Importance of Spectral Information, Seasonality, and Topography on Land Cover Classification of Tropical Land Cover Mapping

Tropical forests provide essential ecosystem services, playing a critical role in climate regulation, biodiversity conservation, and regional hydrological cycles while also supporting livelihoods. However, they are increasingly threatened by deforestation and land-use change. Accurate land cover (LC...

Full description

Saved in:
Bibliographic Details
Main Authors: Chansopheaktra Sovann, Stefan Olin, Ali Mansourian, Sakada Sakhoeun, Sovann Prey, Sothea Kok, Torbern Tagesson
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/9/1551
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849312732662202368
author Chansopheaktra Sovann
Stefan Olin
Ali Mansourian
Sakada Sakhoeun
Sovann Prey
Sothea Kok
Torbern Tagesson
author_facet Chansopheaktra Sovann
Stefan Olin
Ali Mansourian
Sakada Sakhoeun
Sovann Prey
Sothea Kok
Torbern Tagesson
author_sort Chansopheaktra Sovann
collection DOAJ
description Tropical forests provide essential ecosystem services, playing a critical role in climate regulation, biodiversity conservation, and regional hydrological cycles while also supporting livelihoods. However, they are increasingly threatened by deforestation and land-use change. Accurate land cover (LC) mapping is vital to monitor these changes, but mapping tropical forests is challenging due to complex spatial patterns, spectral similarities, and frequent cloud cover. This study aims to improve LC classification accuracy in such a heterogeneous tropical forest region in Southeast Asia, namely Kulen, Cambodia, which is characterized by natural forests, regrowth forests, and agricultural lands including cashew plantations and croplands, using Sentinel-2 imagery, recursive feature elimination (RFE), and Random Forest. We generated 65 variables of spectral bands, indices, bi-seasonal differences, and topographic data from Sentinel-2 Level-2A and Shuttle Radar Topography Mission datasets. These variables were extracted from 1000 random points per 12 LC classes from reference polygons based on observed GPS points, Uncrewed Aerial Vehicle imagery, and high-resolution satellite data. The random forest models were optimized through correlation-based filtering and recursive feature elimination with hyperparameter tuning to improve classification accuracy, validated via confusion matrices and comparisons with global and national-scale products. Our results highlight the significant role of topographic variables such as elevation and slope, along with red-edge spectral bands and spectral indices related to tillage, leaf water content, greenness, chlorophyll, and tasseled cap transformation for tropical land cover mapping. The integration of bi-seasonal datasets improved classification accuracy, particularly for challenging classes like semi-evergreen and deciduous forests. Furthermore, correlation-based filtering and recursive feature elimination reduced the variable set from 65 to 19, improving model efficiency without sacrificing accuracy. Combining these variable selection methods with hyperparameter tuning optimized the classification, providing a more reliable LC product that outperforms existing LC products and proves valuable for deforestation monitoring, forest management, biodiversity conservation, and land use studies.
format Article
id doaj-art-abbb88ee808440f380ce081097e2e809
institution Kabale University
issn 2072-4292
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-abbb88ee808440f380ce081097e2e8092025-08-20T03:52:57ZengMDPI AGRemote Sensing2072-42922025-04-01179155110.3390/rs17091551Importance of Spectral Information, Seasonality, and Topography on Land Cover Classification of Tropical Land Cover MappingChansopheaktra Sovann0Stefan Olin1Ali Mansourian2Sakada Sakhoeun3Sovann Prey4Sothea Kok5Torbern Tagesson6Department of Physical Geography and Ecosystem Science, Lund University, Sölvegatan 12, 223 62 Lund, SwedenDepartment of Physical Geography and Ecosystem Science, Lund University, Sölvegatan 12, 223 62 Lund, SwedenDepartment of Physical Geography and Ecosystem Science, Lund University, Sölvegatan 12, 223 62 Lund, SwedenProvincial Department of Environment, Ministry of Environment, Siem Reap 171201, CambodiaIndependent Researcher, 142Eo, Street 19, Chey Chumneah Commune, Daunh Penh District, Phnom Penh 120208, CambodiaDepartment of Environmental Science, Royal University of Phnom Penh, Phnom Penh 120404, CambodiaDepartment of Physical Geography and Ecosystem Science, Lund University, Sölvegatan 12, 223 62 Lund, SwedenTropical forests