Model Generalization of the Hydrography Network in the CARGEN Project

Savino, Sandro; Rumor, Massimo; Fabio, Canton; Giovanni, Luigi De; Marco, Reineri

doi:10.1007/978-3-642-19143-5_25

Cited by 5 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stanislawski (2008) proposed a knowledge-base-driven river network selection method based on the combination of the upstream drainage area and reach code. Specifically, the rule of the knowledge base is to select the rivers with an upstream watershed area or length (Savino et al, 2011) higher than the threshold, followed by selecting the remaining rivers based on the topological integrity to meet the drainage density requirement. Song et al (2009) utilized segmentation based on thresholds established for river features, such as length, coding grade, tributary distance, and density.…”

Section: Rule-based or Knowledge-based Reasoning Methodmentioning

confidence: 99%

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

Yu,

Ai,

Yang

et al. 2023

Transactions in GIS

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: Rule-based or Knowledge-based Reasoning Methodmentioning

confidence: 99%