Machine learning-based identification and contribution analysis of dominant factors driving algal blooms in the Xiangxi Bay

YANG Jing; YANG Zhong-yong; HE Yu-fang; XIONG Li-wei; HU Yi-ling; JI Dao-bin

PDF(2763 KB)

China Environmental Science ›› 2026, Vol. 46 ›› Issue (3) : 1486-1498.

Machine learning-based identification and contribution analysis of dominant factors driving algal blooms in the Xiangxi Bay

YANG Jing¹, YANG Zhong-yong^1,2, HE Yu-fang³, XIONG Li-wei¹, HU Yi-ling¹, JI Dao-bin^1,2

Author information +

History +

Abstract

Algal blooms are a major ecological and environmental issue in the tributary bays of the Three Gorges Reservoir. To identify the dominant environmental factors driving algal blooms in the Xiangxi Bay, this study utilized high-frequency monitoring data collected from August 9 to August 30, 2024, with chlorophyll-a (Chl.a) concentration as the bloom indicator. Three machine learning models—Random Forest (RF), Support Vector Regression (SVR), and Partial Least Squares Regression (PLS)—were applied to identify key driving factors. The results showed that algal blooms in Xiangxi Bay exhibited pronounced diurnal variation, with nighttime stable stratification and low disturbance favoring bloom formation, while daytime disturbances and high temperatures inhibited algal accumulation. Water velocity (WV) and air temperature (AT) were identified as immediate driving factors, with contribution rates of 27.1% and 18.1%, respectively. specific conductivity (SP) served as an important regulating factor (17.1%), while dissolved oxygen (DO), pH, and water temperature (WT) were secondary feedback factors. Moreover, the impacts of these factors on Algal blooms exhibited significant nonlinearity and lagged response characteristics.

Key words

algal blooms / Xiangxi River / machine learning models / environmental drivers / contribution analysis

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

YANG Jing, YANG Zhong-yong, HE Yu-fang, XIONG Li-wei, HU Yi-ling, JI Dao-bin. Machine learning-based identification and contribution analysis of dominant factors driving algal blooms in the Xiangxi Bay[J]. China Environmental Science. 2026, 46(3): 1486-1498

