Estimating fractional land cover using sentinel-2 and multi-source data with traditional machine learning and deep learning approaches

Land cover mapping is essential for territorial management due to its links with ecological, hydrological, climatic, and socioeconomic processes. Traditional methods use discrete classes per pixel, but this study proposes estimating cover fractions with Sentinel-2 imagery (20 m) and AI. We employed...

Descripción completa

Detalles Bibliográficos
Autores: Sierra Menéndez, Sergio, Ramo Sánchez, Rubén, Padilla, Marc, Quirós, Laura, Cobo García, Adolfo|||0000-0003-1498-9238
Tipo de recurso: artículo
Fecha de publicación:2025
País:España
Institución:Universidad de Cantabria (UC)
Repositorio:UCrea Repositorio Abierto de la Universidad de Cantabria
Idioma:inglés
OAI Identifier:oai:repositorio.unican.es:10902/38287
Acceso en línea:https://hdl.handle.net/10902/38287
Access Level:acceso abierto
Palabra clave:Land cover fraction mapping
Sentinel-2
Machine learning
Deep-learning
Land cover
id ES_f1db6d0f81c2ebff2198b0da55c3b77d
oai_identifier_str oai:repositorio.unican.es:10902/38287
network_acronym_str ES
network_name_str España
repository_id_str
spelling Estimating fractional land cover using sentinel-2 and multi-source data with traditional machine learning and deep learning approachesSierra Menéndez, SergioRamo Sánchez, RubénPadilla, MarcQuirós, LauraCobo García, Adolfo|||0000-0003-1498-9238Land cover fraction mappingSentinel-2Machine learningDeep-learningLand coverLand cover mapping is essential for territorial management due to its links with ecological, hydrological, climatic, and socioeconomic processes. Traditional methods use discrete classes per pixel, but this study proposes estimating cover fractions with Sentinel-2 imagery (20 m) and AI. We employed the French Land cover from Aerospace ImageRy (FLAIR) dataset (810 km2 in France, 19 classes), with labels co-registered with Sentinel-2 to derive precise fractional proportions per pixel. From these references, we generated training sets combining spectral bands, derived indices, and auxiliary data (climatic and tempo-ral variables). Various machine learning models-including XGBoost three deep neural network (DNN) architectures with different depths, and convolutional neural networks (CNNs) were trained and evaluated to identify the optimal configuration for fractional cover estimation. Model validation on the test set employed RMSE, MAE, and R2 metrics at both pixel level (20 m Sentinel-2) and scene level (100 m FLAIR). The training set integrating spectral bands, vegetation indices, and auxiliary variables yielded the best MAE and RMSE results. Among all models, DNN2 achieved the highest performance, with a pixel-level RMSE of 13.83 and MAE of 5.42, and a scene-level RMSE of 4.94 and MAE of 2.36. This fractional approach paves the way for advanced remote sensing applications, including con-tinuous cover-change monitoring, carbon footprint estimation, and sustainability-oriented territorial planning.This research was supported by the industrial doctorate grant DIN2021-011907 funded by MICIU/AEI/https://doi.org/10.13039/501100011033 and DI37 funded by Universidad de Cantabria and project “Photonic Sensors for Sustainable Smart Cities PERFORMANCE” PID2022-137269OBC22l(MICIU/AEI/https://doi.org/10.13039/501100011033andERDF/EU).MDPIUniversidad de Cantabria20252025-10-01journal articlehttp://purl.org/coar/resource_type/c_6501NAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/articlehttps://hdl.handle.net/10902/38287Remote Sensing, 2025, 17(19), 3364reponame:UCrea Repositorio Abierto de la Universidad de Cantabriainstname:Universidad de Cantabria (UC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2Attribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:repositorio.unican.es:10902/382872026-06-02T12:39:31Z
dc.title.none.fl_str_mv Estimating fractional land cover using sentinel-2 and multi-source data with traditional machine learning and deep learning approaches
title Estimating fractional land cover using sentinel-2 and multi-source data with traditional machine learning and deep learning approaches
spellingShingle Estimating fractional land cover using sentinel-2 and multi-source data with traditional machine learning and deep learning approaches
Sierra Menéndez, Sergio
Land cover fraction mapping
Sentinel-2
Machine learning
Deep-learning
Land cover
title_short Estimating fractional land cover using sentinel-2 and multi-source data with traditional machine learning and deep learning approaches
title_full Estimating fractional land cover using sentinel-2 and multi-source data with traditional machine learning and deep learning approaches
title_fullStr Estimating fractional land cover using sentinel-2 and multi-source data with traditional machine learning and deep learning approaches
title_full_unstemmed Estimating fractional land cover using sentinel-2 and multi-source data with traditional machine learning and deep learning approaches
title_sort Estimating fractional land cover using sentinel-2 and multi-source data with traditional machine learning and deep learning approaches
dc.creator.none.fl_str_mv Sierra Menéndez, Sergio
Ramo Sánchez, Rubén
Padilla, Marc
Quirós, Laura
Cobo García, Adolfo|||0000-0003-1498-9238
author Sierra Menéndez, Sergio
author_facet Sierra Menéndez, Sergio
Ramo Sánchez, Rubén
Padilla, Marc
Quirós, Laura
Cobo García, Adolfo|||0000-0003-1498-9238
author_role author
author2 Ramo Sánchez, Rubén
Padilla, Marc
Quirós, Laura
Cobo García, Adolfo|||0000-0003-1498-9238
author2_role author
author
author
author
dc.contributor.none.fl_str_mv Universidad de Cantabria
dc.subject.none.fl_str_mv Land cover fraction mapping
Sentinel-2
Machine learning
Deep-learning
Land cover
topic Land cover fraction mapping
Sentinel-2
Machine learning
Deep-learning
Land cover
description Land cover mapping is essential for territorial management due to its links with ecological, hydrological, climatic, and socioeconomic processes. Traditional methods use discrete classes per pixel, but this study proposes estimating cover fractions with Sentinel-2 imagery (20 m) and AI. We employed the French Land cover from Aerospace ImageRy (FLAIR) dataset (810 km2 in France, 19 classes), with labels co-registered with Sentinel-2 to derive precise fractional proportions per pixel. From these references, we generated training sets combining spectral bands, derived indices, and auxiliary data (climatic and tempo-ral variables). Various machine learning models-including XGBoost three deep neural network (DNN) architectures with different depths, and convolutional neural networks (CNNs) were trained and evaluated to identify the optimal configuration for fractional cover estimation. Model validation on the test set employed RMSE, MAE, and R2 metrics at both pixel level (20 m Sentinel-2) and scene level (100 m FLAIR). The training set integrating spectral bands, vegetation indices, and auxiliary variables yielded the best MAE and RMSE results. Among all models, DNN2 achieved the highest performance, with a pixel-level RMSE of 13.83 and MAE of 5.42, and a scene-level RMSE of 4.94 and MAE of 2.36. This fractional approach paves the way for advanced remote sensing applications, including con-tinuous cover-change monitoring, carbon footprint estimation, and sustainability-oriented territorial planning.
publishDate 2025
dc.date.none.fl_str_mv 2025
2025-10-01
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/10902/38287
url https://hdl.handle.net/10902/38287
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv Remote Sensing, 2025, 17(19), 3364
reponame:UCrea Repositorio Abierto de la Universidad de Cantabria
instname:Universidad de Cantabria (UC)
instname_str Universidad de Cantabria (UC)
reponame_str UCrea Repositorio Abierto de la Universidad de Cantabria
collection UCrea Repositorio Abierto de la Universidad de Cantabria
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869424222366859264
score 15,811543

Similares en LA Referencia