. K., Mohanty, U. C., Dash, S., and Parhi, C. (2023). Flash drought in Odisha- prediction, impact assessment, coping strategies: Current status and future strategies. J. Agrometeorol., 25(4): 491–497. https://doi.org/10.54386/jam.v25i4.2450

Pandey, M. K., Singh, S. K., Upadhyay, J., Tiwari, P., Kar, N. K., and Kushwaha, J. P (2024) AI and IoT based application for rainfall prediction: A Study. https://www.researchgate.net/publication/382339588_AI-_and_IoT-Based_Applications_for_Rainfall_Prediction

Sridhara, S., Chaithra, G. M., and Gopakkali, P. (2021). Assessment and monitoring of drought in Chitradurga district of Karnataka using different drought indices. J. Agrometeorol., 23(2), 221-227. https://doi.org/10.54386/jam.v23i2.72

Strazzo, S. (2019). Application of a hybrid statistical-dynamical system to seasonal prediction of North American temperature and precipitation. Mon. Weather Rev., 147: 607–625.

Suliman, A. H. A. (2024). Meteorological and satellite-based data for drought prediction using data-driven model. J. Agrometeorol.,, 26(4): 466-472. https://doi.org/10.54386/jam.v26i4.2734

Tian, Y., Xu, Y.-P., and Wang, G. (2018). Agricultural drought prediction using climate indices based on support vector regression in the Xiangjiang River basin. Sci. Total Environ., 622: 710–720.

Wali, Vijaya, and Satyanarayana Rao (2020): Drought modelling and forecasting using ARIMA and neural networks for Ballari district, Karnataka. J. Indian Soc. Agric. Stat 74 149-157.

Wilhite, D.A., and Glantz, M.H. (1985). Understanding the drought phenomenon: The role of definitions. Water Int., 10: 111–120.

WMO (2023). Guidelines on the definition and characterization of extreme weather and climate events. WMO-No: 1310, Geneva.

Downloads

Published

01-06-2025

How to Cite

PRASAD, A., SINGH, R., K V RAMANA RAO, & C. K. SAXENA. (2025). Applicability of machine learning models for drought prediction using SPI in Kalahandi, Odisha. Journal of Agrometeorology, 27(2), 216–220. https://doi.org/10.54386/jam.v27i2.2906

Issue

Section

Research Paper

Categories

Most read articles by the same author(s)