Results of the MLP neural network in the land change modeler
| Land-use transitions . | Variables* . | Hidden layer neurons . | Accuracy rate (%) . | Skill measure . |
|---|---|---|---|---|
| Cultivated land to cities and towns | 1, 4, 6 | 2 | 98.65 | 0.9730 |
| Cultivated land to rural residential land | 2, 3, 4 | 3 | 90.89 | 0.8178 |
| Cultivated land to shrubbery lands | 2, 3, 6 | 4 | 91.32 | 0.8263 |
| Cultivated land to middle coverage grassland | 1, 2, 3, 4, 5, 6 | 5 | 86.26 | 0.7251 |
| Other forest land including garden to cities and towns | 2, 4, 6 | 2 | 88.03 | 0.7606 |
| Land-use transitions . | Variables* . | Hidden layer neurons . | Accuracy rate (%) . | Skill measure . |
|---|---|---|---|---|
| Cultivated land to cities and towns | 1, 4, 6 | 2 | 98.65 | 0.9730 |
| Cultivated land to rural residential land | 2, 3, 4 | 3 | 90.89 | 0.8178 |
| Cultivated land to shrubbery lands | 2, 3, 6 | 4 | 91.32 | 0.8263 |
| Cultivated land to middle coverage grassland | 1, 2, 3, 4, 5, 6 | 5 | 86.26 | 0.7251 |
| Other forest land including garden to cities and towns | 2, 4, 6 | 2 | 88.03 | 0.7606 |
*This item indicated the variables selected and used for driving or explaining the land-use transition, which were numbered for short in the table:
1: Digital elevation model map.
2: Slope map.
3: Distance to rural residential land, which is dynamic to be updated during calculation.
4: Distance to cities and towns, which is dynamic to be updated during calculation.
5: Distance to river, which is dynamic to be updated during calculation.
6: Distance to road.