Monitoring the spread of water hyacinth (Pontederia crassipes): challenges and future developments

Citation

Datta A, Maharaj S, Prabhu GN, Bhowmik D, Marino A, Akbari V, Rupavatharam S, Sujeetha JAR, Anantrao GG, Poduvattil VK, Kumar S & Kleczkowski A (2021) Monitoring the spread of water hyacinth (Pontederia crassipes): challenges and future developments. Frontiers in Ecology and Evolution, 9, Art. No.: 631338. https://doi.org/10.3389/fevo.2021.631338

Abstract
Water hyacinth (Pontederia crassipes, also referred to as Eicchornia crassipes) is one of the most invasive weed species in the world, causing significant adverse economic and ecological impacts, particularly in tropical and sub-tropical regions. Large scale real-time monitoring of areas of chronic infestation is critical to formulate effective control strategies for this fast spreading weed species. Assessment of revenue generation potential of the harvested water hyacinth biomass also requires enhanced understanding to estimate the biomass yield potential for a given water body. Modern remote sensing technologies can greatly enhance our capacity to understand, monitor and estimate water hyacinth infestation within inland as well as coastal freshwater bodies. Readily available satellite imagery with high spectral, temporal and spatial resolution, along with conventional and modern machine learning techniques for automated image analysis, can enable discrimination of water hyacinth infestation from other floating or submerged vegetation. Remote sensing can potentially be complemented with an array of other technology-based methods, including aerial surveys, ground-level sensors, and citizen science, to provide comprehensive, timely and accurate monitoring. This review discusses the latest developments in the use of remote sensing and other technologies to monitor water hyacinth infestation, and proposes a novel, multi-modal approach that combines the strengths of the different methods.

Keywords
remote sensing; Synthetic Aperture Radar; Ground sensor network; Unmanned Aerial Vehicle; citizen science; machine learning; aquatic weeds; wetlands

Journal
Frontiers in Ecology and Evolution: Volume 9

• Published version