Recent advances in algal bloom detection and prediction technology using machine learning

The Science of The Total Environment, Journal Year: 2024, Volume and Issue: 938, P. 173546 - 173546

Published: May 27, 2024

Language: Английский

---

An Intelligent Early Warning System for Harmful Algal Blooms: Harnessing the Power of Big Data and Deep Learning

Environmental Science & Technology, Journal Year: 2024, Volume and Issue: 58(35), P. 15607 - 15618

Published: March 4, 2024

Harmful algal blooms (HABs) pose a significant ecological threat and economic detriment to freshwater environments. In order develop an intelligent early warning system for HABs, big data deep learning models were harnessed in this study. Data collection was achieved utilizing the vertical aquatic monitoring (VAMS). Subsequently, analysis stratification of layer conducted employing "DeepDPM-Spectral Clustering" method. This approach drastically reduced number predictive enhanced adaptability system. The Bloomformer-2 model developed conduct both single-step multistep predictions Chl-a, integrating " Alert Level Framework" issued by World Health Organization accomplish HABs. case study Taihu Lake revealed that during winter 2018, water column could be partitioned into four clusters (Groups W1-W4), while summer 2019, five S1-S5). Moreover, subsequent task, exhibited superiority performance across all 2018 2019 (MAE: 0.175-0.394, MSE: 0.042-0.305, MAPE: 0.228-2.279 prediction; MAE: 0.184-0.505, 0.101-0.378, 0.243-4.011 prediction). prediction 3 days indicated Group W1 I alert state at times. Conversely, S1 mainly under alert, with seven specific time points escalating II alert. Furthermore, end-to-end architecture system, coupled automation its various processes, minimized human intervention, endowing it characteristics. research highlights transformative potential artificial intelligence environmental management emphasizes importance interpretability machine applications.

Language: Английский

---

Predicting Harmful Algal Blooms Using Explainable Deep Learning Models: A Comparative Study

Water, Journal Year: 2025, Volume and Issue: 17(5), P. 676 - 676

Published: Feb. 26, 2025

Harmful algal blooms (HABs) have emerged as a significant environmental challenge, impacting aquatic ecosystems, drinking water supply systems, and human health due to the combined effects of activities climate change. This study investigates performance deep learning models, particularly Transformer model, there are limited studies exploring its effectiveness in HAB prediction. The chlorophyll-a (Chl-a) concentration, commonly used indicator phytoplankton biomass proxy for occurrences, is target variable. We consider multiple influencing parameters—including physical, chemical, biological quality monitoring data from stations located west Lake Erie—and employ SHapley Additive exPlanations (SHAP) values an explainable artificial intelligence (XAI) tool identify key input features affecting HABs. Our findings highlight superiority especially Transformer, capturing complex dynamics parameters providing actionable insights ecological management. SHAP analysis identifies Particulate Organic Carbon, Nitrogen, total phosphorus critical factors predictions. contributes development advanced predictive models HABs, aiding early detection proactive management strategies.

Language: Английский

---

Multivariate Regression Analysis for Identifying Key Drivers of Harmful Algal Bloom in Lake Erie

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(9), P. 4824 - 4824

Published: April 26, 2025

Harmful Algal Blooms (HABs), predominantly driven by cyanobacteria, pose significant risks to water quality, public health, and aquatic ecosystems. Lake Erie, particularly its western basin, has been severely impacted HABs, largely due nutrient pollution climatic changes. This study aims identify key physical, chemical, biological drivers influencing HABs using a multivariate regression analysis. Water quality data, collected from multiple monitoring stations in Erie 2013 2020, were analyzed develop predictive models for chlorophyll-a (Chl-a) total suspended solids (TSS). The correlation analysis revealed that particulate organic nitrogen, turbidity, carbon the most influential variables predicting Chl-a TSS concentrations. Two developed, achieving high accuracy with R2 values of 0.973 0.958 TSS. demonstrates robustness techniques identifying HAB drivers, providing framework applicable other systems. These findings will contribute better prediction management strategies, ultimately helping protect resources health.

Language: Английский

---

Prevention and control of algae residue deposition in long-distance water conveyance project

Environmental Pollution, Journal Year: 2024, Volume and Issue: 344, P. 123294 - 123294

Published: Jan. 3, 2024

Language: Английский

---

Investigating the influence of measurement uncertainty on chlorophyll-a predictions as an indicator of harmful algal blooms in machine learning models

Ecological Informatics, Journal Year: 2024, Volume and Issue: 82, P. 102735 - 102735

Published: July 25, 2024

Advancements in data availability, including high frequency, near real-time multiparameter sensors, laboratory analysis, and in-situ remote observations, have driven the development of machine learning (ML) models for applications such as toxic Harmful Algal Bloom (HABs) monitoring. However, performance ML predictions is influenced by both model uncertainties due to inherent structures errors associated with input dataset measurements. For example, measurement uncertainty arises from sample collection, sensor drift analysis handling errors. While impacts are commonly addressed using probabilistic approaches, effect less studied limited availability detailed information. This study focuses on assessing impact prediction chlorophyll-a concentration an index HABs a mesotrophic lake. Using randomized subsets measured datasets that mimic possible distributions, built 1000 Random Forest (RF) Support Vector Regression (SVR) models. An independent was used validate ensemble models, allowing evaluation creation intervals measure propagated uncertainty. Our findings showed MAE ranged between 0.16 μg/l 5.19 μg/l, RMSE ranging 0.20 7.39 μg/l. The highest coverage 0.71 observed RF without values predictor. found training sizes frequency manually sampled nature influence how much covered. results this demonstrate well can capture various patterns when given diverse variables. will give researchers insightful information lessen decision-support tools management.

