Skip to main content
Fig. 4 | Plant Methods

Fig. 4

From: High-throughput phenotyping for non-destructive estimation of soybean fresh biomass using a machine learning model and temporal UAV data

Fig. 4

Correlation between the actual and the predicted fresh soybean biomass (kg/m2). (a) CC and PH combined with 31 VIs in RF, (b) CC and PH combined with 31 VIs in PLSR, (c) CC and PH combined with TGI and GCI in RF and (d) CC and PH combined with TGI and GCI in PLSR. Canopy cover – CC, plant height – PH, vegetation indices – VIs, random forest – RF, partial least squares regression – PLSR, coefficient of determination – R2, root mean square error – RMSE, and mean absolute error – MAE

Back to article page

Plant Methods

ISSN: 1746-4811