Search

The impact of riverbank erosion poses serious threat to the environment, socio-economics and human safety. Due to the extremely complex mechanisms of erosion, assessing the risk of riverbank erosion is challenging. To address this, we propose an interpretable intelligent model framework to accurately assess large-scale riverbank erosion risk. Firstly, we constructed a multi-source dataset that encompasses 29 riverbank erosion influencing factors. Subsequently, by employing an adaptive feature weighting method, a comprehensive water level factor was synthesized, unifying data dimensions. The Relief algorithm was used to identify influential features for riverbank erosion, and an adaptive feature weighting SMOTE (AFW-SMOTE) algorithm was developed to balance the riverbank erosion dataset. Additionally, an ELM and BiGRU autoencoder was designed to effectively capture and learn key information from static and dynamic features. Finally, the outputs of the two autoencoders were integrated using the XGBoost algorithm to produce riverbank erosion risk assessment results, and the risks were visualized. This model not only performs excellently across multiple evaluation metrics but also significantly surpasses 22 other machine learning models. By integrating the Shapley value method, it enhances the model’s interpretability. This provides policymakers and relevant environmental management agencies with a powerful tool to scientifically assess and manage the risk of riverbank erosion.

Recognizing the risk of fluvial bank erosion is an important challenge to ensure the early warning and prevention or control of bank collapse in river catchments, including in the Yangtze River. This study introduces a geomorphons-based algorithm to extract river bank erosion information by adjusting the flatness from multibeam echo-sounding data. The algorithm maps ten subaqueous morphological elements, including the slope, footslope, flat, ridge, peak, valley, pit, spur, hollow, and shoulder. Twenty-one flatness values were used to build an interpretation strategy for the subaqueous features of riverbank erosion. The results show that the bank scarp, which is the erosion carrier, is covered by slope cells when the flatness is 10°. The scour pits and bank scars are indicated by pit cells near the bank and hollow cells in the bank slope at a flatness of 0°. Fluvial subaqueous dunes are considered an important factor accelerating bank erosion, particularly those near the bank toe; the critical flatness of the dunes was evaluated as 3°. The distribution of subaqueous morphological elements was analyzed and used to map the bank erosion inventory. The analysis results revealed that the near-bank zone, with a relatively large water depth, is prone to form large scour pits and a long bank scarp. Arc collapse tends to occur at the long bank scarp to shorten its length. The varied assignment of flatness values among terrestrial, marine, and fluvial environments is discussed, concluding that diversified flatness values significantly enable fluvial subaqueous morphology recognition. Consequently, this study provides a reference for the flatness-based recognition of fluvial morphological elements and enhances the targeting of subaqueous signs and risks of bank failure with a range of multibeam bathymetric data.