Predicting Mustard Yield in Different Agroclimatic Zones of Punjab through Statistical Models

An attempt was made to predict mustard (Brassica compestris) yield for three different districts of Punjab representing three agroclimatic zones i.e. Hoshiarpur, Ludhiana and Bathinda through regression models. Three statistical models have been developed for forecasting the mustard yield by using yield data and weather data viz. maximum and minimum temperature, morning and evening relative humidity, sunshine hours, rainfall and number of rainy days on weekly basis. In the first two models, sensitive period for mustard yield with respect to weather parameters were identified through correlation technique and selected windows were taken for further regression analysis. In the first (Basic) model, different weather parameters were used as independent variables while in the second (Modified) model, composite index was taken as one of the extra variable in multiple regression. In the third model, multiple regression analysis was done using SPSS software. Regression equations were developed separately for all the three models and were used to predict the mustard yield. The data for a period of (1974–2014) was used to develop the forecast model, whereas the three year meteorological data (2015–2017) was used to validate the models. When compared the data for Hoshiarpur district, basic model and modified model explained 88% variation to mustard yield, while model 3 explained 99% variation, respectively. For Ludhiana, among all the three models, basic model explained up to 71% variation, modified model and SPSS model contributes 85% and 91% variation, respectively in mustard yield due to weather parameters. For Bathinda, basic model contributes up to 40%, modified model explained 81% variation and SPSS model predict 91% variation in mustard yield. The results revealed that SPSS model is best fit for Hoshiarpur, Ludhiana and Bathinda region as far as mustard yield is concerned.