Research Article
Soil Classification Based on Deep Learning Algorithm and Visible Near-Infrared Spectroscopy
Table 5
The classification results of six types of soil in the test set by convolutional neural network.
| The total number of calibration set | Type 1 orchards | Type 2 woodlands | Type 3 tea plantations | Type 4 farmlands | Type 5 bare lands | Type 6 grasslands |
| 90 | 91.67% | 100.00% | 100.00% | 100.00% | 0% | 100.00% | (11/12) | (58/58) | (3/3) | (57/57) | (0/1) | (50/50) |
| 80 | 100.00% | 100.00% | 100.00% | 100.00% | 100.00% | 100.00% | (13/13) | (60/60) | (5/5) | (60/60) | (2/2) | (51/51) |
| 70 | 93.75% | 100.00% | 100.00% | 96.87% | 100.00% | 100.00% | (15/16) | (61/61) | (5/5) | (62/64) | (3/3) | (52/52) |
| 60 | 88.24% | 98.48% | 100.00% | 100.00% | 100.00% | 100.00% | (15/17) | (65/66) | (6/6) | (64/64) | (5/5) | (53/53) |
| 50 | 61.90% | 98.57% | 83.33% | 96.92% | 100.00% | 100.00% | (13/21) | (69/70) | (5/6) | (63/65) | (6/6) | (53/53) |
| 40 | 77.27% | 97.26% | 75.00% | 96.97% | 100.00% | 100.00% | (17/22) | (71/73) | (6/8) | (64/66) | (7/7) | (55/55) |
|
|