Detecting abandoned citrus crops using Sentinel-2 time series. A case study in the Comunitat Valenciana region (Spain)

Agricultural land abandonment (ALA) is becoming a growing phenomenon around the world that needs to be monitored and quantified. A massive abandonment of citrus orchards has been experienced in the last years in the Comunitat Valenciana (CV) region (Spain) driven by different socio-economic factors....

Descripción completa

Detalles Bibliográficos
Autores principales: Morell-Monzó, serg, Sebastiá-Frasquet, María T., Estornell, Javier, Moltó, Enrique
Formato: article
Lenguaje:Inglés
Publicado: International Society for Photogrammetry and Remote Sensing 2023
Materias:
Acceso en línea:https://hdl.handle.net/20.500.11939/8643
https://www.sciencedirect.com/science/article/pii/S0924271623001181
_version_ 1855032828180299776
author Morell-Monzó, serg
Sebastiá-Frasquet, María T.
Estornell, Javier
Moltó, Enrique
author_browse Estornell, Javier
Moltó, Enrique
Morell-Monzó, serg
Sebastiá-Frasquet, María T.
author_facet Morell-Monzó, serg
Sebastiá-Frasquet, María T.
Estornell, Javier
Moltó, Enrique
author_sort Morell-Monzó, serg
collection ReDivia
description Agricultural land abandonment (ALA) is becoming a growing phenomenon around the world that needs to be monitored and quantified. A massive abandonment of citrus orchards has been experienced in the last years in the Comunitat Valenciana (CV) region (Spain) driven by different socio-economic factors. Therefore, developing time and cost-efficient methods for monitoring ALA is a priority. Citrus are a perennial crop trees which make orchards have low spectral variation during the year. In the CV region, they are planted in relatively small parcels, thus creating a highly fragmented and heterogeneous landscape. This study proposes a machine learning-based classification framework that uses annual time series of spectral indices extracted from Sentinel-2 images to identify crop status at parcel level. The method is based on features extracted from the reconstructed OSAVI and NDMI time series used to train a Random Forest classifier. Then, a parcel-based classification is performed using the parcel boundaries and the probabilities of belonging to each category for the full pixels inside the boundaries. The research assessed the potential to identify three statuses of crops (non-productive, productive, and abandoned). Results on three different temporal and spatial datasets provided an overall accuracy ranging from 89 to 92 %, demonstrating the importance of multi-temporal data to identify the abandonment of perennial crops. Furthermore, we studied the ability of the model to be spatially and temporally transferred. Limitations to recall the abandoned parcels when using models trained in other areas or time periods are exposed, opening the way to model improvements.
format article
id ReDivia8643
institution Instituto Valenciano de Investigaciones Agrarias (IVIA)
language Inglés
publishDate 2023
publishDateRange 2023
publishDateSort 2023
publisher International Society for Photogrammetry and Remote Sensing
publisherStr International Society for Photogrammetry and Remote Sensing
record_format dspace
spelling ReDivia86432025-04-25T14:49:12Z Detecting abandoned citrus crops using Sentinel-2 time series. A case study in the Comunitat Valenciana region (Spain) Morell-Monzó, serg Sebastiá-Frasquet, María T. Estornell, Javier Moltó, Enrique Sentinel 2 Agricultural land abandonment Citrus crops N01 Agricultural engineering E90 Agrarian structure A50 Agricultural research U10 Mathematical and statistical methods Time series analysis Crop monitoring Perennial crops Agricultural land abandonment (ALA) is becoming a growing phenomenon around the world that needs to be monitored and quantified. A massive abandonment of citrus orchards has been experienced in the last years in the Comunitat Valenciana (CV) region (Spain) driven by different socio-economic factors. Therefore, developing time and cost-efficient methods for monitoring ALA is a priority. Citrus are a perennial crop trees which make orchards have low spectral variation during the year. In the CV region, they