Original Research

Mapping alien and indigenous vegetation in the KwaZulu-Natal Sandstone Sourveld using remotely sensed data

John Odindi, Onisimo Mutanga, Mathieu Rouget, Nomcebo Hlanguza
Bothalia | Vol 46, No 2 | a2103 | DOI: https://doi.org/10.4102/abc.v46i2.2103 | © 2016 John Odindi, Onisimo Mutanga, Mathieu Rouget, Nomcebo Hlanguza | This work is licensed under CC Attribution 4.0
Submitted: 19 May 2016 | Published: 18 November 2016

About the author(s)

John Odindi, School of Agricultural, Earth and Environmental Sciences, University of KwaZulu-Natal, South Africa
Onisimo Mutanga, School of Agricultural, Earth and Environmental Sciences, University of KwaZulu-Natal, South Africa
Mathieu Rouget, School of Agricultural, Earth and Environmental Sciences, University of KwaZulu-Natal, South Africa
Nomcebo Hlanguza, School of Agricultural, Earth and Environmental Sciences, University of KwaZulu-Natal, South Africa

Abstract

Background: The indigenous KwaZulu-Natal Sandstone Sourveld (KZN SS) grassland is highly endemic and species-rich, yet critically endangered and poorly conserved. Ecological threats to this grassland ecosystem are exacerbated by encroachment of woody plants, with severe negative environmental and economic consequences. Hence, there is an increasing need to reliably determine the extent of encroached or invaded areas to design optimal mitigation measures. Because of inherent limitations that characterise traditional approaches like field surveys and aerial photography, adoption of remotely sensed data offer reliable and timely mapping of landscape processes.
Objectives: We sought to map the distribution of woody vegetation within the KZN SS using remote sensing approaches.
Method: New generation RapidEye imagery, characterised by strategically positioned bands, and the advanced machine learning algorithm Random Forest (RF) were used to determine the distribution and composition of alien and indigenous woody vegetation within the KZN SS.
Results: Results show that alien and indigenous encroachment and invasion could be mapped with over 86% accuracy whilst the dominant indigenous and alien tree species could be mapped with over 74% accuracy. These results highlight the potential of new generation RapidEye satellite data in combination with advanced machine learning technique in predicting the distribution of alien and indigenous woody cover within a grassland ecosystem. The successful discrimination of the two classes and the species within the classes can be attributed to the additional strategically positioned bands, particularly the red-edge in the new generation RapidEye image.
Conclusion: Results underscore the potential of new generation RapidEye satellite data with strategically positioned bands and an advanced machine learning algorithm in predicting the distribution of woody cover in a grassland ecosystem.

Keywords

Sandstone Sourveld; remote sensing; encroachment; woody vegetation; invasion

Metrics

Total abstract views: 3682
Total article views: 5450

 

Crossref Citations

1. Characterisation of invasive plant proliferation within remnant riparian green corridors in Lusaka District of Zambia using Sentinel-2 imagery
Mutukwa Sikatala Ben Musole, Olusola O. Ololade, Franko Sokolic
Remote Sensing Applications: Society and Environment  vol: 15  first page: 100245  year: 2019  
doi: 10.1016/j.rsase.2019.100245

2. Estimating soil organic carbon stocks under commercial forestry using topo-climate variables in KwaZulu-Natal, South Africa
Omosalewa Odebiri, Onisimo Mutanga, John Odindi, Kabir Peerbhay, Steven Dovey, Riyad Ismail
South African Journal of Science  vol: 116  issue: 3/4  year: 2020  
doi: 10.17159/sajs.2020/6339

3. Mapping Invasive Herbaceous Plant Species with Sentinel-2 Satellite Imagery: Echium plantagineum in a Mediterranean Shrubland as a Case Study
Patricia Duncan, Erika Podest, Karen J. Esler, Sjirk Geerts, Candice Lyons
Geomatics  vol: 3  issue: 2  first page: 328  year: 2023  
doi: 10.3390/geomatics3020018

4. Detecting and mapping the spatial distribution of Chromoleana odorata invasions in communal areas of South Africa using Sentinel-2 multispectral remotely sensed data
Helen S. Ndlovu, Mbulisi Sibanda, John Odindi, Siphiwokuhle Buthelezi, Onisimo Mutanga
Physics and Chemistry of the Earth, Parts A/B/C  vol: 126  first page: 103081  year: 2022  
doi: 10.1016/j.pce.2021.103081

5. Deep learning-based national scale soil organic carbon mapping with Sentinel-3 data
Omosalewa Odebiri, Onisimo Mutanga, John Odindi
Geoderma  vol: 411  first page: 115695  year: 2022  
doi: 10.1016/j.geoderma.2022.115695

6. Detecting Invasive Alien Plant Species Using Remote Sensing, Machine Learning and Deep Learning
Perry B. Rakgoale, Silas Njoya Ngetar, Huan Liu
Journal of Sensors  vol: 2024  issue: 1  year: 2024  
doi: 10.1155/2024/8854675

