Source identification and prediction of nitrogen and phosphorus pollution of Lake Taihu by an ensemble machine learning technique

Highlight

● A machine learning model was used to identify lake nutrient pollution sources.

● XGBoost model showed the best performance for lake water quality prediction.

● Model feature size was reduced by screening the key features with the MIC method.

● TN and TP concentrations of Lake Taihu are mainly affected by endogenous sources.

● Next-month lake TN and TP concentrations were predicted accurately.

Abstract

Effective control of lake eutrophication necessitates a full understanding of the complicated nitrogen and phosphorus pollution sources, for which mathematical modeling is commonly adopted. In contrast to the conventional knowledge-based models that usually perform poorly due to insufficient knowledge of pollutant geochemical cycling, we employed an ensemble machine learning (ML) model to identify the key nitrogen and phosphorus sources of lakes. Six ML models were developed based on 13 years of historical data of Lake Taihu’s water quality, environmental input, and meteorological conditions, among which the XGBoost model stood out as the best model for total nitrogen (TN) and total phosphorus (TP) prediction. The results suggest that the lake TN is mainly affected by the endogenous load and inflow river water quality, while the lake TP is predominantly from endogenous sources. The prediction of the lake TN and TP concentration changes in response to these key feature variations suggests that endogenous source control is a highly desirable option for lake eutrophication control. Finally, one-month-ahead prediction of lake TN and TP concentrations (R² of 0.85 and 0.95, respectively) was achieved based on this model with sliding time window lengths of 9 and 6 months, respectively. Our work demonstrates the great potential of using ensemble ML models for lake pollution source tracking and prediction, which may provide valuable references for early warning and rational control of lake eutrophication.

Keywords

Eutrophication / Machine learning / Water quality / Nutrients / Prediction

参考文献

[1] Cao H, Han L, Li L. (2022). A deep learning method for cyanobacterial harmful algae blooms prediction in Taihu Lake, China. Harmful Algae, 113: 102189

[2] Chen Q, Ni Z, Wang S, Guo Y, Liu S. (2020). Climate change and human activities reduced the burial efficiency of nitrogen and phosphorus in sediment from Dianchi Lake, China. Journal of Cleaner Production, 274: 122839

[3] Chen T, Guestrin C. (2016). Xgboost: a scalable tree boosting system. In: Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: Association for Computing Machinery, 785–794

[4] Dhaliwal S S, Nahid A A, Abbas R. (2018). Effective intrusion detection system using XGBoost. Information, 9(7): 149

[5] Dong Y, Xu L, Yang Z, Zheng H, Chen L. (2020). Aggravation of reactive nitrogen flow driven by human production and consumption in Guangzhou City China. Nature Communications, 11(1): 1209

[6] Fabian Pedregosa G V, Alexandre G, Vincent M, Bertrand T, Olivier G, Mathieu B, Peter P, Ron W, Vincent D, Jake V. . (2011). Scikit-learn: machine learning in python. Journal of Machine Learning Research, 12(85): 2825–2830

[7] Friedman J H. (2001). Greedy function approximation: a gradient boosting machine. Annals of Statistics, 29(5): 1189–1232

[8] García Nieto P J, García-Gonzalo E, Alonso Fernández J R, Díaz Muñiz C. (2019). Water eutrophication assessment relied on various machine learning techniques: a case study in the Englishmen Lake (Northern Spain). Ecological Modelling, 404: 91–102

[9] Gibbons K J, Bridgeman T B. (2020). Effect of temperature on phosphorus flux from anoxic western Lake Erie sediments. Water Research, 182: 116022

[10] Ho J C, Michalak A M, Pahlevan N. (2019). Widespread global increase in intense lake phytoplankton blooms since the 1980s. Nature, 574(7780): 667–670

[11] Huang J, Zhang Y, Arhonditsis G B, Gao J, Chen Q, Peng J. (2020). The magnitude and drivers of harmful algal blooms in China’s lakes and reservoirs: a national-scale characterization. Water Research, 181: 115902

[12] Huang Y, Chen J, Duan Q, Feng Y, Luo R, Wang W, Liu F, Bi S, Lee J. (2022). A fast antibiotic detection method for simplified pretreatment through spectra-based machine learning. Frontiers of Environmental Science & Engineering, 16(3): 38

