Monitoring Complex Integrated Crop–Livestock Systems at Regional Scale in Brazil: A Big Earth Observation Data Approach
Due to different combinations of agriculture, livestock and forestry managed by rotation, succession and intercropping practices, integrated agriculture production systems such as integrated crop–livestock systems (iCL) constitute a very complex target and a challenge for automatic mapping of croppi...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/7/1648 |
| _version_ | 1827622612419739648 |
|---|---|
| author | Patrick Calvano Kuchler Margareth Simões Rodrigo Ferraz Damien Arvor Pedro Luiz Oliveira de Almeida Machado Marcos Rosa Raffaele Gaetano Agnès Bégué |
| author_facet | Patrick Calvano Kuchler Margareth Simões Rodrigo Ferraz Damien Arvor Pedro Luiz Oliveira de Almeida Machado Marcos Rosa Raffaele Gaetano Agnès Bégué |
| author_sort | Patrick Calvano Kuchler |
| collection | DOAJ |
| description | Due to different combinations of agriculture, livestock and forestry managed by rotation, succession and intercropping practices, integrated agriculture production systems such as integrated crop–livestock systems (iCL) constitute a very complex target and a challenge for automatic mapping of cropping practices based on remote sensing data. The overall objective of this study was to develop a classification strategy for the annual mapping of integrated Crop–Livestock systems (iCL) at a regional scale. This strategy was designed and tested in the six agro-climatic regions of Mato Grosso, the largest Brazilian soybean producer state, using MODIS satellite time-series images acquired between 2012 and 2019, ground data with heterogeneous distribution in space and time and a Random Forest classifier. The results showed that: 1. the use of unbalanced training samples with a class composition close to the real one was the right classifier training strategy; 2. the use of a single training database (pooling samples from different years and regions) to classify each region and year individually proved to be robust enough to provide similar classification accuracies in comparison to those based on the use of a database acquired for each region and for each year. The final hierarchical classification overall accuracy was 0.89 for Level 1, the cropping pattern level (single and double crops DC); 0.84 for Level 2, the DC category level (integrated system iCL soy-pasture/brachiaria, soy-cotton and soy-cereal); 0.77 for Level 3, the iCL level (iCL1 soy-pasture and iCL2 soy-pasture mixed with corn). The F-scores for DC, iCL and iCL1 cropping systems presented high accuracy (0.89, 0.85 and 0.84), while iCL2 was more difficult to classify (0.63). This approach will next be applied across the entire Brazilian soybean corridor, leading to an operational tool for monitoring the adoption of sustainable intensification practices recognized by Brazil’s Agriculture Low Carbon Plan (ABC PLAN). |
| first_indexed | 2024-03-09T11:28:09Z |
| format | Article |
| id | doaj.art-0b055a20f13244f889d328a1a98c698a |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T11:28:09Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-0b055a20f13244f889d328a1a98c698a2023-11-30T23:56:59ZengMDPI AGRemote Sensing2072-42922022-03-01147164810.3390/rs14071648Monitoring Complex Integrated Crop–Livestock Systems at Regional Scale in Brazil: A Big Earth Observation Data ApproachPatrick Calvano Kuchler0Margareth Simões1Rodrigo Ferraz2Damien Arvor3Pedro Luiz Oliveira de Almeida Machado4Marcos Rosa5Raffaele Gaetano6Agnès Bégué7Department of Computer Engineering, Rio de Janeiro State University (UERJ/FEN/DESC/PPGMA), Rua São Francisco Xavier, 524, 5031 D, Maracanã, Rio de Janeiro 20550-900, BrazilDepartment of Computer Engineering, Rio de Janeiro State University (UERJ/FEN/DESC/PPGMA), Rua São Francisco Xavier, 524, 5031 D, Maracanã, Rio de Janeiro 20550-900, BrazilEmbrapa Solos, Rua Jardim Botânico 1024, Rio de Janeiro 22460-000, BrazilCNRS, UMR 6554 LETG, Université Rennes 2, 35043 Rennes, FranceEmbrapa Arroz e Feijão, Rodovia GO-462, km 12, Santo Antonio de Goias 75375-000, BrazilDepartment of Geography, PPGM Universidade Estadual de Feira de Santana, Novo Horizonte 44036-900, BrazilTETIS, University Montpellier, AgroParisTech, CIRAD, CNRS, INRAE 648 Rue Jean François Breton, 34090 Montpellier, FranceTETIS, University Montpellier, AgroParisTech, CIRAD, CNRS, INRAE 648 Rue Jean François Breton, 34090 Montpellier, FranceDue to different combinations of agriculture, livestock