| Budget Amount *help |
¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
Fiscal Year 2016: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2015: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Outline of Final Research Achievements |
This study compares the kernel-based extreme learning machine (KELM) and the two traditional machine learning algorithms including self-organizing maps (SOM) and the random forest (RF) for detecting ecological degradation in Xinjiang (China), using satellite data. The results showed that KELM had the best performance in this study and kappa scores greater than 0.8 were confirmed against the validation data.
Based on the detection of changes in land cover during 2000-2015 using MODIS data (MOD13A2) and KELM, it can be found that the oasis decreased (15,739 km2).
|
