Spatial Artificial Neural Network (SANN) Based Regional Drought Analysis

Drought is one of the most serious hazards that has more effect on human societies than the others. Scentific researches have important roles in drought planning and management of water resources, especially in time of crisis and predicted big event by the event that the crisis management turnover. The main objective of this research is to develop an approach to analyze the spatial patterns of meteorological droughts based on annual precipitation data in Iran. By using a nonparametric spatial analysis neural network algorithm, the normalized and standardized precipitation data are classified into certain degrees of drought severity (extreme drought, severe drought, mild drought, and nondrought) based on a number of truncation levels corresponding to specified quantiles of the standard normal distribution. Then posterior probabilities of drought severity at any given point in the region are determined and the point is assigned a Bayesian Drought Severity Index. This index may be useful for constructing drought severity maps in Iran that display the spatial variability of drought severity for the whole region on a yearly basis.