Table 2 The top ten highest ranked variables, as determined by variable importance measures, for the three machine learning models included in the model ensemble. Variable name suffixes (-1), (-2), and (-3) denote time lags of 1, 2, and 3 years, respectively. One, two, and three asterisks denote the first, second, and third principal component, respectively, for variables available on a monthly time step (see the “Methods” section)
Rank | XGB | RF | NN |
|---|---|---|---|
1 | Solar radiation*** | Solar radiation*** | Relative humidity* |
2 | ITN coverage (-1) | ITN coverage (-1) | Evergreen broadleaf forest (-3) |
3 | Elevation | Elevation | Wind speed* |
4 | Daytime temperature**(-2) | Tassel cap brightness**(-2) | Evergreen broadleaf forest (-1) |
5 | ITN coverage (-2) | ITN coverage (-2) | Elevation |
6 | Night time temperature* (-2) | Wind speed* | Cropping factor |
7 | Enhanced vegetation index**(-1) | Tassel cap brightness**(-3) | Cation exchange capacity |
8 | Rainfall*(-3) | Temperature diurnal difference*(-2) | Evergreen broadleaf forest (-2) |
9 | ITN coverage | ITN coverage | Tropical fruit |
10 | Night time temperature** (-2) | Tassel cap brightness** | Daytime temperature*(-1) |