A5083369463- Remote Sensing and LiDAR Applications
- Remote Sensing in Agriculture
- 3D Surveying and Cultural Heritage
- Land Use and Ecosystem Services
- Forest ecology and management
- Remote Sensing and Land Use
- Forest Ecology and Biodiversity Studies
- Species Distribution and Climate Change
- Ecology and Vegetation Dynamics Studies
- Wildlife Ecology and Conservation
- Environmental Changes in China
- Conservation, Biodiversity, and Resource Management
- Healthcare Systems and Reforms
- Hydrogen embrittlement and corrosion behaviors in metals
- Pacific and Southeast Asian Studies
- Primate Behavior and Ecology
- Remote-Sensing Image Classification
- Fire effects on ecosystems
- Robotics and Sensor-Based Localization
- Forest, Soil, and Plant Ecology in China
- Fatigue and fracture mechanics
- Power Line Inspection Robots
- High-Voltage Power Transmission Systems
- Animal and Plant Science Education
- Fire Detection and Safety Systems
Hainan University
2023-2025
Peking University
2014-2024
Institute of Botany
2019-2021
Chinese Academy of Sciences
2002-2021
University of Chinese Academy of Sciences
2017-2021
Beijing Botanical Garden
2020
Academy of Opto-Electronics
2016-2019
Czech Academy of Sciences, Institute of Botany
2018
Abstract China’s extensive planted forests play a crucial role in carbon storage, vital for climate change mitigation. However, the complex spatiotemporal dynamics of forest area and its storage remain uncaptured. Here we reveal such changes from 1990 to 2020 using satellite field data. Results show doubling area, trend that intensified post-2000. These lead increasing 675.6 ± 12.5 Tg C 1,873.1 16.2 2020, with an average rate ~ 40 yr −1 . The expansion contributed 53% (637.2 5.4 C) total...
Abstract. A high-resolution, spatially explicit forest age map is essential for quantifying carbon stocks and sequestration potential. Prior attempts to estimate on a national scale in China have been limited by sparse resolution incomplete coverage of ecosystems, attributed complex species composition, extensive areas, insufficient field measurements, inadequate methods. To address these challenges, we developed framework that combines machine learning algorithms (MLAs) remote sensing time...
Accurate and repeated forest inventory data are critical to understand ecosystem processes manage resources. In recent years, unmanned aerial vehicle (UAV)-borne light detection ranging (lidar) systems have demonstrated effectiveness at deriving attributes. However, their high cost has largely prevented them from being used in large-scale applications. Here, we developed a very low-cost UAV lidar system that integrates recently emerged DJI Livox MID40 laser scanner (~$600 USD) evaluated its...
Separating structural components is important but also challenging for plant phenotyping and precision agriculture. Light detection ranging (LiDAR) technology can potentially overcome these difficulties by providing high quality data. However, there are in automatically classifying segmenting of interest. Deep learning extract complex features, it mostly used with images. Here, we propose a voxel-based convolutional neural network (VCNN) maize stem leaf classification segmentation. Maize...
Forest inventory holds an essential role in forest management and research, but the existing field methods are highly time-consuming labor-intensive. Here, we developed a simultaneous localization mapping-based backpack light detection ranging (LiDAR) system with dual orthogonal laser scanners open-source Python package called Forest3D for efficient accurate applications. Two key variables, tree height diameter at breast (DBH), were extracted six study sites different species compositions....
Abstract Background Precision agriculture is an emerging research field that relies on monitoring and managing variability in phenotypic traits. An important trait biomass, a comprehensive indicator can reflect crop yields. However, non-destructive biomass estimation at fine levels unknown challenging due to the lack of accurate high-throughput data algorithms. Results In this study, we evaluated capability terrestrial light detection ranging (lidar) estimating maize plot, individual plant,...
Digital elevation models (DEMs) are crucial geographical data source whereas the resolution of commonly used DEM products is low and cannot meet requirement some detailed geo-related applications. Deep learning-based methods have been demonstrated to be effective in super-resolution (SR) techniques, which reconstruct high-resolution (HR) images from low-resolution (LR) images. However, existing deep learning not fully considered multi-scale spatial heterogeneity topographic knowledge that...
The emerging near-surface light detection and ranging (LiDAR) platforms [e.g., terrestrial, backpack, mobile, unmanned aerial vehicle (UAV)] have shown great potential for forest inventory. However, different LiDAR limitations either in data coverage or capturing undercanopy information. fusion of multiplatform is a solution to this problem. Because the complexity irregularity forests inaccurate positioning information under canopies, current still involves substantial manual efforts. In...
Accurate quantification of grassland structural and functional traits is the foundation for management restoration. Light detection ranging (lidar), especially unmanned aerial vehicle (UAV) lidar, has been recognized as an accurate effective technique local to regional-scale vegetation estimation. However, in ecosystems, it more likely be influenced by UAV lidar information loss caused dense canopies. In this study, we investigated how may occur influence estimation accuracy comparing with...
Over the last decade, a number of techniques for individual tree segmentation have been developed terrestrial laser scanning (TLS) data. The superpoint algorithm based on point cloud has widely used in because its high efficiency and numerous geometric features. However, this is generally specific species forest types, limiting universality performance different types. To handle problem, new method topology branches was proposed. Focusing general topological structure trees, proposed...
Spatiotemporal data fusion is a key technique for generating unified time-series images from various satellite platforms to support the mapping and monitoring of vegetation. However, high similarity in reflectance spectrum different vegetation types brings an enormous challenge similar pixel selection procedure spatiotemporal fusion, which may lead considerable uncertainties fusion. Here, we propose object-based data-fusion framework replace original with object-restricted method address...
Abstract Vegetation community complexity is a critical factor influencing terrestrial ecosystem stability. China, the country leading world in vegetation greening resulting from human activities, has experienced dramatic changes composition during past 30 years. However, how China's varies spatially and temporally remains unclear. Here, we examined spatial pattern of its temporal 1980s to 2015 using two maps China as well more than half million field samples. Spatially, distribution...
Abstract Giant trees are pivotal in forest ecosystems, yet our current understanding of their significance is constrained primarily by the limited knowledge precise locations and structural characteristics. Amidst escalating human‐induced disturbances globally, there an urgent need to devise a practical approach discover measure giant accurately efficiently. Here, we propose novel light detection ranging (lidar)‐based framework designed for discovery measurement trees. Our integrates...