International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Publications Copernicus
Download
Citation
Volume XLII-3/W11
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3/W11, 1–7, 2020
https://doi.org/10.5194/isprs-archives-XLII-3-W11-1-2020
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3/W11, 1–7, 2020
https://doi.org/10.5194/isprs-archives-XLII-3-W11-1-2020
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

  14 Feb 2020

14 Feb 2020

FROM PIXEL TO YIELD: FORECASTING POTATO PRODUCTIVITY IN LEBANON AND IDAHO

H. Abou Ali1, D. Delparte1, and L. M. Griffel2 H. Abou Ali et al.
  • 1Idaho State University, Department of Geosciences, 83209 Pocatello, Idaho, USA
  • 2Biofuels and Renewable Energy Technology Dept, Idaho National Lab, 83415 Idaho Falls, Idaho, USA

Keywords: yield prediction, vegetation indices, PlanetScope, remote sensing, precision agriculture, crop monitoring

Abstract. Idaho and Lebanon rely on potatoes as an economically important crop. NDVI (Normalized Difference Vegetation Index), GNDVI (Green Normalized Difference Vegetation Index), SAVI (Soil Adjusted Vegetation Index), and MSAVI2 (Modified Soil Adjusted Vegetation Index 2) indices were calculated from PlanetScope satellite imagery for the 2017 growing season cloud free days. Variations in vegetation health were tracked over time and correlated to yield data provided by growers in Idaho. Based on ordinary least squares regression an Idaho yield forecast model was developed. Vegetation response during the growth stage at which potato tubers were filling out was significant in predicting yield for both the Norkotah and Russet potato variety. This corresponded to a week with high recorded temperatures that impacted the health status of the crops. The yield forecasting model was validated with a cross validation approach and then applied to potato fields in Lebanon. The Idaho model successfully displayed yield variation in crops for Lebanon. Spectral indices along with field topography allow the prediction of yield based on the crop type and variety.