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

doi:10.1080/17538947.2023.2212920

Cited by 5 publications

(2 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, 771 sets of samples have been preprocessed and divided into 650 sets for training, 50 for validation, and 71 for testing. Please refer to Figure 8 in Yu, Ai, Yang, Huang, and Harrie (2023) for the spatial distribution of these samples.…”

Section: Sample Data Constructionmentioning

confidence: 99%

“…Furthermore, the morphology consistency of the river network selection was considered a crucial factor. For this purpose, we utilized a graph autoencoder (GAE) method that integrates drainage network characteristics (DNC), referred to as DNC_GAE (Yu, Ai, Yang, Huang, & Harrie, 2023), to measure the degree of geometric morphological similarity between two river networks. DNC_GAE maps the morphology of a river network into a highdimensional vector and calculates the distance (e.g., cosine similarity) between the two vectors representing the two river networks.…”

Section: Machine Learning Evaluation Indexes and Cartographic Evaluat...mentioning

confidence: 99%

See 1 more Smart Citation

Integrating domain knowledge and graph convolutional neural networks to support river network selection

Yu,

Ai,

Yang

et al. 2023

Transactions in GIS

Self Cite

View full text Add to dashboard Cite

Deep learning is increasingly being used to improve the intelligence of map generalization. Vector‐based map generalization, utilizing deep learning, is an important avenue for research. However, there are three questions: (1) transforming vector data into a deep learning data paradigm; (2) overcoming the limitation of the number of samples; and (3) determining whether existing knowledge can accelerate deep learning. To address these questions, taking river network selection as an example, this study presents a framework integrating hydrological knowledge into graph convolutional neural networks (GCNNs). This framework consists of the following steps: constructing a dual graph of river networks (DG_RN), extracting domain knowledge as node attributes of DG_RN, developing an architecture of GCNNs for the selection, and designing a fine‐tuning rule to refine the GCNN results. Experiments show that our framework outperforms existing machine learning and traditional feature sorting methods using different datasets and achieves good morphological consistency after the selection. Furthermore, these results indicate that DG_RN meets the data paradigm of graph deep learning, and the framework integrating existing characteristics (i.e., Strahler coding, the number of tributaries, the distance between proximity rivers, and upstream drainage area) mitigates the dependence of GCNNs on plenty of samples and enhance its performance.

show abstract

Section: Sample Data Constructionmentioning

confidence: 99%

Section: Machine Learning Evaluation Indexes and Cartographic Evaluat...mentioning

confidence: 99%