[13] Janssen A B G, de Jager V C L, Janse J H, Kong X, Liu S, Ye Q, Mooij W M. (2017). Spatial identification of critical nutrient loads of large shallow lakes: implications for Lake Taihu (China). Water Research, 119: 276–287

[14] Joshi S R, Kukkadapu R K, Burdige D J, Bowden M E, Sparks D L, Jaisi D P. (2015). Organic matter remineralization predominates phosphorus cycling in the mid-Bay sediments in the Chesapeake Bay. Environmental Science & Technology, 49(10): 5887–5896

[15] Kim K. (2016). A hybrid classification algorithm by subspace partitioning through semi-supervised decision tree. Pattern Recognition, 60: 157–163

[16] Kong M, Chao J, Zhuang W, Wang P, Wang C, Hou J, Wu Z, Wang L, Gao G, Wang Y. (2018). Spatial and temporal distribution of particulate phosphorus and their correlation with environmental factors in a shallow eutrophic Chinese lake (Lake Taihu). International Journal of Environmental Research and Public Health, 15(11): 2355

[17] Lake Taihu Basin Authority. (2021). Taihu basin and southeast rivers water resources bulletin (2020). Shanghai: Lake Taihu Basin Authority, 1–24

[18] Li X, Sha J, Wang Z L. (2018). Application of feature selection and regression models for chlorophyll-a prediction in a shallow lake. Environmental Science and Pollution Research International, 25(20): 19488–19498

[19] Li Y, Ni L, Guo Y, Zhao X, Dong Y, Cheng Y. (2022). Challenges and Opportunities to Treat Water Pollution. Paths to Clean Water Under Rapid Changing Environment in China. Singapore: Springer, 13–42

[20] Lima Neto I E, Medeiros P H A, Costa A C, Wiegand M C, Barros A R M, Barros M U G. (2022). Assessment of phosphorus loading dynamics in a tropical reservoir with high seasonal water level changes. Science of the Total Environment, 815: 152875

[21] Liu Y, Luo H, Zhao B, Zhao X, Han Z. (2018). Short-Term Power Load Forecasting Based on Clustering and XGBoost Method. Piscataway: IEEE, 536–539

[22] Lu H, Yang L, Fan Y, Qian X, Liu T (2022). Novel simulation of aqueous total nitrogen and phosphorus concentrations in Taihu Lake with machine learning. Environmental Research, 204(Pt B): 111940

[23] Ministry of Ecology and Environment of the People’s Republic of China (2022). Bulletin on the State of China’s Ecological Environment in 2021. Beijing: Ministry of Ecology and Environment of the People’s Republic of China

[24] MosaffaHSadeghi MMallakpourIJahromiM NPourghasemi H R (2022). Application of machine learning algorithms in hydrology. In: Pourghasemi H R, ed. Computers in Earth and Environmental Sciences. Amsterdam: Elsevier

[25] Newhart K B, Goldman-Torres J E, Freedman D E, Wisdom K B, Hering A S, Cath T Y. (2021). Prediction of peracetic acid disinfection performance for secondary municipal wastewater treatment using artificial neural networks. ACS ES&T Water, 1(2): 328–338

[26] Qin B, Paerl H W, Brookes J D, Liu J, Jeppesen E, Zhu G, Zhang Y, Xu H, Shi K, Deng J. (2019). Why Lake Taihu continues to be plagued with cyanobacterial blooms through 10 years (2007–2017) efforts. Science Bulletin, 64(6): 354–356

[27] QinBXuP WuQLuoL ZhangY (2007). Environmental issues of Lake Taihu, China. In: Qin B, Liu Z, Havens K, eds. Eutrophication of Shallow Lakes with Special Reference to Lake Taihu, China. Dordrecht: Springer Netherlands

[28] Reddy G T, Reddy M P K, Lakshmanna K, Kaluri R, Rajput D S, Srivastava G, Baker K. (2020). Analysis of dimensionality reduction techniques on big data. IEEE Access, 8: 54776–54788

