1Agricultural Meteorological Cell, Department of Agricultural Engineering, N.M. College of Agriculture, Navsari Agricultural University, Navsari, 396 450, Gujarat, India
*(Corresponding Author) Email Id: sandeepagromet@gmail.com
Regression models by modified Hendrick and Scholl technique were developed on rain-fall forecasting for three districts of South Gujarat. The data on the rainfall and weather parameters were analysed for 27 years. The 24-year data were used for development of the model. The validation of model was done using data set of 2012 and 2015. The stepwise regression analysis was executed by trial-and-error method to obtain the finest combination of predictors, significant at 5% level. The multiple regression technique was used for fitting of the model and decided best by highest R2 and lowest per cent error. All rainfall forecasting models gave good estimates and produced error per cent within acceptable range. Analysis revealed that the model error per cent of Navsari, Bharuch and Valsad were −17 to 16%, −21 to 14% and −18 to 16%, respectively. Rainfall fore-casting for year 2016 based on validated model was made for the districts of Navsari, Bharuch and Valsad.
Per cent error, RMSE, Stepwise regression and Rainfall forecasting