It is essential to predict suspended sediment load for understanding river morphology, design of dams, water supply problems, management of reservoirs and determination of pollution levels in rivers. The suspended sediment: load can be determined by means of several methods such as direct measurements at the sediment gauging stations, sediment rating curve, soft modeling methods, and empirical methods which are based on experimental works. The objective of this study is first to determine the best empirical method for Gediz river and then to improve the determined method by genetic algorithm (GA). It is seen that the GA improved Brooks method can be used for Gediz River Basin. In addition, this method was compared with other soft computing (ANN, ANFIS) methods and its performance is found to be as good as them.