This study presents a comprehensive multi-model machine learning (ML) approach to predict river bed load, addressing the challenge of quantifying predictive uncertainty in fluvial geomorphology. Six ML models—random forest (RF), categorical boosting (CAT), extra tree regression (ETR), gradient boosting machine (GBM), Bayesian regression model (BRM), and K-nearest neighbors (KNNs)—were thoroughly evaluated across several performance metrics like root mean square error (RMSE), and correlation coefficient (R). To enhance model training and optimize performance, particle swarm optimization (PSO) was employed for hyperparameter tuning across all the models, leveraging its capability to efficiently explore complex hyperparameter spaces. Our findings indicated that RF, GBM, CAT, and ETR demonstrate superior predictive performance (R score > 0.936), benefiting significantly from PSO. In contrast, BRM displayed lower performance (0.838), indicating challenges with Bayesian approaches. The feature importance analysis, including permutation feature and SHAP values, highlighted the non-linear interdependencies between the variables, with river discharge (Q), bed slope (S), and flow width (W) being the most influential. This study also examined the specific impact of individual variables on model performance by adding and excluding individual variables, which is particularly meaningful when choosing input variables for the model, especially in limited data conditions. Uncertainty quantification through Monte Carlo simulations highlighted the enhanced predictability and reliability of models with larger datasets. The correlation between increased training data and improved model precision was evident in the consistent rise in mean R scores and reduction in standard deviations as the sample size increased. This research underscored the potential of advanced ensemble methods and PSO to mitigate the limitations of single-predictor models and exploit collective model strengths, thereby improving the reliability of predictions in river bed load estimation. The insights from this study provide a valuable framework for future research directions focused on optimizing ensemble configurations for hydro-dynamic modeling.
Abstract The dynamics of suspended particulate matter (SPM) and SPM‐associated biological and physicochemical processes in a river vary under dry and wet weather conditions and hydraulic structures, which moves a free‐flowing river to a semi‐lacustrine environment. This study investigated the response of SPM dynamics and riverbed morphodynamics to climate and anthropogenic stressors based on in‐situ observations and biogeochemical analyses of river water and riverbed sediment. The biochemical analyses and flocculation tests demonstrate abundant biopolymers and high flocculation potential of the river water during the pre‐flood period with algal bloom. This might promote SPM deposition and high‐concentration sediment layer (HCSL) formation on the riverbed. The high fractions of clay minerals and organic carbon in the riverbed sediment indicate the deposition of organic‐rich biomineral flocs. Vertical turbidity profiles with “long tails” of high turbidity near the riverbed also confirmed SPM deposition and HCSL formation. However, the highly turbulent flow conditions during the post‐flood period disturbed the tails of high turbidity and homogenized the vertical profiles of turbidity, temperature, and dissolved oxygen. Additionally, terrestrial humic substances were discharged from the watershed during this period, increasing the deflocculation and stabilization of SPM but decreasing deposition on the riverbed, thereby reducing the fractions of clay minerals and organic carbon in the sediment. This study demonstrated the interaction mechanism of SPM dynamics and riverbed morphodynamics with hydrological and biogeochemical processes in an impounded river under dry and wet weather conditions. The findings provide insights into water resource management to deal with climate change and anthropogenic stressors.
Suspended particulate matter (SPM) is an indispensable component of water environments. Its fate and transport involve various physical and biogeochemical cycles. This paper provides a comprehensive review of SPM dynamics by integrating insights from biogeochemical processes, spatiotemporal observation techniques, and numerical modeling approaches. It also explores methods for diagnosing SPM-mediated biogeochemical processes, such as the flocculation kinetics test and organic matter composition analysis. Advances in remote sensing, in situ monitoring, and high-resolution retrieval algorithms are discussed, highlighting their significance in detecting and quantifying SPM concentrations across varying spatial and temporal scales. Furthermore, this review examines integrated models that incorporate population balance equations on the basis of flocculation kinetics into multi-dimensional sediment transport models. The results from this study provide valuable insights into SPM dynamics, ultimately enhancing our knowledge of SPM behavior and transport in water environments. However, uncertainties remain due to limited field data on flocculation kinetics and the need for parameter optimization in numerical models. Addressing these gaps through enhanced fieldwork and model refinement will significantly improve our ability to predict and manage SPM dynamics, which is critical for sustainable aquatic ecosystem management in an era of rapid environmental change.
'%3e%3cg id='b'%3e%3cpath id='a' stroke='%23000' stroke-width='2' d='M-6-25H6m-12 3H6m-12 3H6'/%3e%3cuse xlink:href='%23a' y='44'/%3e%3c/g%3e%3cpath stroke='%23fff' d='M0 17v10'/%3e%3ccircle r='12' fill='%23cd2e3a'/%3e%3cpath fill='%230047a0' d='M0-12A6 6 0 0 0 0 0a6 6 0 0 1 0 12 12 12 0 0 1 0-24z'/%3e%3c/g%3e%3cg transform='rotate(-123.69)'%3e%3cuse xlink:href='%23b'/%3e%3cpath stroke='%23fff' d='M0-23.5v3M0 17v3.5m0 3v3'/%3e%3c/g%3e%3c/svg%3e)
'%3e%3cpath id='a' fill='%23FF0' d='M0 0v6h4' transform='rotate(18)'/%3e%3cuse xlink:href='%23a' transform='scale(-1 1)'/%3e%3c/g%3e%3cg id='c' transform='rotate(72)'%3e%3cuse xlink:href='%23b'/%3e%3cuse xlink:href='%23b' transform='rotate(72)'/%3e%3c/g%3e%3cuse xlink:href='%23c' transform='scale(-1 1)'/%3e%3c/svg%3e)