Unsupervised land-use change detection using multi-temporal POI embedding

Abstract Rapid land-use change detection (LUCD) is pivotal for refined urban planning and management. In this paper, we investigate LUCD through learning embeddings of points of interest (POIs) from multiple temporalities. There are several prominent challenges: (1) the co-occurrence problem of multi-temporal POIs, (2) the heterogeneity of POI categorization, and (3) The lack of human-crafted labels. Therefore, multi-temporal POIs need to be aligned in the embedding space for effective LUCD. This study proposes a multi-temporal POI embedding (MT-POI2Vec) technique for LUCD in a fully unsupervised manner. In MT-POI2Vec, we first utilize random walks in POI networks to capture their single-period co-occurrence patterns; then, we leverage manifold learning to capture (1) single-period categorical semantics of POIs to enforce semantically similar POI embedding to be close and (2) cross-period categorical semantics to align multi-temporal POI embedding in a unified embedding space. We conducted experiments in Shenzhen, China, which demonstrates that the proposed method is effective. Compared with several baseline models, MT-POI2Vec can better align multi-temporal POIs and thus achieve higher performance in LUCD. In addition, our model can effectively identify areas with unchanged land use and land use changes in residential and industrial areas at a fine scale.

• Publication year

  2023

• Venue

  International Journal of Geographical Information Science

• Publication date

  2023-09-26

• Fields of study

  Geography, Computer Science, Environmental Science

• Identifiers
  DOI 10.1080/13658816.2023.2257262
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Learning urban region representations with POIs and hierarchical graph infomax

  2023cited by this paper
• Geographic mapping with unsupervised multi-modal representation learning from VHR images and POIs

  2023cited by this paper
• Land-Use/Land-Cover change detection based on a Siamese global learning framework for high spatial resolution remote sensing imagery

  2022cited by this paper
• Estimating urban functional distributions with semantics preserved POI embedding

  2022influential reference
• Urban function classification at road segment level using taxi trajectory data: A graph convolutional neural network approach

  2021cited by this paper
• A novel hybrid approach using SVM and spectral indices for enhanced land use land cover mapping of coastal urban plains

  2021cited by this paper
• Identifying core driving factors of urban land use change from global land cover products and POI data using the random forest method

  2021cited by this paper
• A comparison of the integrated fuzzy object-based deep learning approach and three machine learning techniques for land use/cover change monitoring and environmental impacts assessment

  2021cited by this paper
• Assessing land use and land cover change detection using remote sensing in the Lake Tana Basin, Northwest Ethiopia

  2020cited by this paper
• Land Use/Land Cover Changes of Ago-Owu Forest Reserve, Osun State, Nigeria Using Remote Sensing Techniques

  2020cited by this paper
• Qualitative and quantitative analysis of topographically derived CVA algorithms using MODIS and Landsat-8 data over Western Himalayas, India

  2020cited by this paper
• Delineating Mixed Urban "Jobs-Housing" Patterns at a Fine Scale by Using High Spatial Resolution Remote-Sensing Imagery

  2020cited by this paper
• The Traj2Vec model to quantify residents’ spatial trajectories and estimate the proportions of urban land-use types

  2020cited by this paper
• Deep learning-based remote and social sensing data fusion for urban region function recognition

  2020cited by this paper
• Functional urban land use recognition integrating multi-source geospatial data and cross-correlations

  2019cited by this paper
• Land use/land cover change and surface urban heat island intensity: source–sink landscape-based study in Delhi, India

  2019cited by this paper
• Spatial Modeling in GIS and R for Earth and Environmental Sciences

  2019cited by this paper
• Beyond Word2vec: An approach for urban functional region extraction and identification by combining Place2vec and POIs

  2019cited by this paper
• Change detection techniques for remote sensing applications: a survey

  2019cited by this paper
• A graph convolutional neural network for classification of building patterns using spatial vector data

  2019cited by this paper
• Land Use/Land Cover Change Detection and Urban Sprawl Analysis

  2019cited by this paper
• Automated LULC map production using deep neural networks

  2019cited by this paper
• A deep learning framework for land-use/land-cover mapping and analysis using multispectral satellite imagery

  2019cited by this paper
• Land-use/cover change in Coimbatore urban area (Tamil Nadu, India)—a remote sensing and GIS-based study

