Basin‐wide hydromorphological analysis of ephemeral streams using machine learning algorithms ^‡

Sustainable river management now encompasses a much wider concept that includes hydromorphological and fluvial habitat studies. In ephemeral streams, the geomorphological characterization of channels is complex due to episodic flows riparian vegetation dynamics. Stream channel survey classification at watershed scale provide basis for conservation, process interpretation, assessing sensitivity disturbance, identifying reaches supply store sediment. Here, we present stream based on two-step approach: (1) automatic segmentation spatial variability in channel/valley morphology from topographic measurements (LiDAR, light, detection ranging), (2) landform density mapping derived multispectral open-source satellite images (Sentinel-2) using support vector machine (SVM) Random Forest (RF) algorithms. These analyses continuous, quantitative values geometric (channel/valley width, slope gradient, route distance), (active gravel bars with five densities cover), hydraulic (specific power) variables. Four types were identified Rambla de la Viuda catchment (~1500 km2), an gravel-bed eastern Spain. The distribution explained by differences geometry valley gradient) parameter power). landforms/vegetation patterns provided insight causal relationships between erosion deposition processes during high flow periods time since most recent large disruptive flood event. Channel type first-order predictions about location sediment thus information continuity along river. Dam effects downstream resulted disequilibrium, producing narrowing active channel, reduction, decrease bar areal extension. proposed analysis provides comprehensive replicable methodology environmental planning Mediterranean streams guide further surveys reach scale.