Predicting Drought Using Pattern Recognition

Predicting droughts and their impacts upon overall agricultural production helps in drought management. Generally, statistical regressi on or time series techniques are employed to predict agricultural droughts quantitat ively. Linear (error correction, linear discriminant) and nonlinear (k-Nearest Neighbour) t echniques of pattern recognition were used for predicting agricultural droughts qual itatively. A total of five crop districts in the province of Saskatchewan in the Canadian pra iries, were selected. Thirty two variables were derived for each district from the d aily temperature and precipitation data for the period from 1975 to 2002 to develop pattern recognition models. The variables derived from the minimum or maximum temperature were found to be more significant than the variables derived from the precipitation f or predicting moderate-to-very severe agricultural droughts. The 1975-1997 data were used for model development while the 1998-2002 data were used for model testing. About 83% accuracy was achieved in predicting the non-drought category while 71% accuracy was achieved in predicting the drought category. It was concluded that pattern rec ognition techniques could be applied for predicting drought qualitatively, which would a id current methods of drought prediction.