Corn Grain Yield Prediction and Mapping from Unmanned Aerial System (UAS) Multispectral Imagery
Harvester-mounted yield monitor sensors are expensive and require calibration and data cleaning. Therefore, we evaluated six vegetation indices (VI) from unmanned aerial system (Quantix™ Mapper) imagery for corn (<i>Zea mays</i> L.) yield prediction. A field trial was conducted with N si...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/19/3948 |
| _version_ | 1827680598350626816 |
|---|---|
| author | S. Sunoj Jason Cho Joe Guinness Jan van Aardt Karl J. Czymmek Quirine M. Ketterings |
| author_facet | S. Sunoj Jason Cho Joe Guinness Jan van Aardt Karl J. Czymmek Quirine M. Ketterings |
| author_sort | S. Sunoj |
| collection | DOAJ |
| description | Harvester-mounted yield monitor sensors are expensive and require calibration and data cleaning. Therefore, we evaluated six vegetation indices (VI) from unmanned aerial system (Quantix™ Mapper) imagery for corn (<i>Zea mays</i> L.) yield prediction. A field trial was conducted with N sidedress treatments applied at four growth stages (V4, V6, V8, or V10) compared against zero-N and N-rich controls. Normalized difference vegetation index (NDVI) and enhanced vegetation index 2 (EVI2), based on flights at R4, resulted in the most accurate yield estimations, as long as sidedressing was performed before V6. Yield estimations based on earlier flights were less accurate. Estimations were most accurate when imagery from both N-rich and zero-N control plots were included, but elimination of the zero-N data only slightly reduced the accuracy. Use of a ratio approach (VI<sub>Trt</sub>/VI<sub>N-rich</sub> and Yield<sub>Trt</sub>/Yield<sub>N-rich</sub>) enables the extension of findings across fields and only slightly reduced the model performance. Finally, a smaller plot size (9 or 75 m<sup>2</sup> compared to 150 m<sup>2</sup>) resulted in a slightly reduced model performance. We concluded that accurate yield estimates can be obtained using NDVI and EVI2, as long as there is an N-rich strip in the field, sidedressing is performed prior to V6, and sensing takes place at R3 or R4. |
| first_indexed | 2024-03-10T06:51:56Z |
| format | Article |
| id | doaj.art-3c0860db048d448080fa394247efd205 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T06:51:56Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-3c0860db048d448080fa394247efd2052023-11-22T16:43:17ZengMDPI AGRemote Sensing2072-42922021-10-011319394810.3390/rs13193948Corn Grain Yield Prediction and Mapping from Unmanned Aerial System (UAS) Multispectral ImageryS. Sunoj0Jason Cho1Joe Guinness2Jan van Aardt3Karl J. Czymmek4Quirine M. Ketterings5Nutrient Management Spear Program, Department of Animal Science, Cornell University, Ithaca, NY 14853, USANutrient Management Spear Program, Department of Animal Science, Cornell University, Ithaca, NY 14853, USADepartment of Statistics and Data Science, Cornell University, Ithaca, NY 14853, USACenter for Imaging Science, Rochester Institute of Technology, Rochester, NY 14623, USANutrient Management Spear Program, Department of Animal Science, Cornell University, Ithaca, NY 14853, USANutrient Management Spear Program, Department of Animal Science, Cornell University, Ithaca, NY 14853, USAHarvester-mounted yield monitor sensors are expensive and require calibration and data cleaning. Therefore, we evaluated six vegetation indices (VI) from unmanned aerial system (Quantix™ Mapper) imagery for corn (<i>Zea mays</i> L.) yield prediction. A field trial was conducted with N sidedress treatments applied at four growth stages (V4, V6, V8, or V10) compared against zero-N and N-rich controls. Normalized difference vegetation index (NDVI) and enhanced vegetation index 2 (EVI2), based on flights at R4, resulted in the most accurate yield estimations, as long as sidedressing was performed before V6. Yield estimations based on earlier flights were less accurate. Estimations were most accurate when imagery from both N-rich and zero-N control plots were included, but elimination of the zero-N data only slightly reduced the accuracy. Use of a ratio approach (VI<sub>Trt</sub>/VI<sub>N-rich</sub> and Yield<sub>Trt</sub>/Yield<sub>N-rich</sub>) enables the extension of findings across fields and only slightly reduced the model performance. Finally, a smaller plot size (9 or 75 m<sup>2</sup> compared to 150 m<sup>2</sup>) resulted in a slightly reduced model performance. We concluded that accurate yield estimates can be obtained using NDVI and EVI2, as long as there is an N-rich strip in the field, sidedressing is performed prior to V6, and sensing takes place at R3 or R4.https://www.mdpi.com/2072-4292/13/19/3948corn yieldnitrogen sidedressprecision agricultureunmanned aerial systemsyield monitor |
| spellingShingle | S. Sunoj Jason Cho Joe Guinness Jan van Aardt Karl J. Czymmek Quirine M. Ketterings Corn Grain Yield Prediction and Mapping from Unmanned Aerial System (UAS) Multispectral Imagery Remote Sensing corn yield nitrogen sidedress precision agriculture unmanned aerial systems yield monitor |
| title | Corn Grain Yield Prediction and Mapping from Unmanned Aerial System (UAS) Multispectral Imagery |
| title_full | Corn Grain Yield Prediction and Mapping from Unmanned Aerial System (UAS) Multispectral Imagery |
| title_fullStr | Corn Grain Yield Prediction and Mapping from Unmanned Aerial System (UAS) Multispectral Imagery |
| title_full_unstemmed | Corn Grain Yield Prediction and Mapping from Unmanned Aerial System (UAS) Multispectral Imagery |
| title_short | Corn Grain Yield Prediction and Mapping from Unmanned Aerial System (UAS) Multispectral Imagery |
| title_sort | corn grain yield prediction and mapping from unmanned aerial system uas multispectral imagery |
| topic | corn yield nitrogen sidedress precision agriculture unmanned aerial systems yield monitor |
| url | https://www.mdpi.com/2072-4292/13/19/3948 |
| work_keys_str_mv | AT ssunoj corngrainyieldpredictionandmappingfromunmannedaerialsystemuasmultispectralimagery AT jasoncho corngrainyieldpredictionandmappingfromunmannedaerialsystemuasmultispectralimagery AT joeguinness corngrainyieldpredictionandmappingfromunmannedaerialsystemuasmultispectralimagery AT janvanaardt corngrainyieldpredictionandmappingfromunmannedaerialsystemuasmultispectralimagery AT karljczymmek corngrainyieldpredictionandmappingfromunmannedaerialsystemuasmultispectralimagery AT quirinemketterings corngrainyieldpredictionandmappingfromunmannedaerialsystemuasmultispectralimagery |