Green LAI Mapping and Cloud Gap-Filling Using Gaussian Process Regression in Google Earth Engine
For the last decade, Gaussian process regression (GPR) proved to be a competitive machine learning regression algorithm for Earth observation applications, with attractive unique properties such as band relevance ranking and uncertainty estimates. More recently, GPR also proved to be a proficient ti...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/3/403 |
| _version_ | 1827598324410089472 |
|---|---|
| author | Luca Pipia Eatidal Amin Santiago Belda Matías Salinero-Delgado Jochem Verrelst |
| author_facet | Luca Pipia Eatidal Amin Santiago Belda Matías Salinero-Delgado Jochem Verrelst |
| author_sort | Luca Pipia |
| collection | DOAJ |
| description | For the last decade, Gaussian process regression (GPR) proved to be a competitive machine learning regression algorithm for Earth observation applications, with attractive unique properties such as band relevance ranking and uncertainty estimates. More recently, GPR also proved to be a proficient time series processor to fill up gaps in optical imagery, typically due to cloud cover. This makes GPR perfectly suited for large-scale spatiotemporal processing of satellite imageries into cloud-free products of biophysical variables. With the advent of the Google Earth Engine (GEE) cloud platform, new opportunities emerged to process local-to-planetary scale satellite data using advanced machine learning techniques and convert them into gap-filled vegetation properties products. However, GPR is not yet part of the GEE ecosystem. To circumvent this limitation, this work proposes a general adaptation of GPR formulation to parallel processing framework and its integration into GEE. To demonstrate the functioning and utility of the developed workflow, a GPR model predicting green leaf area index (LAI<inline-formula><math display="inline"><semantics><msub><mrow></mrow><mi>G</mi></msub></semantics></math></inline-formula>) from Sentinel-2 imagery was imported. Although by running this GPR model into GEE any corner of the world can be mapped into LAI<inline-formula><math display="inline"><semantics><msub><mrow></mrow><mi>G</mi></msub></semantics></math></inline-formula> at a resolution of 20 m, here we show some demonstration cases over western Europe with zoom-ins over Spain. Thanks to the computational power of GEE, the mapping takes place on-the-fly. Additionally, a GPR-based gap filling strategy based on pre-optimized kernel hyperparameters is also put forward for the generation of multi-orbit cloud-free LAI<inline-formula><math display="inline"><semantics><msub><mrow></mrow><mi>G</mi></msub></semantics></math></inline-formula> maps with an unprecedented level of detail, and the extraction of regularly-sampled LAI<inline-formula><math display="inline"><semantics><msub><mrow></mrow><mi>G</mi></msub></semantics></math></inline-formula> time series at a pixel level. The ability to plugin a locally-trained GPR model into the GEE framework and its instant processing opens up a new paradigm of remote sensing image processing. |
| first_indexed | 2024-03-09T03:47:56Z |
| format | Article |
| id | doaj.art-f1620e30fda5453f89673585752f5d27 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T03:47:56Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-f1620e30fda5453f89673585752f5d272023-12-03T14:31:48ZengMDPI AGRemote Sensing2072-42922021-01-0113340310.3390/rs13030403Green LAI Mapping and Cloud Gap-Filling Using Gaussian Process Regression in Google Earth EngineLuca Pipia0Eatidal Amin1Santiago Belda2Matías Salinero-Delgado3Jochem Verrelst4Institut Cartogràfic i Geològic de Catalunya (ICGC), Parc de Montjüic, 08038 Barcelona, SpainImage Processing Laboratory (IPL), University of Valencia, C/Catedrático José Beltrán 2, 46980 Valencia, SpainImage Processing Laboratory (IPL), University of Valencia, C/Catedrático José Beltrán 2, 46980 Valencia, SpainImage Processing Laboratory (IPL), University of Valencia, C/Catedrático José Beltrán 2, 46980 Valencia, SpainImage Processing Laboratory (IPL), University of Valencia, C/Catedrático José Beltrán 2, 46980 Valencia, SpainFor the last decade, Gaussian process