干旱区研究2025，Vol.42Issue(6)：1032-1042,11.DOI:10.13866/j.azr.2025.06.07
基于多特征融合的面向对象冰川边界提取
Object-based glacier boundary extraction utilizing multi-feature fusion
摘要
Abstract
Pixel-based classification struggles with the accurate identification of glacier changes in areas with similar spectral characteristics,particularly in debris-covered areas where spectral features closely resemble the surrounding mountains and rocks,thereby resulting in low extraction accuracy.This study investigates the Yin-sugaiti and Yalong Glaciers using Google Earth Engine to integrate spectral indices,microwave texture features,and topographic data.An object-based(OB)machine learning algorithm is applied for automated glacier extrac-tion and compared to pixel-based(PB)classification methods.The results show the following.(1)The OB classi-fication approach,integrating multi-feature fusion,significantly improved the glacier extraction accuracy.The OB_RF classifier achieved an overall accuracy of 98.1%,a Kappa coefficient of 0.97,and an F1-score of 98.67%,outperforming the OB_CART and OB_GTB classifiers.When compared to PB_RF,the overall accuracy,Kappa coefficient,and F1-score increased by 1.7%,0.024,and 5.57%,respectively.(2)Between 2001-2022,the Yinsugaiti and Yalong Glaciers retreated at average annual rates of 0.08%and 0.13%,respectively.(3)Supragla-cial debris was primarily distributed below 5000 and 4800 m on the Yinsugaiti and Yalong Glacier,respectively.Over the same period,debris-covered areas on both glaciers expanded upward.关键词
冰川边界提取/面向对象/基于像素/机器学习/多特征融合Key words
glacier boundary extraction/object-based/pixel-based/machine learning/multi-feature fusion引用本文复制引用
林洲艳,王霞迎,夏元平..基于多特征融合的面向对象冰川边界提取[J].干旱区研究,2025,42(6):1032-1042,11.基金项目
国家自然科学基金项目(42174055,42374040) （42174055,42374040）
东华理工大学博士启动基金(DHBK2019187) （DHBK2019187）
