A graph autoencoder network to measure the geometric similarity of drainage networks in scaling transformation
Similarity measurement has been a prevailing research topic in geographic information science. Geometric similarity measurement in scaling transformation (GSM_ST) is critical to ensure spatial data quality while balancing detailed information with distinctive features. However, GSM_ST is an uncertai...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/173624 |
| _version_ | 1811687854136360960 |
|---|---|
| author | Yu, Huafei Ai, Tinghua Yang, Min Huang, Weiming Harrie, Lars |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Yu, Huafei Ai, Tinghua Yang, Min Huang, Weiming Harrie, Lars |
| author_sort | Yu, Huafei |
| collection | NTU |
| description | Similarity measurement has been a prevailing research topic in geographic information science. Geometric similarity measurement in scaling transformation (GSM_ST) is critical to ensure spatial data quality while balancing detailed information with distinctive features. However, GSM_ST is an uncertain problem due to subjective spatial cognition, global and local concerns, and geometric complexity. Traditional rule-based methods considering multiple consistent conditions require subjective adjustments to characteristics and weights, leading to poor robustness in addressing GSM_ST. This study proposes an unsupervised representation learning framework for automated GSM_ST, using a Graph Autoencoder Network (GAE) and drainage networks as an example. The framework involves constructing a drainage graph, designing the GAE architecture for GSM_ST, and using Cosine similarity to measure similarity based on the GAE-derived drainage embeddings in different scales. We perform extensive experiments and compare methods across 71 drainage networks during five scaling transformations. The results show that the proposed GAE method outperforms other methods with a satisfaction ratio of around 88% and has strong robustness. Moreover, our proposed method also can be applied to other scenarios, such as measuring similarity between geographical entities at different times and data from different datasets. |
| first_indexed | 2024-10-01T05:22:55Z |
| format | Journal Article |
| id | ntu-10356/173624 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:22:55Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1736242024-02-23T15:35:51Z A graph autoencoder network to measure the geometric similarity of drainage networks in scaling transformation Yu, Huafei Ai, Tinghua Yang, Min Huang, Weiming Harrie, Lars School of Computer Science and Engineering Computer and Information Science Geometric similarity measurement Drainage network Similarity measurement has been a prevailing research topic in geographic information science. Geometric similarity measurement in scaling transformation (GSM_ST) is critical to ensure spatial data quality while balancing detailed information with distinctive features. However, GSM_ST is an uncertain problem due to subjective spatial cognition, global and local concerns, and geometric complexity. Traditional rule-based methods considering multiple consistent conditions require subjective adjustments to characteristics and weights, leading to poor robustness in addressing GSM_ST. This study proposes an unsupervised representation learning framework for automated GSM_ST, using a Graph Autoencoder Network (GAE) and drainage networks as an example. The framework involves constructing a drainage graph, designing the GAE architecture for GSM_ST, and using Cosine similarity to measure similarity based on the GAE-derived drainage embeddings in different scales. We perform extensive experiments and compare methods across 71 drainage networks during five scaling transformations. The results show that the proposed GAE method outperforms other methods with a satisfaction ratio of around 88% and has strong robustness. Moreover, our proposed method also can be applied to other scenarios, such as measuring similarity between geographical entities at different times and data from different datasets. Published version This work was supported by the National Natural Science Foundation of China [grant number 41531180], the National Natural Science Foundation of China [grant number 42071450], and the China Scholarship Council (CSC) [grant number 202206270076]. Weiming Huang acknowledges the financial support from the Knut and Alice Wallenberg Foundation, and Lars Harrie acknowledges the financial support from Lund University. 2024-02-19T07:17:26Z 2024-02-19T07:17:26Z 2023 Journal Article Yu, H., Ai, T., Yang, M., Huang, W. & Harrie, L. (2023). A graph autoencoder network to measure the geometric similarity of drainage networks in scaling transformation. International Journal of Digital Earth, 16(1), 1828-1852. https://dx.doi.org/10.1080/17538947.2023.2212920 1753-8947 https://hdl.handle.net/10356/173624 10.1080/17538947.2023.2212920 2-s2.0-85159758425 1 16 1828 1852 en International Journal of Digital Earth © 2023 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. The terms on which this article has been published allow the posting of the Accepted Manuscript in a repository by the author(s) or with their consent. application/pdf |
| spellingShingle | Computer and Information Science Geometric similarity measurement Drainage network Yu, Huafei Ai, Tinghua Yang, Min Huang, Weiming Harrie, Lars A graph autoencoder network to measure the geometric similarity of drainage networks in scaling transformation |
| title | A graph autoencoder network to measure the geometric similarity of drainage networks in scaling transformation |
| title_full | A graph autoencoder network to measure the geometric similarity of drainage networks in scaling transformation |
| title_fullStr | A graph autoencoder network to measure the geometric similarity of drainage networks in scaling transformation |
| title_full_unstemmed | A graph autoencoder network to measure the geometric similarity of drainage networks in scaling transformation |
| title_short | A graph autoencoder network to measure the geometric similarity of drainage networks in scaling transformation |
| title_sort | graph autoencoder network to measure the geometric similarity of drainage networks in scaling transformation |
| topic | Computer and Information Science Geometric similarity measurement Drainage network |
| url | https://hdl.handle.net/10356/173624 |
| work_keys_str_mv | AT yuhuafei agraphautoencodernetworktomeasurethegeometricsimilarityofdrainagenetworksinscalingtransformation AT aitinghua agraphautoencodernetworktomeasurethegeometricsimilarityofdrainagenetworksinscalingtransformation AT yangmin agraphautoencodernetworktomeasurethegeometricsimilarityofdrainagenetworksinscalingtransformation AT huangweiming agraphautoencodernetworktomeasurethegeometricsimilarityofdrainagenetworksinscalingtransformation AT harrielars agraphautoencodernetworktomeasurethegeometricsimilarityofdrainagenetworksinscalingtransformation AT yuhuafei graphautoencodernetworktomeasurethegeometricsimilarityofdrainagenetworksinscalingtransformation AT aitinghua graphautoencodernetworktomeasurethegeometricsimilarityofdrainagenetworksinscalingtransformation AT yangmin graphautoencodernetworktomeasurethegeometricsimilarityofdrainagenetworksinscalingtransformation AT huangweiming graphautoencodernetworktomeasurethegeometricsimilarityofdrainagenetworksinscalingtransformation AT harrielars graphautoencodernetworktomeasurethegeometricsimilarityofdrainagenetworksinscalingtransformation |