and forestry managed by rotation, succession and intercropping practices, integrated agriculture production systems such as integrated crop–livestock systems (iCL) constitute a very complex target and a challenge for automatic mapping of cropping practices based on remote sensing data. The overall objective of this study was to develop a classification strategy for the annual mapping of integrated Crop–Livestock systems (iCL) at a regional scale. This strategy was designed and tested in the six agro-climatic regions of Mato Grosso, the largest Brazilian soybean producer state, using MODIS satellite time-series images acquired between 2012 and 2019, ground data with heterogeneous distribution in space and time and a Random Forest classifier. The results showed that: 1. the use of unbalanced training samples with a class composition close to the real one was the right classifier training strategy; 2. the use of a single training database (pooling samples from different years and regions) to classify each region and year individually proved to be robust enough to provide similar classification accuracies in comparison to those based on the use of a database acquired for each region and for each year. The final hierarchical classification overall accuracy was 0.89 for Level 1, the cropping pattern level (single and double crops DC); 0.84 for Level 2, the DC category level (integrated system iCL soy-pasture/brachiaria, soy-cotton and soy-cereal); 0.77 for Level 3, the iCL level (iCL1 soy-pasture and iCL2 soy-pasture mixed with corn). The F-scores for DC, iCL and iCL1 cropping systems presented high accuracy (0.89, 0.85 and 0.84), while iCL2 was more difficult to classify (0.63). This approach will next be applied across the entire Brazilian soybean corridor, leading to an operational tool for monitoring the adoption of sustainable intensification practices recognized by Brazil’s Agriculture Low Carbon Plan (ABC PLAN).https://www.mdpi.com/2072-4292/14/7/1648cropping systemsdouble croppingsustainable agriculturesatellite image time seriesMODISmachine learning |
| spellingShingle | Patrick Calvano Kuchler Margareth Simões Rodrigo Ferraz Damien Arvor Pedro Luiz Oliveira de Almeida Machado Marcos Rosa Raffaele Gaetano Agnès Bégué Monitoring Complex Integrated Crop–Livestock Systems at Regional Scale in Brazil: A Big Earth Observation Data Approach Remote Sensing cropping systems double cropping sustainable agriculture satellite image time series MODIS machine learning |
| title | Monitoring Complex Integrated Crop–Livestock Systems at Regional Scale in Brazil: A Big Earth Observation Data Approach |
| title_full | Monitoring Complex Integrated Crop–Livestock Systems at Regional Scale in Brazil: A Big Earth Observation Data Approach |
| title_fullStr | Monitoring Complex Integrated Crop–Livestock Systems at Regional Scale in Brazil: A Big Earth Observation Data Approach |
| title_full_unstemmed | Monitoring Complex Integrated Crop–Livestock Systems at Regional Scale in Brazil: A Big Earth Observation Data Approach |
| title_short | Monitoring Complex Integrated Crop–Livestock Systems at Regional Scale in Brazil: A Big Earth Observation Data Approach |
| title_sort | monitoring complex integrated crop livestock systems at regional scale in brazil a big earth observation data approach |
| topic | cropping systems double cropping sustainable agriculture satellite image time series MODIS machine learning |
| url | https://www.mdpi.com/2072-4292/14/7/1648 |
| work_keys_str_mv | AT patrickcalvanokuchler monitoringcomplexintegratedcroplivestocksystemsatregionalscaleinbrazilabigearthobservationdataapproach AT margarethsimoes monitoringcomplexintegratedcroplivestocksystemsatregionalscaleinbrazilabigearthobservationdataapproach AT rodrigoferraz monitoringcomplexintegratedcroplivestocksystemsatregionalscaleinbrazilabigearthobservationdataapproach AT damienarvor monitoringcomplexintegratedcroplivestocksystemsatregionalscaleinbrazilabigearthobservationdataapproach AT pedroluizoliveiradealmeidamachado monitoringcomplexintegratedcroplivestocksystemsatregionalscaleinbrazilabigearthobservationdataapproach AT marcosrosa monitoringcomplexintegratedcroplivestocksystemsatregionalscaleinbrazilabigearthobservationdataapproach AT raffaelegaetano monitoringcomplexintegratedcroplivestocksystemsatregionalscaleinbrazilabigearthobservationdataapproach AT agnesbegue monitoringcomplexintegratedcroplivestocksystemsatregionalscaleinbrazilabigearthobservationdataapproach |