Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Monitoring Land Use/Cover Change Using Remotely Sensed Data in Guangzhou of China
Land use/cover change (LUCC) has a crucial influence on ecosystem function, environmental change and decision support. Rapid and precise monitoring of land use/cover change information is essential for utilization and management of land resources. The objectives of this study were to monitor land use/cover change of Guangzhou of China from 1986 to 2018 using remotely sensed data, and analyze the correlation between artificial surface expansion and the gross domestic product (GDP) growth. Supervised classification was performed using Random Forest classifier, and the overall accuracy (OA) ranged from 86.42% to 96.58% and kappa coefficient (K) ranged from 0.8079 to 0.9499. The results show that the built-up area of Guangzhou of China from 1986 to 2018 continued to increase. However, the vegetation area continued to decrease during 32 years. The built-up area increased by 1315.56 km2 (increased by 439.34%) with an average growth of 41.11 km2/year. The vegetation area reduced by 1290.78 km2 (reduced by 19.99%) with an average reduction of 40.34 km2/year. Research has shown that the reduced vegetation area was mainly converted into built-up area. The area of water bodies and bare lands was relatively stable and had a little change. The results indicate that the GDP had a strong positive correlation with built-up area (R2 = 0.98). However, there is a strong negative correlation between the GDP and vegetation area (R2 = 0.97) in Guangzhou City, China. As a consequence, the increase of built-up area was at the cost of the reduction of vegetation area.
Monitoring Land Use/Cover Change Using Remotely Sensed Data in Guangzhou of China
Land use/cover change (LUCC) has a crucial influence on ecosystem function, environmental change and decision support. Rapid and precise monitoring of land use/cover change information is essential for utilization and management of land resources. The objectives of this study were to monitor land use/cover change of Guangzhou of China from 1986 to 2018 using remotely sensed data, and analyze the correlation between artificial surface expansion and the gross domestic product (GDP) growth. Supervised classification was performed using Random Forest classifier, and the overall accuracy (OA) ranged from 86.42% to 96.58% and kappa coefficient (K) ranged from 0.8079 to 0.9499. The results show that the built-up area of Guangzhou of China from 1986 to 2018 continued to increase. However, the vegetation area continued to decrease during 32 years. The built-up area increased by 1315.56 km2 (increased by 439.34%) with an average growth of 41.11 km2/year. The vegetation area reduced by 1290.78 km2 (reduced by 19.99%) with an average reduction of 40.34 km2/year. Research has shown that the reduced vegetation area was mainly converted into built-up area. The area of water bodies and bare lands was relatively stable and had a little change. The results indicate that the GDP had a strong positive correlation with built-up area (R2 = 0.98). However, there is a strong negative correlation between the GDP and vegetation area (R2 = 0.97) in Guangzhou City, China. As a consequence, the increase of built-up area was at the cost of the reduction of vegetation area.
Monitoring Land Use/Cover Change Using Remotely Sensed Data in Guangzhou of China
Liang Guo (Autor:in) / Xiaohuan Xi (Autor:in) / Weijun Yang (Autor:in) / Lei Liang (Autor:in)
2021
Aufsatz (Zeitschrift)
Elektronische Ressource
Unbekannt
Metadata by DOAJ is licensed under CC BY-SA 1.0
Land-cover Classification of Remotely Sensed Data Using Kalman Filtering
| British Library Online Contents | 1997
Decision Tree Classification of Land Cover from Remotely Sensed Data
| Online Contents | 1997
Land Classification Using Remotely Sensed Data: Going Multilabel
| Online Contents | 2016
Multi-source remotely sensed data fusion for improving land cover classification
| Online Contents | 2017