A deep-learning model for predicting the planform evolution of braided sand-bed rivers
Antonio Magherini (Deltares, Student TU Delft)
E. Mosselman (TU Delft - Rivers, Ports, Waterways and Dredging Engineering, Deltares)
V. Chavarrias Borras (Deltares)
R. Taormina (TU Delft - Sanitary Engineering)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Braided rivers are the most dynamic type of rivers, with a rapid and intricate morphological evolution (Stecca et al., 2019). Being able to predict where and how rivers evolve is crucial for supporting spatial-related decisionmaking processes in the vicinity of these rivers. However, a limited understanding and inadequate algorithm implementation of specific morphological processes limits the prediction capabilities of physics-based models (Jagers, 2003; Siviglia and Crosato, 2016). The design of structures, infrastructure, and other interventions is consequently hampered at the expenses of the popoulation safety. In recent years artificial intelligence techniques rapidly gained popularity across different contexts (Blake et al., 2021) and the availability of satellite images increased. This research sets a novel attempt to predict the planform evolution of braided rivers by means of a deeplearning algorithm and using satellite images. The Brahmaputra-Jamuna River, in India and Bangladesh, was selected as case study (Best et al., 2022).