Data-driven models for forecasting algal biomass in a large and deep reservoir DOI
Yuan Li,

Kun Shi,

Mengyuan Zhu

et al.

Water Research, Journal Year: 2024, Volume and Issue: 270, P. 122832 - 122832

Published: Nov. 22, 2024

Language: Английский

Exploring spatiotemporal patterns of algal cell density in lake Dianchi with explainable machine learning DOI
Yiwen Tao, Jingli Ren, Huaiping Zhu

et al.

Environmental Pollution, Journal Year: 2024, Volume and Issue: 356, P. 124395 - 124395

Published: June 18, 2024

Language: Английский

Citations

4
Cyanobacteria hot spot detection integrating remote sensing data with convolutional and Kolmogorov-Arnold networks DOI Creative Commons

B. A. Zambrano-Luna,

Russell Milne, Hao Wang

et al.

The Science of The Total Environment, Journal Year: 2025, Volume and Issue: 960, P. 178271 - 178271

Published: Jan. 1, 2025

Prompt and accurate monitoring of cyanobacterial blooms is essential for public health management understanding aquatic ecosystem dynamics. Remote sensing, in particular satellite observations, presents a good alternative continuous monitoring. This study employs multispectral images from the Sentinel-2 constellation alongside ERA5-Land to enable broad-scale data acquisition. A simple deep convolutional neural network (CNN) architecture was proposed analyze cyanobacteria (CB) concentration dynamics Pigeon Lake, Canada, over five years. The model achieved an R2 value 0.81 RMSE score 0.03 training set 0.15 testing set, demonstrating high predictive accuracy. Using Local Getis-Ord statistic, we identified analyzed trends hot cold spots under null hypothesis that such are randomly distributed, observing changes their distribution median CB time. Additionally, Kolmogorov-Arnold Network (KAN) dense networks (NN) with single hidden layer were trained classify sections lake shoreline into no using Dynamic World dataset within 500m radius lake. KAN recall metric 0.83 detecting spots.

Language: Английский

Citations

0
State Estimation of Lithium-Ion Batteries via Physics-Machine Learning Combined Methods: A Methodological Review and Future Perspectives DOI
Hanqing Yu, Hongcai Zhang, Zhengjie Zhang

et al.

eTransportation, Journal Year: 2025, Volume and Issue: unknown, P. 100420 - 100420

Published: April 1, 2025

Language: Английский

Citations

0
Comparing the performance of 10 machine learning models in predicting Chlorophyll a in western Lake Erie DOI
Yang Song, Chunqi Shen, Hong Yi

et al.

Journal of Environmental Management, Journal Year: 2025, Volume and Issue: 380, P. 125007 - 125007

Published: March 17, 2025

Language: Английский

Citations

0
Vertical characteristics of bacterial community and the interaction of dissolved organic matter in sediments of a shallow lake, China DOI

Xihuan Wang,

Weibo Zhang,

Ang Liu

et al.

Journal of environmental chemical engineering, Journal Year: 2025, Volume and Issue: unknown, P. 116415 - 116415

Published: April 1, 2025

Language: Английский

Citations

0
Seasonal Monitoring Method for TN and TP Based on Airborne Hyperspectral Remote Sensing Images DOI Creative Commons
Lei Dong,

Cailan Gong,

Xinhui Wang

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(9), P. 1614 - 1614

Published: April 30, 2024

Airborne sensing images harness the combined advantages of hyperspectral and high spatial resolution, offering precise monitoring methods for local-scale water quality parameters in small bodies. This study employs airborne remote image data to explore estimation total nitrogen (TN) phosphorus (TP) concentrations Lake Dianshan, Yuandang, as well its main inflow outflow rivers. Our findings reveal following: (1) Spectral bands between 700 750 nm show highest correlation with TN TP during summer autumn seasons. reflectance exhibit greater sensitivity compared winter spring (2) Seasonal models developed using Catboost method demonstrate significantly higher accuracy than other machine learning (ML) models. On test set, root mean square errors (RMSEs) are 0.6 mg/L 0.05 concentrations, average absolute percentage (MAPEs) 23.77% 25.14%, respectively. (3) Spatial distribution maps retrieved indicate their dependence on exogenous inputs close association algal blooms. Higher observed near inlet (Jishui Port), reductions outlet (Lanlu particularly concentration. Areas intense blooms shorelines generally concentrations. offers valuable insights processing bodies provides reliable techniques lake management.

Language: Английский

Citations

3
A novel framework for quantitative attribution of particulate matter pollution mitigation to natural and socioeconomic drivers DOI
Hao Cui, Jian Li,

Yutong Sun

et al.

The Science of The Total Environment, Journal Year: 2024, Volume and Issue: 926, P. 171910 - 171910

Published: March 24, 2024

Language: Английский

Citations

2
Identification of key water environmental factor contributions and spatiotemporal differential characteristics for eutrophication in Dianchi Lake DOI
Chao Gao, Zhijie Liang, P Xin

et al.

Environmental Monitoring and Assessment, Journal Year: 2024, Volume and Issue: 196(12)

Published: Nov. 19, 2024

Language: Английский

Citations

2
Data-driven models for forecasting algal biomass in a large and deep reservoir DOI
Yuan Li,

Kun Shi,

Mengyuan Zhu

et al.

Water Research, Journal Year: 2024, Volume and Issue: 270, P. 122832 - 122832

Published: Nov. 22, 2024

Language: Английский

Citations

1