Drought Monitoring and Prediction using K-Nearest Neighbor Algorithm

Drought is a climate phenomenon that might occur in any climate condition and all regions on the earth. An effective drought management depends on the application of appropriate drought indices. Drought indices are variables that are used to detect and characterize drought conditions. In this work, it is tried to predict drought occurrence based on the standard precipitation index (SPI) using k-nearest neighbor modeling. The model is tested using the precipitation data of Kerman, Iran. The results obtained show that the model gives reasonable predictions of the drought situation in the region. Finally, the efficiency and precision of the model is quantified by some statistical coefficients. Appropriate values for the correlation coefficient (r = 0.874), mean absolute error (MAE = 0.106), root mean square error (RMSE = 0.119) and coefficient of residual mass (CRM = 0.0011) indicate that the presented model is suitable and efficient.