A fuzzy c-means approach regionalization for analysis of meteorological drought homogeneous regions in western India

Drought is a frequently occurring natural hazard in many parts of the world and affects economy, environment and human lives. In India, the western states are severely affected by droughts. Global warming and climate change is causing more frequent and intense droughts in the region. In the present study, meteorological drought is studied using standardized precipitation index for four different timescales of 1, 3, 6 and 12 months. Drought homogeneous regions are identified over 81 stations in three western states of India using monthly precipitation data from 1901 to 2002. Based on fuzzy c-means clustering algorithm and five cluster validity indices, the optimal number of clusters obtained for 1-, 3-, 6- and 12-month timescales are 4, 5, 3 and 4, respectively. Homogeneity of the clusters is ensured using two L-moment-based homogeneity tests (H-Test). Clusters obtained for different timescales are compared and significant variation in cluster pattern is observed for different timescales. The identified regions are anticipated to assist policy maker in effective planning and management of water resources during drought.