Hierarchical Classification of Soybean in the Brazilian Savanna Based on Harmonized Landsat Sentinel Data
The Brazilian Savanna presents a complex agricultural dynamic and cloud cover issues; therefore, there is a need for new strategies for more detailed agricultural monitoring. Using a hierarchical classification system, we explored the Harmonized Landsat Sentinel-2 (HLS) dataset to detect soybean in...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/15/3736 |
| _version_ | 1797412422752927744 |
|---|---|
| author | Taya Cristo Parreiras Édson Luis Bolfe Michel Eustáquio Dantas Chaves Ieda Del’Arco Sanches Edson Eyji Sano Daniel de Castro Victoria Giovana Maranhão Bettiol Luiz Eduardo Vicente |
| author_facet | Taya Cristo Parreiras Édson Luis Bolfe Michel Eustáquio Dantas Chaves Ieda Del’Arco Sanches Edson Eyji Sano Daniel de Castro Victoria Giovana Maranhão Bettiol Luiz Eduardo Vicente |
| author_sort | Taya Cristo Parreiras |
| collection | DOAJ |
| description | The Brazilian Savanna presents a complex agricultural dynamic and cloud cover issues; therefore, there is a need for new strategies for more detailed agricultural monitoring. Using a hierarchical classification system, we explored the Harmonized Landsat Sentinel-2 (HLS) dataset to detect soybean in western Bahia, Brazil. Multispectral bands (MS) and vegetation indices (VIs) from October 2021 to March 2022 were used as variables to feed Random Forest models, and the performances of the complete HLS time-series, HLSS30 (harmonized Sentinel), HLSL30 (harmonized Landsat), and Landsat 8 OLI (L8) were compared. At Level 1 (agricultural areas × native vegetation), HLS, HLSS30, and L8 produced identical models using MS + VIs, with 0.959 overall accuracies (OA) and Kappa of 0.917. At Level 2 (annual crops × perennial crops × pasturelands), HLS and L8 achieved an OA of 0.935 and Kappa > 0.89 using only VIs. At Level 3 (soybean × other annual crops), the HLS MS + VIs model achieved the best performance, with OA of 0.913 and Kappa of 0.808. Our results demonstrated the potential of the new HLS dataset for medium-resolution mapping initiatives at the crop level, which can impact decision-making processes involving large-scale soybean production and agricultural sustainability. |
| first_indexed | 2024-03-09T05:01:49Z |
| format | Article |
| id | doaj.art-28b10299d9c34f1298b068b43fd320e3 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T05:01:49Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-28b10299d9c34f1298b068b43fd320e32023-12-03T12:58:42ZengMDPI AGRemote Sensing2072-42922022-08-011415373610.3390/rs14153736Hierarchical Classification of Soybean in the Brazilian Savanna Based on Harmonized Landsat Sentinel DataTaya Cristo Parreiras0Édson Luis Bolfe1Michel Eustáquio Dantas Chaves2Ieda Del’Arco Sanches3Edson Eyji Sano4Daniel de Castro Victoria5Giovana Maranhão Bettiol6Luiz Eduardo Vicente7Institute of Geosciences, State University of Campinas (Unicamp), Campinas 13083-855, BrazilInstitute of Geosciences, State University of Campinas (Unicamp), Campinas 13083-855, BrazilNational Institute for Space Research (INPE), São José dos Campos 12227-010, BrazilNational Institute for Space Research (INPE), São José dos Campos 12227-010, BrazilBrazilian Agricultural Research Corporation (Embrapa Cerrados), Planaltina 73301-970, BrazilBrazilian Agricultural Research Corporation (Embrapa Agricultura Digital), Campinas 70770-901, BrazilBrazilian Agricultural Research Corporation (Embrapa Cerrados), Planaltina 73301-970, BrazilBrazilian Agricultural Research Corporation (Embrapa Meio Ambiente), Jaguariúna 13820-000, BrazilThe Brazilian