|
Urban Growth Monitoring in Chanthaburi Using Remote Sensing Data on Google Earth Engine |
|---|---|
| รหัสดีโอไอ | |
| Creator | Kumpee Teeravech |
| Title | Urban Growth Monitoring in Chanthaburi Using Remote Sensing Data on Google Earth Engine |
| Contributor | Kanitta Yarak, Topthong Chancharoen |
| Publisher | The Association of Council of IT Deans (CITT) |
| Publication Year | 2566 |
| Journal Title | Journal of Information Science and Technology |
| Journal Vol. | 13 |
| Journal No. | 2 |
| Page no. | 69-78 |
| Keyword | Google Earth Engine, Machine Learning, Urban Growth, Random Forest, CA-Markov Urban Growth Model |
| URL Website | https://tci-thaijo.org/index.php/JIST |
| Website title | Journal of Information Science and Technology |
| ISSN | 2651-1053 |
| Abstract | Google Earth Engine remote sensing data, consisting of 102 images acquired by LANDSAT-5 TM and LANDSAT-8 OLI satellites, were utilized to classify six land use categories using the Random Forest algorithm. The primary objective was to analyze land use patterns spanning a temporal span of three decades. To achieve this, we deployed machine learning techniques, specifically the Random Forest algorithm, with the aim of examining temporal changes and identifying patterns related to urban expansion. Our analysis revealed that between 1992 and 2012, herbaceous and field crops were the predominant land use categories, with areas of 3,404.96 sq.km., 2,596.02 sq.km., 2,404.79 sq.km., 2,604.32 sq.km., and 2,623.44 sq.km. at five-year intervals. However, a significant shift occurred in 2017 and 2022 when land use transitioned toward perennial fruit and woody crops, becoming the top-ranking land use category with areas of 2,695.83 sq.km. and 2,516.83 sq.km. This transformation was accompanied by a simultaneous increase in urban expansion, indicating a noticeable departure from the cultivation of herbaceous and field crops. Moreover, there was a noticeable decline in the extent of land allocated to perennial fruit crops. Projections based on the CA-Markov model predict a sustained trend of urban expansion, with the urban area and infrastructure expected to reach 115.15 sq.km. and 126.02 sq.km. by 2027 and 2032, respectively. |
