Synergy of Sentinel-1 and Sentinel-2 Time Series for Cloud-Free Vegetation Water Content Mapping with Multi-Output Gaussian Processes
Optical Earth Observation is often limited by weather conditions such as cloudiness. Radar sensors have the potential to overcome these limitations, however, due to the complex radar-surface interaction, the retrieving of crop biophysical variables using this technology remains an open challenge. Ai...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Artículo |
| Language: | Inglés |
| Published: |
MDPI
2023
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/20.500.12123/14389 https://www.mdpi.com/2072-4292/15/7/1822 https://doi.org/10.3390/rs15071822 |
| _version_ | 1855485352733573120 |
|---|---|
| author | Caballero, Gabriel Pezzola, Nestor Alejandro Winschel, Cristina Ines Sanchez Angonova, Paolo Andres Casella, Alejandra An Orden, Luciano Salinero-Delgado, Matías Reyes-Muñoz, Pablo Berger, Katja Delegido, Jesús Verrelst, Jochem |
| author_browse | Berger, Katja Caballero, Gabriel Casella, Alejandra An Delegido, Jesús Orden, Luciano Pezzola, Nestor Alejandro Reyes-Muñoz, Pablo Salinero-Delgado, Matías Sanchez Angonova, Paolo Andres Verrelst, Jochem Winschel, Cristina Ines |
| author_facet | Caballero, Gabriel Pezzola, Nestor Alejandro Winschel, Cristina Ines Sanchez Angonova, Paolo Andres Casella, Alejandra An Orden, Luciano Salinero-Delgado, Matías Reyes-Muñoz, Pablo Berger, Katja Delegido, Jesús Verrelst, Jochem |
| author_sort | Caballero, Gabriel |
| collection | INTA Digital |
| description | Optical Earth Observation is often limited by weather conditions such as cloudiness. Radar sensors have the potential to overcome these limitations, however, due to the complex radar-surface interaction, the retrieving of crop biophysical variables using this technology remains an open challenge. Aiming to simultaneously benefit from the optical domain background and the all-weather imagery provided by radar systems, we propose a data fusion approach focused on the cross-correlation between radar and optical data streams. To do so, we analyzed several multiple-output Gaussian processes (MOGP) models and their ability to fuse efficiently Sentinel-1 (S1) Radar Vegetation Index (RVI) and Sentinel-2 (S2) vegetation water content (VWC) time series over a dry agri-environment in southern Argentina. MOGP models not only exploit the auto-correlations of S1 and S2 data streams independently but also the inter-channel cross-correlations. The S1 RVI and S2 VWC time series at the selected study sites being the inputs of the MOGP models proved to be closely correlated. Regarding the set of assessed models, the Convolutional Gaussian model (CONV) delivered noteworthy accurate data fusion results over winter wheat croplands belonging to the 2020 and 2021 campaigns (NRMSEwheat2020
= 16.1%; NRMSEwheat2021 = 10.1%). Posteriorly, we removed S2 observations from the S1 & S2 dataset corresponding to the complete phenological cycles of winter wheat from September to the end of December to simulate the presence of clouds in the scenes and applied the CONV model at the pixel level to reconstruct spatiotemporally-latent VWC maps. After applying the fusion strategy, the phenology of winter wheat was successfully recovered in the absence of optical data. Strong correlations were obtained between S2 VWC and S1 & S2 MOGP VWC reconstructed maps for the assessment dates (R2¯¯¯¯wheat−2020 = 0.95, R2¯¯¯¯wheat−2021 = 0.96). Altogether, the fusion of S1 SAR and S2 optical EO data streams with MOGP offers a powerful innovative approach for cropland trait monitoring over cloudy high-latitude regions. |
| format | Artículo |
| id | INTA14389 |
| institution | Instituto Nacional de Tecnología Agropecuaria (INTA -Argentina) |
| language | Inglés |
| publishDate | 2023 |
| publishDateRange | 2023 |
| publishDateSort | 2023 |
| publisher | MDPI |
| publisherStr | MDPI |