References

[1] 张中天,袁海钰,许强,等.太湖叶绿素a质量浓度年际变化特征及其对多因子协同的响应 [J]. 水利水电科技进展, 2025,45(3):93-98. Zhang Z T, Yuan H Y, Xu Q, et al. Interannual variation of chlorophyll-a concentration in Lake Taihu and its response to multiple factors [J]. Advances in Science and Technology of Water Resources and Hydropower, 2025,45(3):93-98.
[2] Sungjin K, Sewoong C.Causal impact analysis of weir opening on cyanobacterial blooms and water quality in the Yeongsan River, Korea: A bayesian structural time-series analysis and median difference test [J]. Science of the Total Environment, 2024,924.
[3] Llanos, Alex A H, Meza, et al. An artificial neural network model for water quality prediction in the amoju hydrographic subbasin, cajamarca-peru [J]. International Journal of Advanced Computer Science and Applications, 2024,15,(9):1021-1032.
[4] 胡怡玲,杨忠勇,冉薇,等.水流扰动环境中微囊藻群体生长及成群分析 [J]. 中国环境科学, 2025,45(6):3280-3288. Hu Y L, Yang Z Y, Ran W, et al. Growth and colony formation analysis of Microcystis populations under flow-disturbance conditions [J]. China Environmental Science, 2025,45(6):3280-3288.
[5] Conley D J, Paerl H W, Howarth R W, et al. Ecology controlling eutrophication: Nitrogen and phosphorus [J]. Science, 2009,323(5917): 1014-1015.
[6] 朱广伟,许海,朱梦圆,等.我国城市水源水库水质风险成因及对策 [J]. 湖泊科学, 2024,36(1):1-16. Zhu, G W, Xu H, Zhu M Y, et al. Causes and countermeasures of water quality risks in urban drinking water reservoirs in China [J]. Journal of Lake Sciences, 2024,36(1):1-16.
[7] 王思琪.基于多源数据的太湖蓝藻水华风险评估及日内变化时空规律挖掘研究 [D]. 武汉:武汉大学, 2023. Wang S Q. Risk assessment of cyanobacterial blooms in Lake Taihu based on multi-source data and spatiotemporal patterns of diurnal variation [D]. Wuhan: Wuhan University, 2023.
[8] 刘德富,黄钰铃,纪道斌,等.三峡水库支流水华与生态调度 [M]. 北京:中国水利水电出版社, 201311.429. Liu D F, Huang Y L, Ji D B, et al. Algal blooms and ecological regulation in the tributaries of the Three Gorges Reservoir [M]. Beijing: China Water & Power Press, 2013:429.
[9] 杨正健,刘德富,马骏,等.三峡水库支流水华与生态调度新进展 [M]. 北京:中国水利水电出版社, 2021:351. Yang Z J, Liu D F, Ma J, et al. New advances in tributary algal blooms and ecological regulation in the Three Gorges Reservoir [M]. Beijing: China Water & Power Press, 2021:351.
[10] 崔玉洁.三峡水库香溪河藻类生长敏感生态动力学过程及其模拟 [D]. 武汉:武汉大学, 2017. Cui Y J. Ecological dynamic processes sensitive to algal growth and their simulation in the Xiangxi River of the Three Gorges Reservoir [D]. Wuhan: Wuhan University, 2017.
[11] Nan L J, Chen L, Guan W, et al.Spatio-Temporal simulation analysis on water environment of typical eutrophic tributaries of Three Gorges Reservoir based on MIKE 21 [C]//4th International Conference on Green Energy, Environment and Sustainable Development, 2023:102-116.
[12] Jungsu P, Keval P, Lee W H. Recent advances in algal bloom detection and prediction technology using machine learning [J]. Science of the Total Environment, 2024,938,173546.
[13] Ma J, Duan H, Chen C, et al. Projected response of algal blooms in global lakes to future climatic and land use changes: Machine learning approaches [J]. Water Research, 2025,271,122889.
[14] Pan X, Yuan J, Yang Z, et al. Spatio-Temporal variation of cyanobacteria blooms in Taihu Lake using multiple remote sensing indices and machine learning [J]. Remote Sensing, 2024,16,(5):889.
[15] Zhang Z j, Zhang H, Jin Y, et al. Analysing the spatiotemporal variation and influencing factors of Lake Chaohu's CDOM over the past 40years using machine learning [J]. Ecohydrology, 2024,17,(3): e2639-e2639.
[16] 成再强.香溪河库湾倒灌异重流演变与水流振荡的混合效应研究 [D]. 宜昌:三峡大学, 2022. Cheng Z Q. Study on the evolution of backflow density currents and mixed effects of flow oscillations in Xiangxi Bay [D]. Yichang: China Three Gorges University, 2022.
[17] 张家璇.香溪河消落带土壤重金属的生态与健康风险评价及预测 [D]. 宜昌:三峡大学, 2024. Zhang J X. Ecological and health risk assessment and prediction of soil heavy metals in the drawdown zone of Xiangxi River [D]. Yichang: China Three Gorges University, 2024.
[18] 纪道斌,方娇,龙良红,等.三峡水库不同支流库湾蓄水期溶解氧分层特性及差异性 [J]. 环境科学, 2022,43(7):3543-3551. Ji D B, Fang J, Long L H, et al. Stratification characteristics and differences of dissolved oxygen in tributary bays of the Three Gorges Reservoir during impoundment period [J]. Environmental Science, 2022,43(7):3543-3551.
[19] 杨忠勇,钱门亮,纪道斌,等.香溪河初冬降温过程中垂向混合结构特征分析 [J]. 中国环境科学, 2021,41(6):2862-2870. Yang Z Y, Qian M L, Ji D B, et al. Characteristics of vertical mixing structure during early winter cooling in the Xiangxi River [J]. China Environmental Science, 2021,41(6):2862-2870.
[20] 龙良红,黄宇擘,徐慧,等.近20年来三峡水库水动力特性及其水环境效应研究:回顾与展望 [J]. 湖泊科学, 2023,35,(2):383-399. Long L H, Huang Y B, Xu H, et al. Hydrodynamic characteristics of the Three Gorges Reservoir and their water environmental effects over the past 20 years: review and outlook [J]. Journal of Lake Sciences, 2023,35(2):383-397.
