Supplementary file 1_Effectiveness evaluation of combining SAR and multiple optical data on land cover mapping of a fragmented landscape in a cloud computing platform.docx

<p>Land use/land cover (LULC) mapping in fragmented landscapes, characterized by multiple and small land uses, is still a challenge. This study aims to evaluate the effectiveness of Synthetic Aperture Radar (SAR) and multispectral optical data in land cover mapping using Google Earth Engine (G...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Giovanni Romano (21373319) (author)
مؤلفون آخرون: Giovanni Francesco Ricci (21373322) (author), Francesco Gentile (500655) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1852020334180433920
author Giovanni Romano (21373319)
author2 Giovanni Francesco Ricci (21373322)
Francesco Gentile (500655)
author2_role author
author
author_facet Giovanni Romano (21373319)
Giovanni Francesco Ricci (21373322)
Francesco Gentile (500655)
author_role author
dc.creator.none.fl_str_mv Giovanni Romano (21373319)
Giovanni Francesco Ricci (21373322)
Francesco Gentile (500655)
dc.date.none.fl_str_mv 2025-05-16T05:13:36Z
dc.identifier.none.fl_str_mv 10.3389/frsen.2025.1535418.s002
dc.relation.none.fl_str_mv https://figshare.com/articles/dataset/Supplementary_file_1_Effectiveness_evaluation_of_combining_SAR_and_multiple_optical_data_on_land_cover_mapping_of_a_fragmented_landscape_in_a_cloud_computing_platform_docx/29084447
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Photogrammetry and Remote Sensing
google earth engine
Landsat 8
Sentinel-1
Sentinel-2
land cover classification
spectral indices
RF classifier
dc.title.none.fl_str_mv Supplementary file 1_Effectiveness evaluation of combining SAR and multiple optical data on land cover mapping of a fragmented landscape in a cloud computing platform.docx
dc.type.none.fl_str_mv Dataset
info:eu-repo/semantics/publishedVersion
dataset
description <p>Land use/land cover (LULC) mapping in fragmented landscapes, characterized by multiple and small land uses, is still a challenge. This study aims to evaluate the effectiveness of Synthetic Aperture Radar (SAR) and multispectral optical data in land cover mapping using Google Earth Engine (GEE), a cloud computing platform allowing big geospatial data analysis. The proposed approach combines multi-source satellite imagery for accurate land cover classification in a fragmented municipal territory in Southern Italy over a 5-month vegetative period. Within the GEE platform, a set of Sentinel-1, Sentinel-2, and Landsat 8 data was acquired and processed to generate a land cover map for the 2021 greenness period. A supervised pixel-based classification was performed, using a Random Forest (RF) machine learning algorithm, to classify the imagery and derived spectral indices into eight land cover classes. Classification accuracy was assessed using Overall Accuracy (OA), Producer’s and User’s accuracies (PA, UA), and F-score. McNemar’s test was applied to assess the significance of difference between classification results. The optical integrated datasets in combination with SAR data and derivate indices (NDVI, GNDVI, NDBI, VHVV) produce the most accurate LULC map among those produced (OA: 89.64%), while SAR-only datasets performed the lowest accuracy (OA: 61.30%). The classification process offers several advantages, including widespread spectral information, SAR’s ability to capture almost all-weather, day-and-night imagery, and the computation of vegetation indices in the near infrared spectrum interval, in a short revisit time. The proposed digital techniques for processing multi-temporal satellite data provide useful tools for understanding territorial and environmental dynamics, supporting decision-making in land use planning, agricultural expansion, and environmental management in fragmented landscapes.</p>
eu_rights_str_mv openAccess
id Manara_240dfea76ece9ebe29bced9e9014db02
identifier_str_mv 10.3389/frsen.2025.1535418.s002
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/29084447
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Supplementary file 1_Effectiveness evaluation of combining SAR and multiple optical data on land cover mapping of a fragmented landscape in a cloud computing platform.docxGiovanni Romano (21373319)Giovanni Francesco Ricci (21373322)Francesco Gentile (500655)Photogrammetry and Remote Sensinggoogle earth engineLandsat 8Sentinel-1Sentinel-2land cover classificationspectral indicesRF classifier<p>Land use/land cover (LULC) mapping in fragmented landscapes, characterized by multiple and small land uses, is still a challenge. This study aims to evaluate the effectiveness of Synthetic Aperture Radar (SAR) and multispectral optical data in land cover mapping using Google Earth Engine (GEE), a cloud computing platform allowing big geospatial data analysis. The proposed approach combines multi-source satellite imagery for accurate land cover classification in a fragmented municipal territory in Southern Italy over a 5-month vegetative period. Within the GEE platform, a set of Sentinel-1, Sentinel-2, and Landsat 8 data was acquired and processed to generate a land cover map for the 2021 greenness period. A supervised pixel-based classification was performed, using a Random Forest (RF) machine learning algorithm, to classify the imagery and derived spectral indices into eight land cover classes. Classification accuracy was assessed using Overall Accuracy (OA), Producer’s and User’s accuracies (PA, UA), and F-score. McNemar’s test was applied to assess the significance of difference between classification results. The optical integrated datasets in combination with SAR data and derivate indices (NDVI, GNDVI, NDBI, VHVV) produce the most accurate LULC map among those produced (OA: 89.64%), while SAR-only datasets performed the lowest accuracy (OA: 61.30%). The classification process offers several advantages, including widespread spectral information, SAR’s ability to capture almost all-weather, day-and-night imagery, and the computation of vegetation indices in the near infrared spectrum interval, in a short revisit time. The proposed digital techniques for processing multi-temporal satellite data provide useful tools for understanding territorial and environmental dynamics, supporting decision-making in land use planning, agricultural expansion, and environmental management in fragmented landscapes.</p>2025-05-16T05:13:36ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.3389/frsen.2025.1535418.s002https://figshare.com/articles/dataset/Supplementary_file_1_Effectiveness_evaluation_of_combining_SAR_and_multiple_optical_data_on_land_cover_mapping_of_a_fragmented_landscape_in_a_cloud_computing_platform_docx/29084447CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/290844472025-05-16T05:13:36Z
spellingShingle Supplementary file 1_Effectiveness evaluation of combining SAR and multiple optical data on land cover mapping of a fragmented landscape in a cloud computing platform.docx
Giovanni Romano (21373319)
Photogrammetry and Remote Sensing
google earth engine
Landsat 8
Sentinel-1
Sentinel-2
land cover classification
spectral indices
RF classifier
status_str publishedVersion
title Supplementary file 1_Effectiveness evaluation of combining SAR and multiple optical data on land cover mapping of a fragmented landscape in a cloud computing platform.docx
title_full Supplementary file 1_Effectiveness evaluation of combining SAR and multiple optical data on land cover mapping of a fragmented landscape in a cloud computing platform.docx
title_fullStr Supplementary file 1_Effectiveness evaluation of combining SAR and multiple optical data on land cover mapping of a fragmented landscape in a cloud computing platform.docx
title_full_unstemmed Supplementary file 1_Effectiveness evaluation of combining SAR and multiple optical data on land cover mapping of a fragmented landscape in a cloud computing platform.docx
title_short Supplementary file 1_Effectiveness evaluation of combining SAR and multiple optical data on land cover mapping of a fragmented landscape in a cloud computing platform.docx
title_sort Supplementary file 1_Effectiveness evaluation of combining SAR and multiple optical data on land cover mapping of a fragmented landscape in a cloud computing platform.docx
topic Photogrammetry and Remote Sensing
google earth engine
Landsat 8
Sentinel-1
Sentinel-2
land cover classification
spectral indices
RF classifier