Remote sensing is one of the most important tools for monitoring and assisting to estimate and predict Water Quality
parameters (WQPs). The traditional methods used for monitoring pollutants are generally relied on optical images. In
this paper, we present a new approach based on the Synthetic Aperture Radar (SAR) images which we used to map the
region of interest and to estimate the WQPs. To achieve this estimation quality, the texture analysis is exploited to
improve the regression models. These models are established and developed to estimate six common concerned water
quality parameters from texture parameters extracted from Terra SAR-X data. In this purpose, the Gray Level Cooccurrence
Matrix (GLCM) is used to estimate several regression models using six texture parameters such as contrast,
correlation, energy, homogeneity, entropy and variance.
For each predicted model, an accuracy value is computed from the probability value given by the regression analysis
model of each parameter. In order to validate our approach, we have used tow dataset of water region for training and
test process. To evaluate and validate the proposed model, we applied it on the training set. In the last stage, we used the
fuzzy K-means clustering to generalize the water quality estimation on the whole of water region extracted from
segmented Terra SAR-X image. Also, the obtained results showed that there are a good statistical correlation between
the in situ water quality and Terra SAR-X data, and also demonstrated that the characteristics obtained by texture
analysis are able to monitor and predicate the distribution of WQPs in large rivers with high accuracy.