Advancing freshwater ecological forecasts: Harmful algal blooms in Lake Erie

Scavia, Donald; Wang, Yu-Chen; Obenour, Daniel R.

doi:10.1016/j.scitotenv.2022.158959

Cited by 17 publications

(7 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Remarkably, the sites far from the lake shore often confront hypoxia due to their proximity to urban areas, such as the site near Cleveland. These urban areas are associated with elevated pollution emissions, significantly contributing to hypoxia [5,[76][77][78].…”

Section: Number Of Hypoxia Days In the Lake Erie Central Basinmentioning

confidence: 99%

Dissolved Oxygen Forecasting for Lake Erie’s Central Basin Using Hybrid Long Short-Term Memory and Gated Recurrent Unit Networks

Pan,

Zhang,

Deng

et al. 2024

Water

View full text Add to dashboard Cite

Dissolved oxygen (DO) concentration is a pivotal determinant of water quality in freshwater lake ecosystems. However, rapid population growth and discharge of polluted wastewater, urban stormwater runoff, and agricultural non-point source pollution runoff have triggered a significant decline in DO levels in Lake Erie and other freshwater lakes located in populated temperate regions of the globe. Over eleven million people rely on Lake Erie, which has been adversely impacted by anthropogenic stressors resulting in deficient DO concentrations near the bottom of Lake Erie’s Central Basin for extended periods. In the past, hybrid long short-term memory (LSTM) models have been successfully used for the time-series forecasting of water quality in rivers and ponds. However, the prediction errors tend to grow significantly with the forecasting period. Therefore, this research aimed to improve the accuracy of DO forecasting models by taking advantage of Lake Erie’s real-time water quality (water temperature and DO concentration) monitoring network to establish temporal and spatial links between adjacent monitoring stations. We developed hybrid LSTM models that combine LSTM, convolutional neuron network LSTM (CNN-LSTM), hybrid CNN with gated recurrent unit (CNN-GRU) models, and convolutional LSTM (ConvLSTM) to forecast near-bottom DO concentrations in Lake Erie’s Central Basin. These hybrid LSTM models improve their capacity to handle complicated datasets with spatial and temporal variability. These models can serve as accurate and reliable tools for forecasting DO concentrations in freshwater lakes to help environmental protection agencies better access and manage the health of these vital ecosystems. Following analysis of a 21-site Lake Erie dataset for 2020 and 2021, the ConvLSTM model emerged as the most accurate and reliable, boasting an MSE of 0.51 mg/L, MAE of 0.42 mg/L, and an R-squared of 0.95 over the 12 h prediction range. The model foresees future hypoxia in Lake Erie. Notably, the temperature near site 713 holds significance for Central Basin DO forecasting in Lake Erie, as indicated by outcomes derived from the Shapley additive explanations (SHAP).

show abstract

Section: Number Of Hypoxia Days In the Lake Erie Central Basinmentioning

confidence: 99%

Dissolved Oxygen Forecasting for Lake Erie’s Central Basin Using Hybrid Long Short-Term Memory and Gated Recurrent Unit Networks

Pan,

Zhang,

Deng

et al. 2024

Water

View full text Add to dashboard Cite

show abstract

“…Concerns associated with eutrophic water bodies include health and aesthetic issues in natural waters and drinking water sources, along with diminished levels of dissolved oxygen, adversely impacting sh and other aquatic life. While phosphorus is naturally present in some soils, signi cant contributions to aquatic systems can be attributed to anthropogenic sources like fertilized elds, animal waste, wastewater treatment plants, and industries utilizing phosphorus in cleaning and production processes (Nava-López et al, 2016; Wang et al, 2021;Scavia et al, 2023). Depending on the source, phosphorus is often linked with suspended sediments, posing additional water quality concerns (Suplee, 2021; Kozyrev, 2023).…”

Section: Introductionmentioning

confidence: 99%

Exploring the Trends in Sediment and Phosphorus Concentrations and Loads in Part of the Canadian Great Lakes Basin

