A5063543521- Geographic Information Systems Studies
- Topic Modeling
- Semantic Web and Ontologies
- Natural Language Processing Techniques
- Geochemistry and Geologic Mapping
- Geological Modeling and Analysis
- Data Quality and Management
- Advanced Graph Neural Networks
- Biomedical Text Mining and Ontologies
- Web Data Mining and Analysis
- Advanced Text Analysis Techniques
- Simulation and Modeling Applications
- Text and Document Classification Technologies
- Service-Oriented Architecture and Web Services
- Seismology and Earthquake Studies
- Data Management and Algorithms
- Mineral Processing and Grinding
- Advanced Computational Techniques and Applications
- Advanced Measurement and Detection Methods
- 3D Shape Modeling and Analysis
- Remote Sensing and LiDAR Applications
- Image Retrieval and Classification Techniques
- 3D Surveying and Cultural Heritage
- Fire effects on ecosystems
- Recommender Systems and Techniques
China University of Geosciences
2018-2025
China University of Geosciences (Beijing)
2025
Ministry of Education of the People's Republic of China
2025
China Three Gorges University
2017-2025
Ministry of Natural Resources
2023-2024
East China University of Technology
2023
Chinese Academy of Surveying and Mapping
2023
A large amount of continuously increasing textual geoscience data is stored and not fully utilized. Text mining enables the discovery analysis valuable information,and presents insights hidden in geological texts. This research aims to use text visualization techniques obtain content words -for purpose visually analyzing reports. The framework proposed this study can enable researchers quickly understand key information improve transmission efficiency First, we implemented an improved...
Toponym recognition, or the challenge of detecting place names that have a similar referent, is involved in number activities connected to geographical information retrieval and sciences. This research focuses on recognizing Chinese toponyms from social media communications. While broad named entity recognition methods are frequently used locate places, their accuracy hampered by many linguistic abnormalities seen posts, such as informal sentence constructions, name abbreviations,...
Mineral exploration reports and documents are a rich data source that contains large amount of geological environments in which mineral deposits form. Among them, it is difficult to extract the required answers from data. Despite availability search engines digital databases can be used store data, users unable retrieve information needed for specific field timely manner. As result, usually have contend with burden browsing filtering information, time-consuming process. To address this...
The enhancement of remote sensing interpretation accuracy for rock strata in complex terrain areas has long been limited by challenges field validation and the insufficient integration geological knowledge traditional spectral–spatial feature selection methods. This study proposes a framework that integrates textual data, which enhances lithological identification systematically combining multi-source with machine learning algorithms. Using dataset 2591 survey reports scientific literature,...
Multiple tasks within the field of geographical information retrieval and sciences necessitate toponym matching, which involves challenge aligning toponyms that share a common referent. The multiple string similarity approaches struggle when confronted with complexities associated unofficial and/or historical variants identical toponyms. Also, current state-of-the-art approaches/tools to supervised machine learning rely on labeled samples, they do not adequately address intricacies character...
The suddenness of landslide disasters often causes significant loss life and property. Accurate assessment disaster susceptibility is great significance in enhancing the ability accurate prevention. To address problems strong subjectivity selection indicators low efficiency process caused by insufficient application a priori knowledge assessment, this paper, we propose novel framework combing domain graph machine learning algorithms. Firstly, combine unstructured data, extract based on...
Providing sequential recommendations along with easily comprehensible natural language explanations can significantly enhance users’ trust in the recommender systems. However, this approach presents two key challenges: 1) The different objectives of tasks make it challenging to achieve joint optimization and mutual enhancement. 2) simultaneous generation accurate high-quality serious challenges model’s time space efficiency. To address these challenges, we propose a general efficient...
ABSTRACT Geographic knowledge graph (GKG) embedding (referred to as representation learning) enables the mapping of geographic entities and relationships into a continuous vector space, thereby better capturing semantic structural information among in space. The learning GKGs requires generating corresponding negative samples based on positive samples. Negative sampling is an essential component GKG models. However, traditional sample generation algorithms suffer from high error rates poor...