A5022022551- Remote Sensing in Agriculture
- Plant Water Relations and Carbon Dynamics
- Land Use and Ecosystem Services
- Forest ecology and management
- Remote Sensing and LiDAR Applications
- Bamboo properties and applications
- Remote Sensing and Land Use
- Conservation, Biodiversity, and Resource Management
- Leaf Properties and Growth Measurement
- Forest Management and Policy
- Ecology and Vegetation Dynamics Studies
- Groundwater flow and contamination studies
- Species Distribution and Climate Change
- Forest, Soil, and Plant Ecology in China
- Soil and Unsaturated Flow
- Remote-Sensing Image Classification
- Hydrology and Watershed Management Studies
- Atmospheric and Environmental Gas Dynamics
- Urban Stormwater Management Solutions
- Fire effects on ecosystems
- African Botany and Ecology Studies
- Soil erosion and sediment transport
- Agroforestry and silvopastoral systems
- Advanced Image Fusion Techniques
- Tree-ring climate responses
Zhejiang A & F University
2016-2025
Qiqihar Medical University
2024
Zhejiang University
2017-2018
Recently, convolutional neural networks (CNNs) showed excellent performance in many tasks, such as computer vision and remote sensing semantic segmentation. Especially, the ability to learn high-representation features of CNN draws much attention. And random forest (RF) algorithm, on other hand, is widely applied for variables selection, classification, regression. Based previous fusion models that fused with models, conditional fields (CRFs), support vector machine (SVM), RF, this article...
The subtropical vegetation plays an important role in maintaining the structure and function of global ecosystems, its contribution to carbon balance are receiving increasing attention. fractional cover (FVC) as indicator for monitoring environment change, is widely used analyze spatiotemporal pattern regional even vegetation. China distribution area Therefore, we first dimidiate pixel model extract FVC during 2001–2018 based on MODIS land surface reflectance data, then linear regression...
Moso bamboo forests, recognized as a distinctive and significant forest resource in subtropical China, contribute substantially to efficient carbon sequestration. The accurate assessment of the aboveground biomass (AGB) forests is crucial for evaluating their impact on balance within ecosystems at regional scale. In this study, we focused located Shanchuan Township, Zhejiang Province, China. primary objective was utilize various data sources, namely UAV-LiDAR (UL), Sentinel-2 (ST),...
Land Use and Cover Change (LUCC) has emerged as a primary driver of terrestrial carbon storage changes. However, the contributions LUCC to Above-Ground Carbon (AGC) in subtropical forests remain unclear due complex diverse trajectory. Quantitative assessment impact different trajectories on is essential for regional cycle mechanisms. Therefore, this study focuses Zhejiang Province, representative forest region China, accurately assess contribution AGC changes from 1984 2019. We first mapped...
Bamboo forest has great potential in climate change mitigation. However, the spatiotemporal pattern of carbon storage global bamboo is still cannot be accurately estimated, because lack an accurate distribution information. In this paper, was mapped with following steps. To begin with, training samples were obtained based on investigation data, statistic and literature data. Then, a decision tree constructed for mapping by integrating Landsat 8 OLI MODIS Finally, area estimated using pixel...
Above-ground biomass (AGB) directly relates to the productivity of forests. Precisely, AGB mapping for regional forests based on very high resolution (VHR) imagery is widely needed evaluation productivity. However, diversity variables and algorithms difficulties inherent in optical make it complex. In this paper, we explored potentials state-of-art algorithm convolutional neural networks (CNNs), which are used its high-level representation, but rarely applied estimation. Four experiments...
Future land use and cover change (LUCC) simulations play an important role in providing fundamental data to reveal the carbon cycle response of forest ecosystems LUCC. Subtropical forests have great potential for sequestration, yet their future dynamics under natural human influences are unclear. Zhejiang Province China is distribution area subtropical forests. For management, it significance explore dynamic changes Zhejiang. As a popular LUCC spatial simulation model, cellular automata (CA)...
As the basic unit of nature, basins concentrate most vegetation cover terrestrial ecosystems and play an important role in forest carbon fixation regulation local climates. However, there are obvious differences between different terms topography, climate, population, economy, other factors, so it is to conduct a comparative study on spatiotemporal patterns factors affecting storage basins. The province Zhejiang rich resources, natural economic within province; GDP higher eastern northern...
Carbon flux is the main basis for judging carbon source/sink of forest ecosystems. Bamboo forests have gained much attention because their high sequestration capacity. In this study, we used a boreal ecosystem productivity simulator (BEPS) model to simulate gross primary (GPP) and net (NPP) bamboo in China during 2001–2018, then explored spatiotemporal evolution fluxes response climatic factors. The results showed that: (1) simulated observed GPP values exhibited good correlation with...
Urbanization inevitably poses a threat to urban ecology by altering its external structure and internal attributes. Nighttime light (NTL) has become increasingly extensive practical, offering special perspective on the world in revealing urbanization. In this study, we applied Normalized Impervious Surface Index (NISI) constructed NTL MODIS NDVI examine urbanization process Yangtze River Delta (YRD). Geographical detectors combined with factors involving human natural influences were...
Monitoring plant phenology is vital to maintaining the global carbon balance and management under climate change. Bamboo forest an essential type in subtropical China with a strong sequestration capacity. In recent years, vegetation indices (VIs), which characterize canopy structural parameters, solar-induced chlorophyll fluorescence (SIF), indicating photosynthetic activity of vegetation, have provided new perspectives on at regional scales. However, best data sources methods for extracting...
Accurate individual tree detection by unmanned aerial vehicles (UAVs) is a critical technique for smart forest management and serves as the foundation evaluating ecological functions. Existing object segmentation methods, on other hand, have reduced accuracy when detecting segmenting trees in complicated urban landscapes, well poor mask quality. This study proposes novel Mask-CSP-attention-coupled network (MCAN) based Mask R-CNN algorithm. MCAN uses Cross Stage Partial Net (CSPNet) framework...
Forest biomass is an essential indicator of forest ecosystem carbon cycle and global climate change research, traditional machine learning cannot explain the mechanism feature variable impact on aboveground (AGB). Therefore, we proposed interpretable bamboo AGB prediction method based Shaply Additive exPlanation (SHAP) XGBoost model to variables AGB. The estimated using monthly annual scale leaf area index (LAI), enhanced vegetation (EVI), ratio (RVI), precipitation (Pre), maximum...
China is one of the countries with most abundant bamboo forest resources in world, and Zhejiang province among top-3 Chinese provinces richest forests. For rational forests management, it great significance to study spatiotemporal dynamic changes Aboveground Carbon (AGC) stocks Zhejiang. In this study, remote sensing variables, such as spectral, vegetation indices texture features Zhejiang, were extracted from 32 Landsat TM OLI images got four different years (2000, 2004, 2008 2014). These...