Prediction of Suspended Sediment Concentration Based on the Turbidity-Concentration Relationship Determined via Underwater Image Analysis

Abstract

Sediment measurement data are essential for sediment transport analysis and therefore highly important in overall river planning. Extant sediment measurement methods consume considerable manpower and time and are limited by factors including economic reasons and worker risks. This study primarily aimed to predict the changes in SSC (Suspended Sediment Concentration) and turbidity by examining the change in color in underwater images. While maintaining a constant flow in a channel, the turbidity and concentration were measured under different SSC. Multiple regression models were developed using turbidity measurement results, and they exhibited high explanatory powers (adjusted R2 > 0.91). Furthermore, upon verification using the verification dataset of the experimental results, an excellent predictive power (RMSE ≈ 0.4 NTU) was demonstrated. The model with the highest predictive power, which was inclusive of red and green bands and showed no underlying multicollinearity was used to predict turbidity. Finally, the turbidity and suspended sediment concentration relationship determined from the experimental results was used to estimate the sediment concentration from the color changes in the underwater images. The concentrations that were predicted by the model showed satisfactory results, compared to the measurements (RMSE ≈ 21 ppm). This study indicated the feasibility of continuous SSC monitoring using underwater images as a new measurement method.