An Al-based Spatial Knowledge Graph for Enhancing Spatial Data and Knowledge Search and Discovery

Geospatial data has been widely used in Geographic Information Systems to understand spatial relationships in various application domains such as disaster response, agriculture risk management, environmental planning, and water resource protection. Many data sharing platforms such as NASA Open Data Portal and USGS Geo Data portal have been developed to enhance spatial data sharing services. However, enabling intelligent and efficient spatial data sharing and communication across different domains and stakeholders (e.g., data producers, researchers, and domain experts) is a formidable task. The challenges appear in building meaningful semantics between data products using spatiotemporal similarity measures to efficiently help users find all the relevant data and information at the space-time scale. In this paper, we developed a novel AI-based graph embedding algorithm to build semantic relationships between different spatial data sets to enable efficient and accurate data search. We applied the graph embedding algorithm to 30,000 NASA metadata records to test our algorithm's performance. In the end, we visualized the knowledge graph using the Neo4j database graphical user interface.

[1]  Marti A. Hearst,et al.  A Simple Algorithm for Identifying Abbreviation Definitions in Biomedical Text , 2002, Pacific Symposium on Biocomputing.

[2]  Mihai Dascalu,et al.  RoBERT – A Romanian BERT Model , 2020, COLING.

[3]  R. Sakia.  The Box-Cox transformation technique: a review , 1992 .

[4]  James P. Callan,et al.  Explicit Semantic Ranking for Academic Search via Knowledge Graph Embedding , 2017, WWW.

[5]  ANDREA ROSSI,et al.  Knowledge Graph Embedding for Link Prediction: A Comparative Analysis , 2021, ACM Trans. Knowl. Discov. Data.

[6]  Xing Xie,et al.  A Survey on Knowledge Graph-Based Recommender Systems , 2020, IEEE Transactions on Knowledge and Data Engineering.

[7]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[8]  Yu Liu,et al.  Understanding Place Characteristics in Geographic Contexts through Graph Convolutional Neural Networks , 2020, Smart Spaces and Places.

[9]  Tianlong Chen,et al.  When Does Self-Supervision Help Graph Convolutional Networks? , 2020, ICML.

[10]  Konstantinos I. Diamantaras,et al.  Design and implementation of an open source Greek POS Tagger and Entity Recognizer using spaCy , 2019, 2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI).

[11]  Zhiyuan Liu,et al.  FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation , 2018, EMNLP.

[12]  Joan Bruna,et al.  Few-Shot Learning with Graph Neural Networks , 2017, ICLR.

[13]  Yinghui Wu,et al.  Mining Summaries for Knowledge Graph Search , 2018, IEEE Transactions on Knowledge and Data Engineering.

[14]  Ryutaro Ichise,et al.  An Automatic Knowledge Graph Creation Framework from Natural Language Text , 2018, IEICE Trans. Inf. Syst..

[15]  Chi Zhang,et al.  The transborder flux of phosphorus in the Lancang-Mekong River Basin: Magnitude, patterns and impacts from the cascade hydropower dams in China , 2020 .

[16]  Shaowen Wang,et al.  A cyberGIS-enabled multi-criteria spatial decision support system: A case study on flood emergency management , 2018, Int. J. Digit. Earth.

[17]  Jianfeng Gao,et al.  Embedding Entities and Relations for Learning and Inference in Knowledge Bases , 2014, ICLR.

[18]  Hao Hu,et al.  Understanding the non-stationary relationships between corn yields and meteorology via a spatiotemporally varying coefficient model , 2021 .

[19]  C. Robusto.  The Cosine-Haversine Formula , 1957 .