Rainfall Estimation over Roof-Top Using Land-Cover Classification of Google Earth Images

Abstract

'Water' is one of the most valuable resources available to the mankind. In the world, due to exponential growth in population and industrialization we are witnessing scarcity of water. In addition, water table levels are falling rapidly than ever. Hence proper management and appropriate utilization of water has become the need of an hour. Hence this problem is required to be tackled with the novel approach. The idea behind this proposal is to design and development of rain water harvesting system based on rainfall runoff estimation over rooftop. The Google Earth image is combination of remote sensed satellite images and aerial photographs. The information on land use and land cover is obtained using satellites Google Earth images which are simple, economical and precise approach. In the proposed work an efficient classification technique is proposed in which K-means clustering algorithm and textural parameters based on GLCM are used for classification of the Google Earth images into land cover and land use sector. In Land use and land cover classification whole image gets classified into different region such as Grass area, Water area, Roof-top area, Soil area etc. Then area under the different regions is computed. Area measurement is required for computing rainfall runoff using estimation model. Experimental result shows that the computation of the areas of roof tops and road surfaces are nearly accurate and rainfall runoff calculation can be estimated very near to actual.