Mapping distribution of water hyacinth (Eichhornia crassipes) in Rwanda using multispectral remote sensing imagery

Abstract

Water hyacinth, Eichhornia crassipes (C. Mart) Solms (Pontederiaceae), is an invasive aquatic macrophyte with major negative economic and ecological impacts in Rwanda and other East African countries since its establishment in the region in the 1960s. Reliable estimates of water hyacinth distribution are required to determine the severity of the problem and identify waterbodies requiring management. Remote sensing techniques, based on the Landsat 8 sensor, offer promising alternatives to accurately detect, map and monitor the extent of the water hyacinth invasion in Rwandan waterbodies. The aim of the current study was to investigate the utility of multispectral remote sensed imagery using Random Forest and Support Vector Machine algorithms to detect and map water hyacinth in Rwandan waterbodies. Random Forest had a high overall accuracy of 85%, compared with Support Vector Machine (65%). These algorithms confirmed different levels of water hyacinth infestations in three main Rwandan rivers. Many of the wetlands along these riparian systems and most of the lakes, particularly those from the Eastern Province of the country were found to be invaded by water hyacinth. These findings would, therefore, assist government partners and policy makers to put in place sustainable methods, such as biological control, along with integrated pest management, to control the of water hyacinth invasion in Rwanda.

Keywords: invasive aquatic macrophytes, Landsat 8, Random Forest algorithm, spatial distribution, Support Vector Machine algorithm