Sheng Gao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Sheng Gao has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Fulong Chen
Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
1 shared publication - Meng Zhu
Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
1 shared publication - Pilong Shi
Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
1 shared publication - Qin Wang
Jiuzhaigou Valley Scenic Area Administration, Jiuzhaigou 623402, China
1 shared publication - Wei Zhou
International Research Center of Big Data for Sustainable Development Goals, Beijing 100094, China
1 shared publication
Latest Publications
- Open Access
- 27 November 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (23) , 5516
Susceptibility Mapping of Unhealthy Trees in Jiuzhaigou Valley Biosphere Reserve
Jiuzhaigou Valley is recognized as both a world natural heritage site and a biosphere reserve. Conducting research on vegetation health within its scope can provide a demonstration role for sustainable development research. In this study, we proposed a technology integration approach that combined remote sensing intelligent identification and quantitative retrieval, and achieved vegetation health monitoring and susceptibility mapping of unhealthy trees. Leveraging WorldView-2 high-resolution satellite images, unhealthy trees were elaborately identified through the object-oriented classification method employing spectral and texture features, with F1 Score exceeding 75%. By applying fuzzy operations on indices related to leaf pigment and canopy architecture, we ultimately generated susceptibility maps of unhealthy trees on Sentinel-2 satellite images, with Area Under the Curve (AUC) exceeding 0.85. Our findings underscore that the vegetation health in Jiuzhaigou Valley is predominantly influenced by human activities and geological hazards. The forests of Jiuzhaigou Valley exhibit a certain degree of resilience to geological disasters, while human activities have been continuously exerting adverse effects on forest health in recent years, necessitating heightened attention. The methodology proposed in this study for mapping unhealthy trees susceptibility presents a cost-effective solution that can be readily applied for vegetation health monitoring and early warning in analogous biosphere reserves.
- 27 November 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (23) , 5516
Open AccessSusceptibility Mapping of Unhealthy Trees in Jiuzhaigou Valley Biosphere Reserve
Jiuzhaigou Valley is recognized as both a world natural heritage site and a biosphere reserve. Conducting research on vegetation health within its scope can provide a demonstration role for sustainable development research. In this study, we proposed a technology integration approach that combined remote sensing intelligent identification and quantitative retrieval, and achieved vegetation health monitoring and susceptibility mapping of unhealthy trees. Leveraging WorldView-2 high-resolution satellite images, unhealthy trees were elaborately identified through the object-oriented classification method employing spectral and texture features, with F1 Score exceeding 75%. By applying fuzzy operations on indices related to leaf pigment and canopy architecture, we ultimately generated susceptibility maps of unhealthy trees on Sentinel-2 satellite images, with Area Under the Curve (AUC) exceeding 0.85. Our findings underscore that the vegetation health in Jiuzhaigou Valley is predominantly influenced by human activities and geological hazards. The forests of Jiuzhaigou Valley exhibit a certain degree of resilience to geological disasters, while human activities have been continuously exerting adverse effects on forest health in recent years, necessitating heightened attention. The methodology proposed in this study for mapping unhealthy trees susceptibility presents a cost-effective solution that can be readily applied for vegetation health monitoring and early warning in analogous biosphere reserves.