Understanding Place Characteristics in Geographic Contexts through Graph Convolutional Neural Networks
Datos Bibliográficos
| ID | 3775835 |
|---|---|
| Autores | Di Zhu (0000-0002-3237-6032, Peking University), Fan Zhang (0000-0002-3643-018X, Peking University), Shengyin Wang (Peking University), Yaoli Wang (0000-0002-6815-7616, Peking University), Ximeng Cheng (0000-0001-9923-7240, Peking University), Zhou Huang (0000-0002-1255-1913, Peking University), Yu Liu (0000-0002-0016-2902, Peking University) |
| Año | 2020 |
| Volumen | 110 |
| Número | 2 |
| Páginas | 408-420 |
| Fecha de publicación | 2020-03-03 |
| Peer Reviewed | Sí |
| Open Access | No |
| Tipo | ARTICLE |
| Revista | Annals of the American Association of Geographers (JOURNAL) |
| Identificadores de la revista | ISSN: 2469-4452 • E-ISSN: 2469-4460 |
| Editorial | Informa UK Limited (PUBLISHER • GB) |
| DOI | 10.1080/24694452.2019.1694403 |
| OpenAlex | W3001859009 |
| Idioma | EN |
| Citas recibidas | 34 |
| Referencias citadas | 31 |
Inferring the unknown properties of a place relies on both its observed attributes and the characteristics of the places to which it is connected. Because place characteristics are unstructured and the metrics for place connections can be diverse, it is challenging to incorporate them in a spatial prediction task where the results could be affected by how the neighborhoods are delineated and where the true relevance among places is hard to identify. To bridge the gap, we introduce graph convolutional neural networks (GCNNs) to model places as a graph, where each place is formalized as a node, place characteristics are encoded as node features, and place connections are represented as the edges. GCNNs capture the knowledge of the relevant geographic context by optimizing the weights among graph neural network layers. A case study was designed in the Beijing metropolitan area to predict the unobserved place characteristics based on the observed properties and specific place connections. A series of comparative experiments was conducted to highlight the influence of different place connection measures on the prediction accuracy and to evaluate the predictability across different characteristic dimensions. This research enlightens the promising future of GCNNs in formalizing places for geographic knowledge representation and reasoning
Convolutional neural network · Data science · Geography · Graph · Machine learning · Metropolitan area · Predictability · Computer Science · Geographic Information Systems Studies · Human Mobility and Location-Based Analysis · Mathematics · Urban Transport and Accessibility · Artificial Intelligence · Theoretical Computer Science
Semantic-Enhanced Graph Convolutional Neural Networks for Multi-Scale Urban Functional-Feature Identification Based on Human Mobility
Analysis and Optimization of the Spatial Patterns of Commercial Service Facilities Based on Multisource Spatiotemporal Data and Graph Neural Networks
Predicting User Activity Intensity Using Geographic Interactions Based on Social Media Check-In Data
Application of Graph Convolutional Neural Networks and multi-sources data on urban functional zones identification, A case study of Changchun, China
Detecting home countries of social media users with machine-learned ranking approach
Explainable Geospatial Machine Learning Models
Neural embeddings of urban big data reveal spatial structures in cities
Understanding the movement predictability of international travelers using a nationwide mobile phone dataset collected in South Korea
Physics-informed graph learning for spatially contiguous and capacity-constrained hospital service area delineation
Jointly spatial-temporal representation learning for individual trajectories
Urban function classification at road segment level using taxi trajectory data
Desirable streets
A framework for urban land use classification by integrating the spatial context of points of interest and graph convolutional neural network method
Uncovering inconspicuous places using social media check-ins and street view images
A self-supervised detection method for mixed urban functions based on trajectory temporal image
How does spatial structure affect psychological restoration? A method based on graph neural networks and street view imagery
Can Moran Eigenvectors Improve Machine Learning of Spatial Data? Insights From Synthetic Data Validation
Predicting vibrancy of metro station areas considering spatial relationships through graph convolutional neural networks
Explainable spatially explicit geospatial artificial intelligence in urban analytics
Sensing lakeplace
Unveiling multifaceted resilience
Towards Human-centric Digital Twins
Multiple representations in geospatial databases, the brain’s spatial cells, and deep learning algorithms
Putting Geographical Information Science in Place – Towards Theories of Platial Information and Platial Information Systems
Quantitative geography III
Human settlement value assessment from a place perspective
Beyond Distance Decay
Modeling shared e-micromobility as a label propagation process for detecting overlapping communities
GeoAI-enhanced community detection on spatial networks with graph deep learning
Modeling Region Affiliation with Fuzzy Membership Based on Spatial and Social Interactions
RegionGCN
Urban Visual Intelligence
Spatiotemporal Interpolation Using Graph Neural Network
Tobler's First Law in GeoAI
Measuring human perceptions of a large-scale urban region using machine learning
Mobile Communications, Social Networks, and Urban Travel
Geographically weighted regression with a non-Euclidean distance metric
Places
The geography of Twitter topics in London
Deep learning
Power of Place
The Power of Place (RLE Social & Cultural Geography)
Inferring trip purposes and uncovering travel patterns from taxi trajectory data
Thirty years of spatial econometrics
A graph theory interpretation of nodal regions
Sense of place
The Uncertain Geographic Context Problem
Social Sensing
Modeling Interregional Interaction
The Nature of Geographic Knowledge
Collapsing Space and Time
Multiscale Geographically Weighted Regression (MGWR)
| Obras citantes distintas | 34 |
|---|---|
| Citas por año | 5,67 |
| Intervalo de citas | 2020 - 2026 (7) |
| Velocidad de citación | current |
| Altamente citado | No |
| Tipos de cita | Neutras: 29 |