Climate Change Prediction Utilizing Machine Learning Techniques

IJEP 44(3): 206-215 : Vol. 44 Issue. 3 (March 2024)

Parul Khatri* and Tripti Arjariya*

Bhabha University, Bhopal – 462 026, Madhya Pradesh, India


The most significant renewable natural resource is water. Water management is crucial for the sustainability of human life. One of the most crucial aspects of an area’s water management is the rainfall prediction. A collection of observations of a variable made at regular periods is referred to as a time series. On the other hand, a prediction is only a computation of what will happen in the future of the variable of interest using information from the past under the presumption that the pattern followed in the past would likewise be continued in the future. Using traditional and computational models, this effort will attempt to develop forecasting models for the time series dataset. This research will make use of yearly climate data for Varanasi city for a total of 112 years (1910-2022). Moving average, exponential smoothing with one parameter and the traditional model auto-regressive integrated moving average (ARIMA) are the distinct statistical models to be taken into consideration. Varanasi rainfall data is steady; consequently, there is no need to differentiate the data series. Nevertheless, the provided data was non-normal; as a result, the data was transformed to make it normal. This converted data was taken into account for all models, including hybrid models, when further analysis was performed. When using moving average, forecasts was made for several time periods and the best one was selected using error measurements. Individual forecasts were also performed using the computational model k-nearest neighbour (KNN) and the interpolation technique cubic spline. In the instance of a cubic spline, many knots were tested, the best value was picked and analysis was performed based on the chosen knot. Finally, the best statistical models and the interpolation model spline were combined with kNN to create hybrid models and these hybrid models were used to forecast the provided data for the years 2018-2023. All models, both individual and hybrid, were compared and the best model from each was chosen based on the error metrics mean absolute percentage error (MAPE), mean absolute deviation or mean absolute error (MAD/MAE) and root mean square error (RMSE).


Water management, K-nearest neighbour, Forecasting, Weather data, Data mining, Auto-regressive integrated moving average


