Airborne LiDAR-assisted deep learning methodology for riparian land cover classification using aerial photographs and its application for flood modelling

Abstract

In response to challenges in land cover classification (LCC), many researchers have experimented recently with classification methods based on artificial intelligence techniques. For LCC mapping of the vegetated Asahi River in Japan, the current study uses deep learning (DL)-based DeepLabV3+ module for image segmentation of aerial photographs. We modified the existing model by concatenating data on its resultant output port to access the airborne laser bathymetry (ALB) dataset, including voxel-based laser points and vegetation height (i.e. digital surface model data minus digital terrain model data). Findings revealed that the modified approach improved the accuracy of LCC greatly compared to our earlier unsupervised ALB-based method, with 25 and 35% improvement, respectively, in overall accuracy and the macro F1-score for November 2017 dataset (no–leaf condition). Finally, by estimating flow-resistance parameters in flood modelling using LCC mapping-derived data, we conclude that the upgraded DL methodology produces better fit between numerically analyzed and observed peak water levels. HIGHLIGHTS DeepLabV3+ model has been modified for ALB data application to riparian LCC mapping.; Compared to the ALB-based method, the DL-based method is highlighted for distinguishing riparian vegetation species.; Hydraulic parameters derived using DL-based LCC results were reasonably used for flood simulation.; Our simulated water levels were much closer to field observations than those simulated using existing ALB-based methods.;

Keywords

• airborne laser bathymetry
• deep learning
• flow-resistance parameterization
• riparian land cover classification
• semantic segmentation