Land-cover classification in Addo Elephant National Park: Analyzing the impact of variables, classifiers, and object-based approach
A comprehensive understanding of land-use and land-cover (LULC) dynamics is vital in steering effective conservation and management efforts, especially in ecologically rich regions like Addo Elephant National Park (AENP). Despite its importance, up-to-date LULC maps of AENP remain scarce, needing an...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-12-01
|
| Series: | Ecological Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1574954125002882 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849233596779331584 |
|---|---|
| author | Mohammad Safaei Jane Southworth Cerian Gibbes Hannah V. Herrero Mashoukur Rahaman Bewuket B. Tefera Jason K. Blackburn |
| author_facet | Mohammad Safaei Jane Southworth Cerian Gibbes Hannah V. Herrero Mashoukur Rahaman Bewuket B. Tefera Jason K. Blackburn |
| author_sort | Mohammad Safaei |
| collection | DOAJ |
| description | A comprehensive understanding of land-use and land-cover (LULC) dynamics is vital in steering effective conservation and management efforts, especially in ecologically rich regions like Addo Elephant National Park (AENP). Despite its importance, up-to-date LULC maps of AENP remain scarce, needing an in-depth investigation to aid conservation planning. Using Landsat time-series data, this study produced 30-m resolution LULC maps for the years 2002, 2014, and 2022, and examined changes within six LULC categories. Object-based classification was compared with a pixel-based approach, revealing the superior performance of the pixel-based approach. Two machine learning (ML) techniques, Random Forest (RF) and Support Vector Machines (SVM), were compared with a deep learning (DL) technique, UNet++. The land-cover classification process using ML algorithms involved experimentation with various predictor variables, including spectral bands, spectral indices, time-series data, and textural information. Spectral mixture analysis was performed, and the resulting fraction layers were used as independent variables in the models. The study identified RF as the preferred classification algorithm using the optimal combination of these variables, achieving high accuracy of 89.1 %, 91.2 %, and 91.9 % for the years 2002, 2014, and 2022, respectively. Variable importance analysis highlighted the consistent significance of elevation, slope, and the time-series of normalized difference indices. The final land-cover maps revealed grass as the predominant class both inside and outside AENP, followed by thicket within the park, and agriculture outside it. Land-cover change analysis indicated small changes (<3 %), primarily involving transitions between thicket and grass classes inside the park, and grass and agriculture outside. |
| format | Article |
| id | doaj-art-46aa91d28907430383f8d6e448baf64f |
| institution | Kabale University |
| issn | 1574-9541 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Informatics |
| spelling | doaj-art-46aa91d28907430383f8d6e448baf64f2025-08-20T05:05:31ZengElsevierEcological Informatics1574-95412025-12-019010327910.1016/j.ecoinf.2025.103279Land-cover classification in Addo Elephant National Park: Analyzing the impact of variables, classifiers, and object-based approachMohammad Safaei0Jane Southworth1Cerian Gibbes2Hannah V. Herrero3Mashoukur Rahaman4Bewuket B. Tefera5Jason K. Blackburn6Department of Geography, University of Florida, Gainesville, FL, USA; Corresponding author.Department of Geography, University of Florida, Gainesville, FL, USADepartment of Geography & Environmental Studies, University of Colorado, Colorado Springs, CO, USADepartment of Geography & Sustainability, University of Tennessee, Knoxville, TN, USADepartment of Geography, University of Florida, Gainesville, FL, USADepartment of Geography, University of Florida, Gainesville, FL, USADepartment of Geography, University of Florida, Gainesville, FL, USAA comprehensive understanding of land-use and land-cover (LULC) dynamics is vital in steering effective conservation and management efforts, especially in ecologically rich regions like Addo Elephant National Park (AENP). Despite its importance, up-to-date LULC maps of AENP remain scarce, needing an in-depth investigation to aid conservation planning. Using Landsat time-series data, this study produced 30-m resolution LULC maps for the years 2002, 2014, and 2022, and examined changes within six LULC categories. Object-based classification was compared with a pixel-based approach, revealing the superior performance of the pixel-based approach. Two machine learning (ML) techniques, Random Forest (RF) and Support Vector Machines (SVM), were compared with a deep learning (DL) technique, UNet++. The land-cover classification process using ML algorithms involved experimentation with various predictor variables, including spectral bands, spectral indices, time-series data, and textural information. Spectral mixture analysis was performed, and the resulting fraction layers were used as independent variables in the models. The study identified RF as the preferred classification algorithm using the optimal combination of these variables, achieving high accuracy of 89.1 %, 91.2 %, and 91.9 % for the years 2002, 2014, and 2022, respectively. Variable importance analysis highlighted the consistent significance of elevation, slope, and the time-series of normalized difference indices. The final land-cover maps revealed grass as the predominant class both inside and outside AENP, followed by thicket within the park, and agriculture outside it. Land-cover change analysis indicated small changes (<3 %), primarily involving transitions between thicket and grass classes inside the park, and grass and agriculture outside.http://www.sciencedirect.com/science/article/pii/S1574954125002882Land-use and land-coverAddo Elephant National ParkDeep learningChange detectionSpectral mixture analysisGoogle earth engine |
| spellingShingle | Mohammad Safaei Jane Southworth Cerian Gibbes Hannah V. Herrero Mashoukur Rahaman Bewuket B. Tefera Jason K. Blackburn Land-cover classification in Addo Elephant National Park: Analyzing the impact of variables, classifiers, and object-based approach Ecological Informatics Land-use and land-cover Addo Elephant National Park Deep learning Change detection Spectral mixture analysis Google earth engine |
| title | Land-cover classification in Addo Elephant National Park: Analyzing the impact of variables, classifiers, and object-based approach |
| title_full | Land-cover classification in Addo Elephant National Park: Analyzing the impact of variables, classifiers, and object-based approach |
| title_fullStr | Land-cover classification in Addo Elephant National Park: Analyzing the impact of variables, classifiers, and object-based approach |
| title_full_unstemmed | Land-cover classification in Addo Elephant National Park: Analyzing the impact of variables, classifiers, and object-based approach |
| title_short | Land-cover classification in Addo Elephant National Park: Analyzing the impact of variables, classifiers, and object-based approach |
| title_sort | land cover classification in addo elephant national park analyzing the impact of variables classifiers and object based approach |
| topic | Land-use and land-cover Addo Elephant National Park Deep learning Change detection Spectral mixture analysis Google earth engine |
| url | http://www.sciencedirect.com/science/article/pii/S1574954125002882 |
| work_keys_str_mv | AT mohammadsafaei landcoverclassificationinaddoelephantnationalparkanalyzingtheimpactofvariablesclassifiersandobjectbasedapproach AT janesouthworth landcoverclassificationinaddoelephantnationalparkanalyzingtheimpactofvariablesclassifiersandobjectbasedapproach AT ceriangibbes landcoverclassificationinaddoelephantnationalparkanalyzingtheimpactofvariablesclassifiersandobjectbasedapproach AT hannahvherrero landcoverclassificationinaddoelephantnationalparkanalyzingtheimpactofvariablesclassifiersandobjectbasedapproach AT mashoukurrahaman landcoverclassificationinaddoelephantnationalparkanalyzingtheimpactofvariablesclassifiersandobjectbasedapproach AT bewuketbtefera landcoverclassificationinaddoelephantnationalparkanalyzingtheimpactofvariablesclassifiersandobjectbasedapproach AT jasonkblackburn landcoverclassificationinaddoelephantnationalparkanalyzingtheimpactofvariablesclassifiersandobjectbasedapproach |