Application of Machine Learning for eutrophication analysis and algal bloom prediction in an urban river: A 10-year study of the Han River, South Korea (2024)

Ly, Q. V., Nguyen, X. C., Lê, N. C., Truong, T. D., Hoang, T. H. T., Park, T. J., Maqbool, T., Pyo, J. C., Cho, K. H., Lee, K. S. (2021). Application of Machine Learning for eutrophication analysis and algal bloom prediction in an urban river: A 10-year study of the Han River, South Korea. Science of the Total Environment, 797, Article 149040. https://doi.org/10.1016/j.scitotenv.2021.149040

Ly, Quang Viet ; Nguyen, Xuan Cuong ; Lê, Ngoc C. et al. / Application of Machine Learning for eutrophication analysis and algal bloom prediction in an urban river : A 10-year study of the Han River, South Korea. In: Science of the Total Environment. 2021 ; Vol. 797.

@article{e4bdb43c41354f5ca3d1731e3496a984,

title = "Application of Machine Learning for eutrophication analysis and algal bloom prediction in an urban river: A 10-year study of the Han River, South Korea",

abstract = "The increasing release of nutrients to aquatic environments has led to great concern regarding eutrophication and the risk of unwanted algal blooms. Based on observational data of 20 water quality parameters measured on a monthly basis at 40 stations from 2011 to 2020, this study applied different Machine Learning (ML) algorithms to suggest the best option for algal bloom prediction in the Han River, a large river in South Korea. Eight different ML algorithms were categorized into several groups of statistical learning, regression family, and deep learning, and were then compared for their suitability to predict the chlorophyll-derived trophic index (TSI-Chla). ML algorithms helped identify the most important water quality parameters contributing to algal bloom prediction. The ML results confirmed that eutrophication and algal proliferation were governed by the complex interplay between nutrients (nitrogen and phosphorus), organic contaminants, and environmental factors. Of the models tested, the adaptive neuro-fuzzy inference system (ANFIS) exhibited the best performance owing to its consistent and outperforming prediction both quantitatively (i.e., via regression) and qualitatively (i.e., via classification), which was evidenced by the lowest value of mean absolute error (MAE) of 0.09, and the highest F1-score, Recall and Precision of 0.97, 0.98 and 0.96, respectively. In a further step, a representative web application was constructed to assist common users to predict the trophic status of the Han River. This study demonstrated that ML techniques are not only promising for highly accurate water quality modeling of urban rivers, but also reduce time and labor intensity for experiments, which decreases the number of monitored water quality parameters, providing further insights into the driving factors of water quality deterioration. They ultimately help devise proactive strategies for sustainable water management.",

keywords = "Complex watershed, Deep Learning, Fuzzy System, Statistical Learning, Trophic Status, Water pollution",

author = "Ly, {Quang Viet} and Nguyen, {Xuan Cuong} and L{\^e}, {Ngoc C.} and Truong, {Tien Dung} and Hoang, {Thu Huong T.} and Park, {Tae Jun} and Tahir Maqbool and Pyo, {Jong Cheol} and Cho, {Kyung Hwa} and Lee, {Kwang Sik} and Jin Hur",

note = "Publisher Copyright: {\textcopyright} 2021 Elsevier B.V.",

year = "2021",

month = nov,

day = "25",

doi = "10.1016/j.scitotenv.2021.149040",

language = "English",

volume = "797",

journal = "Science of the Total Environment",

issn = "0048-9697",

publisher = "Elsevier",

}

Ly, QV, Nguyen, XC, Lê, NC, Truong, TD, Hoang, THT, Park, TJ, Maqbool, T, Pyo, JC, Cho, KH, Lee, KS 2021, 'Application of Machine Learning for eutrophication analysis and algal bloom prediction in an urban river: A 10-year study of the Han River, South Korea', Science of the Total Environment, vol. 797, 149040. https://doi.org/10.1016/j.scitotenv.2021.149040

Application of Machine Learning for eutrophication analysis and algal bloom prediction in an urban river: A 10-year study of the Han River, South Korea. / Ly, Quang Viet; Nguyen, Xuan Cuong; Lê, Ngoc C. et al.
In: Science of the Total Environment, Vol. 797, 149040, 25.11.2021.

Research output: Contribution to journal › Article › peer-review

TY - JOUR

T1 - Application of Machine Learning for eutrophication analysis and algal bloom prediction in an urban river

T2 - A 10-year study of the Han River, South Korea

AU - Ly, Quang Viet

AU - Nguyen, Xuan Cuong

AU - Lê, Ngoc C.

