Three-phase data augmentation for the prediction of sediment flux in mountain basins during typhoon events

Abstract Discrepancies between estimated sediment and actual yields are large. The sedimentation often causes severe damage due to a lack of on-site measurement data in the current disaster prevention system. This paper presents robust early-warning system which statistical analysis used predict is conducted within context underlying physical mechanisms. three-phase employs collection, generation, AI (Artificial Intelligence) prediction. Data collection involves use HEC-HMS (Hydrologic Engineering Center – Hydrologic Modeling System) transform measured precipitation into flow discharge from various sub-catchments. Empirical formulas related landslide volume soil erosion then establish suitable boundary conditions for generation. Finally, 2D model, SRH-2D (Sediment River Hydraulic-Two Dimension model), simulate pertaining temporal variations flux under storm event scenarios. simulated as input training testing three artificial neural networks. primary strength this study improve prediction ability large-scale issues mountain rivers. These models returned good results with 1–6 h lead times by interdisciplinary integration hydraulic fields.