| record_format | dspace |
| spelling | INTA143892023-04-03T12:17:33Z Synergy of Sentinel-1 and Sentinel-2 Time Series for Cloud-Free Vegetation Water Content Mapping with Multi-Output Gaussian Processes Caballero, Gabriel Pezzola, Nestor Alejandro Winschel, Cristina Ines Sanchez Angonova, Paolo Andres Casella, Alejandra An Orden, Luciano Salinero-Delgado, Matías Reyes-Muñoz, Pablo Berger, Katja Delegido, Jesús Verrelst, Jochem Imágenes por Satélites Indice de Vegetación Contenido de Humedad Teledetección Nubes Satellite Imagery Vegetation Index Moisture Content Remote Sensing Clouds Sentinel-1 Sentinel-2 Optical Earth Observation is often limited by weather conditions such as cloudiness. Radar sensors have the potential to overcome these limitations, however, due to the complex radar-surface interaction, the retrieving of crop biophysical variables using this technology remains an open challenge. Aiming to simultaneously benefit from the optical domain background and the all-weather imagery provided by radar systems, we propose a data fusion approach focused on the cross-correlation between radar and optical data streams. To do so, we analyzed several multiple-output Gaussian processes (MOGP) models and their ability to fuse efficiently Sentinel-1 (S1) Radar Vegetation Index (RVI) and Sentinel-2 (S2) vegetation water content (VWC) time series over a dry agri-environment in southern Argentina. MOGP models not only exploit the auto-correlations of S1 and S2 data streams independently but also the inter-channel cross-correlations. The S1 RVI and S2 VWC time series at the selected study sites being the inputs of the MOGP models proved to be closely correlated. Regarding the set of assessed models, the Convolutional Gaussian model (CONV) delivered noteworthy accurate data fusion results over winter wheat croplands belonging to the 2020 and 2021 campaigns (NRMSEwheat2020 = 16.1%; NRMSEwheat2021 = 10.1%). Posteriorly, we removed S2 observations from the S1 & S2 dataset corresponding to the complete phenological cycles of winter wheat from September to the end of December to simulate the presence of clouds in the scenes and applied the CONV model at the pixel level to reconstruct spatiotemporally-latent VWC maps. After applying the fusion strategy, the phenology of winter wheat was successfully recovered in the absence of optical data. Strong correlations were obtained between S2 VWC and S1 & S2 MOGP VWC reconstructed maps for the assessment dates (R2¯¯¯¯wheat−2020 = 0.95, R2¯¯¯¯wheat−2021 = 0.96). Altogether, the fusion of S1 SAR and S2 optical EO data streams with MOGP offers a powerful innovative approach for cropland trait monitoring over cloudy high-latitude regions. EEA Hilario Ascasubi Fil: Caballero, Gabriel. University of Valencia. Image Processing Laboratory (IPL); España Fil: Pezzola, Alejandro. Instituto Nacional de Tecnología Agropecuaria (INTA). Estación Experimental Agropecuaria Hilario Ascasubi; Argentina Fil: Winschel, Cristina Ines. Instituto Nacional de Tecnología Agropecuaria (INTA). Estación Experimental Agropecuaria Hilario Ascasubi; Argentina Fil: Sanchez Angonova, Paolo Andres. Instituto Nacional de Tecnología Agropecuaria (INTA). Estación Experimental Agropecuaria Hilario Ascasubi; Argentina Fil: Casella, Alejandra. Instituto Nacional de Tecnología Agropecuaria (INTA). Instituto de Clima y Agua; Argentina Fil: Orden, Luciano. Instituto Nacional de Tecnología Agropecuaria (INTA). Estación Experimental Agropecuaria Hilario Ascasubi; Argentina Fil: Orden, Luciano. Universidad Miguel Hernández. Centro de Investigación e Innovación Agroalimentaria y Agroambiental. GIAAMA Reseach Group; España Fil: Salinero-Delgado, Matías. University of Valencia. Image Processing Laboratory (IPL); España Fil: Reyes-Muñoz, Pablo. University of Valencia. Image Processing Laboratory (IPL); España Fil: Berger, Katja. University of Valencia. Image Processing Laboratory (IPL); España Fil: Berger, Katja. Mantle Labs GmbH; Austria Fil: Delegido, Jesús. Universidad de Valencia. Image Processing Laboratory (IPL); España Fil: Verrelst, Jochem. University of Valencia. Image Processing Laboratory (IPL); España 2023-04-03T12:14:52Z 2023-04-03T12:14:52Z 2023-03 info:ar-repo/semantics/artículo info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion http://hdl.handle.net/20.500.12123/14389 https://www.mdpi.com/2072-4292/15/7/1822 2072-4292 https://doi.org/10.3390/rs15071822 eng info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) application/pdf MDPI Remote Sensing 15 (7) : 1822 (March 2023) |
| spellingShingle | Imágenes por Satélites Indice de Vegetación Contenido de Humedad Teledetección Nubes Satellite Imagery Vegetation Index Moisture Content Remote Sensing Clouds Sentinel-1 Sentinel-2 Caballero, Gabriel Pezzola, Nestor Alejandro Winschel, Cristina Ines Sanchez Angonova, Paolo Andres Casella, Alejandra An Orden, Luciano Salinero-Delgado, Matías Reyes-Muñoz, Pablo Berger, Katja Delegido, Jesús Verrelst, Jochem Synergy of Sentinel-1 and Sentinel-2 Time Series for Cloud-Free Vegetation Water Content Mapping with Multi-Output Gaussian Processes |
| title | Synergy of Sentinel-1 and Sentinel-2 Time Series for Cloud-Free Vegetation Water Content Mapping with Multi-Output Gaussian Processes |
| title_full | Synergy of Sentinel-1 and Sentinel-2 Time Series for Cloud-Free Vegetation Water Content Mapping with Multi-Output Gaussian Processes |
| title_fullStr | Synergy of Sentinel-1 and Sentinel-2 Time Series for Cloud-Free Vegetation Water Content Mapping with Multi-Output Gaussian Processes |
| title_full_unstemmed | Synergy of Sentinel-1 and Sentinel-2 Time Series for Cloud-Free Vegetation Water Content Mapping with Multi-Output Gaussian Processes |
| title_short | Synergy of Sentinel-1 and Sentinel-2 Time Series for Cloud-Free Vegetation Water Content Mapping with Multi-Output Gaussian Processes |
| title_sort | synergy of sentinel 1 and sentinel 2 time series for cloud free vegetation water content mapping with multi output gaussian processes |
| topic | Imágenes por Satélites Indice de Vegetación Contenido de Humedad Teledetección Nubes Satellite Imagery Vegetation Index Moisture Content Remote Sensing Clouds Sentinel-1 Sentinel-2 |
| url | http://hdl.handle.net/20.500.12123/14389 https://www.mdpi.com/2072-4292/15/7/1822 https://doi.org/10.3390/rs15071822 |
| work_keys_str_mv | AT caballerogabriel synergyofsentinel1andsentinel2timeseriesforcloudfreevegetationwatercontentmappingwithmultioutputgaussianprocesses AT pezzolanestoralejandro synergyofsentinel1andsentinel2timeseriesforcloudfreevegetationwatercontentmappingwithmultioutputgaussianprocesses AT winschelcristinaines synergyofsentinel1andsentinel2timeseriesforcloudfreevegetationwatercontentmappingwithmultioutputgaussianprocesses AT sanchezangonovapaoloandres synergyofsentinel1andsentinel2timeseriesforcloudfreevegetationwatercontentmappingwithmultioutputgaussianprocesses AT casellaalejandraan synergyofsentinel1andsentinel2timeseriesforcloudfreevegetationwatercontentmappingwithmultioutputgaussianprocesses AT ordenluciano synergyofsentinel1andsentinel2timeseriesforcloudfreevegetationwatercontentmappingwithmultioutputgaussianprocesses AT salinerodelgadomatias synergyofsentinel1andsentinel2timeseriesforcloudfreevegetationwatercontentmappingwithmultioutputgaussianprocesses AT reyesmunozpablo synergyofsentinel1andsentinel2timeseriesforcloudfreevegetationwatercontentmappingwithmultioutputgaussianprocesses AT bergerkatja synergyofsentinel1andsentinel2timeseriesforcloudfreevegetationwatercontentmappingwithmultioutputgaussianprocesses AT delegidojesus synergyofsentinel1andsentinel2timeseriesforcloudfreevegetationwatercontentmappingwithmultioutputgaussianprocesses AT verrelstjochem synergyofsentinel1andsentinel2timeseriesforcloudfreevegetationwatercontentmappingwithmultioutputgaussianprocesses |