A5030654256- Remote Sensing in Agriculture
- Remote Sensing and LiDAR Applications
- Plant Water Relations and Carbon Dynamics
- Land Use and Ecosystem Services
- Species Distribution and Climate Change
- Remote Sensing and Land Use
- Urban Heat Island Mitigation
- Remote-Sensing Image Classification
- Advanced Image Fusion Techniques
- Leaf Properties and Growth Measurement
- Climate change impacts on agriculture
- Climate variability and models
- Automated Road and Building Extraction
- Soil Moisture and Remote Sensing
- Hydrology and Watershed Management Studies
- Soil Geostatistics and Mapping
- Wildlife Ecology and Conservation
- Climate change and permafrost
- Atmospheric and Environmental Gas Dynamics
- Ecology and Vegetation Dynamics Studies
- Water resources management and optimization
- Avian ecology and behavior
- Environmental Changes in China
- Soil and Unsaturated Flow
- Plant responses to elevated CO2
Sun Yat-sen University
2016-2025
Ho Chi Minh City University of Science
2024
Vietnam National University Ho Chi Minh City
2024
Research Center for Ecology and Environment of Central Asia
2019-2023
Chinese Academy of Sciences
2019-2023
Xinjiang Institute of Ecology and Geography
2019-2023
University of Toronto
2023
University of Chinese Academy of Sciences
2020-2023
Key Laboratory of Guangdong Province
2017-2019
Tsinghua University
2013-2016
Abstract Modeling land surface processes requires complete and reliable soil property information to understand hydraulic heat dynamics related processes, but currently, there is no data set of thermal parameters that can meet this demand for global use. In study, we propose a fitting approach obtain the optimal water retention from ensemble pedotransfer functions (PTFs), which are evaluated using coverage National Cooperative Soil Survey Characterization Database show better performance...
Detecting changes using bitemporal remote sensing imagery is vital to understand the dynamics of land surface. Existing change detection models based on deep learning suffer from problem scale variation and pseudochange due their insufficient multilevel aggregation inadequate capability feature representation, which limits accuracy. This study proposes a densely attentive refinement network (DARNet) improve very-high-resolution images. DARNet U-shape encoder–decoder architecture with...
Since the launch of first land-observation satellite (Landsat-1) in 1972, land-cover mapping has accumulated a wide range knowledge peer-reviewed literature. However, this never been comprehensively analysed for new discoveries. Here, we developed spatialized database scientific literature English about mapping. Using database, tried to identify spatial temporal patterns and hotspots research around world. Among other findings, observed (1) significant mismatch between hotspot areas that are...
We report on a global cropland extent product at 30-m spatial resolution developed with two land cover maps (i.e. FROM-GLC, Finer Resolution Observation and Monitoring, Global Land Cover; FROM-GLC-agg) 250-m probability map. A common validation sample database was used to determine optimal thresholds of in different parts the world generate cropland/noncropland mask according classification accuracies for samples. decision tree then applied combine masks: one existing from literature other...
As the Earth’s population continues to grow and demand for food increases, need improved timely information related properties dynamics of global agricultural systems is becoming increasingly important. Global land cover maps derived from satellite data provide indispensable regarding geographic distribution areal extent croplands. However, use information, such as cropping intensity (defined here number cycles per year), not routinely available over large areas because mapping this remote...
Abstract Extensive studies have focused on instantaneous and time‐lag impacts of climatic factors vegetation growth; however, the chronical accumulative indirect antecedent carrying over for a period time growth, defined as cumulative effects, are less investigated. Here we aimed to disentangle effects growth by using indexes accumulated meteorological data. First, investigated explanation fit climate changes variations applying stepwise multiple linear regression with Akaike information...
Abstract. Land surface phenological cycles of vegetation greening and browning are influenced by variability in climatic forcing. Quantitative spatial information on their is important for agricultural applications, wildfire fuel accumulation, land management, modeling, climate change studies. Most phenology studies have focused temperature-driven Northern Hemisphere systems, where shows annually recurring patterns. However, precipitation-driven non-annual arid semi-arid systems (i.e.,...
Vegetation phenology is a sensitive indicator that reflects the vegetation–atmosphere interactions and vegetation processes under global atmospheric changes. Fast-developing remote sensing technologies monitor land surface at high spatial temporal resolutions have been widely used in retrieval analysis large scale. While researchers developed many retrieving methods based on data, relationships differences among are unclear, there lack of evaluation comparison with field recoding data. In...
Long-term time series of spatially explicit cropland maps are essential for global crop modelling and climate change studies. The spatial resolution temporal continuity have been improving several data sets released recently. Here, we calculated country-level areas from the annual land-cover (LC) produced by European Space Agency Climate Change Initiative (ESA-CCI) project Food Agricultural Organization United Nations statistical (FAOSTAT) 1992 to 2014. Because these two used different...
Identifying and extracting building boundaries from remote sensing data has been one of the hot topics in photogrammetry for decades. The active contour model (ACM) is a robust segmentation method that widely used boundary extraction, but which often results biased extraction due to tree background mixtures. Although classification methods can improve this efficiently by separating buildings other objects, there are ineluctable salt pepper artifacts. In paper, we combine convolutional neural...
The monitoring of tree species diversity is important for forest or wetland ecosystem service maintenance resource management. Remote sensing an efficient alternative to traditional field work map over large areas. Previous studies have used light detection and ranging (LiDAR) imaging spectroscopy (hyperspectral multispectral remote sensing) richness prediction. recent development very high spatial resolution (VHR) RGB images has enabled detailed characterization canopies structures. In this...
Building change detection from very high-spatial-resolution (VHR) remote sensing images has gained increasing popularity in a variety of applications, such as urban planning and damage assessment. Detecting fine-grained "from–to" changes (change transition one land cover type to another) buildings the VHR is still challenging multitemporal representation complicated. Recently, fully convolutional neural networks (FCNs) have been proven be capable feature extraction semantic segmentation...
Abstract The cropping intensity has received growing concern in the agriculture field applications such as harvest area research. Notwithstanding significant amount of existing literature on local intensities, research considering global datasets appears to be limited spatial resolution and precision. In this paper, we present an annual dynamic dataset covering period from 2001 2019 at a 250-m with average overall accuracy 89%, exceeding current data 500-m resolution. We used enhanced...
Abstract Vegetation plays a key role in regulating the material and energy exchanges among biosphere, atmosphere, pedosphere. Modeling predicting vegetation variables such as leaf area index (LAI) gross primary productivity (GPP) are crucial to understand project processes of growth response climate change. While number studies developed models simulate GPP using satellite‐derived LAI, requirement satellite‐based model inputs largely limits power these models. This study machine learning...
High-throughput maize phenotyping at both organ and plant levels plays a key role in molecular breeding for increasing crop yields. Although the rapid development of light detection ranging (LiDAR) provides new way to characterize three-dimensional (3D) structure, there is need develop robust algorithms extracting 3D phenotypic traits from LiDAR data assist gene identification selection. Accurate field environments remains challenging, owing difficulties segmentation organs individual plants...