April 2026, article in a peer review,
i-Science

Giel W.A. Hagenbeek, Tim H.M. van Emmerik, Tianlong Jia, Pummarin Khamdahsag, Kittiphon Boonma, Riccardo Taormina, Thomas Mani and Marc Rußwurm

  • Publication type: article in a peer review
  • Publication journal: i-Science
  • Publication date: May 2026
  • Collaborators : Geo-information Science and Remote Sensing Laboratory, Wageningen University and Research, Droevendaalsesteeg 3 6708 PB Wageningen Gelderland, the Netherlands Hydrology and Environmental Hydraulics Group, Wageningen University and Research, Droevendaalsesteeg 3 6708 PB Wageningen Gelderland, the Netherlands Delft University of Technology, Faculty of Civil Engineering and Geosciences, Department of Water Management, Stevinweg 1, 2628 CN Delft, the Netherlands Karlsruhe Institute of Technology (KIT), Institute of Water and Environment, Karlsruhe, Germany Sustainable Environment Research Institute, Chulalongkorn University, Bangkok 10330, Thailand Geoinformatics Center, Asian Institute of Technology, Pathumthani, Thailand The Ocean Cleanup, Rotterdam, the Netherlands University of Bonn, Institute for Food and Resource Economics, Bonn, Germany
  • DOI: 10.1016/j.isci.2026.116238

Abstract

Rivers are major pathways for plastic pollution to oceans, with high emissions in tropical regions. Research in
the Saigon River showed that invasive water hyacinths (WHs) can trap macroplastics and serve as proxies for
detecting river plastic using remote sensing. We explore this phenomenon and its detection methods’ transferability to the Chao Phraya River. Along a 62.1 km river course, WHs trapped an average of 32% of floating
plastics, reaching local maxima of 78%, comparable to 54%–82% in the Saigon. Plastic concentration in WHs
was 59 times higher than in open water, increasing downstream. Object detection models transferred well for
WHs and entangled plastics (Chao Phraya: mAP 50 = 68% and 54%; Saigon River: mAP 50 = 70% and 52%) but
poorly for free-floating plastics (23% vs. 48%). Physical sampling found 14 times more plastics within WHs
than imagery, highlighting WHs’ role in trapping plastics and their potential for monitoring and targeted clean
up efforts.