regression (GPR) proved to be a competitive machine learning regression algorithm for Earth observation applications, with attractive unique properties such as band relevance ranking and uncertainty estimates. More recently, GPR also proved to be a proficient time series processor to fill up gaps in optical imagery, typically due to cloud cover. This makes GPR perfectly suited for large-scale spatiotemporal processing of satellite imageries into cloud-free products of biophysical variables. With the advent of the Google Earth Engine (GEE) cloud platform, new opportunities emerged to process local-to-planetary scale satellite data using advanced machine learning techniques and convert them into gap-filled vegetation properties products. However, GPR is not yet part of the GEE ecosystem. To circumvent this limitation, this work proposes a general adaptation of GPR formulation to parallel processing framework and its integration into GEE. To demonstrate the functioning and utility of the developed workflow, a GPR model predicting green leaf area index (LAI<inline-formula><math display="inline"><semantics><msub><mrow></mrow><mi>G</mi></msub></semantics></math></inline-formula>) from Sentinel-2 imagery was imported. Although by running this GPR model into GEE any corner of the world can be mapped into LAI<inline-formula><math display="inline"><semantics><msub><mrow></mrow><mi>G</mi></msub></semantics></math></inline-formula> at a resolution of 20 m, here we show some demonstration cases over western Europe with zoom-ins over Spain. Thanks to the computational power of GEE, the mapping takes place on-the-fly. Additionally, a GPR-based gap filling strategy based on pre-optimized kernel hyperparameters is also put forward for the generation of multi-orbit cloud-free LAI<inline-formula><math display="inline"><semantics><msub><mrow></mrow><mi>G</mi></msub></semantics></math></inline-formula> maps with an unprecedented level of detail, and the extraction of regularly-sampled LAI<inline-formula><math display="inline"><semantics><msub><mrow></mrow><mi>G</mi></msub></semantics></math></inline-formula> time series at a pixel level. The ability to plugin a locally-trained GPR model into the GEE framework and its instant processing opens up a new paradigm of remote sensing image processing.https://www.mdpi.com/2072-4292/13/3/403Google Earth Engine (GEE)Gaussian process regression (GPR)machine learningSentinel-2gap fillingleaf area index (LAI) |
| spellingShingle | Luca Pipia Eatidal Amin Santiago Belda Matías Salinero-Delgado Jochem Verrelst Green LAI Mapping and Cloud Gap-Filling Using Gaussian Process Regression in Google Earth Engine Remote Sensing Google Earth Engine (GEE) Gaussian process regression (GPR) machine learning Sentinel-2 gap filling leaf area index (LAI) |
| title | Green LAI Mapping and Cloud Gap-Filling Using Gaussian Process Regression in Google Earth Engine |
| title_full | Green LAI Mapping and Cloud Gap-Filling Using Gaussian Process Regression in Google Earth Engine |
| title_fullStr | Green LAI Mapping and Cloud Gap-Filling Using Gaussian Process Regression in Google Earth Engine |
| title_full_unstemmed | Green LAI Mapping and Cloud Gap-Filling Using Gaussian Process Regression in Google Earth Engine |
| title_short | Green LAI Mapping and Cloud Gap-Filling Using Gaussian Process Regression in Google Earth Engine |
| title_sort | green lai mapping and cloud gap filling using gaussian process regression in google earth engine |
| topic | Google Earth Engine (GEE) Gaussian process regression (GPR) machine learning Sentinel-2 gap filling leaf area index (LAI) |
| url | https://www.mdpi.com/2072-4292/13/3/403 |
| work_keys_str_mv | AT lucapipia greenlaimappingandcloudgapfillingusinggaussianprocessregressioningoogleearthengine AT eatidalamin greenlaimappingandcloudgapfillingusinggaussianprocessregressioningoogleearthengine AT santiagobelda greenlaimappingandcloudgapfillingusinggaussianprocessregressioningoogleearthengine AT matiassalinerodelgado greenlaimappingandcloudgapfillingusinggaussianprocessregressioningoogleearthengine AT jochemverrelst greenlaimappingandcloudgapfillingusinggaussianprocessregressioningoogleearthengine |