DATA CLASSIFICATION TECHNIQUES AND SYSTEM FOR PREDICTING DISCHARGES IN THE GAMBIA RIVER BASIN

Abstract

Within the framework of water resources management, numerous research works and methods were led in world. In this trail, we noted a fast development of time series data mining (TSDM) which supplies a new method for water resources management. This article examines the trend of discharge during the high water period (from July till November) in the basin of Gambia measured at the Mako station for 1970-2013 period. Methodology consisted at first in calculation and in standardization of data by the method of z-score of some statistical parameters (mean, maximum, minimum, range and standard deviation). Obtained series were afterward submitted to classifications techniques such as k-means clustering and Agglomerative Hierarchical Clustering (AHC) of TSDM to cluster and discover the discharge patterns in terms of the autoregressive model. Based on these methods, a discharge forecast model has been developed. For the validation of the indicated model, and with respect to the maximum discharge, the coefficients of discharge growth and decay, respectively on the phase of rise and the phases of rise and descent waters, were calculated. This study presents basin discharge dynamics in high water period based on TSDM.

Keywords

• data mining
• discharge
• forecast model
• hydrological process
• clustering
• techniques