Improving the accuracy of remotely sensed irrigated areas using post-classification enhancement through UAV [Unmanned Aerial Vehicle] capability
Although advances in remote sensing have enhanced mapping and monitoring of irrigated areas, producing accurate cropping information through satellite image classification remains elusive due to the complexity of landscapes, changes in reflectance of different land-covers, the remote sensing data se...
| Autores principales: | , , , , |
|---|---|
| Formato: | Journal Article |
| Lenguaje: | Inglés |
| Publicado: |
MDPI
2018
|
| Materias: | |
| Acceso en línea: | https://hdl.handle.net/10568/93406 |
| _version_ | 1855520512814350336 |
|---|---|
| author | Nhamo, Luxon Dijk, R. van Magidi, J. Wiberg, David A. Tshikolomo, K. |
| author_browse | Dijk, R. van Magidi, J. Nhamo, Luxon Tshikolomo, K. Wiberg, David A. |
| author_facet | Nhamo, Luxon Dijk, R. van Magidi, J. Wiberg, David A. Tshikolomo, K. |
| author_sort | Nhamo, Luxon |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | Although advances in remote sensing have enhanced mapping and monitoring of irrigated areas, producing accurate cropping information through satellite image classification remains elusive due to the complexity of landscapes, changes in reflectance of different land-covers, the remote sensing data selected, and image processing methods used, among others. This study extracted agricultural fields in the former homelands of Venda and Gazankulu in Limpopo Province, South Africa. Landsat 8 imageries for 2015 were used, applying the maximum likelihood supervised classifier to delineate the agricultural fields. The normalized difference vegetation index (NDVI) applied on Landsat imageries on the mapped fields during the dry season (July to August) was used to identify irrigated areas, because years of satellite data analysis suggest that healthy crop conditions during dry seasons are only possible with irrigation. Ground truth points totaling 137 were collected during fieldwork for pre-processing and accuracy assessment. An accuracy of 96% was achieved on the mapped agricultural fields, yet the irrigated area map produced an initial accuracy of only 71%. This study explains and improves the 29% error margin from the irrigated areas. Accuracy was enhanced through post-classification correction (PCC) using 74 post-classification points randomly selected from the 2015 irrigated area map. High resolution aerial photographs of the 74 sample fields were acquired by an unmanned aerial vehicle (UAV) to give a clearer picture of the irrigated fields. The analysis shows that mapped irrigated fields that presented anomalies included abandoned croplands that had green invasive alien species or abandoned fruit plantations that had high NDVI values. The PCC analysis improved irrigated area mapping accuracy from 71% to 95%. |
| format | Journal Article |
| id | CGSpace93406 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2018 |
| publishDateRange | 2018 |
| publishDateSort | 2018 |
| publisher | MDPI |
| publisherStr | MDPI |
| record_format | dspace |
| spelling | CGSpace934062025-03-11T09:50:20Z Improving the accuracy of remotely sensed irrigated areas using post-classification enhancement through UAV [Unmanned Aerial Vehicle] capability Nhamo, Luxon Dijk, R. van Magidi, J. Wiberg, David A. Tshikolomo, K. irrigated sites remote sensing unmanned aerial vehicles land use mapping land cover mapping satellite imagery landsat farmland vegetation index crops Although advances in remote sensing have enhanced mapping and monitoring of irrigated areas, producing accurate cropping information through satellite image classification remains elusive due to the complexity of landscapes, changes in reflectance of different land-covers, the remote sensing data selected, and image processing methods used, among others. This study extracted agricultural fields in the former homelands of Venda and Gazankulu in Limpopo Province, South Africa. Landsat 8 imageries for 2015 were used, applying the maximum likelihood supervised classifier to delineate the agricultural fields. The normalized difference vegetation index (NDVI) applied on Landsat imageries on the mapped fields during the dry season (July to August) was used to identify irrigated areas, because years of satellite data analysis suggest that healthy crop conditions during dry seasons are only possible with irrigation. Ground truth points totaling 137 were collected during fieldwork for pre-processing and accuracy assessment. An accuracy of 96% was achieved on the mapped agricultural fields, yet the irrigated area map produced an initial accuracy of only 71%. This study explains and improves the 29% error margin from the irrigated areas. Accuracy was enhanced through post-classification correction (PCC) using 74 post-classification points randomly selected from the 2015 irrigated area map. High resolution aerial photographs of the 74 sample fields were acquired by an unmanned aerial vehicle (UAV) to give a clearer picture of the irrigated fields. The analysis shows that mapped irrigated fields that presented anomalies included abandoned croplands that had green invasive alien species or abandoned fruit plantations that had high NDVI values. The PCC analysis improved irrigated area mapping accuracy from 71% to 95%. 2018 2018-06-21T09:36:36Z 2018-06-21T09:36:36Z Journal Article https://hdl.handle.net/10568/93406 en Open Access MDPI Nhamo, Luxon; van Dijk, R.; Magidi, J.; Wiberg, David; Tshikolomo, K. 2018. Improving the accuracy of remotely sensed irrigated areas using post-classification enhancement through UAV [Unmanned Aerial Vehicle] capability. Remote Sensing, 10(5):1-12. (Special issue: Remote Sensing for Crop Water Management). doi: 10.3390/rs10050712 |
| spellingShingle | irrigated sites remote sensing unmanned aerial vehicles land use mapping land cover mapping satellite imagery landsat farmland vegetation index crops Nhamo, Luxon Dijk, R. van Magidi, J. Wiberg, David A. Tshikolomo, K. Improving the accuracy of remotely sensed irrigated areas using post-classification enhancement through UAV [Unmanned Aerial Vehicle] capability |
| title | Improving the accuracy of remotely sensed irrigated areas using post-classification enhancement through UAV [Unmanned Aerial Vehicle] capability |
| title_full | Improving the accuracy of remotely sensed irrigated areas using post-classification enhancement through UAV [Unmanned Aerial Vehicle] capability |
| title_fullStr | Improving the accuracy of remotely sensed irrigated areas using post-classification enhancement through UAV [Unmanned Aerial Vehicle] capability |
| title_full_unstemmed | Improving the accuracy of remotely sensed irrigated areas using post-classification enhancement through UAV [Unmanned Aerial Vehicle] capability |
| title_short | Improving the accuracy of remotely sensed irrigated areas using post-classification enhancement through UAV [Unmanned Aerial Vehicle] capability |
| title_sort | improving the accuracy of remotely sensed irrigated areas using post classification enhancement through uav unmanned aerial vehicle capability |
| topic | irrigated sites remote sensing unmanned aerial vehicles land use mapping land cover mapping satellite imagery landsat farmland vegetation index crops |
| url | https://hdl.handle.net/10568/93406 |
| work_keys_str_mv | AT nhamoluxon improvingtheaccuracyofremotelysensedirrigatedareasusingpostclassificationenhancementthroughuavunmannedaerialvehiclecapability AT dijkrvan improvingtheaccuracyofremotelysensedirrigatedareasusingpostclassificationenhancementthroughuavunmannedaerialvehiclecapability AT magidij improvingtheaccuracyofremotelysensedirrigatedareasusingpostclassificationenhancementthroughuavunmannedaerialvehiclecapability AT wibergdavida improvingtheaccuracyofremotelysensedirrigatedareasusingpostclassificationenhancementthroughuavunmannedaerialvehiclecapability AT tshikolomok improvingtheaccuracyofremotelysensedirrigatedareasusingpostclassificationenhancementthroughuavunmannedaerialvehiclecapability |