Short Release Note for Zenodo Reference
Title: Transfer Learning with Convolutional Neural Networks for Hydrological Streamline Detection
Authors: Nattapon Jaroenchai, Shaowen Wang, Lawrence V. Stanislawski, Ethan Shavers, E. Lynn Usery, Shaohua Wang, Sophie Wang, Li Chen
Institutions: University of Illinois at Urbana-Champaign, U.S. Geological Survey, Central South University
Abstract:
This study explores the use of transfer learning in convolutional neural networks to enhance hydrological streamline detection accuracy. By fine-tuning pre-trained U-Net models with varying ResNet backbones, the research demonstrates improved performance in geographic transferability, with significant findings in the application of DenseNet169 and ResNet50 models.
Keywords:
Transfer Learning, Convolutional Neural Network, Hydrological Streamline Detection, Remote Sensing
Zenodo DOI:
Repository Link:
https://github.com/cybergis/transfer_learning_notebooks
Data and Resources:
The repository includes comprehensive datasets, Jupyter notebooks, and instructions for replicating and extending the study's findings.