Runoff estimation using the SCS-CN method and GIS: a case study in the Wuseta watershed, upper blue Nile Basin, Ethiopia

Discover Water, Journal Year: 2025, Volume and Issue: 5(1)

Published: April 24, 2025

Language: Английский

River Surface Space–Time Image Velocimetry Based on Dual-Channel Residual Network

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(10), P. 5284 - 5284

Published: May 9, 2025

Space–Time Image Velocimetry (STIV) estimates the one-dimensional time-averaged velocity by analyzing main orientation of texture (MOT) in space–time images (STIs). However, environmental interference often blurs weak tracer textures STIs, limiting accuracy traditional MOT detection algorithms based on shallow features like images’ gray gradient. To solve this problem, we propose a deep learning-based model using dual-channel ResNet (DCResNet). The integrates and edge channels through ResNet18, performs weighted fusion extracted from two channels, finally outputs MOT. An adaptive threshold Sobel operator channel improves model’s ability to extract STI. Based typical mountainous river (located at Panzhihua hydrological station City, Sichuan Province), an STI dataset is constructed. DCResNet achieves optimal 7:3 gray–edge ratio, with MAEs 0.41° (normal scenarios) 1.2° (complex noise scenarios), respectively, outperforming single-channel models. In flow comparison experiments, demonstrates excellent performance robustness. Compared current meter results, MRE 4.08%, which better than FFT method.

Language: Английский

Robust River Surface Velocity Measurement Based on Adaptive Masked Fft-Stivrobust River Surface Velocity Measurement Based on Adaptive Masked Fft-Stiv

Published: Jan. 1, 2024

Language: Английский