Accuracy analysis of multi-series phenological landcover classification using U-Net-based deep learning model – Focusing on the Seoul, Republic of Korea –

Earth & Environmental Sciences

• learning 91%
• land cover 90%
• analysis 29%
• satellite image 28%
• green space 18%
• spectral reflectance 18%
• environmental policy 16%
• ministry 15%
• land surface 13%
• decision making 11%
• remote sensing 10%
• policy 9%
• land 8%
• river 7%

Engineering & Materials Science

• Deep learning 100%
• Satellites 24%
• Remote sensing 16%
• Rivers 15%
• Learning algorithms 13%
• Decision making 11%