VELSD1.0:面向深度学习的长白山火山喷发地貌遥感数据集
作者:
基金项目:

本文为上海市自然科学基金项目(编号22ZR1423200)、吉林长白山火山国家野外科学观测研究站课题(编号NORSCBS23- 02)和国家重点研发计划项目(编号2021YFC3101604)联合资助的成果


VELSD1.0: A volcanic eruption landform dataset based on remote sensing image for Changbaishan Mountain with deep learning
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    作为保存最完整的多成因复合活火山之一,长白山火山喷发地貌场景中的地表覆盖类型广泛发育且遥感解译标签清晰。目前,遥感数据集是利用深度学习进行大区域火山喷发地貌场景遥感分类的数据基础。本文以哨兵2(Sentinel- 2)遥感图像为数据源,结合地质资料和野外调查建立了一个面向深度学习分类的长白山火山喷发地貌遥感数据集(VELSD1. 0)。该数据集中地表覆盖类型包含高植被覆盖、中植被覆盖、低植被覆盖、裸露土壤、玄武岩、粗面岩、混合岩、水体、阴影、人工景观,组成元素包括遥感图像、标签数据、解译标签及说明文件;覆盖范围约2500 km2,共计40000个样本;单张样本图像尺寸为25像元×25像元,空间分辨率为10 m。利用经典的卷积神经网络(GoogLeNet、ResNet)和Transformer (Vision Transformer、Swin Transformer)模型对构建VELSD1. 0数据集进行了验证和分析。结果表明,本数据集对深度学习模型具有良好的适用性和可迁移性,总体分类准确度、Kappa系数和多类平均精度分别达到82. 93%、75. 64%和84. 22%。可为其他火山喷发地貌深度学习分类提供借鉴,提升火山地貌遥感调查的信息化和智能化。

    Abstract:

    Changbaishan Mountain, one of the most well- preserved polygenetic composite active volcanoes, boasts a diverse range of surface cover types, making it an ideal location for studying volcanic eruption landforms. The clear interpretation labels in remote sensing imagery make this region a valuable resource for large- scale volcanic landform classification using deep learning methods. This paper introduces the volcanic eruption landform scene dataset (VELSD1. 0), derived from Sentinel- 2 remote sensing imagery of Changbaishan Mountain, China. The dataset was developed in conjunction with geological data and field investigations. In the dataset, VELSD1. 0 comprises ten surface cover types: high vegetation coverage, middle vegetation coverage, low vegetation coverage, exposed soil, basaltic rocks, trachytic rocks, mixed rocks of trachyte and pumice, water, shadow, and artificial landscape. The dataset includes three constituent elements: remote sensing images, labeled data, and an interpreted label and explanatory file. Covering an area of 2500 km2, the dataset contains approximately 40,000 sample images of volcanic eruption landform. Each sample image measures 25 pixels×25 pixels with the spatial resolution of 10 m. To validate and analyze VELSD1. 0, we employed both classical convolutional neural networks (e. g. , GoogLeNet, ResNet) and transformer- based architectures (e. g. , Vision Transformer, Swin Transformer). Experimental results demonstrate the dataset' s strong applicability and transferability for deep learning models, achieving an overall classification accuracy (OA) of 82. 93%, a Kappa coefficient (KC) of 75. 64%, and a mean average precision (mAP) of 84. 22%. VELSD1. 0 effectively supports deep learning classification of other volcanic eruption landforms from remote sensing imagery, contributing to the informatization and intellectualization of remote sensing surveys for volcanic landforms.

    参考文献
    相似文献
    引证文献
引用本文

李成范,韩晶鑫,武成智,刘岚,颜丽丽,刘学锋,赵俊娟.2025. VELSD1.0:面向深度学习的长白山火山喷发地貌遥感数据集[J].地质学报,99(2):616-630.
LI Chengfan, HAN Jingxin, WU Chengzhi, LIU Lan, YAN Lili, LIU Xuefeng, ZHAO Junjuan.2025. VELSD1.0: A volcanic eruption landform dataset based on remote sensing image for Changbaishan Mountain with deep learning[J]. Acta Geologica Sinica,99(2):616-630.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2024-02-18
  • 最后修改日期:2024-04-07
  • 录用日期:2024-04-08
  • 在线发布日期: 2025-02-19