  2018cited by this paper
• Integrating landscape metrics and socioeconomic features for urban functional region classification

  2018cited by this paper
• From ITDL to Place2Vec: Reasoning About Place Type Similarity and Relatedness by Learning Embeddings From Augmented Spatial Contexts

  2017cited by this paper
• Analyzing spatiotemporal land use/cover dynamic using remote sensing imagery and GIS techniques case: Kan basin of Iran

  2017cited by this paper
• Land use classification and change detection by using multi-temporal remotely sensed imagery: The case of Chunati wildlife sanctuary, Bangladesh

  2017cited by this paper
• Sensing spatial distribution of urban land use by integrating points-of-interest and Google Word2Vec model

  2017influential reference
• A new approach for land cover classification and change analysis: Integrating backdating and an object-based method

  2016cited by this paper
• Geospatial analysis of shoreline and land use/land cover changes through remote sensing and GIS techniques

  2016cited by this paper
• Change Detection Techniques in Remote Sensing

  2016cited by this paper
• Mining point-of-interest data from social networks for urban land use classification and disaggregation

  2015cited by this paper
• Remote Sensing based multi-temporal land cover classification and change detection in northwestern Ethiopia

  2015cited by this paper
• Semantically Smooth Knowledge Graph Embedding

  2015cited by this paper
• NDVI-based land-cover change detection using harmonic analysis

  2015cited by this paper
• Label Distribution Learning

  2013cited by this paper
• A comprehensive change detection method for updating the National Land Cover Database to circa 2011

  2013cited by this paper
• A new insight into land use classification based on aggregated mobile phone data

  2013cited by this paper
• Efficient Estimation of Word Representations in Vector Space

  2013cited by this paper
• Change Detection Using Change Vector Analysis from Landsat TM Images in Wuhan

  2011cited by this paper
• Evaluation of plan implementation in the transitional China: A case of Guangzhou city master plan

  2011cited by this paper
• Land-Use and Land-Cover Change Detection

  2011cited by this paper
• Visualizing Data using t-SNE

  2008cited by this paper
• Comprehensive Survey on Distance/Similarity Measures between Probability Density Functions

  2007cited by this paper
• Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering

  2001cited by this paper

• Fine-grained urban land use simulation: Integrating spatial dynamic modeling with a pre-trained vision-language model

  2026cites this paper
• VecCity: A Taxonomy-guided Library for Map Entity Representation Learning [Experiment, Analysis & Benchmark]

  2025cites this paper
• Research on the Performance Evaluation of Urban Innovation Spaces: A Case Study in Harbin

  2025cites this paper
• A multimodal data fusion framework for urban functional zone mapping based on local-global information enhancement and adaptive spatial units: from standard datasets to global city validation

  2025cites this paper
• Bi-temporal change detection for topographic map updates using panoptic segmentation of VNIR orthophotos and LiDAR data

  2025cites this paper
• A Workflow of Deep Models With Concept Learning and Domain‐Specific Attention for Change Detection in Vector Building Footprints

  2025cites this paper
• Multi-spatial urban function modeling: A multi-modal deep network approach for transfer and multi-task learning

  2025cites this paper
• Spatially explicit knowledge in geo-embeddings: Interpreting location representation derived from human movement trajectories

  2025cites this paper
• SPOK: tokenizing geographic space for enhanced spatial reasoning in GeoAI

  2025cites this paper
• Urban Representation Learning for Fine-grained Economic Mapping: A Semi-supervised Graph-based Approach

  2025cites this paper
• Learning dual context aware POI representations for geographic mapping

  2025cites this paper
• Measuring urban physical environments using image deep features

  2025cites this paper
• Representation learning for geospatial data

  2025cites this paper
• Quantifying Stylistic Evolution in Classical Chinese Literature Using Word Embeddings and Trajectory Analysis

  2025cites this paper
• Graph reasoning-based spatial representation learning from geo-entities for multi-modal urban functional zone sensing

  2025cites this paper
• An urban change detection method based on multimodal data and knowledge graph technology

  2025cites this paper
• Disentangling the hourly dynamics of mixed urban function: A multimodal fusion perspective using dynamic graphs

  2024cites this paper
• Self-supervised representation learning for geospatial objects: A survey

  2024cites this paper
• A multimodal data fusion model for accurate and interpretable urban land use mapping with uncertainty analysis

  2024cites this paper