Skip to main content

Table 8 Accuracy assessment for the estimation of AGB in wheat from vegetation indices, plant height metrics and their combination with SMLR and three machine learning techniques

From: Improved estimation of aboveground biomass in wheat from RGB imagery and point cloud data acquired with a low-cost unmanned aerial vehicle system

Input variables

Technique

Calibration (N = 201)

Validation (N = 85)

R 2

RMSE (t/ha)

AIC

R 2

RMSE (t/ha)

rRMSE (%)

VIs

SMLR

0.69

1.52

742.63

0.70

1.58

34.49

SVR

0.69

1.53

696.27

0.64

1.75

38.13

ELM

0.69

1.52

759.25

0.64

1.73

37.27

RF

0.70

1.51

423.87

0.69

1.61

34.06

Canopy height metrics

SMLR

0.68

1.53

747.72

0.72

1.54

33.61

SVR

0.68

1.56

708.20

0.70

1.55

33.71

ELM

0.65

1.65

751.30

0.71

1.55

33.63

RF

0.73

1.44

398.32

0.74

1.39

30.95

VIs and canopy height metrics

SMLR

0.72

1.43

717.41

0.75

1.46

31.77

SVR

0.71

1.50

592.05

0.73

1.51

33.10

ELM

0.72

1.45

733.02

0.73

1.51

32.77

RF

0.76

1.34

369.23

0.78

1.34

28.98

  1. The accuracy metrics were calculated from calibration data and validation data separately. The number in bold for each column represents the maximum R2, minimum RMSE, minimum AIC and minimum rRMSE, respectively