Construct Channel Network Topology From Remote Sensing Images by Morphology and Graph Analysis

Channel network topology plays an important role in hydrological analysis. This letter proposes an innovative method to construct it based only on remote sensing images. The method uses spectral water indexes and mask of large lakes and ocean areas derived from remote sensing data to generate the map of channels. Then, a morphological thinning algorithm is introduced to extract the initial skeleton of channels. Moreover, an iterative pruning process based on a graph algorithm is proposed to simplify the initial skeleton. Finally, according to the simplified skeleton and its adjacency matrix, a new connectivity graph can be constructed to describe the channel network topology. The proposed method can construct complete skeleton structure and the topology of channels with good connectivity in an automatic way. The output will facilitate detailed hydrological modeling and further applications.