[21] Zhang C X, Lei G C, Zhao F X, et al. Functional trait-based phytoplankton biomass and assemblage analyses in the pre-growing season for comprehensive algal bloom risk assessment [J]. Water Research, 2024,257,121755.
[22] 刘德富,郑丙辉,黄应平,等.三峡水库支流水华机理及防控技术 [Z]. 三峡大学, 2014. Liu D F, Zheng B H, Huang Y P, et al. Mechanisms and control technologies of algal blooms in tributaries of the Three Gorges Reservoir [Z]. China Three Gorges University, 2014.
[23] Yu Z Z, Wang L L. Factors influencing thermal structure in a tributary bay of Three Gorges Reservoir [J]. Journal of Hydrodynamics, 2011, 23(4):407-415.
[24] 国家环保总局.水和废水监测分析方法(第四版) [M]. 北京:中国环境科学出版社, 2002:670-672. National Environmental Protection Agency. Standard methods for the examination of Water and wastewater (4th ed) [M]. China Environmental Press, 2002:670-672.
[25] Delgado A, Vidal R, Jayme I, et al. Applying grey clustering method and pearson correlation to assess water quality [J]. International Journal of Emerging Technology and Advanced Engineering, 2022,12(8):19-29.
[26] 吴珺玥,赵二刚,郭增良,等.基于Spearman系数和TCN的光伏出力超短期多步预测 [J]. 太阳能学报, 2023,44(09):180-186. Wu J Y, Zhao E G, Guo Z L, et al. Ultra-short-term multi-step prediction of photovoltaic power output based on Spearman correlation and TCN [J]. Acta Energiae Solaris Sinica, 2023,44(9):180-186.
[27] Li W, Wang Q W, Yao J F. Distance correlation test for high- dimensional independence [J]. Bernoulli, 2024,30,(4):3165-3192.
[28] 佘星源,何术锋,林育青,等.汉江中下游多目标生态流量时空耦合计算 [J]. 中国环境科学, 2025,45(9):5093-5103. She X Y, He S F, Lin Y Q, et al. Spatiotemporal coupled calculation of multi-objective ecological flows in the middle and lower reaches of the Hanjiang River [J]. China Environmental Science, 2025,45(9):5093-5103.
[29] Zhao S B, Shi N F, Sun S B, et al. Prediction of tobacco moisture content based on improved support vector regression model [J]. Journal of Sensors, 2024,2024,(1):2167-2178.
[30] 龙良红,黄宇擘,关文海,等.水动力过程驱动的三峡水库澎溪河水华生消机制 [J]. 中国环境科学, 2025,45(6):3245-3255. Long L H, Huang Y B, Guan W H, et al. Mechanisms of algal bloom dynamics in Pengxi River of the Three Gorges Reservoir driven by hydrodynamic processes [J]. China Environmental Science, 2025,45 (6):3245-3255.
[31] 陈家炜.水源水库扬水曝气运行对藻类和有机物的影响研究 [D]. 西安:西安建筑科技大学, 2018. Chen J W. Study on the effects of pumped aeration operation on algae and organic matter in source reservoir [D]. Xi’an: Xi’an University of Architecture and Technology, 2018.
[32] Baho D L, Leu E, Pomati F, et al. Resilience of natural phytoplankton communities to pulse disturbances from micropollutant exposure and vertical mixing [J]. Environ Toxicol Chem, 2019,38,(10):2197-2208.
[33] DB44/T2261-2020 水华程度分级与监测技术规程 [S]. DB44/T2261-2020 Technical specification for classification and monitoring of algal blooms [S].
[34] Gao C, Liang Z J, Xin P L, et al. Identification of key water environmental factor contributions and spatiotemporal differential characteristics for eutrophication in Dianchi Lake [J]. Environmental Monitoring and Assessment, 2024,196,(12):1217.
[35] Jiang Y Y, Song Y Y, Liu J L, et al. Machine learning assisted precise prediction of algae bloom in large-scale water diversion engineering [J]. Desalination, 2025,610.
[36] Jokiel, Paul L J, Christopher P R, Ku'ulei S. Coral-algae metabolism and diurnal changes in the CO₂-carbonate system of bulk sea water [J]. Peerj, 2014,2,(1):378.
[37] 薛宗璞,朱伟,柏松,等.太湖微囊藻漂移—聚集规律——基于风与光共同作用的模拟 [J]. 湖泊科学, 2024,36,(6):1660-1671. Xue Z P, Zhu W, Bai S, et al. Simulation of drift–aggregation patterns of Microcystis in Lake Taihu under combined effects of wind and light. [J]. Journal of Lake Sciences, 2024,36(6):1660-1671.
[38] 罗晓春,杭鑫,曹云,等.太湖富营养化条件下影响蓝藻水华的主导气象因子 [J]. 湖泊科学, 2019,31(5):1248-1258. Luo X C, Hang X, Cao Y, et al. Dominant meteorological factors affecting cyanobacterial blooms under eutrophic conditions in Lake Taihu [J]. Journal of Lake Sciences, 2019,31(5):1248-1258.
[39] Jiang Mingshun C, Jennifer M. Modeling water quality and cyanobacteria blooms in Lake Okeechobee: II. Dynamics of diurnal cycles and impacts of cyanobacteria diel vertical migration [Z]. Ecological Modelling, 2025,505.
[40] Madyouni Haifa M, Pol B. Simulation of thermal stratification and water temperature dynamics in the Joumine reservoir (Tunisia) [Z]. Ecological Informatics, 2025,86.
[41] 张群,许旭明,陈倩.潮白河流域水库浮游动物群落季节变化特征及其驱动因素 [J]. 北京大学学报(自然科学版), 2023,59(2): 290-300. Zhang Q, Xu X, Chen Q. Seasonal variation and driving factors of zooplankton communities in reservoir of the Chaobai River Basin [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2023,59(2): 290-300.
[42] Chen Y C,Yue Y H, Wang J, et al. Microbial community dynamics and assembly mechanisms across different stages of cyanobacterial bloom in a large freshwater lake [J]. Science of the Total Environment, 2024,907,168207.