Deciphering Eutrophication-Limiting Nutrients in Lakes: A Multiscale Analysis of Chinese Waters DOI
Yong Fang, Ruting Huang, Xianyang Shi

et al.

ACS ES&T Water, Journal Year: 2024, Volume and Issue: 4(7), P. 2995 - 3006

Published: June 24, 2024

The total nitrogen/total phosphorus (TN/TP) ratio is considered a valuable indicator for evaluating the abundance of phytoplankton and eutrophic condition water body, but its effectiveness as an eutrophication at different watershed scales has not been fully explored. In this study, we collected data from 103 lakes within four major watersheds in China utilized machine learning models eXtreme Gradient Boosting (XGBoost) k-nearest neighbors (KNN) to predict TN/TP three scales. We identified notable disparities ratio, chlorophyll concentration, algal cell density across By incorporating time input variable, were able capture temporal trends which enhanced predictive accuracy fit models. optimization ratios model indicators' coefficient determination, root-mean-square error, mean absolute percentage error are 35.71 ± 25.26%, 0.43 0.17%, 1.47 1.19%, respectively. XGBoost demonstrated higher better than KNN. Our results reveal substantial impact scale on predicting eutrophication-limiting nutrients bodies.

Language: Английский

Evaluation of water environmental capacity in a northern river-reservoir continuum using environmental fluid dynamics code DOI
Qingqing Sun,

Hengyang Ren,

Mohd Aadil Bhat

et al.

The Science of The Total Environment, Journal Year: 2025, Volume and Issue: 959, P. 178274 - 178274

Published: Jan. 1, 2025

Language: Английский

Citations

0
Quantile regression Reveals phosphorous overwhelms nitrogen in controlling high chlorophyll-a concentration in freshwater lakes DOI

Haojie Han,

Xing Yan, Xiaohan Li

et al.

Journal of Hydrology, Journal Year: 2025, Volume and Issue: unknown, P. 132845 - 132845

Published: Feb. 1, 2025

Language: Английский

Citations

0
A new method for predicting chlorophyll-a concentration in a reservoir: Coupling EFDC hydrodynamic and water quality model with ConvLSTM-MLP network DOI

Haobin Meng,

Jing Zhang, Yao‐Feng Chang

et al.

Journal of Hydrology, Journal Year: 2025, Volume and Issue: unknown, P. 133485 - 133485

Published: May 1, 2025

Language: Английский

Citations

0
Predication of Water Pollution Peak Concentrations by Hybrid BP Artificial Neural Network Coupled with Genetic Algorithm DOI Creative Commons
Yanbo Lu, Tong Li, Deng Ying

et al.

Applied Artificial Intelligence, Journal Year: 2024, Volume and Issue: 38(1)

Published: April 13, 2024

Water pollutions can severely affect water environment, causing quality degradation and threatening aquatic wildlife. Deemed as guideline for maximum environmental impact assessment, pollution peak concentration (WPPC) has been intensively studied to organize effective countermeasures. In this study, a back propagation artificial neural network (BPANN) coupled with genetic algorithm (GA) was constructed predict concentrations. Compared BPANN, multiple linear regressions model (MLRM) step-wise (SMLRM), GA-BPANN showed superior accuracy in both simulating predicting concentrations (R2 = 0.93 0.67 0.69 respectively). 12 cases, model's mean absolute relative error (MARE) ranges from 0.0 0.58, averaged at 0.09, significantly lower than MLRM SMLRM (MARE 0.29, 0.45 0.48). Further analysis revealed that be used an efficient tool simulation early warning prediction.

Language: Английский

Citations

2
Impacts of hydrodynamic disturbance on black blooms: An in-situ study in Lake Taihu DOI
Donghao Wu, Yijie Yin,

Aichun Shen

et al.

Journal of Hydrology, Journal Year: 2024, Volume and Issue: 641, P. 131794 - 131794

Published: Aug. 13, 2024

Language: Английский

Citations

2
Deciphering Eutrophication-Limiting Nutrients in Lakes: A Multiscale Analysis of Chinese Waters DOI
Yong Fang, Ruting Huang, Xianyang Shi

et al.

ACS ES&T Water, Journal Year: 2024, Volume and Issue: 4(7), P. 2995 - 3006

Published: June 24, 2024

The total nitrogen/total phosphorus (TN/TP) ratio is considered a valuable indicator for evaluating the abundance of phytoplankton and eutrophic condition water body, but its effectiveness as an eutrophication at different watershed scales has not been fully explored. In this study, we collected data from 103 lakes within four major watersheds in China utilized machine learning models eXtreme Gradient Boosting (XGBoost) k-nearest neighbors (KNN) to predict TN/TP three scales. We identified notable disparities ratio, chlorophyll concentration, algal cell density across By incorporating time input variable, were able capture temporal trends which enhanced predictive accuracy fit models. optimization ratios model indicators' coefficient determination, root-mean-square error, mean absolute percentage error are 35.71 ± 25.26%, 0.43 0.17%, 1.47 1.19%, respectively. XGBoost demonstrated higher better than KNN. Our results reveal substantial impact scale on predicting eutrophication-limiting nutrients bodies.

Language: Английский

Citations

0