A recognition method for drainage patterns using a graph convolutional network

Yu, Huafei; Ai, Tinghua; Yang, Min; Huang, Lina; Yuan, Jiaming

doi:10.1016/j.jag.2022.102696

Cited by 27 publications

(10 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first is to define the convolution operation in the spectral domain using a Fourier transform. These models require a consistent number of graph nodes (Kipf & Weiling, 2017; Yu et al, 2022). Therefore, fake nodes whose features are meaningless should be added to the graph data when the graph size fails to satisfy the specified requirements.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Identification of drainage patterns using a graph convolutional neural network

Liu

Zhai

Qian

et al. 2023

Transactions in GIS

View full text Add to dashboard Cite

Various geological factors shape drainage patterns. Identifying drainage patterns is a classic problem in topographical knowledge mining and map generalization. Existing rule‐based methods rely heavily on the parameter settings of cartographers for drainage‐pattern recognition. These methods effectively identify drainage patterns in specific areas but require manual parameter tuning to identify drainage patterns in other areas. Owing to the complexity of topological and geometric characteristics, drainage pattern recognition involves nonlinear problems, and it is difficult to build mapping relationships between characteristics and patterns using rule‐based methods. Therefore, we proposed a data‐driven method based on a graph convolutional neural network to avoid heavy reliance on human experience and automatically mine implicit relationships between characteristics and drainage patterns. First, six typical drainage patterns (dendritic, rectangular, parallel, trellis, reticulate, and fanned) were listed based on map specifications, and the unique characteristics of each drainage pattern were illustrated. Subsequently, the drainage graphs were constructed. The characteristics of the whole, local, and individual units in the drainage networks were quantified based on drainage vector data. Finally, an identification model was developed using graph convolution, self‐attention pooling, and multiple fully connected layers for drainage pattern recognition. After training and testing, the accuracy of our model (0.801 ± 0.014) was better than that of the rule‐based method (0.572 ± 0.000) and the traditional machine learning methods (less than 0.733 ± 0.016). The results demonstrate that the ability of our model to identify drainage patterns surpasses that of other methods.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Wang et al (2020) divided roads into segments of equal length using linear tessellation and identified a grid pattern. Yu et al (2022) used spectral GCNNs to identify drainage patterns and achieved a good performance.…”

Section: Related Workmentioning

confidence: 99%

Identification of drainage patterns using a graph convolutional neural network

Liu

Zhai

Qian

et al. 2023

Transactions in GIS

View full text Add to dashboard Cite

show abstract

“…The first step is to reconstruct vector data (e.g., points, polylines, or polygons) commonly used in map generalization to align with the deep learning data paradigm. Current reconstruction methods for specific problems include using a triangulation network structure for point cloud data classification and semantic segmentation (Bazazian & Nahata, 2020; Jiang et al, 2021), a coordinate sequence structure for line simplification (Yu & Chen, 2022), and a dual graph of drainage and a minimum binary tree (Yu, Ai, Yang, Huang, & Gao, 2023; Yu et al, 2022) of building for pattern recognition (Yan et al, 2019). However, map generalization involves multiple operators, such as selection, simplification, and aggregation, and different objects like bends or nodes of rivers, roads, and boundary lines for simplification; arcs or strokes of river and road networks for selection; and polygons of buildings and lakes for aggregation.…”

Section: Introductionmentioning

confidence: 99%

“…However, a decision‐making method with intelligent reasoning is not yet developed into a universally applicable model. This is attributed to the complexity of expressing river network features, including topological, geometric, and semantic features, making choosing one or several general parameters challenging (Sen & Gokgoz, 2015; Stanislawski, 2009; Yu et al, 2022). Moreover, the influence of neighboring first‐ and second‐order tributaries on target rivers has been inadequately considered despite their significant impact on selection, which leads to the maintenance of river network morphology remaining a concern during selection.…”

Section: Introductionmentioning

confidence: 99%

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

“…Wang et al (2020) studied the orthogonal grid distribution pattern of street networks based on the graph convolutional neural network model 10 . Yu Y (2022) and Yu H (2022) had applied the graph convolutional neural network method to the related recognition research of various vector ground objects [11][12] .…”

Section: Introductionmentioning

confidence: 99%