Savanna presents a complex agricultural dynamic and cloud cover issues; therefore, there is a need for new strategies for more detailed agricultural monitoring. Using a hierarchical classification system, we explored the Harmonized Landsat Sentinel-2 (HLS) dataset to detect soybean in western Bahia, Brazil. Multispectral bands (MS) and vegetation indices (VIs) from October 2021 to March 2022 were used as variables to feed Random Forest models, and the performances of the complete HLS time-series, HLSS30 (harmonized Sentinel), HLSL30 (harmonized Landsat), and Landsat 8 OLI (L8) were compared. At Level 1 (agricultural areas × native vegetation), HLS, HLSS30, and L8 produced identical models using MS + VIs, with 0.959 overall accuracies (OA) and Kappa of 0.917. At Level 2 (annual crops × perennial crops × pasturelands), HLS and L8 achieved an OA of 0.935 and Kappa > 0.89 using only VIs. At Level 3 (soybean × other annual crops), the HLS MS + VIs model achieved the best performance, with OA of 0.913 and Kappa of 0.808. Our results demonstrated the potential of the new HLS dataset for medium-resolution mapping initiatives at the crop level, which can impact decision-making processes involving large-scale soybean production and agricultural sustainability.https://www.mdpi.com/2072-4292/14/15/3736Cerradoagriculture monitoringremote sensingmultisensor<i>Glycine max</i> L.HLS |
| spellingShingle | Taya Cristo Parreiras Édson Luis Bolfe Michel Eustáquio Dantas Chaves Ieda Del’Arco Sanches Edson Eyji Sano Daniel de Castro Victoria Giovana Maranhão Bettiol Luiz Eduardo Vicente Hierarchical Classification of Soybean in the Brazilian Savanna Based on Harmonized Landsat Sentinel Data Remote Sensing Cerrado agriculture monitoring remote sensing multisensor <i>Glycine max</i> L. HLS |
| title | Hierarchical Classification of Soybean in the Brazilian Savanna Based on Harmonized Landsat Sentinel Data |
| title_full | Hierarchical Classification of Soybean in the Brazilian Savanna Based on Harmonized Landsat Sentinel Data |
| title_fullStr | Hierarchical Classification of Soybean in the Brazilian Savanna Based on Harmonized Landsat Sentinel Data |
| title_full_unstemmed | Hierarchical Classification of Soybean in the Brazilian Savanna Based on Harmonized Landsat Sentinel Data |
| title_short | Hierarchical Classification of Soybean in the Brazilian Savanna Based on Harmonized Landsat Sentinel Data |
| title_sort | hierarchical classification of soybean in the brazilian savanna based on harmonized landsat sentinel data |
| topic | Cerrado agriculture monitoring remote sensing multisensor <i>Glycine max</i> L. HLS |
| url | https://www.mdpi.com/2072-4292/14/15/3736 |
| work_keys_str_mv | AT tayacristoparreiras hierarchicalclassificationofsoybeaninthebraziliansavannabasedonharmonizedlandsatsentineldata AT edsonluisbolfe hierarchicalclassificationofsoybeaninthebraziliansavannabasedonharmonizedlandsatsentineldata AT micheleustaquiodantaschaves hierarchicalclassificationofsoybeaninthebraziliansavannabasedonharmonizedlandsatsentineldata AT iedadelarcosanches hierarchicalclassificationofsoybeaninthebraziliansavannabasedonharmonizedlandsatsentineldata AT edsoneyjisano hierarchicalclassificationofsoybeaninthebraziliansavannabasedonharmonizedlandsatsentineldata AT danieldecastrovictoria hierarchicalclassificationofsoybeaninthebraziliansavannabasedonharmonizedlandsatsentineldata AT giovanamaranhaobettiol hierarchicalclassificationofsoybeaninthebraziliansavannabasedonharmonizedlandsatsentineldata AT luizeduardovicente hierarchicalclassificationofsoybeaninthebraziliansavannabasedonharmonizedlandsatsentineldata |