Application of Clustering Data Mining Techniques in Temporal Data Sets of Hydrology:A Review

Hydrologic cycle are rather very complex and it is very difficult to predict the behaviour of runoff based on temporal data sets of hydrological process, as these are often very large and difficult to analyse and display. Clustering can be done by the different number of algorithms such as hierarchical, partitioning, grid and density based algorithms. This paper is original concerns in two main aspects. First, it provides an evolutionary algorithm for clustering starting from data mining mechanism, tasks and its learning. Second, it provides a taxonomy that highlights some very important aspects in the context of clustering algorithms, namely, hierarchical, partitional algorithms, density based, grid based and model-based. A number of references are provided that describe applications of evolutionary algorithms for clustering in different domains as well as in Hydrology. Also, in this paper a brief overview of temporal data mining concepts including time series sequences are discussed.