Log-linear, exponential and fractional relations for estimating seasonal snowmelt from early-spring snow accumulation in the Indus and Kabul river basins in the western Himalayas are developed with a view to improve the prediction given by bivariate linear regression models earlier developed by the senior author in collaboration with others. This study shows that although the transformed data may improve the above prediction, they fail to satisfy the condition of nonlinearity; a property that must be borne in mind before recommending any nonlinear regression model. Any further improvement in the prediction of seasonal flow volume from basin snow cover area, therefore, has to come from within the domain of linear regression models only or from improvements in the original input data.

This content is only available as a PDF.