Application of ANN in Estimating IRED of Stepped Gabion Weir

A rectangular basket assembled from a hexagonal mesh of heavily galvanised steel wire, filled with rock stacked atop one another to form a weir structure, is known as a Gabion weir. They are porous structures that can sometimes be vegetated and are considered an aesthetic structural solution with minimal habitat. Recently, the stepped gabion weirs have become a popular structure replacing stepped spillways that can check floods. The performance of an artificial neural network, one of the robust machine learning techniques, is investigated in predicting the inverse relative energy dissipation of the stepped gabion weir. The proposed ANN model in the present study is then compared with different machine learning techniques available in the literature. Based on performance parameters, it is observed that the proposed ANN model has the highest accuracy compared to the GMDH and GEP models in predicting the relative energy dissipation of the stepped gabion weir.