Table 3 Performance of soil free iron content models based on correlated spectrum.
From: Estimation of soil free Iron content using spectral reflectance and machine learning algorithms
Spectral | Modeling | Training | Testing | ||||
|---|---|---|---|---|---|---|---|
Transform | Methods | R2 | RMSE (g/kg) | RRMSE (%) | R2 | RMSE (g/kg) | RRMSE (%) |
Original | PLS | 0.605 | 7.361 | 33.0 | 0.549 | 7.543 | 35.0 |
SVM | 0.737 | 6.153 | 29.0 | 0.557 | 7.768 | 35.4 | |
RF | 0.883 | 4.308 | 19.6 | 0.335 | 9.558 | 43.5 | |
DNN | 0.748 | 5.929 | 26.2 | 0.654 | 6.841 | 31.2 | |
FD | PLS | 0.569 | 7.721 | 33.9 | 0.415 | 8.589 | 39.8 |
SVM | 0.585 | 7.799 | 37.8 | 0.458 | 8.786 | 40.0 | |
RF | 0.893 | 4.759 | 21.5 | 0.147 | 10.825 | 49.3 | |
DNN | 0.607 | 7.554 | 33.4 | 0.623 | 7.742 | 35.3 | |
SNV | PLS | 0.471 | 8.509 | 38.4 | 0.434 | 8.463 | 38.2 |
SVM | 0.546 | 7.899 | 37.1 | 0.478 | 8.426 | 38.4 | |
RF | 0.898 | 4.369 | 19.9 | 0.578 | 7.585 | 34.6 | |
DNN | 0.666 | 7.014 | 31.7 | 0.626 | 7.219 | 32.9 | |
CR | PLS | 0.694 | 6.472 | 28.8 | 0.636 | 6.776 | 31.4 |
SVM | 0.702 | 6.461 | 30.8 | 0.636 | 7.010 | 31.9 | |
RF | 0.823 | 3.612 | 16.4 | 0.502 | 8.122 | 37.0 | |
DNN | 0.738 | 6.144 | 27.1 | 0.646 | 6.990 | 31.8 | |
