A5034161454- Topic Modeling
- Land Use and Ecosystem Services
- Geological Modeling and Analysis
- Rock Mechanics and Modeling
- Semantic Web and Ontologies
- Dam Engineering and Safety
- Natural Language Processing Techniques
- Hydrological Forecasting Using AI
- Geochemistry and Geologic Mapping
- Urban Transport and Accessibility
- Scientific Computing and Data Management
- Soil and Land Suitability Analysis
- Water Quality Monitoring and Analysis
- Methane Hydrates and Related Phenomena
- Web Data Mining and Analysis
- Speech Recognition and Synthesis
- Air Quality Monitoring and Forecasting
- Landslides and related hazards
- Geophysics and Gravity Measurements
- Remote Sensing and Land Use
- Genomics and Phylogenetic Studies
- Advanced Computational Techniques and Applications
- Remote Sensing in Agriculture
Tsinghua University
2019-2025
University of Manchester
2025
Abstract. Accurate, detailed, and up-to-date information on cropland extent is crucial for provisioning food security environmental sustainability. However, because of the complexity agricultural landscapes lack sufficient training samples, it remains challenging to monitor dynamics at high spatial temporal resolutions across large geographical extents, especially regions where land use changing dramatically. Here we developed a cost-effective annual mapping framework that integrated...
Landslide dams, formed by natural disasters or human activities, pose significant challenges for lifespan prediction, which is crucial effective water conservancy management and disaster prevention. This study proposes a hybrid CNN–Transformer model optimized using the Improved Black-Winged Kite Algorithm (IBKA) aimed at improving accuracy of landslide dam prediction combining local feature extraction with global dependency modeling. The integrates CNN’s Transformer’s modeling capabilities,...
Geoscience research has generated vast amounts of data, creating a need for effective extraction and integration knowledge to address global-change challenges, promote sustainable development, accelerate scientific discovery. Foundation language models, trained through extensive pre-training instruction tuning on large text corpora, can facilitate this process. However, when foundational models lack sufficient geoscience expertise, with relevant data generate content that is inconsistent...
Nitrous oxide produced during wastewater treatment is a major greenhouse gas, and accurate prediction control of N2O emissions are crucial for achieving carbon neutrality. In this study, aiming to address the complex issues emission in treatment, large-scale multidimensional data from Altenrhein plant was used build sample database. The role symmetry model architecture analysis discussed, six intelligent models were proposed based on deep learning technology. results showed that...
Earth observations, especially satellite data, have produced a wealth of methods and results in meeting global challenges, often presented unstructured texts such as papers or reports. Accurate extraction instrument entities from these can help to link reuse observation resources. The direct use an existing dictionary extract suffers the problem poor matching, which leads low recall. In this study, we present named entity recognition model automatically texts. Due lack manually labeled apply...
Thousands of satellites and instruments are providing very unique long-term, refined, diverse perception capabilities for the states changes Earth's surface environment. When leveraging Earth Observation (EO) techniques in SDG monitoring specific regions, an important prerequisite is to evaluate whether EO could meet user requirements terms spatial coverage, temporal frequency observing variables or objects. It highly expected have a quantitative model that can not only represent observation...
<p>    The concept of Healthy Cities, introduced by the World Health Organization, demonstrates value health for whole urban system. As one most important components systems, transportation plays an role in Cities. Many evaluation systems focus on factors such as road networks, parking spaces, speed, accessibility, convenience, and commuting time, while vulnerability resilience are rarely evaluated. This study presents preliminary progress traffic...