Symbolic and subsymbolic<scp>GeoAI</scp>: Geospatial knowledge graphs and spatially explicit machine learning

Mai, Gengchen; Hu, Yingjie; Gao, Song; Cai, Ling; Martins, Bruno; Scholz, Johannes; Gao, Jing; Janowicz, Krzysztof

doi:10.1111/tgis.13012

Cited by 26 publications

(8 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, the symbolic Geo‐SPARQL query language is developed to support efficient implementation of subsequent geoscience models in a relatively straightforward way, including meteorological simulation (Wang, Zhang, et al., 2022), forest fire risk prediction (Ge et al., 2022), and visual supervision of large‐scope heat source factories (Lai et al., 2023). The second mode involves sub‐symbolic distributed reasoning of Geo‐KGs (Mai, Hu, et al., 2022), drawing inspiration from SOTA KGE and GNN models. Therein, the representative works are the location‐aware KGE model for geographic Q&A and spatial semantic lifting (Mai et al., 2020), advancing KG completion with temporal scopes (Cai et al., 2021), and KGE‐enabled socioeconomic indicator prediction in location‐based social network (Zhou et al., 2023).…”

Section: Related Workmentioning

confidence: 99%

Knowledge‐driven spatial competitive intelligence for tourism

Gao,

Peng,

et al. 2024

Transactions in GIS

View full text Add to dashboard Cite

Competition among tourism enterprises is an ineluctable component of sustainable tourism growth, requiring comprehensive studies to understand its dynamic and develop appropriate strategies. The literature employs text mining or statistical analyses to identify correlations between tourism areas as competitive relationships. However, this approach may not be fully applicable, due to the sparsity of crucial coexistence phenomena, and may fail to investigate fine‐grained attractions' competition inside destination using large‐scale geospatial data. To overcome the limitations, this study proposes a knowledge‐driven competitive intelligence framework for tourism management, utilizing knowledge graph (KG) construction and inference technologies. First, multi‐mode heterogeneous tourism data are integrated into a unified KG, including tourist check‐in, online text, and basic geographic information. Second, the spatial‐dependent GNN‐based model absorbing abundant spatial semantic knowledge from tourism‐oriented KG can enhance the performance of competition reasoning. Third, with multiple analyses via symbolic queries on KG, a comprehensive panorama of competition situations can be revealed.

show abstract

Section: Related Workmentioning

confidence: 99%

Knowledge‐driven spatial competitive intelligence for tourism

Gao,

Peng,

et al. 2024

Transactions in GIS

View full text Add to dashboard Cite

show abstract

“…As an important type of KG, geospatial knowledge graphs (GeoKGs) are essentially a symbolic representation of geospatial knowledge. It has become an indispensable component of Symbolic GeoAI (Mai, Hu, et al, 2022) and supports various intelligent geospatial applications such as qualitative spatial reasoning (Cai et al, 2022; Freksa, 1991; Zhu, Janowicz, Cai, et al, 2022), geographic entity recognition and resolution (Alex et al, 2015; Gritta et al, 2018), geographic KG summarization (Yan et al, 2019), geographic question answering (Mai et al, 2020, 2021; Scheider et al, 2021), and so on. Nowadays, there are multiple large‐scale, open‐sourced GeoKGs available to use including GeoNames (Ahlers, 2013), LinkedGeoData (Auer et al, 2009), YAGO2 (Hoffart et al, 2013), GNIS‐LD (Regalia et al, 2018), and KnowWhereGraph (Janowicz, 2021; Janowicz et al, 2022).…”

Section: Related Workmentioning

confidence: 99%

EVKG: An interlinked and interoperable electric vehicle knowledge graph for smart transportation system

Mai

Zhu

et al. 2023

Transactions in GIS

Self Cite

View full text Add to dashboard Cite

Over the past decade, the electric vehicle (EV) industry has experienced unprecedented growth and diversification, resulting in a complex ecosystem. To effectively manage this multifaceted field, we present an EV‐centric knowledge graph (EVKG) as a comprehensive, cross‐domain, extensible, and open geospatial knowledge management system. The EVKG encapsulates essential EV‐related knowledge, including EV adoption, EV supply equipment, and electricity transmission network, to support decision‐making related to EV technology development, infrastructure planning, and policy‐making by providing timely and accurate information and analysis. To enrich and contextualize the EVKG, we integrate the developed EV‐relevant ontology modules from existing well‐known knowledge graphs and ontologies. This integration enables interoperability with other knowledge graphs in the Linked Data Open Cloud, enhancing the EVKG's value as a knowledge hub for EV decision‐making. Using six competency questions, we demonstrate how the EVKG can be used to answer various types of EV‐related questions, providing critical insights into the EV ecosystem. Our EVKG provides an efficient and effective approach for managing the complex and diverse EV industry. By consolidating critical EV‐related knowledge into a single, easily accessible resource, the EVKG supports decision‐makers in making informed choices about EV technology development, infrastructure planning, and policy‐making. As a flexible and extensible platform, the EVKG is capable of accommodating a wide range of data sources, enabling it to evolve alongside the rapidly changing EV landscape.

show abstract

“…In this work, empowered by Geospatial Artificial Intelligence (GeoAI) such as spatially explicit machine learning and deep learning approaches (Janowicz et al, 2020;Mai et al, 2022a), we present the CATS, a deep-learning-based Conditional Adversarial Trajectory Synthesis framework for privacy-preserving trajectory generation and publication. By leveraging deep learning approaches such as conditional adversarial neural network training, CATS is able to generate high-quality individual-level synthetic trajectory data from k-anonymized and aggregated human mobility matrices, which can serve as supplements and alternatives to raw data for privacy-preserving data publication.…”

Section: Introductionmentioning

confidence: 99%

CATS: Conditional Adversarial Trajectory Synthesis for privacy-preserving trajectory data publication using deep learning approaches

Rao,

Gao,

Zhu

2023

International Journal of Geographical Information Science

Self Cite

View full text Add to dashboard Cite

The prevalence of ubiquitous location-aware devices and mobile Internet enables us to collect massive individual-level trajectory dataset from users. Such trajectory big data bring new opportunities to human mobility research but also raise public concerns with regard to location privacy. In this work, we present the Conditional Adversarial Trajectory Synthesis (CATS), a deep-learning-based GeoAI methodological framework for privacy-preserving trajectory data generation and publication. CATS applies K-anonymity to the underlying spatiotemporal distributions of human movements, which provides a distributional-level strong privacy guarantee. By leveraging conditional adversarial training on K-anonymized human mobility matrices, trajectory global context learning using the attention-based mechanism, and recurrent bipartite graph matching of adjacent trajectory points, CATS is able to reconstruct trajectory topology from conditionally sampled locations and generate high-quality individual-level synthetic trajectory data, which can serve as supplements or alternatives to raw data for privacy-preserving trajectory data publication. The experiment results on over 90k GPS trajectories show that our method has a better performance in privacy preservation, spatiotemporal characteristic preservation, and downstream utility compared with baseline methods, which brings new insights into privacy-preserving human mobility research using generative AI techniques and explores data ethics issues in GIScience.

show abstract

Symbolic and subsymbolicGeoAI: Geospatial knowledge graphs and spatially explicit machine learning

Cited by 26 publications

References 68 publications

Knowledge‐driven spatial competitive intelligence for tourism

Knowledge‐driven spatial competitive intelligence for tourism

EVKG: An interlinked and interoperable electric vehicle knowledge graph for smart transportation system

CATS: Conditional Adversarial Trajectory Synthesis for privacy-preserving trajectory data publication using deep learning approaches

Contact Info

Product

Resources

About