With the best model, the wheat yield over the entire field was calculated in ArcGIS Spatial Analyst v. 10.6 software (Esri, Redlands, California, United States) to map the aerial photographs. The field was divided into 25 × 25 cm cells (c1, c2, ⋯, cnc, where nc is the total number of cells) using GIS. With the model (f), the pixel-by-pixel predicted values of the target traits, including wheat yield, were calculated for the entire field (y^p1,y^p2,,y^pnp, where pi is the i-th pixel in the UAV image of the field, and np is the total number of pixels in the image). Then the average yield of wheat in each cell (ci) was calculated from the pixel-by-pixel values:

where nci is the total number of pixel in each cell.

Cells that contained two plots during soybean cultivation and cells containing both corridor and experimental plot areas during wheat cultivation were eliminated (Figure 2C). This resulted in 8756 cells of predicted wheat yield values (mean of 125 cells per soybean plot). To assess the relationship between predicted yield and manually sampled yield, the overall distributions of these values for each plot were compared.

Note: The content above has been extracted from a research article, so it may not display correctly.

Please log in to submit your questions online.
Your question will be posted on the Bio-101 website. We will send your questions to the authors of this protocol and Bio-protocol community members who are experienced with this method. you will be informed using the email address associated with your Bio-protocol account.

We use cookies on this site to enhance your user experience. By using our website, you are agreeing to allow the storage of cookies on your computer.