AU - Truong, Tien Dung

AU - Hoang, Thu Huong T.

AU - Park, Tae Jun

AU - Maqbool, Tahir

AU - Pyo, Jong Cheol

AU - Cho, Kyung Hwa

AU - Lee, Kwang Sik

AU - Hur, Jin

N1 - Publisher Copyright:© 2021 Elsevier B.V.

PY - 2021/11/25

Y1 - 2021/11/25

N2 - The increasing release of nutrients to aquatic environments has led to great concern regarding eutrophication and the risk of unwanted algal blooms. Based on observational data of 20 water quality parameters measured on a monthly basis at 40 stations from 2011 to 2020, this study applied different Machine Learning (ML) algorithms to suggest the best option for algal bloom prediction in the Han River, a large river in South Korea. Eight different ML algorithms were categorized into several groups of statistical learning, regression family, and deep learning, and were then compared for their suitability to predict the chlorophyll-derived trophic index (TSI-Chla). ML algorithms helped identify the most important water quality parameters contributing to algal bloom prediction. The ML results confirmed that eutrophication and algal proliferation were governed by the complex interplay between nutrients (nitrogen and phosphorus), organic contaminants, and environmental factors. Of the models tested, the adaptive neuro-fuzzy inference system (ANFIS) exhibited the best performance owing to its consistent and outperforming prediction both quantitatively (i.e., via regression) and qualitatively (i.e., via classification), which was evidenced by the lowest value of mean absolute error (MAE) of 0.09, and the highest F1-score, Recall and Precision of 0.97, 0.98 and 0.96, respectively. In a further step, a representative web application was constructed to assist common users to predict the trophic status of the Han River. This study demonstrated that ML techniques are not only promising for highly accurate water quality modeling of urban rivers, but also reduce time and labor intensity for experiments, which decreases the number of monitored water quality parameters, providing further insights into the driving factors of water quality deterioration. They ultimately help devise proactive strategies for sustainable water management.

AB - The increasing release of nutrients to aquatic environments has led to great concern regarding eutrophication and the risk of unwanted algal blooms. Based on observational data of 20 water quality parameters measured on a monthly basis at 40 stations from 2011 to 2020, this study applied different Machine Learning (ML) algorithms to suggest the best option for algal bloom prediction in the Han River, a large river in South Korea. Eight different ML algorithms were categorized into several groups of statistical learning, regression family, and deep learning, and were then compared for their suitability to predict the chlorophyll-derived trophic index (TSI-Chla). ML algorithms helped identify the most important water quality parameters contributing to algal bloom prediction. The ML results confirmed that eutrophication and algal proliferation were governed by the complex interplay between nutrients (nitrogen and phosphorus), organic contaminants, and environmental factors. Of the models tested, the adaptive neuro-fuzzy inference system (ANFIS) exhibited the best performance owing to its consistent and outperforming prediction both quantitatively (i.e., via regression) and qualitatively (i.e., via classification), which was evidenced by the lowest value of mean absolute error (MAE) of 0.09, and the highest F1-score, Recall and Precision of 0.97, 0.98 and 0.96, respectively. In a further step, a representative web application was constructed to assist common users to predict the trophic status of the Han River. This study demonstrated that ML techniques are not only promising for highly accurate water quality modeling of urban rivers, but also reduce time and labor intensity for experiments, which decreases the number of monitored water quality parameters, providing further insights into the driving factors of water quality deterioration. They ultimately help devise proactive strategies for sustainable water management.

KW - Complex watershed

KW - Deep Learning

KW - Fuzzy System

KW - Statistical Learning

KW - Trophic Status

KW - Water pollution

UR - http://www.scopus.com/inward/record.url?scp=85111028118&partnerID=8YFLogxK

U2 - 10.1016/j.scitotenv.2021.149040

DO - 10.1016/j.scitotenv.2021.149040

M3 - Article

C2 - 34311376

AN - SCOPUS:85111028118

SN - 0048-9697

VL - 797

JO - Science of the Total Environment

JF - Science of the Total Environment

M1 - 149040

ER -

Ly QV, Nguyen XC, Lê NC, Truong TD, Hoang THT, Park TJ et al. Application of Machine Learning for eutrophication analysis and algal bloom prediction in an urban river: A 10-year study of the Han River, South Korea. Science of the Total Environment. 2021 Nov 25;797:149040. doi: 10.1016/j.scitotenv.2021.149040