Abstract
The less predictable characteristics of droughts make drought both a hazard and a disaster: a hazard because it is a natural accident of unpredictable occurrence but of recognisable recurrence, and a disaster because it causes the disruption of the water supply to the natural and agricultural ecosystems as well as to other human activities. What make less predictable characteristics of droughts is its uncertainty, fuzzification and gray properties. Rough set theory was introduced to conduct drought forecast problem in the paper for its advantages in dealing with uncertain and incomplete problems. A case study was carried out, and the rules for drought forecast was acquired in the light of data selection, preprocessing, attributes reduction, rules generation and filtering, which could be used in drought forecast for the study area. In general, the results showed that it was quite successful with the application of rough set theory in the forecast of drought severity.