A Comparative Assessment of Machine and Deep Learning Approaches for Grassland Mapping with Sentinel-1, Sentinel-2 and Ancillary Data
Land · 07.07.2026 · 15 (7) · 1215
DOI: 10.3390/land15071215 ↗Kurz gefasst
Fachartikel in der Zeitschrift Land, online erschienen am 07.07.2026. Verfasst von Princess Khoza und 4 weiteren Autor:innen. Die Arbeit nennt 94 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Department of Agriculture, Agricultural Research Council-Natural Resources and Engineering, National Research Foundation (NRF) Thuthuka project.
Abstract (Originalsprache)
Grasslands represent one of the most extensive terrestrial biomes globally, covering approximately one-third of the Earth’s land surface, yet they are increasingly threatened by land-use change and overgrazing, underscoring the need for reliable monitoring approaches. This study compares the performance of machine learning and deep learning algorithms for grassland mapping using multi-source remote sensing data derived from Sentinel-1, Sentinel-2, and terrain variables. The research was conducted in Mpumalanga Province, South Africa, a heterogeneous landscape comprising lowland savannas, high-altitude grasslands, escarpments, and riverine wetlands. Random Forest (RF) and Support Vector Machine (SVM) classifiers were implemented in Google Earth Engine using fused satellite and terrain datasets with field-collected samples for training and validation, while a One-Dimensional Convolutional Neural Network (1D-CNN) was developed in Python 3.13.5 using the same inputs. Results demonstrate that integrating multi-source data improves classification accuracy, with radar-based features contributing the most. RF achieved the highest performance, with an overall accuracy of 97.7% and grass-class precision, recall, and F1-score exceeding 0.97, closely followed by the 1D-CNN with 91% overall accuracy and complete grass detection. In contrast, SVM performed notably lower with an overall accuracy of 80,8%. These findings highlight the effectiveness of advanced learning approaches for grassland mapping and support their application in ecological restoration and environmental management.
Förderung
- Department of Agriculture
- Agricultural Research Council-Natural Resources and Engineering
- National Research Foundation (NRF) Thuthuka project
Zitieren
APA
Khoza, P., Mashaba-Munghemezulu, Z., Mabetoa, E., Sibanda, S., & Chirima, G. J. (2026). A Comparative Assessment of Machine and Deep Learning Approaches for Grassland Mapping with Sentinel-1, Sentinel-2 and Ancillary Data. Land, 15(7), 1215. https://doi.org/10.3390/land15071215
Vancouver
Khoza P, Mashaba-Munghemezulu Z, Mabetoa E, Sibanda S, Chirima GJ. A Comparative Assessment of Machine and Deep Learning Approaches for Grassland Mapping with Sentinel-1, Sentinel-2 and Ancillary Data. Land. 2026;15(7):1215. doi:10.3390/land15071215
BibTeX
@article{Khoza2026,
author = {Khoza, Princess and Mashaba-Munghemezulu, Zinhle and Mabetoa, Elias and Sibanda, Sipho and Chirima, George Johannes},
title = {A Comparative Assessment of Machine and Deep Learning Approaches for Grassland Mapping with Sentinel-1, Sentinel-2 and Ancillary Data},
journal = {Land},
year = {2026},
volume = {15},
number = {7},
pages = {1215},
doi = {10.3390/land15071215}
}
EUVIMED