[29] Reshef D N, Reshef Y A, Finucane H K, Grossman S R, McVean G, Turnbaugh P J, Lander E S, Mitzenmacher M, Sabeti P C. (2011). Detecting novel associations in large data sets. Science, 334(6062): 1518–1524

[30] Sheridan R P, Wang W M, Liaw A, Ma J, Gifford E M. (2016). Extreme gradient boosting as a method for quantitative structure–activity relationships. Journal of Chemical Information and Modeling, 56(12): 2353–2360

[31] Siade A J, Bostick B C, Cirpka O A, Prommer H. (2021). Unraveling biogeochemical complexity through better integration of experiments and modeling. Environmental Science. Processes & Impacts, 23(12): 1825–1833

[32] Song K, Zhu S, Lu Y, Dao G, Wu Y, Chen Z, Wang S, Liu J, Zhou W, Hu H Y. (2022). Modelling the thresholds of nitrogen/phosphorus concentration and hydraulic retention time for bloom control in reclaimed water landscape. Frontiers of Environmental Science & Engineering, 16(10): 129

[33] Sundar S, Rajagopal M C, Zhao H, Kuntumalla G, Meng Y, Chang H C, Shao C, Ferreira P, Miljkovic N, Sinha S. . (2020). Fouling modeling and prediction approach for heat exchangers using deep learning. International Journal of Heat and Mass Transfer, 159: 120112

[34] Tong Y D, Xu X W, Qi M, Sun n J J, Zhang Y Y, Zhang W, Wang M Z, Wang X J, Zhang Y. (2021). Lake warming intensifies the seasonal pattern of internal nutrient cycling in the eutrophic lake and potential impacts on algal blooms. Water Research, 188: 116570

[35] Tong Y D, Xu X W, Zhang S L, Shi L M, Zhang X Y, Wang M Z, Qi M, Chen C, Wen Y T, Zhao Y. . (2019). Establishment of season-specific nutrient thresholds and analyses of the effects of nutrient management in eutrophic lakes through statistical machine learning. Journal of Hydrology, 578: 124079

[36] Tourian M, Tarpanelli A, Elmi O, Qin T, Brocca L, Moramarco T, Sneeuw N. (2016). Spatiotemporal densification of river water level time series by multimission satellite altimetry. Water Resources Research, 52(2): 1140–1159

[37] Wang L, Wang Y, Cheng H, Cheng J. (2018a). Estimation of the nutrient and chlorophyll a reference conditions in Taihu Lake based on a new method with Extreme–Markov Theory. International Journal of Environmental Research and Public Health, 15(11): 2372

[38] Wang M, Ma L, Strokal M, Ma W, Liu X, Kroeze C. (2018b). Hotspots for nitrogen and phosphorus losses from food production in China: a county-scale analysis. Environmental Science & Technology, 52(10): 5782–5791

[39] Wang M, Xu X, Wu Z, Zhang X, Sun P, Wen Y, Wang Z, Lu X, Zhang W, Wang X. . (2019). Seasonal pattern of nutrient limitation in a eutrophic lake and quantitative analysis of the impacts from internal nutrient cycling. Environmental Science & Technology, 53(23): 13675–13686

[40] Wang S, Li J, Zhang B, Spyrakos E, Tyler A N, Shen Q, Zhang F, Kuster T, Lehmann M K, Wu Y, Peng D. (2018c). Trophic state assessment of global inland waters using a MODIS-derived Forel-Ule index. Remote Sensing of Environment, 217: 444–460

[41] Wu Z, Liu Y, Liang Z, Wu S, Guo H. (2017). Internal cycling, not external loading, decides the nutrient limitation in eutrophic lake: A dynamic model with temporal Bayesian hierarchical inference. Water Research, 116: 231–240

[42] Xia J, Zeng J. (2022). Environmental factors assisted the evaluation of entropy water quality indices with efficient machine learning technique. Water Resources Management, 36(6): 2045–2060

[43] XiongJLin CCaoZHuMXueK ChenXMa R (2022). Development of remote sensing algorithm for total phosphorus concentration in eutrophic lakes: conventional or machine learning? Water Research, 215: 118213

[44] Yakovleva E, Hopke P K, Wallace L. (1999). Receptor modeling assessment of particle total exposure assessment methodology data. Environmental Science & Technology, 33(20): 3645–3652

