.png){kind=icon}
.png){kind=icon}
Return
Comparative machine learning classification of a heterogeneous Ramsar wetland using Sentinel-1 and Sentinel-2 imagery with quantity and allocation disagreement diagnostics
.png){kind=icon}
OA
AI
C
E
I
S
DOI：10.3389/frsen.2026.1814582.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
IntroductionStrategic and active management of protected and heterogeneous wetland landscapes requires timely; accurate; and spatially explicit land-use and land-cover (LULC) information. This study presents a comprehensive landscape-level characterisation of LULC across South Africa’s first proclaimed World Heritage and Ramsar site; the iSimangaliso Wetland Park (IWP); and its surrounding areas.MethodsMulti-season Sentinel-2 imagery acquired in 2025 (autumn: March‐May; spring: September‐November) was integrated with Sentinel-1 backscatter; topographic variables; and ancillary datasets to enhance class separability in this complex environment. A total of 6; 588 training samples and 2; 358 validation samples were used to classify eight LULC classes; including open water; wetland; planted forest; natural forest; cropland; grassland; barren; and built-up areas; using four machine learning algorithms: Random Forest (RF); Support Vector Machine (SVM); Classification and Regression Trees (CART); and K-Nearest Neighbours (KNN). Classification performance was evaluated using confusion‐matrix metrics (overall; producer’s; and user’s accuracy); complemented by quantity disagreement (QD) and allocation disagreement (AD) to distinguish between proportional and spatial allocation errors.ResultsRF achieved the highest overall accuracy (0.91); followed by SVM (0.88); CART (0.87); and KNN (0.84). Class‐based analysis showed that spectrally distinct classes; such as open water; achieved very high accuracy (<0.90); whereas heterogeneous classes; including wetlands and grassland; exhibited lower accuracy due to spectral similarity. Misclassification errors were spatially clustered; primarily along wetland‐upland boundaries. Uncertainty metrics further indicated low classification confidence in areas with mixed vegetation and hydrologically dynamic conditions.DiscussionThe methodological novelty of this study lies in integrating full spatial coverage classification with disagreement-based accuracy analysis and spatially explicit uncertainty scrutiny; providing a robust evaluation and baseline for long-term LULC monitoring and conservation planning in complex wetland systems.
Keywords:
machine learning
google earth engine
iSimangaliso wetland park
land-use and land-cover
sentinel- 1 and 2
Journal
F
IF:
3.7
Papers:
560
Citations:
993
Organization
Cited Papers