In-season forecasting of within-field grain yield from Sentinel-2 time series data
Precise knowledge of cropland productivity is relevant for farmers to enable optimizing managing practices; particularly with the perspective of anticipating crop yield ahead of harvest. The current availability of high spatiotemporal resolution Sentinel-2 satellite data offers a unique opportunity...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-02-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843223004600 |
| _version_ | 1797357792463421440 |
|---|---|
| author | Eatidal Amin Luca Pipia Santiago Belda Gregor Perich Lukas Valentin Graf Helge Aasen Shari Van Wittenberghe José Moreno Jochem Verrelst |
| author_facet | Eatidal Amin Luca Pipia Santiago Belda Gregor Perich Lukas Valentin Graf Helge Aasen Shari Van Wittenberghe José Moreno Jochem Verrelst |
| author_sort | Eatidal Amin |
| collection | DOAJ |
| description | Precise knowledge of cropland productivity is relevant for farmers to enable optimizing managing practices; particularly with the perspective of anticipating crop yield ahead of harvest. The current availability of high spatiotemporal resolution Sentinel-2 satellite data offers a unique opportunity to monitor croplands over time. In this context, the recently introduced kernel NDVI (kNDVI) statistically optimizes the conventional NDVI formulation by applying a nonlinear function to the involved bands, and so maximizes the spectral information extraction. This study proposes a workflow for within-field yield forecasting from Sentinel-2 kNDVI time series analysis focusing on winter cereal croplands in Switzerland over three years, comparing with NDVI as baseline. For a temporally continuous modelling of crop yields, Gaussian Process Regression (GPR) was applied to reconstruct cloud-free time series of the complete crop growing seasons. Following, distinct machine learning regression models (GPR, Kernel Ridge Regression and Random Forest) were developed to forecast yield at any point in time throughout the cropland growing season. The integration of Growing Degree Days (GDD) information as temporal spacing reference of the time series considerably improved the accuracy and consistency of in-season yield forecasting. Training and testing within the same year demonstrated that yield can be accurately forecast approximately 2–2.5 months ahead of harvest, at crops’ anthesis (flowering) phase, with an RMSE up to 0.71 t/ha and a relative RMSE of 7.60%. Although the forecasting accuracy of the models decreased when predicting yield for the unseen years, still satisfactory results were obtained: RMSE = 0.97 t/ha, relative RMSE = 11.47%. |
| first_indexed | 2024-03-08T14:50:20Z |
| format | Article |
| id | doaj.art-a8bb85440b7f41fb9a8aa795e47f6f54 |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-03-08T14:50:20Z |
| publishDate | 2024-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-a8bb85440b7f41fb9a8aa795e47f6f542024-01-11T04:30:33ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322024-02-01126103636In-season forecasting of within-field grain yield from Sentinel-2 time series dataEatidal Amin0Luca Pipia1Santiago Belda2Gregor Perich3Lukas Valentin Graf4Helge Aasen5Shari Van Wittenberghe6José Moreno7Jochem Verrelst8Image Processing Laboratory (IPL), University of Valencia, C/ Catedrático Agustín Escardino Benlloch, 9, Paterna, Valencia, 46980, Spain; Corresponding author.Institut Cartogràfic i Geològic de Catalunya, Parc de Montjüic, Barcelona, 08038, SpainDepartment of Applied Mathematics, University of Alicante, San Vicente del Raspeig, Alicante, 03690, SpainCrop Science, Institute of Agricultural Sciences, ETH Zürich, Universitätstrasse 2, Zürich, 8092, SwitzerlandCrop Science, Institute of Agricultural Sciences, ETH Zürich, Universitätstrasse 2, Zürich, 8092, Switzerland; Earth Observation of Agroecosystems Team, Division Agroecology and Environment, Agroscope, Reckenholzstrasse 191, Zürich, 8046, SwitzerlandEarth Observation of Agroecosystems Team, Division Agroecology and Environment, Agroscope, Reckenholzstrasse 191, Zürich, 8046, SwitzerlandImage Processing Laboratory (IPL), University of Valencia, C/ Catedrático Agustín Escardino Benlloch, 9, Paterna, Valencia, 46980, SpainImage Processing