EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cyanobacteria hot spot detection integrating remote sensing data with convolutional and Kolmogorov-Arnold networks

B A Zambrano-Luna, Russell Milne, Hao Wang

Science of The Total Environment · 2025

DOI: 10.1016/j.scitotenv.2024.178271 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science of The Total Environment, 2025. Verfasst von B A Zambrano-Luna und 2 weiteren Autor:innen. Beteiligte Einrichtung: Interdisciplinary Lab for Mathematical Ecology and Epidemiology & Department of Mathematical and Statistical Sciences, University of Alberta, Canada. Hauptthemen laut MEDLINE: Cyanobacteria, Environmental Monitoring, Remote Sensing Technology, Neural Networks, Computer. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Alberta Conservation Association, Canada Research Chairs Program, Natural Sciences and Engineering Research Council of Canada.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Prompt and accurate monitoring of cyanobacterial blooms is essential for public health management and understanding aquatic ecosystem dynamics. Remote sensing, in particular satellite observations, presents a good alternative for continuous monitoring. This study employs multispectral images from the Sentinel-2 constellation alongside ERA5-Land to enable broad-scale data acquisition. A simple deep convolutional neural network (CNN) architecture was proposed to analyze cyanobacteria (CB) concentration dynamics in Pigeon Lake, Canada, over five years. The model achieved an R2 value of 0.81 and an RMSE score of 0.03 for the training set and 0.15 for the testing set, demonstrating high predictive accuracy. Using the Local Getis-Ord statistic, we identified and analyzed trends in hot and cold spots under the null hypothesis that such spots are randomly distributed, observing changes in their distribution and the median CB concentration in hot spots over time. Additionally, a Kolmogorov-Arnold Network (KAN) and dense neural networks (NN) with a single hidden layer were trained to classify sections of the lake shoreline into hot and no hot spots using the Dynamic World dataset within a 500m radius of the lake. The KAN achieved a recall metric of 0.83 for detecting hot spots.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CyanobacteriaEnvironmental MonitoringRemote Sensing TechnologyNeural Networks, ComputerLakesEutrophicationCanada

Stichwörter der Autor:innen

Convolutional neural networkCyanobacterial bloomsHot and cold spotsKolmogorov-Arnold networkSentinel-2

Autor:innen und Institutionen

  • Interdisciplinary Lab for Mathematical Ecology and Epidemiology & Department of Mathematical and Statistical Sciences, University of Alberta, Canada.
  • Interdisciplinary Lab for Mathematical Ecology and Epidemiology & Department of Mathematical and Statistical Sciences, University of Alberta, Canada. Electronic address: hao8@ualberta.ca.

Förderung

  • Alberta Conservation Association
  • Canada Research Chairs Program
  • Natural Sciences and Engineering Research Council of Canada

Zitieren

APA

Zambrano-Luna, B. A., Milne, R., & Wang, H. (2025). Cyanobacteria hot spot detection integrating remote sensing data with convolutional and Kolmogorov-Arnold networks. Science of The Total Environment. https://doi.org/10.1016/j.scitotenv.2024.178271

Vancouver

Zambrano-Luna BA, Milne R, Wang H. Cyanobacteria hot spot detection integrating remote sensing data with convolutional and Kolmogorov-Arnold networks. Science of The Total Environment. 2025. doi:10.1016/j.scitotenv.2024.178271

BibTeX
@article{ZambranoLuna2025,
  author = {Zambrano-Luna, B A and Milne, Russell and Wang, Hao},
  title = {Cyanobacteria hot spot detection integrating remote sensing data with convolutional and Kolmogorov-Arnold networks},
  journal = {Science of The Total Environment},
  year = {2025},
  doi = {10.1016/j.scitotenv.2024.178271}
}
Kostenlos starten →