EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI-Driven Monitoring for Fish Welfare in Aquaponics: A Predictive Approach

Jorge Saúl Fandiño Pelayo iD, Luis Sebastián Mendoza Castellanos iD, Rocío Cazes Ortega iD, Luis G Hernández-Rojas iD

Sensors · 2025

DOI: 10.3390/s25196107 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Jorge Saúl Fandiño Pelayo und 3 weiteren Autor:innen. Beteiligte Einrichtung: Facultad de Ciencias Naturales e Ingeniería, Unidades Tecnológicas de Santander (UTS), Bucaramanga 680005, Colombia. Hauptthemen laut MEDLINE: Environmental Monitoring, Artificial Intelligence, Fishes, Animal Welfare. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study addresses the growing need for intelligent monitoring in aquaponic systems by developing a predictive system based on artificial intelligence and environmental sensing. The goal is to improve fish welfare through the early detection of adverse water conditions. The system integrates low-cost digital sensors to continuously measure key physicochemical variables—pH, dissolved oxygen, and temperature—using these as inputs for real-time classification of fish health status. Four supervised machine learning models were evaluated: linear discriminant analysis (LDA), support vector machines (SVMs), neural networks (NNs), and random forest (RF). A dataset of 1823 instances was collected over eight months from a red tilapia aquaponic setup. The random forest model yielded the highest classification accuracy (99%), followed by NN (98%) and SVM (97%). LDA achieved 82% accuracy. Performance was validated using 5-fold cross-validation and label permutation tests to confirm model robustness. These results demonstrate that sensor-based predictive models can reliably detect early signs of fish stress or mortality, supporting the implementation of intelligent environmental monitoring and automation strategies in sustainable aquaponic production.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Environmental MonitoringArtificial IntelligenceFishesAnimal WelfareAnimalsNeural Networks, ComputerSupport Vector MachineTilapiaDiscriminant AnalysisMachine Learning

Stichwörter der Autor:innen

aquaponicsembedded monitoringenvironmental sensorsfish welfare classificationmachine learningneural networkspredictive analyticsrandom forestsmart sensing systemswater quality monitoring

Autor:innen und Institutionen

  • Facultad de Ciencias Naturales e Ingeniería, Unidades Tecnológicas de Santander (UTS), Bucaramanga 680005, Colombia.
  • Facultad de Ingeniería, Universidad Autónoma de Bucaramanga (UNAB), Bucaramanga 680005, Colombia.
  • Tecnológico de Monterrey, School of Engineering and Sciences, Monterrey 64849, N.L., Mexico.

ORCID-Profile: Jorge Saúl Fandiño Pelayo, Luis Sebastián Mendoza Castellanos, Rocío Cazes Ortega, Luis G Hernández-Rojas

Zitieren

APA

Fandiño Pelayo, J. S., Mendoza Castellanos, L. S., Cazes Ortega, R., & Hernández-Rojas, L. G. (2025). AI-Driven Monitoring for Fish Welfare in Aquaponics: A Predictive Approach. Sensors. https://doi.org/10.3390/s25196107

Vancouver

Fandiño Pelayo JS, Mendoza Castellanos LS, Cazes Ortega R, Hernández-Rojas LG. AI-Driven Monitoring for Fish Welfare in Aquaponics: A Predictive Approach. Sensors. 2025. doi:10.3390/s25196107

BibTeX
@article{FandioPelayo2025,
  author = {Fandiño Pelayo, Jorge Saúl and Mendoza Castellanos, Luis Sebastián and Cazes Ortega, Rocío and Hernández-Rojas, Luis G},
  title = {AI-Driven Monitoring for Fish Welfare in Aquaponics: A Predictive Approach},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25196107}
}
Kostenlos starten →