Skip to main navigation Skip to search Skip to main content

基于预训练模型的矢量海岸线形态模式判别方法

Translated title of the contribution: A pre-trained model-based method for discriminating morphological patterns of vector-based coastlines
  • Min Yang
  • , Hongran Ma
  • , Bo Kong*
  • , Pengcheng Liu
  • , Tinghua Ai
  • *Corresponding author for this work
  • Key Laboratory for Geographical Process Analysis
  • College of Urban and Environmental Sciences

Research output: Contribution to journal › Article › peer-review

Abstract

Discriminating the morphological patterns of vector-based coastlines is vital for monitoring coastal evolution,marine disaster forecasting,and coastal zone planning,and it also serves as an important step in coastline cartography.Discriminating methods based on traditional machine learning technique rely on manually defined features and require large amounts of labeled samples with long-term training.To overcome these drawbacks,this study proposes a pre-trained model-based method that decouples generic geometric feature learning of coastlines from downstream morphological pattern discrimination.First,the coastlines are represented as Token sequences suitable for embedding learning using the operations of coordinate system resetting and coordinate normalization.Then,a self-supervised coordinate prediction task based on random masking is designed and integrated into the BERT model to construct a pre-trained model for the embedding learning of coastline geometric features.Finally,the pre-trained BERT model is fine-tuned with labeled dataset and transferred to the morphological pattern discrimination task.Based on open-source coastline data,a pre-trained dataset containing 195649 samples and a labeled dataset with 1000 samples were collected.The proposed method achieves an F1 score of 90.72% in a discrimination task involving five types of coastline morphological patterns,outperforming methods based on LSTM and 1D-CNN by 7.31%~9.38%. © 2026, SinoMaps Press. All rights reserved.
Translated title of the contributionA pre-trained model-based method for discriminating morphological patterns of vector-based coastlines
Original languageChinese
Pages (from-to)404-414
Number of pages11
JournalCehui Xuebao/Acta Geodaetica et Cartographica Sinica
Volume55
Issue number3
DOIs
StatePublished - 16 Apr 2026

Funding

National Natural Science Foundation of China, Number: -, Acronym: NNSFC, National Natural Science Foundation of China (NNSFC) [42471486,42571519];

Indexed by

  • Scopus
  • EI

Fingerprint

Dive into the research topics of 'A pre-trained model-based method for discriminating morphological patterns of vector-based coastlines'. Together they form a unique fingerprint.

Cite this