Scholarlink

<p>Continuous measurement of surface suspended sediment concentration (SSC) is of prime importance for understanding sediment transport dynamics in waterway engineering. Previous studies primarily rely on in-situ contact sensors and remote sensing (RS) imagery; however, these methods are often constrained by flow disturbance or insufficient spatiotemporal resolution, respectively. This study aims to develop a cost-effective framework for continuous SSC measurement in small-scale catchments by integrating image processing techniques with artificial intelligence (AI) algorithms. The results revealed that color variables associated with SSC include gray variable of whole region (Gray), non-highlight areas of the gray variable (Gray<sub>n</sub>), red variable of whole region (R), non-highlight areas of the red variable (R<sub>n</sub>), green variable of whole region (G), non-highlight areas of the green variable (G<sub>n</sub>). And their corresponding factor loadings were 0.882, 0.948, 0.967, 0.973, 0.947, and 0.920, respectively. Furthermore, the RF model performed best in AI models, achieving an R² of 0.76. After incorporating environmental factors into the AI model, the R² reached 0.85. In addition, this study investigated the relationship between Illumination and Grayscale, R, G, B. This study demonstrated that the models based on color variables contributed to the continuous measurement of SSC in the field.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Continuous Measurement of River Surface Suspended Sediment Concentration Based on Image Analysis

  • 期刊论文

  • 发表日期：

    2025年12月26日

查看全文
  • Jingang Wu,
  • Binrui Gan,
  • Shengfa Yang,
  • Rui Li

摘要

Continuous measurement of surface suspended sediment concentration (SSC) is of prime importance for understanding sediment transport dynamics in waterway engineering. Previous studies primarily rely on in-situ contact sensors and remote sensing (RS) imagery; however, these methods are often constrained by flow disturbance or insufficient spatiotemporal resolution, respectively. This study aims to develop a cost-effective framework for continuous SSC measurement in small-scale catchments by integrating image processing techniques with artificial intelligence (AI) algorithms. The results revealed that color variables associated with SSC include gray variable of whole region (Gray), non-highlight areas of the gray variable (Grayn), red variable of whole region (R), non-highlight areas of the red variable (Rn), green variable of whole region (G), non-highlight areas of the green variable (Gn). And their corresponding factor loadings were 0.882, 0.948, 0.967, 0.973, 0.947, and 0.920, respectively. Furthermore, the RF model performed best in AI models, achieving an R² of 0.76. After incorporating environmental factors into the AI model, the R² reached 0.85. In addition, this study investigated the relationship between Illumination and Grayscale, R, G, B. This study demonstrated that the models based on color variables contributed to the continuous measurement of SSC in the field.