A Review of Machine Learning Models for Harmful Algal Bloom Monitoring in Freshwater Systems DOI Open Access
Ibrahim Busari,

Debabrata Sahoo,

R. Daren Harmel

et al.

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

Machine learning-based design and monitoring of algae blooms: Recent trends and future perspectives – A short review DOI

Abdul Gaffar Sheik,

Arvind Kumar,

Reeza Patnaik

et al.

Critical Reviews in Environmental Science and Technology, Journal Year: 2023, Volume and Issue: 54(7), P. 509 - 532

Published: Sept. 7, 2023

AbstractMachine learning (ML) models are widely used methods for analyzing data from sensors and satellites to monitor climate change, predict natural disasters, protect wildlife. However, the application of these technologies monitoring managing algal blooms in freshwater environments is relatively new novel. The commonly (ABS) so far artificial neural networks (ANN), random forests (RF), support vector machine (SVM), data-driven modeling, long short-term memory (LSTM). In past, researchers have mostly worked on predicting effluent parameters, nutrients, microculture, area weather conditions, meteorological factors, ground waters, energy optimization, metallic substances using ML models. Most studies employed performance metrics like root mean squared error, peak signal, precision, determination coefficient as their primary model measures accuracy analysis, usage transfer, activation function. While there been some this topic, several research gaps still be addressed. most significant related limited different algae bloom scenarios, interpretability models, lack integration with existing systems. Keeping mind, review article has methodically arranged present an overview past studies, limitations, way forward toward prediction ABS, thus benefitting future area. This aims summarize that available, including benchmarking values.HighlightsReal-time dynamics essential mitigating blooms.Various complexities hinder applications current algorithms ABS.Activation transfer functions can selection ABS.Integrated drive feature engineering control ABS.Keywords: Activation-functionalgae bloomsmonitoringmachine learningperformance predictionHANDLING EDITORS: Hyunjung Kim Scott Bradford Disclosure statementNo potential conflict interest was reported by authors.

Language: Английский

Citations

11
The need for advancing algal bloom forecasting using remote sensing and modeling: Progress and future directions DOI Creative Commons
Cassia Brocca Caballero, Vitor S. Martins, Rejane S. Paulino

et al.

Ecological Indicators, Journal Year: 2025, Volume and Issue: 172, P. 113244 - 113244

Published: Feb. 21, 2025

Language: Английский

Citations

0
Multi-Scale Feature Fusion Model for Real-Time Blood Glucose Monitoring and hyperglycemia Prediction Based on Wearable Devices DOI
Yang Song,

Ziyu Yuan,

Yuxin Wu

et al.

Medical Engineering & Physics, Journal Year: 2025, Volume and Issue: 138, P. 104312 - 104312

Published: March 1, 2025

Language: Английский

Citations

0
HGS-At-LSTM: attention-based long short-term memory model combined with halving grid search optimizer for harmful algal bloom forecasting DOI

Abir Loussaief,

Raïda Ktari, Yessine Hadj Kacem

et al.

International Journal of Data Science and Analytics, Journal Year: 2025, Volume and Issue: unknown

Published: May 2, 2025

Language: Английский

Citations

0
Global Oceanic Mesoscale Eddies Trajectories Prediction With Knowledge-Fused Neural Network DOI
Xinmin Zhang, Baoxiang Huang, Ge Chen

et al.

IEEE Transactions on Geoscience and Remote Sensing, Journal Year: 2024, Volume and Issue: 62, P. 1 - 14

Published: Jan. 1, 2024

Efficient eddy trajectory prediction driven by multi-information fusion can facilitate the scientific research of oceanography, while complicated dynamics mechanism makes this issue challenging. Benefiting from ocean observing technology, dataset be qualified for data-intensive paradigms. In paper, is used to inspire design idea neural network (termed EddyTPNet) and also transformed into prior knowledge guide learning process. This study among first implement with physics informed network. First, an in-depth analysis kinematic characteristics indicates that longitude latitude should decoupled; Second, directional dispersion global propagation embedded decoder EddyTPNet improve performance; Finally, predicts trajectories through pre-training adapts complex local regions via model transfer. Extensive experimental results demonstrate reliably forecast motion eddies next 7 days, ensuring a low daily mean geodetic error. exploratory provides valuable insights solving problem phenomena using knowledge-based time series networks.

Language: Английский

Citations

3
Mapping Harmful Algae Blooms: The Potential of Hyperspectral Imaging Technologies DOI Creative Commons
Fernando Arias,

Mayteé Zambrano,

Edson S. Galagarza

et al.

