Assessment of the Impact of Meteorological Variables on Lake Water Temperature Using the SHapley Additive exPlanations Method DOI Open Access
Teerachai Amnuaylojaroen, Mariusz Ptak, Mariusz Sojka

et al.

Water, Journal Year: 2024, Volume and Issue: 16(22), P. 3296 - 3296

Published: Nov. 17, 2024

The water temperature of lakes is one their fundamental characteristics, upon which numerous processes in lake ecosystems depend. Therefore, it crucial to have detailed knowledge about its changes and the factors driving those changes. In this article, a neural network model was developed examine impact meteorological variables on by integrating daily data with interday variations. Neural networks were selected for ability complex, non-linear relationships between variables, often found environmental data. Among various architectures, Artificial Network (ANN) chosen due superior performance, achieving an R2 0.999, MSE 0.0352, MAE 0.1511 validation tests. These results significantly outperformed other models such as Multi-Layer Perceptrons (MLPs), Recurrent Networks (RNNs), Long Short-Term Memory (LSTM). Two (Lake Mikołajskie Sławskie) differing morphometric parameters located different physico-geographical regions Poland analyzed. Performance metrics both show that capable providing accurate forecasts, effectively capturing primary patterns data, generalizing well new datasets. Key cases turned out be air temperature, while response wind cloud cover exhibited diverse result features locations measurement sites.

Language: Английский

Fate of a toxic Microcystis aeruginosa bloom introduced into a subtropical estuary from a flow-managed canal and management implications DOI Creative Commons
Edward J. Phli̇ps,

Susan Badylak,

Eric C. Milbrandt

et al.

Journal of Environmental Management, Journal Year: 2025, Volume and Issue: 375, P. 124362 - 124362

Published: Feb. 1, 2025

The Caloosahatchee Estuary in southwest Florida, USA, is regularly subject to the introduction of toxic Microcystis aeruginosa blooms, often originating from eutrophic Lake Okeechobee via C-43 Canal. focus this study was determine responses one these introduced blooms progressively elevated salinity levels as bloom water mass moved through estuary. In upper estuary, salinities were freshwater, and surface large colonies M. observed, along with peak microcystin toxin concentrations up 107 μg L-1, all particulate fraction. mid-estuary, increased 2-6, again 259 however, significant extracellular also observed (i.e., 17.8 L-1), suggesting a level osmotic stress on aeruginosa. lower ranged 6 25 very few viable but 0.5 L-1) present throughout column. It noteworthy that average total column + extracellular) remained constant movement during its transit revealing negligible rate degradation ten-day transit. results provide insights into changes distribution gradient, which has implications for management risks ecosystem human health, how may be affected by releases three control structures Discharge rates play major roles Canal-Caloosahatchee ecosystem. potential discharge regulation are discussed perspectives allochthonous autochthonous origin.

Language: Английский

Citations

2
Satellite remote sensing of turbidity in Lake Xingkai using eight years of OLCI observations DOI
Li Jian, Yang Li,

Kaishan Song

et al.

Journal of Environmental Management, Journal Year: 2025, Volume and Issue: 377, P. 124636 - 124636

Published: Feb. 26, 2025

Language: Английский

Citations

0
A review of machine learning and internet-of-things on the water quality assessment: methods, applications and future trends DOI Creative Commons

Gangani Dharmarathne,

A.M.S.R. Abekoon,

Madhusha Bogahawaththa

et al.

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 105182 - 105182

Published: May 1, 2025

Language: Английский

Citations

0
Assessment of the Impact of Meteorological Variables on Lake Water Temperature Using the SHapley Additive exPlanations Method DOI Open Access
Teerachai Amnuaylojaroen, Mariusz Ptak, Mariusz Sojka

et al.

Water, Journal Year: 2024, Volume and Issue: 16(22), P. 3296 - 3296

Published: Nov. 17, 2024

The water temperature of lakes is one their fundamental characteristics, upon which numerous processes in lake ecosystems depend. Therefore, it crucial to have detailed knowledge about its changes and the factors driving those changes. In this article, a neural network model was developed examine impact meteorological variables on by integrating daily data with interday variations. Neural networks were selected for ability complex, non-linear relationships between variables, often found environmental data. Among various architectures, Artificial Network (ANN) chosen due superior performance, achieving an R2 0.999, MSE 0.0352, MAE 0.1511 validation tests. These results significantly outperformed other models such as Multi-Layer Perceptrons (MLPs), Recurrent Networks (RNNs), Long Short-Term Memory (LSTM). Two (Lake Mikołajskie Sławskie) differing morphometric parameters located different physico-geographical regions Poland analyzed. Performance metrics both show that capable providing accurate forecasts, effectively capturing primary patterns data, generalizing well new datasets. Key cases turned out be air temperature, while response wind cloud cover exhibited diverse result features locations measurement sites.

Language: Английский

Citations

0