Realized niches are crucial in defining their optimal conditions and serve as valuable tools for predicting the phytoplankton dynamics in relation to eutrophication, climate change, and harmful phytoplankton blooms. However, previous studies have largely focused on marine ecosystems, leaving freshwater systems less studied. In this study, we elucidate the patterns of phytoplankton community succession based on their niche characteristics in the Shanmei (SM) Reservoir, a drinking water source in Quanzhou, Fujian Province. Additionally, variations in phytoplankton were mainly explained by their realized niche. In the SM Reservoir, total chlorophyll a concentrations ranged from 252 to 24,008 ng/L. The phytoplankton community was dominated by Chlorophyta and Cyanophyta, which consisted mostly of Pseudanabaena and Microcystis, especially in summer. This dominance was attributed to their wide niche breadth and high mean niche for temperature, nitrogen, and dissolved reactive phosphorus. On the other hand, Cryptophyta and Bacillariophyta reached higher concentrations in autumn and winter, linked to their low mean temperature niches. Under the multiple pressures of climate change and anthropogenic activities, Chlorophyta and Cyanophyta are likely to thrive in environments characterized by rising water temperatures and elevated nutrient concentrations. This is particularly true for buoyant cyanobacteria such as Pseudanabaena, which are well‐suited to the stratified water layers induced by higher water temperatures. Therefore, incorporating niche characteristics of harmful bloom‐forming species would contribute to the prevention and management of harmful phytoplankton blooms, ultimately improving the safety of drinking water.

Our study aims to investigate the water quality and distribution patterns of phytoplankton communities in the Jinjiang River Basin in Quanzhou, as well as their relationship with environmental factors. We integrated data from the national water quality databases of the two main tributaries of the West and East Jinjiang Rivers between 2020 and 2023, supplemented by field surveys. Redundancy analysis was used to explore the effect of environmental factors on phytoplankton communities. Our findings revealed that the West Jinjiang River experienced a significant influence from excessive fertilizer use in tea cultivation, leading to an increase in TN concentrations compared to the East Jinjiang River. The abundance of phytoplankton in the Jinjiang River Basin was 10⁵ cells·L⁻¹, with phytoplankton being dominated by Chlorophyta, Cyanphyta, and diatoms, accounting for an average of 50%, 20%, and 19% of the total phytoplankton abundance, respectively. Redundancy analysis indicated that temperature, pH, and nutrient concentrations were important factors influencing the phytoplankton communities. With increasing temperature and nutrients concentrations, the abundance of Chlorophyta and Dinophyta significantly increased. This study provides a solid foundation for the regular “health diagnosis” of crucial rivers and lakes in Quanzhou and supports the establishment of a health guarantee system for rivers and lakes.

Algal proliferation in subtropical drinking water reservoirs has become increasingly severe, and developing a reliable prediction for algal abundance through high-frequency in situ data is essential for early risk warning and effective management. This study analyzed the interannual variations in algal abundance in the Shanmei (SM) Reservoir, located in Quanzhou City, Fujian Province, China, based on the high-frequency data between 2020 and 2025, and forecasted algal abundance 24 h ahead via the optimized Transformer model. Results revealed that the SM reservoir exhibited seasonal variability in environmental factors, with persistently elevated pH during spring and summer, ranging from 7.12 to 9.66, and relatively high total nitrogen concentrations, ranging from 1.17 to 2.28 mg/L. Overall, algal abundance increased throughout the study period, and the annual average algal abundance in 2025 was 8.18 × 10⁶ cells/L, which was twice that in 2021. Model comparisons revealed that the optimized Transformer model exhibited the highest performance in terms of R² = 0.88 when predicting the next hour using 12 days of data. Feature importance analysis based on SHapley Additive exPlanations (SHAPs) revealed that the predictions of algal dynamics were primarily influenced by previous-hours algal abundance, permanganate index, dissolved oxygen, air temperature, wind speed, and pH. This study revealed that the optimized independent learning model with integrated multi-scale features can significantly enhance the predictive performance of algal dynamics, offering a technical basis for early warning of algal blooms and refined reservoir management.