Data‐Driven Modeling and Computational Intelligence Methods in Hydrology

Author:

Abstract
Along with the physically based (process) models based on mathematical descriptions of hydrological processes, the so‐called data‐driven models (DDM) are becoming popular. They are based on the use of methods of computational intelligence and machine learning and assume the presence of considerable amount of data describing the modeled phenomenon. The article covers various aspects of DDM, including the data preparation and a brief overview of the used techniques – neural networks, regression and model trees, instance‐based learning, and nonlinear dynamics. A number of references to the successful application of data‐driven methods are provided along with the links to the relevant web sites and software packages. An example where several data‐driven methods were used in a hydrologic forecasting problem is provided.

This publication has 35 references indexed in Scilit: