Follow NEMC
 |
 |
 |
Detection of Melt Pond from Aerial Photos through Object-Based Image Classification Scheme
Oral Presentation
Prepared by X. Miao1, H. Xie2, Z. Li3, R. Lei4
1 - University of Texas at San Antonio, University of Texas at San Antonio, SB 4.02.07, TX, San Antonio
2 - University of Texas at San Antonio, University of Texas at San Antonio, One UTSA Circle, SB 4.02.07, TX, San Antonio
Contact Information: xinmiao@missouristate.edu; 417-631-1855
ABSTRACT
Melt ponds are pools of open fresh water on surface of Arctic sea ice in the warmer months and have a significant influence on Earth's radiation balance since they strongly absorb solar radiation rather than reflecting it as snow and ice do. However, manually delineating of melt pond from remotely sensed images is time-consuming and labor-intensive. In this study, we use the object-based remote sensing classification scheme to extract melt ponds efficiently from 1,727 aerial photos taken during the Chinese Arctic Exploration in 2010. Our results illustrate the spatial distribution and morphological characters of melt ponds in different latitudes of the Arctic Pacific sector. This method can be applied to massive photos and images taken in past years and future years, in deriving the melt pond distribution and changes through years. The results can be used to fine-tune climate models.
Oral Presentation
Prepared by X. Miao1, H. Xie2, Z. Li3, R. Lei4
1 - University of Texas at San Antonio, University of Texas at San Antonio, SB 4.02.07, TX, San Antonio
2 - University of Texas at San Antonio, University of Texas at San Antonio, One UTSA Circle, SB 4.02.07, TX, San Antonio
Contact Information: xinmiao@missouristate.edu; 417-631-1855
ABSTRACT
Melt ponds are pools of open fresh water on surface of Arctic sea ice in the warmer months and have a significant influence on Earth's radiation balance since they strongly absorb solar radiation rather than reflecting it as snow and ice do. However, manually delineating of melt pond from remotely sensed images is time-consuming and labor-intensive. In this study, we use the object-based remote sensing classification scheme to extract melt ponds efficiently from 1,727 aerial photos taken during the Chinese Arctic Exploration in 2010. Our results illustrate the spatial distribution and morphological characters of melt ponds in different latitudes of the Arctic Pacific sector. This method can be applied to massive photos and images taken in past years and future years, in deriving the melt pond distribution and changes through years. The results can be used to fine-tune climate models.