A tale of two blooms: do ecological paradigms for algal bloom success and succession require revisiting?

Journal of Great Lakes Research, Journal Year: 2024, Volume and Issue: 50(3), P. 102336 - 102336

Published: April 1, 2024

Lake Erie algal bloom discussions have historically focused on cyanobacteria, with foundational "blooms like it hot" and "high nutrient" paradigms considered as primary drivers behind cyanobacterial success. Yet, recent surveys rediscovered winter-spring diatom blooms, introducing another key player in the eutrophication story which has been overlooked. These blooms (summer vs. winter) treated solitary events separated by spatial temporal gradients. However, new evidence suggests they may not be so isolated, linked a manner that manifests an cycle. Equally notable are emerging reports of cold and/or oligotrophic freshwaters, interpreted some shifts classical paradigms. led many to ask "what is bloom?". Furthermore, questioning classic caused others wonder if we overlooking additional factors constrain In light data ideas, revisited concepts within context derived five take-aways: 1) Additional bloom-formers (diatoms) need included discussions, 2) The term "bloom" must reinforced clear definition quantitative metrics for each event, 3) Algal should studied solitarily, 4) Shifts physiochemical conditions serve alternative interpretation potential ecological paradigms, 5) success succession (i.e., pH light) require consideration.

Language: Английский

---

Unveiling the trifecta of cyanobacterial quorum sensing: LuxI, LuxR and LuxS as the intricate machinery for harmful algal bloom formation in freshwater ecosystems

The Science of The Total Environment, Journal Year: 2024, Volume and Issue: 924, P. 171644 - 171644

Published: March 11, 2024

Language: Английский

---

Temporal continuous monitoring of cyanobacterial blooms in Lake Taihu at an hourly scale using machine learning

The Science of The Total Environment, Journal Year: 2022, Volume and Issue: 857, P. 159480 - 159480

Published: Oct. 18, 2022

Language: Английский

---

Estimation of Water Quality Parameters through a Combination of Deep Learning and Remote Sensing Techniques in a Lake in Southern Chile

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(17), P. 4157 - 4157

Published: Aug. 24, 2023

In this study, we combined machine learning and remote sensing techniques to estimate the value of chlorophyll-a concentration in a freshwater ecosystem South American continent (lake Southern Chile). previous nine artificial intelligence (AI) algorithms were tested predict water quality data from measurements during monitoring campaigns. addition field (Case A), meteorological variables B) satellite C) used Lake Llanquihue. The models SARIMAX, LSTM, RNN, all which showed generally good statistics for prediction variable. Model validation metrics that three effectively predicted chlorophyll as an indicator presence algae bodies. Coefficient determination values ranging 0.64 0.93 obtained, with LSTM model showing best any cases tested. performed well across most stations, lower MSE (<0.260 (μg/L)2), RMSE (<0.510 ug/L), MaxError (<0.730 μg/L), MAE (<0.442 μg/L). This model, combines techniques, is applicable other Chilean world lakes have similar characteristics. addition, it starting point decision-makers protection conservation resource quality.

Language: Английский

---

Forecasting freshwater cyanobacterial harmful algal blooms for Sentinel-3 satellite resolved U.S. lakes and reservoirs

Journal of Environmental Management, Journal Year: 2023, Volume and Issue: 349, P. 119518 - 119518

Published: Nov. 7, 2023

This forecasting approach may be useful for water managers and associated public health to predict near-term future high-risk cyanobacterial harmful algal blooms (cyanoHAB) occurrence. Freshwater cyanoHABs grow excessive concentrations cause human, animal, environmental concerns in lakes reservoirs. Knowledge of the timing location cyanoHAB events is important quality management recreational drinking systems. No quantitative tool exists forecast across broad geographic scales at regular intervals. Publicly available satellite monitoring has proven effective detecting cyanobacteria biomass near-real time within United States. Weekly abundance was quantified from Ocean Land Colour Instrument (OLCI) onboard Sentinel-3 as response variable. An Integrated Nested Laplace Approximation (INLA) hierarchical Bayesian spatiotemporal model applied World Health Organization (WHO) recreation Alert Level 1 exceedance >12 μg L−1 chlorophyll-a with dominance 2192 resolved States nine climate zones. The INLA compared against support vector classifier random forest machine learning models; Dense Neural Network, Long Short-Term Memory (LSTM), Recurrent Network (RNN), Gneural (GNU) neural network models. Predictors were limited data sources relevant growth, readily on a weekly basis, national scale operational forecasting. Relevant predictors included surface temperature, precipitation, lake geomorphology. Overall, outperformed models prediction accuracy 90% 88% sensitivity, 91% specificity, 49% precision demonstrated by training 2017 through 2020 independently assessing predictions 2021 calendar year. probability true positive responses greater than false negative less responses. indicated correctly assigned lower probabilities when they didn't exceed WHO threshold higher did threshold. robust missing unbalanced sampling between waterbodies.

Language: Английский

---

Leveraging explainable machine learning for enhanced management of lake water quality

Journal of Environmental Management, Journal Year: 2024, Volume and Issue: 370, P. 122890 - 122890

Published: Oct. 13, 2024

Language: Английский

---

Source identification and prediction of nitrogen and phosphorus pollution of Lake Taihu by an ensemble machine learning technique

Frontiers of Environmental Science & Engineering, Journal Year: 2022, Volume and Issue: 17(5)

Published: Nov. 21, 2022

Language: Английский

---

Rapid structure sensing of suspended particles in water using particulate Mueller matrix polarimetry

Measurement, Journal Year: 2025, Volume and Issue: unknown, P. 116754 - 116754

Published: Jan. 1, 2025

Language: Английский

---

Prediction of Blue-Green Algae Cells in a City Water Source Based on the LSTM Model

Water, Journal Year: 2025, Volume and Issue: 17(2), P. 237 - 237

Published: Jan. 16, 2025

China’s freshwater resources are relatively small per capita, and the traditional passive control of hydrographic outbreaks can no longer meet modern water management needs. Data-driven models, such as Long Short-Term Memory Networks (LSTMs), have been gradually applied to management, but most research has focused on enhancement prediction effect hybrid models while neglecting importance data structure. In this study, we predicted number dominant algae (blue-green algae) in a source based LSTM explored effects different feature combinations time window steps performance. It was found that model significantly improved by adding multiple features, R2 31.98% compared with single prediction. Meanwhile, (T-value) increased from 7 300, 0.4%, iteration 96%. The results suggested appropriate input selection is beneficial for prediction, windows led reduced benefits. Lastly, study offers insights into future directions three key dimensions: indicator, optimization algorithm, combination.

Language: Английский

---

Enhanced Detection of Harmful Algal Blooms Using Topological Data Analysis for Clustering Spatially Distributed Water Quality and Hydrodynamic Data

KSCE Journal of Civil Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 100177 - 100177

Published: Feb. 1, 2025

Language: Английский

---