中国科学数据（中英文网络版）2025，Vol.10Issue(2)：278-293,16.DOI:10.11922/11-6035.csd.2024.0097.zh
2023年桂林市2米分辨率城市湿地分类数据集
A dataset of urban wetland classification at 2-meter resolution in Guilin City in 2023
摘要
Abstract
Urban wetlands play a crucial role in sustainable urban development.Effective extraction of information on urban wetland area,type,and distribution is fundamental to understanding the functions and services of urban ecosystems.However,inconsistencies in urban wetland classification systems and the lack of effective fine classification methods for urban wetlands constrain the accurate extraction of urban wetland information.In this study,we developed a dataset of urban wetland classification at 2-meter resolution in Guilin City in 2023,based on GF-1 and GF-6 PMS satellite imagery acquired in 2023,using a two-stage classification approach in combination with object-oriented random forest classification with a knowledge-based hierarchical decision tree algorithm.The dataset includes eight types of wetlands:swamps,marshes,rivers,lakes,inland beaches,reservoirs,aquaculture ponds,and canals/channels.To evaluate the classification accuracy,validation samples were generated through stratified random sampling,and the results were compared with existing datasets.The overall accuracy of the validated classification results is 94.61％.This dataset can provide fundamental data to support the conservation and sustainable development of urban wetlands in Guilin city.关键词
城市湿地/精细分类/桂林市/两阶段分类/GF-1/6Key words
urban wetlands/fine classification/Guilin/two-stage classification/GF-1/6引用本文复制引用
孟子博,沈国状,廖静娟,李杰鹏,陈方..2023年桂林市2米分辨率城市湿地分类数据集[J].中国科学数据（中英文网络版）,2025,10(2):278-293,16.基金项目
国家重点研发计划(2022YFC3800700) National Key R&D Program of China(2022YFC3800700) （2022YFC3800700）