Language: Английский

---

Sustainable strategy for enhancing growth of marine diatom and lipid production using RO and AC spent water

Systems Microbiology and Biomanufacturing, Journal Year: 2024, Volume and Issue: 4(3), P. 906 - 914

Published: March 17, 2024

Language: Английский

---

Research on a Non-Stationary Groundwater Level Prediction Model Based on VMD-iTransformer and Its Application in Sustainable Water Resource Management of Ecological Reserves

Sustainability, Journal Year: 2024, Volume and Issue: 16(21), P. 9185 - 9185

Published: Oct. 23, 2024

The precise forecasting of groundwater levels significantly influences plant growth and the sustainable management ecosystems. Nonetheless, non-stationary characteristics level data often hinder current deep learning algorithms from precisely capturing variations in levels. We used Variational Mode Decomposition (VMD) an enhanced Transformer model to address this issue. Our objective was develop a called VMD-iTransformer, which aims forecast level. This research nine monitoring stations located Hangjinqi Ecological Reserve Kubuqi Desert, China, as case studies over four months. To enhance predictive performance we introduced novel approach fluctuations Desert region. technique achieve predictions conditions. Compared with classic model, our more effectively captured non-stationarity prediction accuracy by 70% test set. novelty lies its initial decomposition multimodal signals using adaptive approach, followed reconfiguration conventional model’s structure (via self-attention inversion feed-forward neural network (FNN)) challenge multivariate time prediction. Through evaluation results, determined that method had mean absolute error (MAE) 0.0251, root square (RMSE) 0.0262, percentage (MAPE) 1.2811%, coefficient determination (R2) 0.9287. study validated VMD iTransformer offering modeling for predicting context, thereby aiding water resource ecological reserves. VMD-iTransformer enhances projections level, facilitating reasonable distribution resources long-term preservation ecosystems, providing technical assistance ecosystems’ vitality regional development.

Language: Английский

---

Influence of regulated water discharges on phytoplankton composition and biomass in a subtropical canal

Journal of Environmental Management, Journal Year: 2024, Volume and Issue: 373, P. 123470 - 123470

Published: Dec. 3, 2024

Phytoplankton composition and biomass were investigated in the C-43 Canal southwest Florida during a period of shifting discharges from water control structures. The canal receives regulated eutrophic Lake Okeechobee via S77 structure. During periods high discharge spring early summer, cyanobacteria dominated phytoplankton community, including blooms harmful algal bloom (HAB) species Raphidiopsis raciborskii, Limnothrix redekei Microcystis aeruginosa. low lake, mid-summer autumn, inputs to came primarily tributaries watershed surrounding C-43. decreased, but relative importance dinoflagellates increased, July. dinoflagellate community included Ceratium, Durinskia baltica, Glochidinium penardiforme, Gymnodinium fuscum, Parvodinium goslaviense, umbonatum/inconspicuum complex, Peridiniopsis quadridens, Woloszynskia reticulata, an unidentified thecate athecate species. D. baltica P. goslaviense recorded for first time Florida. Data was also obtained on temperature, conductivity, fluorescent dissolved organic matter, chlorophyll a, total nitrogen, inorganic phosphorus, PO

Language: Английский

---

A Review of Machine Learning Models for Harmful Algal Bloom Monitoring in Freshwater Systems

Journal of Natural Resources and Agricultural Ecosystems, Journal Year: 2023, Volume and Issue: 1(2), P. 63 - 76

Published: Jan. 1, 2023

Highlights Machine Learning (ML) models are identified, reviewed, and analyzed for HAB predictions. Data preprocessing is vital efficient ML model development. toxin production monitoring limited. Abstract. Harmful algal blooms (HABs) detrimental to livestock, humans, pets, the environment, global economy, which calls a robust approach their management. While process-based can inform practitioners about enabling conditions, they have inherent limitations in accurately predicting harmful blooms. To address these limitations, potentially leverage large volumes of IoT data aid near real-time evolved as tools understanding patterns relationships between water quality parameters expansion. This review describes currently used forecasting HABs freshwater ecosystems presents structures application related toxins. The revealed that regression trees, random forest, Artificial Neural Network (ANN), Support Vector Regression (SVR), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU) most frequently monitoring. shows models' prowess identifying significant variables influencing growth, drivers, multistep prediction. Hybrid also improve prediction algal-related through improved optimization techniques variable selection algorithms. often focus on biomass prediction, few studies apply limitation be associated with lack high-frequency datasets development, exploring this domain encouraged. serves guide policymakers researchers implement reveals potential decision support early Keywords: Cyanobacteria, Freshwater, blooms, learning, Water quality.

Language: Английский

---