provide essential ecosystem services, playing a critical role in climate regulation, biodiversity conservation, and regional hydrological cycles while also supporting livelihoods. However, they are increasingly threatened by deforestation and land-use change. Accurate land cover (LC) mapping is vital to monitor these changes, but mapping tropical forests is challenging due to complex spatial patterns, spectral similarities, and frequent cloud cover. This study aims to improve LC classification accuracy in such a heterogeneous tropical forest region in Southeast Asia, namely Kulen, Cambodia, which is characterized by natural forests, regrowth forests, and agricultural lands including cashew plantations and croplands, using Sentinel-2 imagery, recursive feature elimination (RFE), and Random Forest. We generated 65 variables of spectral bands, indices, bi-seasonal differences, and topographic data from Sentinel-2 Level-2A and Shuttle Radar Topography Mission datasets. These variables were extracted from 1000 random points per 12 LC classes from reference polygons based on observed GPS points, Uncrewed Aerial Vehicle imagery, and high-resolution satellite data. The random forest models were optimized through correlation-based filtering and recursive feature elimination with hyperparameter tuning to improve classification accuracy, validated via confusion matrices and comparisons with global and national-scale products. Our results highlight the significant role of topographic variables such as elevation and slope, along with red-edge spectral bands and spectral indices related to tillage, leaf water content, greenness, chlorophyll, and tasseled cap transformation for tropical land cover mapping. The integration of bi-seasonal datasets improved classification accuracy, particularly for challenging classes like semi-evergreen and deciduous forests. Furthermore, correlation-based filtering and recursive feature elimination reduced the variable set from 65 to 19, improving model efficiency without sacrificing accuracy. Combining these variable selection methods with hyperparameter tuning optimized the classification, providing a more reliable LC product that outperforms existing LC products and proves valuable for deforestation monitoring, forest management, biodiversity conservation, and land use studies.https://www.mdpi.com/2072-4292/17/9/1551land covertropical forestrecursive feature eliminationrandom forestKulenCambodia
spellingShingle Chansopheaktra Sovann
Stefan Olin
Ali Mansourian
Sakada Sakhoeun
Sovann Prey
Sothea Kok
Torbern Tagesson
Importance of Spectral Information, Seasonality, and Topography on Land Cover Classification of Tropical Land Cover Mapping
Remote Sensing
land cover
tropical forest
recursive feature elimination
random forest
Kulen
Cambodia
title Importance of Spectral Information, Seasonality, and Topography on Land Cover Classification of Tropical Land Cover Mapping
title_full Importance of Spectral Information, Seasonality, and Topography on Land Cover Classification of Tropical Land Cover Mapping
title_fullStr Importance of Spectral Information, Seasonality, and Topography on Land Cover Classification of Tropical Land Cover Mapping
title_full_unstemmed Importance of Spectral Information, Seasonality, and Topography on Land Cover Classification of Tropical Land Cover Mapping
title_short Importance of Spectral Information, Seasonality, and Topography on Land Cover Classification of Tropical Land Cover Mapping
title_sort importance of spectral information seasonality and topography on land cover classification of tropical land cover mapping
topic land cover
tropical forest
recursive feature elimination
random forest
Kulen
Cambodia
url https://www.mdpi.com/2072-4292/17/9/1551
work_keys_str_mv AT chansopheaktrasovann importanceofspectralinformationseasonalityandtopographyonlandcoverclassificationoftropicallandcovermapping
AT stefanolin importanceofspectralinformationseasonalityandtopographyonlandcoverclassificationoftropicallandcovermapping
AT alimansourian importanceofspectralinformationseasonalityandtopographyonlandcoverclassificationoftropicallandcovermapping
AT sakadasakhoeun importanceofspectralinformationseasonalityandtopographyonlandcoverclassificationoftropicallandcovermapping
AT sovannprey importanceofspectralinformationseasonalityandtopographyonlandcoverclassificationoftropicallandcovermapping
AT sotheakok importanceofspectralinformationseasonalityandtopographyonlandcoverclassificationoftropicallandcovermapping
AT torberntagesson importanceofspectralinformationseasonalityandtopographyonlandcoverclassificationoftropicallandcovermapping