Laboratory (IPL), University of Valencia, C/ Catedrático Agustín Escardino Benlloch, 9, Paterna, Valencia, 46980, SpainImage Processing Laboratory (IPL), University of Valencia, C/ Catedrático Agustín Escardino Benlloch, 9, Paterna, Valencia, 46980, SpainPrecise knowledge of cropland productivity is relevant for farmers to enable optimizing managing practices; particularly with the perspective of anticipating crop yield ahead of harvest. The current availability of high spatiotemporal resolution Sentinel-2 satellite data offers a unique opportunity to monitor croplands over time. In this context, the recently introduced kernel NDVI (kNDVI) statistically optimizes the conventional NDVI formulation by applying a nonlinear function to the involved bands, and so maximizes the spectral information extraction. This study proposes a workflow for within-field yield forecasting from Sentinel-2 kNDVI time series analysis focusing on winter cereal croplands in Switzerland over three years, comparing with NDVI as baseline. For a temporally continuous modelling of crop yields, Gaussian Process Regression (GPR) was applied to reconstruct cloud-free time series of the complete crop growing seasons. Following, distinct machine learning regression models (GPR, Kernel Ridge Regression and Random Forest) were developed to forecast yield at any point in time throughout the cropland growing season. The integration of Growing Degree Days (GDD) information as temporal spacing reference of the time series considerably improved the accuracy and consistency of in-season yield forecasting. Training and testing within the same year demonstrated that yield can be accurately forecast approximately 2–2.5 months ahead of harvest, at crops’ anthesis (flowering) phase, with an RMSE up to 0.71 t/ha and a relative RMSE of 7.60%. Although the forecasting accuracy of the models decreased when predicting yield for the unseen years, still satisfactory results were obtained: RMSE = 0.97 t/ha, relative RMSE = 11.47%.http://www.sciencedirect.com/science/article/pii/S1569843223004600Sentinel-2Crop yield forecastingMachine learningGaussian process regression (GPR)Time series gap-fillingGrowing degree days (GDD) |
| spellingShingle | Eatidal Amin Luca Pipia Santiago Belda Gregor Perich Lukas Valentin Graf Helge Aasen Shari Van Wittenberghe José Moreno Jochem Verrelst In-season forecasting of within-field grain yield from Sentinel-2 time series data International Journal of Applied Earth Observations and Geoinformation Sentinel-2 Crop yield forecasting Machine learning Gaussian process regression (GPR) Time series gap-filling Growing degree days (GDD) |
| title | In-season forecasting of within-field grain yield from Sentinel-2 time series data |
| title_full | In-season forecasting of within-field grain yield from Sentinel-2 time series data |
| title_fullStr | In-season forecasting of within-field grain yield from Sentinel-2 time series data |
| title_full_unstemmed | In-season forecasting of within-field grain yield from Sentinel-2 time series data |
| title_short | In-season forecasting of within-field grain yield from Sentinel-2 time series data |
| title_sort | in season forecasting of within field grain yield from sentinel 2 time series data |
| topic | Sentinel-2 Crop yield forecasting Machine learning Gaussian process regression (GPR) Time series gap-filling Growing degree days (GDD) |
| url | http://www.sciencedirect.com/science/article/pii/S1569843223004600 |
| work_keys_str_mv | AT eatidalamin inseasonforecastingofwithinfieldgrainyieldfromsentinel2timeseriesdata AT lucapipia inseasonforecastingofwithinfieldgrainyieldfromsentinel2timeseriesdata AT santiagobelda inseasonforecastingofwithinfieldgrainyieldfromsentinel2timeseriesdata AT gregorperich inseasonforecastingofwithinfieldgrainyieldfromsentinel2timeseriesdata AT lukasvalentingraf inseasonforecastingofwithinfieldgrainyieldfromsentinel2timeseriesdata AT helgeaasen inseasonforecastingofwithinfieldgrainyieldfromsentinel2timeseriesdata AT sharivanwittenberghe inseasonforecastingofwithinfieldgrainyieldfromsentinel2timeseriesdata AT josemoreno inseasonforecastingofwithinfieldgrainyieldfromsentinel2timeseriesdata AT jochemverrelst inseasonforecastingofwithinfieldgrainyieldfromsentinel2timeseriesdata |