Input and output data for real-time maximum flood inundation modelling using machine learning

This dataset contains the input and output files for training, testing, and validation of the Random Forest (RF) model for real-time flood inundation modelling downstream of Bhadrachalam, India. The data folder has two subfolders, each for depth and velocity models. Each folder contains two subfolders, one containing the inputs for the RF model and the other containing the outputs of the RF model. The outputs were obtained from the 2-dimensional modelling using the LISFLOOD-FP hydrodynamic model. THe inputs of the model are topographic features elevation, topographic wetness index, multi-resolution valley bottom index, terrain ruggedness index, etc. and flood characteristics like peak flows at main and tributary rivers, duration of the event, etc. The outputs of the models are maximum flood depth and velocity for RF depth and RF velocity models.