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(4), P. 608 - 608

Published: Feb. 11, 2025

Harmful algae blooms (HABs) pose critical threats to aquatic ecosystems and human economies, driven by their rapid proliferation, oxygen depletion capacity, toxin release, biodiversity impacts. These blooms, increasingly exacerbated climate change, compromise water quality in both marine freshwater ecosystems, significantly affecting life coastal economies based on fishing tourism while also posing serious risks inland bodies. This article examines the role of hyperspectral imaging (HSI) monitoring HABs. HSI, with its superior spectral resolution, enables precise classification mapping diverse species, emerging as a pivotal tool environmental surveillance. An array HSI techniques, algorithms, deployment platforms are evaluated, analyzing efficacy across varied geographical contexts. Notably, sensor-based studies achieved up 90% accuracy, regression-based chlorophyll-a (Chl-a) estimations frequently reaching coefficients determination (R2) above 0.80. quantitative findings underscore potential for robust HAB diagnostics early warning systems. Furthermore, we explore current limitations future management, highlighting strategic importance addressing growing economic challenges posed paper seeks provide comprehensive insight into HSI’s capabilities, fostering integration global strategies against proliferation.

Language: Английский

Citations

0
Early warning and monitoring of the safety risk of coastal nuclear power plant cold source under the stress from Phaeocystis globosa blooms DOI
Jialin Ni, Hongyi Chen, Lichun Dai

et al.

Marine and Freshwater Research, Journal Year: 2024, Volume and Issue: 75(2)

Published: Jan. 29, 2024

Context In recent years, Phaeocystis globosa has become a typical red tide species in the Beibu Gulf, posing safety hazard to cold-water intake system of Guangxi Fangchenggang Nuclear Power Plant. Aims To establish an effective early risk-warning monitoring and ensure nuclear power plant intakes. Methods this study, multifactor multilevel was established using warning idea ‘risk grading’. Key results The showed that method can analyse influence trend marine-environment changes on growth P. improve timeliness forecasting. Conclusions paper effectively guide coastal enterprises conduct risk accuracy Implications methed is great significance dealing with disasters caused by blooms.

Language: Английский

Citations

3
Deep learning methods for multi-horizon long-term forecasting of Harmful Algal Blooms DOI Creative Commons
Silvia Martín-Suazo, Jesús Morón-López, Stanislav Vakaruk

et al.

Knowledge-Based Systems, Journal Year: 2024, Volume and Issue: 301, P. 112279 - 112279

Published: July 27, 2024

The increasing occurrence of Harmful Algal Blooms (HABs) in water systems poses significant challenges to ecological health, public safety, and economic stability globally. Deep Learning (DL) models, notably Convolutional Neural Networks (CNN) Long-Short Term Memory (LSTM), have been widely employed for HAB prediction. However, the emergence state-of-the-art multi-horizon forecasting DL architectures such as Basis Expansion Analysis Interpretable Time Series Forecasting (N-BEATS) provides a novel solution long-term This study compares performance N-BEATS with LSTM CNN models using high temporal granularity quality data from As Conchas reservoir (NW Spain) forecast chlorophyll-a (Chl-a) concentrations, key indicator HABs. evaluation encompasses one-day one-week prediction horizons, aligning World Health Organization (WHO) alert criteria. Results indicate that outperforms predictions when multiple consecutive days within week. Furthermore, augmenting input additional variables does not significantly enhance predictive accuracy, challenging assumption complexity always improves model performance. also explores transferability trained across different monitoring buoys same body, emphasizing adaptability broad applicability diverse aquatic environments. research underscores potential valuable tool prediction, particularly longer-term forecasting.

Language: Английский

Citations

3
Enriching Facial Anti-Spoofing Datasets via an Effective Face Swapping Framework DOI Creative Commons
Jiachen Yang, Guipeng Lan, Shuai Xiao

et al.

Sensors, Journal Year: 2022, Volume and Issue: 22(13), P. 4697 - 4697

Published: June 22, 2022

In the era of rapid development Internet things, deep learning, and communication technologies, social media has become an indispensable element. However, while enjoying convenience brought by technological innovation, people are also facing negative impact them. Taking users’ portraits multimedia systems as examples, with maturity facial forgery personal malicious tampering forgery, which pose a potential threat to privacy security impact. At present, detection methods learning-based methods, depend on data certain extent. Enriching anti-spoofing datasets is effective method solve above problem. Therefore, we propose face swapping framework based StyleGAN. We utilize feature pyramid network extract features map them latent space order realize transformation identity, explore representation identity information adaptive editing module. design simple post-processing process improve authenticity images. Experiments show that our proposed can effectively complete provide high-quality for ensure systems.

Language: Английский

Citations

13
Numerical computation based few-shot learning for intelligent sea surface temperature prediction DOI
Zhengjian Li, Jingyi He,

Tianlei Ni

et al.

Multimedia Systems, Journal Year: 2022, Volume and Issue: 29(5), P. 3001 - 3013

Published: May 21, 2022

Language: Английский

Citations

9