Towards a set of agrosystem-specific cropland mapping methods to address the global cropland diversity
Accurate cropland information is of paramount importance for crop monitoring. This study compares five existing cropland mapping methodologies over five contrasting Joint Experiment for Crop Assessment and Monitoring (JECAM) sites of medium to large average field size using the time series of 7-day...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Artículo |
| Language: | Inglés |
| Published: |
Informa UK Limited
2018
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/20.500.12123/4057 https://www.tandfonline.com/doi/full/10.1080/01431161.2016.1194545 https://doi.org/10.1080/01431161.2016.1194545 |
| _version_ | 1855483356490235904 |
|---|---|
| author | Waldner, François De Abelleyra, Diego Veron, Santiago Ramón Zhang, Miao Wu, Bingfang Plotnikov, Dmitry Bartalev, Sergey Lavreniuk, Mykola Skakun, Sergii Kussul, Nataliia Le Maire, Guerric Dupuy, Stéphane Jarvis, Ian Defourny, Pierre |
| author_browse | Bartalev, Sergey De Abelleyra, Diego Defourny, Pierre Dupuy, Stéphane Jarvis, Ian Kussul, Nataliia Lavreniuk, Mykola Le Maire, Guerric Plotnikov, Dmitry Skakun, Sergii Veron, Santiago Ramón Waldner, François Wu, Bingfang Zhang, Miao |
| author_facet | Waldner, François De Abelleyra, Diego Veron, Santiago Ramón Zhang, Miao Wu, Bingfang Plotnikov, Dmitry Bartalev, Sergey Lavreniuk, Mykola Skakun, Sergii Kussul, Nataliia Le Maire, Guerric Dupuy, Stéphane Jarvis, Ian Defourny, Pierre |
| author_sort | Waldner, François |
| collection | INTA Digital |
| description | Accurate cropland information is of paramount importance for crop monitoring. This study compares five existing cropland mapping methodologies over five contrasting Joint Experiment for Crop Assessment and Monitoring (JECAM) sites of medium to large average field size using the time series of 7-day 250 m Moderate Resolution Imaging Spectroradiometer (MODIS) mean composites (red and near-infrared channels). Different strategies were devised to assess the accuracy of the classification methods: confusion matrices and derived accuracy indicators with and without equalizing class proportions, assessing the pairwise difference error rates and accounting for the spatial resolution bias. The robustness of the accuracy with respect to a reduction of the quantity of calibration data available was also assessed by a bootstrap approach in which the amount of training data was systematically reduced. Methods reached overall accuracies ranging from 85% to 95%, which demonstrates the ability of 250 m imagery to resolve fields down to 20 ha. Despite significantly different error rates, the site effect was found to persistently dominate the method effect. This was confirmed even after removing the share of the classification due to the spatial resolution of the satellite data (from 10% to 30%). This underlines the effect of other agrosystems characteristics such as cloudiness, crop diversity, and calendar on the ability to perform accurately. All methods have potential for large area cropland mapping as they provided accurate results with 20% of the calibration data, e.g. 2% of the study area in Ukraine. To better address the global cropland diversity, results advocate movement towards a set of cropland classification methods that could be applied regionally according to their respective performance in specific landscapes. |
| format | Artículo |
| id | INTA4057 |
| institution | Instituto Nacional de Tecnología Agropecuaria (INTA -Argentina) |
| language | Inglés |
| publishDate | 2018 |
| publishDateRange | 2018 |
| publishDateSort | 2018 |
| publisher | Informa UK Limited |
| publisherStr | Informa UK Limited |
| record_format | dspace |
