Classification of Surface Water using Machine Learning Methods from Landsat Data in Nepal

With over 6,000 rivers and 5358 lakes, surface water is one of the important resources in Nepal. However, their quantity and quality are decreasing due to human activities and climate change. Hence, the monitoring and estimation of surface water is an essential task. In Nepal, surface water has different characteristics such as varying temperature, turbidity, depth, and vegetation cover, for which remote sensing technology plays vital role in classification. In recent years machine learning methods with training dataset, have been outperforming different traditional methods. In this study, we tried to use satellite image from Landsat 8 to classify surface water in Nepal. Input of Landsat bands, their derived indices and ground truth from high resolution images available in Google Earth will be used. And their performance will be evaluated based on overall accuracy using cross-validation technique. The study will be will helpful to select optimum machine learning method for surface water classification and therefore, monitoring and management of the surface water in Nepal.