[45] YangCLi JYinH (2022a). Phosphorus internal loading and sediment diagenesis in a large eutrophic lake (Lake Chaohu, China). Environmental Pollution, 292(Pt B): 118471

[46] Yang C, Yang P, Geng J, Yin H, Chen K. (2020). Sediment internal nutrient loading in the most polluted area of a shallow eutrophic lake (Lake Chaohu, China) and its contribution to lake eutrophication. Environmental Pollution, 262: 114292

[47] Yang K, Yu Z, Luo Y, Yang Y, Zhao L, Zhou X. (2018). Spatial and temporal variations in the relationship between lake water surface temperatures and water quality: a case study of Dianchi Lake. Science of the Total Environment, 624: 859–871

[48] Yang N, Wang L, Lin L, Li Y, Zhang W, Niu L, Zhang H, Wang L. (2022b). Pelagic-benthic coupling of the microbial food web modifies nutrient cycles along a cascade-dammed river. Frontiers of Environmental Science & Engineering, 16(4): 50

[49] Yu Q, Wang F, Yan W, Zhang F, Lv S, Li Y. (2018). Carbon and nitrogen burial and response to climate change and anthropogenic disturbance in Chaohu Lake, China. International Journal of Environmental Research and Public Health, 15(12): 2734

[50] Yuan F, Wei Y D, Gao J, Chen W. (2019). Water crisis, environmental regulations and location dynamics of pollution-intensive industries in China: a study of the Taihu Lake watershed. Journal of Cleaner Production, 216: 311–322

[51] Yuan H, Wang H, Zhou Y, Jia B, Yu J, Cai Y, Yang Z, Liu E, Li Q, Yin H. (2021). Water-level fluctuations regulate the availability and diffusion kinetics process of phosphorus at lake water-sediment interface. Water Research, 200: 117258

[52] Zhang Q, Li Z, Zhu L, Zhang F, Sekerinski E, Han J C, Zhou Y. (2021). Real-time prediction of river chloride concentration using ensemble learning. Environmental Pollution, 291: 118116

[53] Zhang X, Li B, Xu H, Wells M, Tefsen B, Qin B. (2019). Effect of micronutrients on algae in different regions of Taihu, a large, spatially diverse, hypereutrophic lake. Water Research, 151: 500–514

[54] Zhang Y, Luo P, Zhao S, Kang S, Wang P, Zhou M, Lyu J. (2020). Control and remediation methods for eutrophic lakes in the past 30 years. Water Science and Technology, 81(6): 1099–1113

[55] Zhou Z, Lin C, Li S, Liu S, Li F, Yuan B. (2022). Four kinds of capping materials for controlling phosphorus and nitrogen release from contaminated sediment using a static simulation experiment. Frontiers of Environmental Science & Engineering, 16(3): 29

[56] Zhu Q, Gu A, Li D, Zhang T, Xiang L. (2021). Online recognition of drainage type based on UV-vis spectra and derivative neural network algorithm. Frontiers of Environmental Science & Engineering, 15(6): 136

[57] Zou L, Li H, Wang S, Zheng K, Wang Y, Du G, Li J. (2019). Characteristic and correlation analysis of influent and energy consumption of wastewater treatment plants in Taihu Basin. Frontiers of Environmental Science & Engineering, 13(6): 83

Acknowledgements

The authors thank the National Natural Science Foundation of China (Nos. 52192681, U21A20160, and 51821006) for supporting this work. We thank Professor Boqiang Qin from the Nanjing Institute of Geography and Limnology, Chinese Academy of Sciences for providing monitoring data from the Lake Taihu Water Quality Monitoring Station (China).

Data Accessibility Statement

By repository: The code applied in this study are openly available in GitHub at the website of github.com/huyirong-97/FESE_TN-TP-prediction-code. The data used in this study were obtained from other research institutions and are not allowed for disclosure. So, we don’t have the right to share it to the public database.

Electronic Supplementary Material

Supplementary material is available in the online version of this article at https://doi.org/10.1007/s11783-023-1655-7 and is accessible for authorized users.

版权

2023 Higher Education Press