Table 6 Error metrics of both models in (kg/ha) at 95% confidence interval evaluated in training and testing dataset: MBE (Mean Bias Error), AMBE (Absolute Mean Bias Error), RMSE (Root Mean Square Error), NMAD (normalized median absolute deviation), RE (Relative Error), AE (Absolute Error) and η (the Nash and Sutcliffe index)
From: Yield prediction by machine learning from UAS-based multi-sensor data fusion in soybean
Dataset | Model | MBE | AMBE | RMSE | NMAD | RE | AE | η |
|---|---|---|---|---|---|---|---|---|
Training | RF | 13.61 | 140.25 | 181.19 | 167.48 | 1.14% | 4.03% | 0.80 |
XGBoost | 30.39 | 240.45 | 303.99 | 292.12 | 1.98% | 6.87% | 0.21 | |
Testing | RF | − 4.17 | 325.33 | 410.24 | 384.62 | 1.37% | 9.06% | − 2.46 |
XGBoost | − 7.15 | 306.76 | 394.66 | 353.04 | 1.18% | 8.55% | − 1.52 |