Algal blooms are a major risk to aquatic ecosystem health and potable water safety. Traditional statistical models often fail to accurately predict algal bloom dynamics due to their complexity. Machine learning, adept at managing high-dimensional and non-linear data, provides a superior predictive approach to this challenge. In this study, we employed support vector machine (SVM), random forest (RF), and backpropagation neural network (BPNN) models to predict the severity of algal blooms in the Anzhaoxin River Basin based on an algal density-based grading standard. The SVM model demonstrated the highest accuracy with training and test set accuracies of 0.96 and 0.92, highlighting its superiority in small-sample learning. The Shapley Additive Explanations (SHAP) technique was utilized to evaluate the contribution of environmental variables in various predictive models. The results show that TP is the most significant environmental factor affecting the algal bloom outbreak in Anzhaoxin River, and the phosphorus management strategy is more suitable for the management of the artificial water body in northeast China. This study contributes to exploring the potential application of machine learning models in diagnosing and predicting riverine ecological issues, providing valuable insights and support for the protection and management of aquatic ecosystems in the Anzhaoxin River Basin.

This work focused on the Xinghua River, a typical urbanizing river, to investigate how different anthropogenic activities affect the composition, sources, and environmental impact of dissolved organic matter (DOM) during urbanization. Using fluorescence spectroscopy combined with multivariate statistics, we systematically explored DOM characteristics and their response to urbanization. A total of four fluorescent components were identified, including protein-like components C1 and C3, and humic-like components C2 and C4, with protein-like substances constituting the major fraction of DOM. Fluorescence indices indicated that DOM in the Xinghua River was primarily derived from autochthonous sources (FI > 1.9), with a low degree of humification reflecting the dominance of fresh organic matter input during urbanization. Spatial analysis revealed that from upstream to downstream, the source of DOM gradually shifted from autochthonous dominance to increased allochthonous input, accompanied by increasing trends in both protein-like and humic-like components, indicating an accumulative effect of anthropogenic activities along the river. 2D-COS further revealed that the transformation sequence of DOM components along the flow direction was C3 → C1 → C4 → C2, suggesting that tyrosine/tryptophan-like substances were the most sensitive to anthropogenic disturbance. Redundancy analysis identified total phosphorus (TP), total dissolved solids (TDS), and permanganate index (COD_Mn) as the key environmental factors influencing DOM distribution, highlighting the synergistic regulatory roles of nitrogen and phosphorus nutrients and organic pollution loads on DOM composition. This study not only elucidates the gradient effects of human activities on DOM in the Xinghua River but also provides a scientific basis for water management in urban rivers worldwide, particularly for zone-based control and source-oriented management.