Machine Learning Models for Detecting Emerging Contaminants in Seagrass Ecosystems via Drone Imagery

View at publisher Summarise with VIRAT
Authors: Mughair Aslam Bhatti, Bakirov Juma, Intizor Avazmetova, Anorgul I. Ashirova, Avezova Umida Maksudovna
Cited by: 0
References: 9

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Machine learning (ML) models are increasingly being applied to environmental monitoring, particularly for detecting emerging contaminants in marine ecosystems. Seagrass ecosystems, vital for biodiversity and carbon sequestration, are highly sensitive to pollutants, which can degrade their health and function. Traditional methods of contaminant detection often involve time-consuming fieldwork and limited spatial coverage. However, drone imagery, combined with ML techniques, offers a powerful tool for rapid, large-scale monitoring. ML algorithms can analyze high-resolution drone images to detect subtle changes in water quality, seagrass health, and potential contamination levels, including heavy metals, pesticides, and pharmaceuticals.

Fields of Study & Subjects

Water Quality Monitoring Technologies Remote-Sensing Image Classification Marine and coastal plant biology

Publication details

Journal / source
IGI Global eBooks
Pages
225–250
Publication date
1 April 2026
Language
EN
Document type
Book chapter