Development of stational models for estimation of rainfall erosivity factor in different timescales

Rainfall has a considerable role in soil erosion and can be used to determine the rate of soil erosion at different areas. In general, the erosivity factor is represented by erosivity indices that are based on rainfall characteristics and drastically varies from place to place. However, developing appropriate models or calibrating available indices for erosivity estimation has been rarely taken into account in developing countries. The present study has, therefore, attempted to evaluate the accuracy of existing indices for estimation of erosivity factor and appropriate model calibration, and development was ultimately made. To achieve the study purposes, at first, the location of maximum number of accessible 14 stations distributed throughout Iran with 23-year common data span as well as the quality and the quantity of corresponding data was investigated to model the Wischmeier and Smith's erosivity index. The index was estimated by different erosivity indices, viz. Fournier, modified Fournier, Roose and Lo, mainly based on easily accessible rainfall data, and necessary comparisons were accordingly made. The results of comparison showed that the Roose's index had more applicability in estimating the Wishmeier and Smith's index in study stations with determination coefficient varied from 31 to 98 % (p < 0.32) and relative errors between 9.0 and 98.3 %. A calibrated Roose's index with reasonable statistical performance was consequently developed for different stations.