Drainage pattern recognition supported by graph Transformer
Drainage patterns recognition is essential for analyzing terrain and geomorphology,exploring geological minerals,and transforming river network data across various scales.However,traditional spatial statistical methods based on morpho-logical and geometric features are not robust enough.To overcome this deficiency,graph convolutional methods have emerged as a popular solution.Nevertheless,these methods often focus narrowly on local features,disregarding the crucial global per-spective necessary for comprehensive analysis.To address this issue,our study proposes a drainage pattern recognition method supported by graph Transformer.This method incorporates geometric knowledge by constructing river network graph struc-tures using dual graphs.It integrates a GraphSAGE-based local learning module and a Transformer-based global learning mod-ule,training the graph Transformer model.Experimental results demonstrate that our method achieves 94％accuracy in accu-rately recognizing drainage patterns by combining local segment composite features and global river network morphology fea-tures.This outperforms the 1st-ChebNet and GraphSAGE methods,presenting a promising approach for intelligent drainage pattern recognition.
万方数据
维普
