Improving Coffee Yield Interpolation in the Presence of Outliers Using Multivariate Geostatistics and Satellite Data
Precision agriculture for coffee production requires spatial knowledge of crop yield. However, difficulties in implementation lie in low-sampled areas. In addition, the asynchronicity of this crop adds complexity to the modeling. It results in a diversity of phenological stages within a field and al...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | AgriEngineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2624-7402/6/1/6 |
| _version_ | 1797242417181622272 |
|---|---|
| author | César de Oliveira Ferreira Silva Celia Regina Grego Rodrigo Lilla Manzione Stanley Robson de Medeiros Oliveira |
| author_facet | César de Oliveira Ferreira Silva Celia Regina Grego Rodrigo Lilla Manzione Stanley Robson de Medeiros Oliveira |
| author_sort | César de Oliveira Ferreira Silva |
| collection | DOAJ |
| description | Precision agriculture for coffee production requires spatial knowledge of crop yield. However, difficulties in implementation lie in low-sampled areas. In addition, the asynchronicity of this crop adds complexity to the modeling. It results in a diversity of phenological stages within a field and also continuous production of coffee over time. Big Data retrieved from remote sensing can be tested to improve spatial modeling. This research proposes to apply the Sentinel-2 vegetation index (NDVI) and the Sentinel-1 dual-polarization C-band Synthetic Aperture Radar (SAR) dataset as auxiliary variables in the multivariate geostatistical modeling of coffee yield characterized by the presence of outliers and assess improvement. A total of 66 coffee yield points were sampled from a 4 ha area in a quasi-regular grid located in southeastern Brazil. Ordinary kriging (OK) and block cokriging (BCOK) were applied. Overall, coupling coffee yield with the NDVI and/or SAR in BCOK interpolation improved the accuracy of spatial interpolation of coffee yield even in the presence of outliers. Incorporating Big Data for improving the modeling for low-sampled fields requires taking into account the difference in supports between different datasets since this difference can increase uncontrolled uncertainty. In this manner, we will consider, for future research, new tests with other covariates. This research has the potential to support precision agriculture applications as site-specific plant nutrient management. |
| first_indexed | 2024-04-24T18:38:53Z |
| format | Article |
| id | doaj.art-7ce64e750a24415597a4dc4aaa8c14e8 |
| institution | Directory Open Access Journal |
| issn | 2624-7402 |
| language | English |
| last_indexed | 2024-04-24T18:38:53Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | AgriEngineering |
| spelling | doaj.art-7ce64e750a24415597a4dc4aaa8c14e82024-03-27T13:16:16ZengMDPI AGAgriEngineering2624-74022024-01-0161819410.3390/agriengineering6010006Improving Coffee Yield Interpolation in the Presence of Outliers Using Multivariate Geostatistics and Satellite DataCésar de Oliveira Ferreira Silva0Celia Regina Grego1Rodrigo Lilla Manzione2Stanley Robson de Medeiros Oliveira3School of Agricultural Engineering, Campinas State University (UNICAMP), Campinas 13083-875, BrazilEmbrapa Digital Agriculture, Campinas 13083-886, BrazilSchool of Science, Technology and Education, São Paulo State University (UNESP), Ourinhos 19903-302, BrazilSchool of Agricultural Engineering, Campinas State University (UNICAMP), Campinas 13083-875, BrazilPrecision agriculture for coffee production requires spatial knowledge of crop yield. However, difficulties in implementation lie in low-sampled areas. In addition, the asynchronicity of this crop adds complexity to the modeling. It results in a diversity of phenological stages within a field and also continuous production of coffee over time. Big Data retrieved from remote sensing can be tested to improve spatial modeling. This research proposes to apply the Sentinel-2 vegetation index (NDVI) and the Sentinel-1 dual-polarization C-band Synthetic Aperture Radar (SAR) dataset as auxiliary variables in the multivariate geostatistical modeling of coffee yield characterized by the presence of outliers and assess improvement. A total of 66 coffee yield points were sampled from a 4 ha area in a quasi-regular grid located in southeastern Brazil. Ordinary kriging (OK) and block cokriging (BCOK) were applied. Overall, coupling coffee yield with the NDVI and/or SAR in BCOK interpolation improved the accuracy of spatial interpolation of coffee yield even in the presence of outliers. Incorporating Big Data for improving the modeling for low-sampled fields requires taking into account the difference in supports between different datasets since this difference can increase uncontrolled uncertainty. In this manner, we will consider, for future research, new tests with other covariates. This research has the potential to support precision agriculture applications as site-specific plant nutrient management.https://www.mdpi.com/2624-7402/6/1/6<i>Coffea arabica</i> L.precision agriculturecokrigingvariogram |
| spellingShingle | César de Oliveira Ferreira Silva Celia Regina Grego Rodrigo Lilla Manzione Stanley Robson de Medeiros Oliveira Improving Coffee Yield Interpolation in the Presence of Outliers Using Multivariate Geostatistics and Satellite Data AgriEngineering <i>Coffea arabica</i> L. precision agriculture cokriging variogram |
| title | Improving Coffee Yield Interpolation in the Presence of Outliers Using Multivariate Geostatistics and Satellite Data |
| title_full | Improving Coffee Yield Interpolation in the Presence of Outliers Using Multivariate Geostatistics and Satellite Data |
| title_fullStr | Improving Coffee Yield Interpolation in the Presence of Outliers Using Multivariate Geostatistics and Satellite Data |
| title_full_unstemmed | Improving Coffee Yield Interpolation in the Presence of Outliers Using Multivariate Geostatistics and Satellite Data |
| title_short | Improving Coffee Yield Interpolation in the Presence of Outliers Using Multivariate Geostatistics and Satellite Data |
| title_sort | improving coffee yield interpolation in the presence of outliers using multivariate geostatistics and satellite data |
| topic | <i>Coffea arabica</i> L. precision agriculture cokriging variogram |
| url | https://www.mdpi.com/2624-7402/6/1/6 |
| work_keys_str_mv | AT cesardeoliveiraferreirasilva improvingcoffeeyieldinterpolationinthepresenceofoutliersusingmultivariategeostatisticsandsatellitedata AT celiareginagrego improvingcoffeeyieldinterpolationinthepresenceofoutliersusingmultivariategeostatisticsandsatellitedata AT rodrigolillamanzione improvingcoffeeyieldinterpolationinthepresenceofoutliersusingmultivariategeostatisticsandsatellitedata AT stanleyrobsondemedeirosoliveira improvingcoffeeyieldinterpolationinthepresenceofoutliersusingmultivariategeostatisticsandsatellitedata |