Paul,

Goswami,

Rudra

et al. 2024

Preprint

View full text Add to dashboard Cite

The specific objective of this study is to explore the long-term trend of total phosphorus (TP) and total suspended sediment (TSS) concentrations and loads (C/L)s in various streams/rivers in the Great Lakes Basin. This includes related statistical analyses, such as confidence intervals, to assess variability and identify cases where measures should be taken to reduce TSS and TP. Trend analysis of TSS and TP (C/L)s are performed, combining bootstrapping with the Weighted Regressions on Time, Discharge, and Season i.e., WRTDS_BT technique. The technique is used at ten selected monitoring stations of Northern Lake Erie, Eastern Lake Huron, and Lake Ontario & Niagara Peninsula in Ontario, Canada. Trend analysis over selected tributaries using flow-normalized (FN) TSS and TP (C/L)s reveals that trends in [FN-TSS] and [FN-TP] (C/L)s were highly variable, with significant decrease in a few stations. However, in most tributaries, TSS concentration levels are significantly higher than Canadian Water Quality Guidelines (CWQG) limit of 30 mg/L (following Toronto Region Conservation Authority (TRCA), Ontario) and TP concentration levels are significantly higher than the Ontario’s provincial water quality objectives (PWQO) limit of 0.03 mg/L. Measures to reduce TSS and TP is effective at five tributaries (Humber River, Don River, Saugeen River, Big Creek, Nottawasaga River). Although the drivers are not explicitly identified, potential attributions are discussed for policymakers in the study area.

show abstract

“…The escalating concentrations and loads (C/L)s of phosphorus, and sediment in water bodies, such as lakes and coastal waters, is a complex and growing global concern due to their adverse impacts on water quality and environmental health (Stammler et al, 2017;Wang et al, 2021;Scavia et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

Exploring the Trends in Sediment and Phosphorus Concentrations and Loads in Part of the Canadian Great Lakes Basin

Paul,

Goswami,

Rudra

et al. 2024

Environ. Process.

View full text Add to dashboard Cite

The speci c objective of this study is to explore the long-term trend of total phosphorus (TP) and total suspended sediment (TSS) concentrations and loads (C/L)s in various streams/rivers in the Great Lakes Basin. This includes related statistical analyses, such as con dence intervals, to assess variability and identify cases where measures should be taken to reduce TSS and TP. Trend analysis of TSS and TP (C/L)s are performed, combining bootstrapping with the Weighted Regressions on Time, Discharge, and Season i.e., WRTDS_BT technique. The technique is used at ten selected monitoring stations of Northern Lake Erie, Eastern Lake Huron, and Lake Ontario & Niagara Peninsula in Ontario, Canada. Trend analysis over selected tributaries using ow-normalized (FN) TSS and TP (C/L)s reveals that trends in [FN-TSS] and [FN-TP] (C/L)s were highly variable, with signi cant decrease in a few stations. However, in most tributaries, TSS concentration levels are signi cantly higher than Canadian Water Quality Guidelines (CWQG) limit of 30 mg/L (following Toronto Region Conservation Authority (TRCA), Ontario) and TP concentration levels are signi cantly higher than the Ontario's provincial water quality objectives (PWQO) limit of 0.03 mg/L. Measures to reduce TSS and TP is effective at ve tributaries (Humber River, Don River, Saugeen River, Big Creek, Nottawasaga River). Although the drivers are not explicitly identi ed, potential attributions are discussed for policymakers in the study area. HighlightsFour tributaries had [FN-TSS] concentrations below CWQG limit (30 mg/L).Two tributaries had [FN-TP] concentration below PWQO limit (0.03 mg/L).Two tributaries had concentrations below both CWQG and PWQO limit.BMPs are effective at six tributaries.

show abstract

Advancing freshwater ecological forecasts: Harmful algal blooms in Lake Erie

Cited by 17 publications

References 79 publications

Dissolved Oxygen Forecasting for Lake Erie’s Central Basin Using Hybrid Long Short-Term Memory and Gated Recurrent Unit Networks

Dissolved Oxygen Forecasting for Lake Erie’s Central Basin Using Hybrid Long Short-Term Memory and Gated Recurrent Unit Networks

Exploring the Trends in Sediment and Phosphorus Concentrations and Loads in Part of the Canadian Great Lakes Basin

Exploring the Trends in Sediment and Phosphorus Concentrations and Loads in Part of the Canadian Great Lakes Basin

Contact Info

Product

Resources

About