  1. Dhawal, H. and N. Mishra. 2016. A survey on rainfall prediction techniques. Int. J. Computer Application. 6(2): 28-42.
  2. Omar, P. J., et al. 2021. Study of methods available for groundwater and surface water interaction: a case study on Varanasi, India. In The Ganga river basin: A hydrometeorological approach. Sprin-ger. pp 67-83.
  3. Omar, P. J., et al. 2022. Identification of soil erosion-prone zone utilizing geo-informatics techniques and WSPM model. Sustain. Water Resour. Manage., 8(3): 66.
  4. Shivhare, N., P.K. Singh Dikshit and S.B. Dwivedi. 2018. A comparison of SWAT model calibration techniques for hydrological modeling in the Ganga river watershed. Eng., 4(5): 643-652.
  5. Shivhare, N. et al. 2018. Identification of critical soil erosion prone areas and prioritization of micro-watersheds using geoinformatics techniques. Ecol. eng., 121: 26-34.
  6. Gupta, A., et al. 2013. Time series analysis of forecasting Indian rainfall. Int. J. Inventive Eng. Sci., 1(6): 42-45.
  7. Rahul, A. K., et al. 2020. Estimation of behavioural change of SSC of bed profile in the river using ADCP. Arabian J. Geosci., 13: 1-9.
  8. Rahul, A.K., et al. 2021. Modelling of daily suspended sediment concentration using FFBPNN and SVM algorithms. J. Soft Computing Civil Eng., 5(2): 120-134.
  9. Kashiwao, T. 2017. A neural network-based local rainfall prediction system using meteorological data on the internet: A case study using data from the Japan Meteorological Agency. Appl. Soft Computing. 56: 317-330.
  10. Mandale, A. and B. A. Jadhawar. 2015. Weather forecast prediction: a data mining application. Int. J. Eng. Res. Gen. Sci., 3(2).
  11. Kar, K., N. Thakur and P. Sanghvi. 2019. Prediction of rainfall using fuzzy dataset. Int. J. Computer Sci. Mobile Computing. 8(4): 182-186.
  12. Darji, M.P., V.K. Dabhi and H.B. Prajapati. 2015. Rainfall forecasting using neural network: A survey. International Conference on Advances in computer engineering and applications (ICACEA), Ghaz-iabad, India. Proceedings, pp 706-713.
  13. Lee, S., S. Cho and P. M. Wong. 1998. Rainfall prediction using artificial neural networks. j. geogr. inf. Decision Analysis. 2(2): 233-242.
  14. Sharma, A. and G. Nijhawan. 2015. Rainfall prediction using neural network. Int. J. Computer Sci. Trends Tech., 3(3): 65-69.
  15. Mislan, M., et al. 2015. Rainfall monthly prediction based on artificial neural network: a case study in Tenggarong station, East Kalimantan, Indonesia. Procedia Computer Sci., 59: 142-151.
  16. Pai, D. S. and M. Rajeevan. 2006. Empirical prediction of Indian summer monsoon rainfall with different lead periods based on global SST anomalies. Meteorol. Atmos. Physics. 92(1-2): 33-43.
  17. Ihara, C., K. Yochanan and A.M. Cane. 2008. Warming trend of the Indian ocean SST and Indian ocean dipole from 1880 to 2004. J. Climate. 21 (10): 2035-2046.
  18. Remesan, R., et al. 2009. Runoff prediction using an integrated hybrid modelling scheme. J. Hydrol., 372(1-4): 48-60.
  19. Indrabayu, N.H., M.S. Pallu and A. Achmad. 2013. A new approach of expert system for rainfall prediction based on data series. Int. J. Eng. Res. Appl.,3(2): 1805-1809.
  20. Shivhare, N., et al. 2019. ARIMA based daily wea-ther forecasting tool: A case study for Varanasi. Mausam. 70(1): 133-140.
  21. Shivhare, N., et al. 2019. Utilizing SWAT for surface water discharge modelling: a case study of a watershed in Ganga basin. EasyChair.
  22. Hipel, K.W., A.I. McLeod and W.C. Lennox. 1977. Advances in Box Jenkins modeling: Model construction. Water Resour. Res.,13(3): 567-
  23. Nirmala, M. and S.M. Sundaram. 2010. A seasonal ARIMA model for forecasting monthly rainfall in Tamil Nadu. National J. Adv. Building Sci. Mechanics. 1(2): 43-47.
  24. Samui, P. 2011. Application of least square support vector machine (LSSVM) for determination of evaporation losses in reservoirs. Eng., 3(4):
  25. Joseph, J. and T.K. Ratheesh. 2013. Rainfall prediction using data mining techniques. Int. J. Computer Applications. 83: 8.
  26. Mahalakshmi, D.V., et al. 2014. Net surface radiation retrieval using earth observation satellite data and machine learning algorithm. ISPRS Annals Photogramm. Remote Sens. Spatial Inf. Sci., II(8): 9-12.
  27. Mohamed, T.M. and A.A.A. Ibrahim. 2016. Fitting probability distributions of annual rainfall in Sudan. SUST J. Eng. Comp. Sci.,17(2): 34-39.
  28. Swain, S., S.K. Mishra and A. Pandey. 2018. Assessment of meteorological droughts over Hoshan-gabad district, India. IOP conf. series earth env. sci., 491(1): 012012.
  29. Kaushik, I. and S. M. Singh. 2008. Seasonal ARIMA model for forecasting of monthly rainfall and temperature. J. Env. Res. Develop., 3(2): 506-514.
  30. Graham, A. and E.P. Mishra. 2017. Time series analysis model to forecast rainfall for Allahabad region. J. Pharmacognosy Phytochem., 6(5): 1418-1421.
  31. Chaudhari, A. R., D. P. Rana and R. G. Mehta. 2013. Data mining with meteorological data. Int. J. Adv. Computer Res., 3(3): 25.
  32. Azizan, I., S.A.B.A. Karim and S.S.K. Raju. 2018. Fitting rainfall data by using cubic spline interpolation. MATEC Web Conf., 225: 05001. technologies (ICICT). Proceedings, vol. 3, pp 1-9.