Singapore: land change, 2016–2025
Two Sentinel-2 satellite images of a 20 km square around Singapore, from 2016-09-03 and 2025-09-06, were classified by a ResNet18 model trained on EuroSAT. Every 640 m cell is put in one of four land-cover groups, and the two dates are compared cell by cell.
- Before
- 2016-09-03
- After
- 2025-09-06
- Area analysed
- 317 km²
Change
-4.5 km²net change in built-up area
In cells the model is sure of on both dates (confidence ≥ 0.8): 2 km² became built-up, 4.5 km² changed in total.
The model is undecided on this scene; treat the results with caution.
Part of the image is cloudy or missing; results are unreliable there.
Prior knowledge (Natural Earth): 14 cells in open water well away from the shore were counted as water; the model had seen another class there.
Land cover on both dates
| 2016 | 2025 | ± | |
|---|---|---|---|
| Agriculture no notable change | 0.4% | 0% | -0.4 |
| Natural vegetation increased | 7.5% | 8.5% | +1 |
| Built-up decreased | 39.7% | 38.3% | -1.4 |
| Water no notable change | 52.4% | 53.2% | +0.8 |
Largest transitions (confident cells)
- Natural vegetation → Built-up1.6 km²
- Built-up → Natural vegetation1.6 km²
- Natural vegetation → Water0.8 km²
- Agriculture → Built-up0.4 km²
Limits
- Every value shown is a model estimate, not a measurement.
- Areas are not measurements but approximations counted from cells. The figures are always computed on 640 m cells; the scale only changes how the map is drawn.
- The model was trained on European images only; results for places tagged "experimental" are less reliable.
- Clouds, shadows and seasonal differences can show change that is not there.