Automatic segmentation of parallel drainage patterns supported by a graph convolution neural network

Yu, Huafei; Ai, Tinghua; Yang, Min; Huang, Lina; Gao, Aji

doi:10.1016/j.eswa.2022.118639

Cited by 12 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To determine the optimal set of features and prevent information redundancy, we conducted a sensitivity analysis experiment of river network knowledge using GraphSAGE (see Hamilton et al (2017) and Yu, Ai, Yang, Huang, and Gao (2023) for details). An experiment testing each feature individually is to remove features that provide insufficient information.…”

Section: Experiments and Discussionmentioning

confidence: 99%

“…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%

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: Experiments and Discussionmentioning

confidence: 99%

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

show abstract

“…As an inductive representation learning for node embedding, the GraphSAGE algorithm is especially advantageous and useful for large graphs with rich node attribute information [25][26][27]. The main idea of GraphSAGE is to adhere to GNN and aggregate the neighbours' information by embedding them into each node.…”

Section: B Link Predictionmentioning

confidence: 99%

Constructing Industrial Knowledge Graph Through Ontology and Link Prediction

Wan,

Chen,

Liu

et al. 2023

2023 IEEE 19th International Conference on Automation Science and Engineering (CASE)

View full text Add to dashboard Cite

Given that the numerous data embedded in manufacturing processes and products are separated, it is challenging to tackle and integrate heterogeneous data in industrial scenarios. In this context, an industrial knowledge graph (iKG) has been developed as a promising semantic organisation to leverage the rich information from multiple resources. However, relations are usually missing and hidden in original iKGs, which results in the necessity for iKG completion. Given these two perspectives, a framework of iKG construction is proposed based on ontology and link prediction in this study. Firstly, an ontology design framework is deployed to generate domain-centric ontologies after extracting numerous data (e.g., entities and relations). Secondly, the missing relations between each couple of entities are discovered over existing knowledge to increase the number of edges that complete and refine iKGs. Thirdly, iKG visualisation is conducted by importing data into the generated ontology. The feasibility and effectiveness of the proposed framework are substantiated and demonstrated in a case study using real-world data.

show abstract

Transformations in hydrological resilience: Unraveling the impact of landscape hydric potential on flood dynamics: A case study, Drwinka catchment (Poland)

Młyński,

Wojkowski,

Wałęga

et al. 2025

Journal of Environmental Management

View full text Add to dashboard Cite

Automatic segmentation of parallel drainage patterns supported by a graph convolution neural network

Cited by 12 publications

References 29 publications

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

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

Constructing Industrial Knowledge Graph Through Ontology and Link Prediction

Transformations in hydrological resilience: Unraveling the impact of landscape hydric potential on flood dynamics: A case study, Drwinka catchment (Poland)

Contact Info

Product

Resources

About