| spelling | INTA40572018-12-11T15:49:19Z Towards a set of agrosystem-specific cropland mapping methods to address the global cropland diversity Waldner, François De Abelleyra, Diego Veron, Santiago Ramón Zhang, Miao Wu, Bingfang Plotnikov, Dmitry Bartalev, Sergey Lavreniuk, Mykola Skakun, Sergii Kussul, Nataliia Le Maire, Guerric Dupuy, Stéphane Jarvis, Ian Defourny, Pierre Agroecosistemas Tierras Agrícolas Cartografía del Uso de la Tierra Agroecosystems Farmland Land Use Mapping Global Positioning Systems Sistema de Posicionamiento Global Moderate Resolution Imaging Spectroradiometer MODIS Accurate cropland information is of paramount importance for crop monitoring. This study compares five existing cropland mapping methodologies over five contrasting Joint Experiment for Crop Assessment and Monitoring (JECAM) sites of medium to large average field size using the time series of 7-day 250 m Moderate Resolution Imaging Spectroradiometer (MODIS) mean composites (red and near-infrared channels). Different strategies were devised to assess the accuracy of the classification methods: confusion matrices and derived accuracy indicators with and without equalizing class proportions, assessing the pairwise difference error rates and accounting for the spatial resolution bias. The robustness of the accuracy with respect to a reduction of the quantity of calibration data available was also assessed by a bootstrap approach in which the amount of training data was systematically reduced. Methods reached overall accuracies ranging from 85% to 95%, which demonstrates the ability of 250 m imagery to resolve fields down to 20 ha. Despite significantly different error rates, the site effect was found to persistently dominate the method effect. This was confirmed even after removing the share of the classification due to the spatial resolution of the satellite data (from 10% to 30%). This underlines the effect of other agrosystems characteristics such as cloudiness, crop diversity, and calendar on the ability to perform accurately. All methods have potential for large area cropland mapping as they provided accurate results with 20% of the calibration data, e.g. 2% of the study area in Ukraine. To better address the global cropland diversity, results advocate movement towards a set of cropland classification methods that could be applied regionally according to their respective performance in specific landscapes. Instituto de Clima y Agua Fil: Waldner, François. Université catholique de Louvain. Earth and Life Institute - Environment, Croix du Sud; Belgica Fil: De Abelleyra, Diego. Instituto Nacional de Tecnología Agropecuaria (INTA). Instituto de Clima y Agua; Argentina Fil: Veron, Santiago Ramón. Instituto Nacional de Tecnología Agropecuaria (INTA). Instituto de Clima y Agua; Argentina. Universidad de Buenos Aires. Facultad de Agronomía. Departamento de Métodos Cuantitativos y Sistemas de Información; Argentina Fil: Zhang, Miao. Chinese Academy of Science. Institute of Remote Sensing and Digital Earth; China Fil: Wu, Bingfang. Chinese Academy of Science. Institute of Remote Sensing and Digital Earth; China Fil: Plotnikov, Dmitry. Russian Academy of Sciences. Space Research Institute. Terrestrial Ecosystems Monitoring Laboratory; Rusia Fil: Bartalev, Sergey. Russian Academy of Sciences. Space Research Institute. Terrestrial Ecosystems Monitoring Laboratory; Rusia Fil: Lavreniuk, Mykola. Space Research Institute NAS and SSA. Department of Space Information Technologies; Ucrania Fil: Skakun, Sergii. Space Research Institute NAS and SSA. Department of Space Information Technologies; Ucrania. University of Maryland. Department of Geographical Sciences; Estados Unidos Fil: Kussul, Nataliia. Space Research Institute NAS and SSA. Department of Space Information Technologies; Ucrania Fil: Le Maire, Guerric. UMR Eco&Sols, CIRAD; Francia. Empresa Brasileira de Pesquisa Agropecuária. Meio Ambiante; Brasil Fil: Dupuy, Stéphane. Centre de Coopération Internationale en Recherche Agronomique pour le Développement. Territoires, Environnement, Télédétection et Information Spatiale; Francia