Classification of iSimangaliso Wetland Park using Landsat and Sentinel-2 data based on a random forest algorithm within google earth engine

Coastal wetland systems are increasingly threatened by anthropogenic pressures, including land-use change and climate variability, yet their long-term dynamics remain poorly understood. This study assessed land-use and land-cover (LULC) changes within and around iSimangaliso Wetland Park, South Africa, from 2000 to 2025 using multi-temporal Landsat and Sentinel-2 imagery and a Random Forest classification framework in Google Earth Engine. Analysis of six time points (2000, 2005, 2010, 2015, 2020, 2025) revealed substantial landscape transformation over 25 years. Built-up areas and natural forests showed the largest increases, expanding by 570.83 km2 (193.18%) and 780.25 km 2 (36.02%), respectively. Wetlands, grasslands, barren land, and croplands declined considerably, indicating extensive land-cover conversion. Pronounced wetland -grassland transitions and fluctuating water extents around Lake St Lucia, Lake Sibaya, and the Mfolozi and Mkhuze floodplains highlighted the dynamic nature of the park’s ecosystems. These changes reflect the combined influence of human pressures, rainfall variability and hydrological shifts, emphasizing the need for long-term monitoring to support conservation and management.

Authors

Institutions

Publication Details

Journal
Frontiers in Remote Sensing
Published
2026-11-19
DOI
https://doi.org/10.3389/frsen.2026.1972828
Primary Topic
Remote-Sensing Image Classification
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Classification of iSimangaliso Wetland Park using Landsat and Sentinel-2 data based on a random forest algorithm within google earth engine

Sifiso Xulu, E.J.J. Sieben, Irvin D. Shandu, Cornelia Chifurira
Frontiers in Remote Sensing
Remote-Sensing Image Classification
article

Classification of iSimangaliso Wetland Park using Landsat and Sentinel-2 data based on a random forest algorithm within google earth engine

Sifiso Xulu, E.J.J. Sieben, Irvin D. Shandu, Cornelia Chifurira
article en

Abstract

Coastal wetland systems are increasingly threatened by anthropogenic pressures, including land-use change and climate variability, yet their long-term dynamics remain poorly understood. This study assessed land-use and land-cover (LULC) changes within and around iSimangaliso Wetland Park, South Africa, from 2000 to 2025 using multi-temporal Landsat and Sentinel-2 imagery and a Random Forest classification framework in Google Earth Engine. Analysis of six time points (2000, 2005, 2010, 2015, 2020, 2025) revealed substantial landscape transformation over 25 years. Built-up areas and natural forests showed the largest increases, expanding by 570.83 km2 (193.18%) and 780.25 km 2 (36.02%), respectively. Wetlands, grasslands, barren land, and croplands declined considerably, indicating extensive land-cover conversion. Pronounced wetland -grassland transitions and fluctuating water extents around Lake St Lucia, Lake Sibaya, and the Mfolozi and Mkhuze floodplains highlighted the dynamic nature of the park’s ecosystems. These changes reflect the combined influence of human pressures, rainfall variability and hydrological shifts, emphasizing the need for long-term monitoring to support conservation and management.

Frontiers in Remote SensingVol. 7
University of South Africa (ZA), University of KwaZulu-Natal (ZA)
Remote-Sensing Image Classification
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon