Home > Research > Maintaining Biodiversity: Global Change > Detecting aliens from space
Current Research Programmes

Detecting aliens from space

Biological invasions are responsible for some of the most devastating impacts on the world’s ecosystems, and freshwater ecosystems are among the worst affected. Invasions not only threaten freshwater biodiversity, but also the key ecosystem services provided by wetlands. Tackling the impact of invasive species on wetlands is a major challenge that requires detailed information on alien species distribution and spread. This is particularly urgent in South Africa, where freshwater resources are scarce and increasingly pressured.

Water Hyacinth infestation at Hartebeespoort Dam in Johannesburg (a); Hartebeesport Dam viewed from an over passing satellite (b); Accurate mapping of the entire waterbody and used to limit the classification of vegetation to only the dam (c); Accurate mapping of the moving Water Hyacinth mat on Hartebeesport Dam (d)

This project utilises satellite data and cloud computing platforms to map the distribution of Water Hyacinth Eichhornia crassipes across South African waterbodies and explore reasons for its spread. PhD student Geethen Singh is undertaking this valuable research in collaboration with Chevonne Reynolds, Benjamin Rosman and Marcus Byrne of the University of the Witwatersrand.

South Africa’s surface water is frequently imaged by overpassing satellites. These images can track water level changes from national extents down to individual dams, providing scientists and water managers with near real-time monitoring of water resources. Invasive aquatic alien plant species present a serious threat to South Africa’s freshwater resources as they increase water loss through evapotranspiration. Water weeds can increase water loss by 130–180%. Water body area and the percentage cover of invasive aquatic weeds are crucial information needed to facilitate the removal and management of invasive plants such as Water Hyacinth. However, field assessments to obtain this information are often time-consuming, costly and labour intensive. Freely available satellite images provide a cost-effective alternative to reliably and regularly estimate the cover of water weeds. In this way, the extent of water weed infestation and its associated drivers can be tracked.

Once an invasive alien species has become established in a wetland, it can be very difficult to stop or even slow its invasion. Thus, the early detection of and rapid response to invasive alien species are needed to make management targeted, feasible and effective. Consequently, there is an urgent need for techniques that enable consistent, fast and accurate monitoring. This will allow invasion biologists the unprecedented capability to systematically monitor invasive alien species over the introduction, establishment and secondary dispersal phases of the invasion process, across large areas with a reduced risk of accidental invasive alien plant dispersal by field personnel.

Over the last year, Geethen has made excellent progress in creating a remote sensing method to monitor water, aquatic vegetation and the invasive Water Hyacinth. He is using semi-automated satellite image analysis techniques, such as semantic segmentation of freely available Landsat and Sentinel-2 imagery, to map the distribution of Water Hyacinth across South Africa. In collaboration with the Centre for Biological Control at Rhodes University, who provided valuable ground-truthing data for the species, Geethen has been able to produce accurate and robust predictions of aquatic vegetation and its subsequent discrimination across South Africa.

By conducting his analyses in the Google Earth Engine cloud computing platform, Geethen is able to produce up-to-date maps of invasive species distributions and percentage cover on a near-real-time basis. He has created an application to make these products available to managers and decision makers when they require them. Geethen is currently investigating how other satellite-derived data products can provide information on biotic and abiotic drivers of water hyacinth at a national and waterbody scale. This will include using satellite telemetry data of southern African waterbirds to assess the contribution of this little considered vector in invasive species spread. With the ability to identify the dominant drivers within regions comes the ability for managers to tailor more effective strategies to combat invasive populations.

Activities in 2020

  • Geethen published a manuscript on a method to derive the national distribution of Water Hyacinth.
  • Geethen presented a GIS course to Wits honours students.
  • Geethen co-created and presented a two-day introductory course on the Google Earth Engine to OTS students and staff.
  • Geethen created and presented a one-day workshop to SASSCAL grant members.
  • Geethen created and presented a Google Earth Engine for conservation practical component for a master’s Course and co-created one for the Conservation and Ecology online OTS course.
  • Geethen attended numerous online ‘geo for good’ summit talks, webinars and talks during the lockdown.
  • Geethen was involved in the discussion stages of a European Space Agency-funded project for mapping invasive aquatic weeds.


  • Geethen has published the first paper based on his PhD research.
  • Geethen has gained teaching/instructor experience through the multiple courses he has created and/or delivered.

Key co-supporters

DSi-NRF CoE grant.

Research team 2020
Dr Chevonne Reynolds (APES, Wits)
Dr Benjamin Rosman (Applied Maths, Wits)
Prof. Marcus Byrne (APES, Wits)

Student:  Geethen Singh (PhD, Wits)