Convolutional Neural Network based Water Resource Monitoring Using Satellite Images

Perception of surface water is a utilitarian necessity for contemplating natural and hydrological processes. Ongoing advances in satellite-based optical remote sensors have advanced the field of detecting surface water to another period. Observing surface water with old-style strategies isn't a simple undertaking. Remote detecting with wide inclusion and different fleeting observing is the best answer for surface water checking, This paper exhibits the extraction of water resources from nonwater bodies, for example, vegetation, urban regions, and so forth. Using machine learning (ML) algorithms. The data used in the process have been collected from BHUVAN open data archive. This paper also targets measuring the area of a particular water body using GIS. Water bodies have strong absorbability and low radiation in the range from visible to infrared wavelength. CNN speaks of a blueprint for all-round picture handling using neural means. CNN force imperative casing function admirably fit the preparation of spatially or momentarily coursed data. The results display the binary classified output which has been extracted using a neural network and also waterbody statistics using GIS