A5102895369- Hydrology and Watershed Management Studies
- Flood Risk Assessment and Management
- Remote Sensing and LiDAR Applications
- Remote-Sensing Image Classification
- Cryospheric studies and observations
- Climate change and permafrost
- Groundwater and Watershed Analysis
- Hydrology and Sediment Transport Processes
- Advanced Neural Network Applications
- Soil Moisture and Remote Sensing
- Meteorological Phenomena and Simulations
- Advanced Image Fusion Techniques
- Precipitation Measurement and Analysis
- Machine Learning and Data Classification
- Landslides and related hazards
- Automated Road and Building Extraction
- Climate variability and models
- Remote Sensing in Agriculture
- Hydrocarbon exploration and reservoir analysis
Peking University
2018-2024
Chinese Academy of Sciences
2021
Institute of Computing Technology
2021
Man-made reservoirs are key components of terrestrial hydrological systems. Identifying the location and number is premise for studying impact human activities on water resources environmental changes. While complete bottom-up censuses can provide a comprehensive view reservoir landscape, they time-consuming laborious thus infeasible global scale. Moreover, it challenging to distinguish man-made from natural lakes in remote sensing images. This study proposes convolutional neural network...
High-resolution land cover mapping over large areas is a challenging task due to the lack of high-quality labels. A potential solution leverage existing knowledge contained in freely available lower-resolution products. However, relatively low resolution and accuracy products lead numerous inaccurate labels, which harms performance neural network. This article addresses challenge by jointly optimizing network parameters correcting noisy labels with novel online noise correction approach...
The availability of lake bathymetry maps is imperative for estimating water volumes and their variability, which a sensitive indicator climate. It difficult, if not impossible, to obtain bathymetric measurements from all the thousands lakes across globe due costly labor and/or harsh topographic regions. In this study, we develop new digital model (DLBM) using step-wise recession method (WRM) generate 3-dimensional based on elevation (DEM) alone, with two assumptions: (1) typically, lake’s...
Accurate precipitation data is crucial in many applications such as hydrology, meteorology, and ecology. Compared with ground observations, satellite-based estimates can provide much more spatial information to characterize precipitation. In this study, the products of Integrated Multi-satellitE Retrievals for Global Precipitation Measurement (IMERG) Tropical Rainfall Mission (TRMM) Multisatellite Analysis (TMPA) were firstly evaluated over Tibetan Plateau (TP) 2015 against observations at...
Global inland surface water bodies such as lakes and reservoirs, important components of the hydrosphere ecosphere, are increasingly affected by climate change. Generating bathymetric volume-area-height (BVAH) curves for global can enhance our understanding their topography impacts. However, accurately quantifying topographic patterns these remains challenging due to difficulties in collecting comprehensive data. Therefore, we collected processed over 2000 maps from 50 different data sources...
Channel network topology plays an important role in hydrological analysis. This letter proposes innovative method to construct it based only on remote sensing images. The uses spectral water indexes and mask of large lakes ocean areas derived from data generate the map channels. Then, a morphological thinning algorithm is introduced extract initial skeleton Moreover, iterative pruning process graph proposed simplify skeleton. Finally, according simplified its adjacency matrix, new...
Dams constructed by humans are important facilities for irrigation, flood control, and power generation. Recognizing the location number of dams is crucial studying impact human activities on ecosystem change. Although many countries organizations have established their own dam datasets, it only tip iceberg real construction. Therefore, effectively accurately obtaining geographic still a significant problem to be solved. This article proposes an improved convolutional neural network (CNN)...
Presents corrections to above named paper.
In the published article [1], authors realized some errors in affiliation and email address of Yang Hong, thus wish to make following revisions: Add Affiliation 5 “School Civil Engineering Environmental Science, University Oklahoma, Norman, OK 73019, USA” for Hong Change yanghong@ou [...]