7. Vegetation of Brazilian campos rupestres on siliceous substrates and their global analogues
Ladislav Mucina
Flora  vol: 238  first page: 11  year: 2018  
doi: 10.1016/j.flora.2017.06.007

8. Can biophysical parameters derived from Sentinel-2 space-borne sensor improve land cover characterisation in semi-arid regions?
Bester Tawona Mudereri, Tavengwa Chitata, Concilia Mukanga, Elvis Tawanda Mupfiga, Calisto Gwatirisa, Timothy Dube
Geocarto International  vol: 36  issue: 19  first page: 2204  year: 2021  
doi: 10.1080/10106049.2019.1695956

9. Evaluating the potential of freely available multispectral remotely sensed imagery in mapping American bramble (Rubus cuneifolius)
Perushan Rajah, John Odindi, Onisimo Mutanga
South African Geographical Journal  vol: 100  issue: 3  first page: 291  year: 2018  
doi: 10.1080/03736245.2018.1461683

10. Can Sentinel-2 be used to detect invasive alien trees and shrubs in Savanna and Grassland Biomes?
Alanna J. Rebelo, Shaeden Gokool, Petra B. Holden, Mark G. New
Remote Sensing Applications: Society and Environment  vol: 23  first page: 100600  year: 2021  
doi: 10.1016/j.rsase.2021.100600

11. Evaluating Landsat-8, Landsat-9 and Sentinel-2 imageries in land use and land cover (LULC) classification in a heterogeneous urban area
Simbarashe Jombo, Samuel Adelabu
GeoJournal  vol: 88  issue: S1  first page: 377  year: 2023  
doi: 10.1007/s10708-023-10982-8

12. Mapping soil organic carbon distribution across South Africa's major biomes using remote sensing-topo-climatic covariates and Concrete Autoencoder-Deep neural networks
Omosalewa Odebiri, Onisimo Mutanga, John Odindi, Rowan Naicker
Science of The Total Environment  vol: 865  first page: 161150  year: 2023  
doi: 10.1016/j.scitotenv.2022.161150

13. Improving the management of threatened ecosystems in an urban biodiversity hotspot through the Durban Research Action Partnership
Mathieu Rouget, Sean O’Donoghue, Chantal Taylor, Debra Roberts, Rob Slotow
Bothalia, African Biodiversity & Conservation  vol: 46  issue: 2  year: 2016  
doi: 10.4102/abc.v46i2.2199

14. Crop mapping in smallholder farms using unmanned aerial vehicle imagery and geospatial cloud computing infrastructure
Shaeden Gokool, Maqsooda Mahomed, Kiara Brewer, Vivek Naiken, Alistair Clulow, Mbulisi Sibanda, Tafadzwanashe Mabhaudhi
Heliyon  vol: 10  issue: 5  first page: e26913  year: 2024  
doi: 10.1016/j.heliyon.2024.e26913

15. Evaluating the capability of Worldview-2 imagery for mapping alien tree species in a heterogeneous urban environment
Simbarashe Jombo, Elhadi Adam, Marcus J. Byrne, Solomon W. Newete, Danielle Sinnett
Cogent Social Sciences  vol: 6  issue: 1  year: 2020  
doi: 10.1080/23311886.2020.1754146

16. Modelling soil organic carbon stock distribution across different land-uses in South Africa: A remote sensing and deep learning approach
Omosalewa Odebiri, Onisimo Mutanga, John Odindi, Rowan Naicker
ISPRS Journal of Photogrammetry and Remote Sensing  vol: 188  first page: 351  year: 2022  
doi: 10.1016/j.isprsjprs.2022.04.026

17. Predicting soil organic carbon stocks under commercial forest plantations in KwaZulu-Natal province, South Africa using remotely sensed data
Omosalewa Odebiri, Onisimo Mutanga, John Odindi, Kabir Peerbhay, Steven Dovey
GIScience & Remote Sensing  vol: 57  issue: 4  first page: 450  year: 2020  
doi: 10.1080/15481603.2020.1731108

18. Evaluating the potential of the red edge channel for C3 (Festuca spp.) grass discrimination using Sentinel-2 and Rapid Eye satellite image data
Charles Otunga, John Odindi, Onisimo Mutanga, Clement Adjorlolo
Geocarto International  vol: 34  issue: 10  first page: 1123  year: 2019  
doi: 10.1080/10106049.2018.1474274

19. A bi-seasonal classification of woody plant species using Sentinel-2A and SPOT-6 in a localised species-rich savanna environment
Emmanuel Fundisi, Solomon G. Tesfamichael, Fethi Ahmed
Geocarto International  vol: 37  issue: 21  first page: 6272  year: 2022  
doi: 10.1080/10106049.2021.1939441

20. Mapping the spatial distribution of the yellowwood tree (Podocarpus henkelii) in the Weza-Ngele forest using the newly launched Sentinel-2 multispectral imager data
Ntombifuthi Nzimande, Onisimo Mutanga, Zolo Kiala, Mbulisi Sibanda
South African Geographical Journal  vol: 103  issue: 2  first page: 204  year: 2021  
doi: 10.1080/03736245.2020.1722211