are planted in relatively small parcels, thus creating a highly fragmented and heterogeneous landscape. This study proposes a machine learning-based classification framework that uses annual time series of spectral indices extracted from Sentinel-2 images to identify crop status at parcel level. The method is based on features extracted from the reconstructed OSAVI and NDMI time series used to train a Random Forest classifier. Then, a parcel-based classification is performed using the parcel boundaries and the probabilities of belonging to each category for the full pixels inside the boundaries. The research assessed the potential to identify three statuses of crops (non-productive, productive, and abandoned). Results on three different temporal and spatial datasets provided an overall accuracy ranging from 89 to 92 %, demonstrating the importance of multi-temporal data to identify the abandonment of perennial crops. Furthermore, we studied the ability of the model to be spatially and temporally transferred. Limitations to recall the abandoned parcels when using models trained in other areas or time periods are exposed, opening the way to model improvements. 2023-06-09T07:08:01Z 2023-06-09T07:08:01Z 2023 article publishedVersion Morell-Monzó, S., Sebastiá-Frasquet, M. T., Estornell, J. & Moltó, E. (2023). Detecting abandoned citrus crops using Sentinel-2 time series. A case study in the Comunitat Valenciana region (Spain). ISPRS Journal of Photogrammetry and Remote Sensing, 201, 54-66. 1872-8235 (online) 0924-2716 (PrintISSN) https://hdl.handle.net/20.500.11939/8643 10.1016/j.isprsjprs.2023.05.003 https://www.sciencedirect.com/science/article/pii/S0924271623001181 en This research was partially funded by regional government of Spain, Generalitat Valenciana, within the framework of the research project AICO/2020/246. Funding for open access charge: CRUE-Universitat Politècnica de València Attribution-NonCommercial-NoDerivatives 4.0 Internacional http://creativecommons.org/licenses/by-nc-nd/4.0/ openAccess International Society for Photogrammetry and Remote Sensing electronico
spellingShingle Sentinel 2
Agricultural land abandonment
Citrus crops
N01 Agricultural engineering
E90 Agrarian structure
A50 Agricultural research
U10 Mathematical and statistical methods
Time series analysis
Crop monitoring
Perennial crops
Morell-Monzó, serg
Sebastiá-Frasquet, María T.
Estornell, Javier
Moltó, Enrique
Detecting abandoned citrus crops using Sentinel-2 time series. A case study in the Comunitat Valenciana region (Spain)
title Detecting abandoned citrus crops using Sentinel-2 time series. A case study in the Comunitat Valenciana region (Spain)
title_full Detecting abandoned citrus crops using Sentinel-2 time series. A case study in the Comunitat Valenciana region (Spain)
title_fullStr Detecting abandoned citrus crops using Sentinel-2 time series. A case study in the Comunitat Valenciana region (Spain)
title_full_unstemmed Detecting abandoned citrus crops using Sentinel-2 time series. A case study in the Comunitat Valenciana region (Spain)
title_short Detecting abandoned citrus crops using Sentinel-2 time series. A case study in the Comunitat Valenciana region (Spain)
title_sort detecting abandoned citrus crops using sentinel 2 time series a case study in the comunitat valenciana region spain
topic Sentinel 2
Agricultural land abandonment
Citrus crops
N01 Agricultural engineering
E90 Agrarian structure
A50 Agricultural research
U10 Mathematical and statistical methods
Time series analysis
Crop monitoring
Perennial crops
url https://hdl.handle.net/20.500.11939/8643
https://www.sciencedirect.com/science/article/pii/S0924271623001181
work_keys_str_mv AT morellmonzoserg detectingabandonedcitruscropsusingsentinel2timeseriesacasestudyinthecomunitatvalencianaregionspain
AT sebastiafrasquetmariat detectingabandonedcitruscropsusingsentinel2timeseriesacasestudyinthecomunitatvalencianaregionspain
AT estornelljavier detectingabandonedcitruscropsusingsentinel2timeseriesacasestudyinthecomunitatvalencianaregionspain
AT moltoenrique detectingabandonedcitruscropsusingsentinel2timeseriesacasestudyinthecomunitatvalencianaregionspain