Fil: Jarvis, Ian. Agriculture and Agri-Food Canada. Science and Technology Branch. Agri-Climate, Geomatics and Earth Observation; Canadá Fil: Defourny, Pierre. Université Catholique de Louvain. Earth and Life Institute - Environment, Croix du Sud; Belgica 2018-12-11T15:42:01Z 2018-12-11T15:42:01Z 2016 info:ar-repo/semantics/artículo info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion http://hdl.handle.net/20.500.12123/4057 https://www.tandfonline.com/doi/full/10.1080/01431161.2016.1194545 0143-1161 1366-5901 (Online) https://doi.org/10.1080/01431161.2016.1194545 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 Informa UK Limited International journal of remote sensing 37 (14) : 3196–3231. (2016) |
| spellingShingle | Agroecosistemas Tierras Agrícolas Cartografía del Uso de la Tierra Agroecosystems Farmland Land Use Mapping Global Positioning Systems Sistema de Posicionamiento Global Moderate Resolution Imaging Spectroradiometer MODIS Waldner, François De Abelleyra, Diego Veron, Santiago Ramón Zhang, Miao Wu, Bingfang Plotnikov, Dmitry Bartalev, Sergey Lavreniuk, Mykola Skakun, Sergii Kussul, Nataliia Le Maire, Guerric Dupuy, Stéphane Jarvis, Ian Defourny, Pierre Towards a set of agrosystem-specific cropland mapping methods to address the global cropland diversity |
| title | Towards a set of agrosystem-specific cropland mapping methods to address the global cropland diversity |
| title_full | Towards a set of agrosystem-specific cropland mapping methods to address the global cropland diversity |
| title_fullStr | Towards a set of agrosystem-specific cropland mapping methods to address the global cropland diversity |
| title_full_unstemmed | Towards a set of agrosystem-specific cropland mapping methods to address the global cropland diversity |
| title_short | Towards a set of agrosystem-specific cropland mapping methods to address the global cropland diversity |
| title_sort | towards a set of agrosystem specific cropland mapping methods to address the global cropland diversity |
| topic | Agroecosistemas Tierras Agrícolas Cartografía del Uso de la Tierra Agroecosystems Farmland Land Use Mapping Global Positioning Systems Sistema de Posicionamiento Global Moderate Resolution Imaging Spectroradiometer MODIS |
| url | http://hdl.handle.net/20.500.12123/4057 https://www.tandfonline.com/doi/full/10.1080/01431161.2016.1194545 https://doi.org/10.1080/01431161.2016.1194545 |
| work_keys_str_mv | AT waldnerfrancois towardsasetofagrosystemspecificcroplandmappingmethodstoaddresstheglobalcroplanddiversity AT deabelleyradiego towardsasetofagrosystemspecificcroplandmappingmethodstoaddresstheglobalcroplanddiversity AT veronsantiagoramon towardsasetofagrosystemspecificcroplandmappingmethodstoaddresstheglobalcroplanddiversity AT zhangmiao towardsasetofagrosystemspecificcroplandmappingmethodstoaddresstheglobalcroplanddiversity AT wubingfang towardsasetofagrosystemspecificcroplandmappingmethodstoaddresstheglobalcroplanddiversity AT plotnikovdmitry towardsasetofagrosystemspecificcroplandmappingmethodstoaddresstheglobalcroplanddiversity AT bartalevsergey towardsasetofagrosystemspecificcroplandmappingmethodstoaddresstheglobalcroplanddiversity AT lavreniukmykola towardsasetofagrosystemspecificcroplandmappingmethodstoaddresstheglobalcroplanddiversity AT skakunsergii towardsasetofagrosystemspecificcroplandmappingmethodstoaddresstheglobalcroplanddiversity AT kussulnataliia towardsasetofagrosystemspecificcroplandmappingmethodstoaddresstheglobalcroplanddiversity AT lemaireguerric towardsasetofagrosystemspecificcroplandmappingmethodstoaddresstheglobalcroplanddiversity AT dupuystephane towardsasetofagrosystemspecificcroplandmappingmethodstoaddresstheglobalcroplanddiversity AT jarvisian towardsasetofagrosystemspecificcroplandmappingmethodstoaddresstheglobalcroplanddiversity AT defournypierre towardsasetofagrosystemspecificcroplandmappingmethodstoaddresstheglobalcroplanddiversity |