Comparative Analysis of Fine-Tuned Foundation Models for Land Cover Classification using Sentinel-2 Imagery, Study Area: Sumatra and Kalimantan, Indonesia

Land cover classification plays a pivotal role in understanding and managing Earth's resources, influencing decisions in agriculture, forestry, urban planning, and environmental conservation. This study evaluates the performance of fine-tuning the Prithvi Foundation Model, Clay Foundation Model...

Full description

Saved in:
Bibliographic Details
Main Authors: W. Wiratama, M. K. Chong, Y. L. Lim, C. J. Ho
Format: Article
Language:English
Published: Copernicus Publications 2025-08-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1559/2025/isprs-archives-XLVIII-G-2025-1559-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850054673332961280
author W. Wiratama
M. K. Chong
Y. L. Lim
C. J. Ho
author_facet W. Wiratama
M. K. Chong
Y. L. Lim
C. J. Ho
author_sort W. Wiratama
collection DOAJ
description Land cover classification plays a pivotal role in understanding and managing Earth's resources, influencing decisions in agriculture, forestry, urban planning, and environmental conservation. This study evaluates the performance of fine-tuning the Prithvi Foundation Model, Clay Foundation Model, and U-Net++ with Sentinel-2 imagery for land cover classification in the regions of Kalimantan and Sumatra, Indonesia. Using a dataset of Sentinel-2 image tiles labelled with 12 land cover classes, the models were trained and assessed using Intersection over Union (IoU) metrics. Results demonstrate the superior performance of the Clay Foundation Model, achieving a mean IoU of 0.4819. This research paper highlights the potential of Vision Transformer-based foundation models in distinguishing complex land cover categories and suggests directions for future research.
format Article
id doaj-art-2b41fa8fd9bb4f1f836b663487a747d8
institution DOAJ
issn 1682-1750
2194-9034
language English
publishDate 2025-08-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-2b41fa8fd9bb4f1f836b663487a747d82025-08-20T02:52:11ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342025-08-01XLVIII-G-20251559156410.5194/isprs-archives-XLVIII-G-2025-1559-2025Comparative Analysis of Fine-Tuned Foundation Models for Land Cover Classification using Sentinel-2 Imagery, Study Area: Sumatra and Kalimantan, IndonesiaW. Wiratama0M. K. Chong1Y. L. Lim2C. J. Ho3ST Engineering Geo-Insights, SingaporeST Engineering Geo-Insights, SingaporeST Engineering Geo-Insights, SingaporeST Engineering Geo-Insights, SingaporeLand cover classification plays a pivotal role in understanding and managing Earth's resources, influencing decisions in agriculture, forestry, urban planning, and environmental conservation. This study evaluates the performance of fine-tuning the Prithvi Foundation Model, Clay Foundation Model, and U-Net++ with Sentinel-2 imagery for land cover classification in the regions of Kalimantan and Sumatra, Indonesia. Using a dataset of Sentinel-2 image tiles labelled with 12 land cover classes, the models were trained and assessed using Intersection over Union (IoU) metrics. Results demonstrate the superior performance of the Clay Foundation Model, achieving a mean IoU of 0.4819. This research paper highlights the potential of Vision Transformer-based foundation models in distinguishing complex land cover categories and suggests directions for future research.https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1559/2025/isprs-archives-XLVIII-G-2025-1559-2025.pdf
spellingShingle W. Wiratama
M. K. Chong
Y. L. Lim
C. J. Ho
Comparative Analysis of Fine-Tuned Foundation Models for Land Cover Classification using Sentinel-2 Imagery, Study Area: Sumatra and Kalimantan, Indonesia
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title Comparative Analysis of Fine-Tuned Foundation Models for Land Cover Classification using Sentinel-2 Imagery, Study Area: Sumatra and Kalimantan, Indonesia
title_full Comparative Analysis of Fine-Tuned Foundation Models for Land Cover Classification using Sentinel-2 Imagery, Study Area: Sumatra and Kalimantan, Indonesia
title_fullStr Comparative Analysis of Fine-Tuned Foundation Models for Land Cover Classification using Sentinel-2 Imagery, Study Area: Sumatra and Kalimantan, Indonesia
title_full_unstemmed Comparative Analysis of Fine-Tuned Foundation Models for Land Cover Classification using Sentinel-2 Imagery, Study Area: Sumatra and Kalimantan, Indonesia
title_short Comparative Analysis of Fine-Tuned Foundation Models for Land Cover Classification using Sentinel-2 Imagery, Study Area: Sumatra and Kalimantan, Indonesia
title_sort comparative analysis of fine tuned foundation models for land cover classification using sentinel 2 imagery study area sumatra and kalimantan indonesia
url https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1559/2025/isprs-archives-XLVIII-G-2025-1559-2025.pdf
work_keys_str_mv AT wwiratama comparativeanalysisoffinetunedfoundationmodelsforlandcoverclassificationusingsentinel2imagerystudyareasumatraandkalimantanindonesia
AT mkchong comparativeanalysisoffinetunedfoundationmodelsforlandcoverclassificationusingsentinel2imagerystudyareasumatraandkalimantanindonesia
AT yllim comparativeanalysisoffinetunedfoundationmodelsforlandcoverclassificationusingsentinel2imagerystudyareasumatraandkalimantanindonesia
AT cjho comparativeanalysisoffinetunedfoundationmodelsforlandcoverclassificationusingsentinel2imagerystudyareasumatraandkalimantanindonesia