ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Self-attention for raw optical Satellite Time Series Classification

Russwurm, Marc*; Koerner, Marco
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING2020-11DOI: 10.1016/j.isprsjprs.2020.06.006
181被引12阅读
引用收藏
分享

摘要

The amount of available Earth observation data has increased dramatically in recent years. Efficiently making use of the entire body of information is a current challenge in remote sensing; it demands lightweight problemagnostic models that do not require region- or problem-specific expert knowledge. End-to-end trained deep learning models can make use of raw sensory data by learning feature extraction and classification in one step, solely from data. Still, many methods proposed in remote sensing research require implicit feature extraction through data preprocessing or explicit design of features. In this work, we compare recent deep learning models on crop type classification on raw and preprocessed Sentinel 2 data. We concentrate on the common neural network architectures for time series, i.e., 1D-convolutions, recurrence, and the novel self-attention architecture. Our central findings are that data preprocessing still increased the overall classification performance for all models while the choice of model was less crucial. Self-attention and recurrent neural networks, by their architecture, outperformed convolutional neural networks on raw satellite time series. We explore this by a feature importance analysis based on gradient backpropagation that exploits the differentiable nature of deep learning models. Further, we qualitatively show how self-attention scores focus selectively on a few classification-relevant observations.

学科与关键词

关键词
Self-attentionTransformerTime series classificationMultitemporal Earth observationCrop type mappingVegetation monitoringDeep learning
相关
加载中…
  • SITS-Former: A pre-trained spatio-spectral-temporal representation model for Sentinel-2 time series classification
    Yuan, Yuan; Lin, Lei; Liu, Qingshan*; Hang, Renlong; Zhou, Zeng-GuangInternational Journal of Applied Earth Observation and Geoinformation, 2022, 106: 102651.被引 50
  • Effect of Attention Mechanism in Deep Learning-Based Remote Sensing Image Processing: A Systematic Literature Review
    Ghaffarian, Saman*; Valente, Joao; van der Voort, Mariska; Tekinerdogan, BedirRemote Sensing, 2021, 13(15): 2965.被引 93
  • Vision Transformers for Remote Sensing Image Classification
    Bazi, Yakoub*; Bashmal, Laila; Rahhal, Mohamad M. Al; Dayil, Reham Al; Ajlan, Naif AlRemote Sensing, 2021, 13(3): 516.被引 307
查看全部 →

发表信息

论文状态
公开发表
期刊
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
发表日期
2020-11
卷期
第 169 卷
页码
421-435
DOI
10.1016/j.isprsjprs.2020.06.006
语言
MULTI-LANGUAGE
期刊收录
NSL.SCIE
期刊等级
1区
成果收录
SCIE
资助标注
German Federal Ministry for Economic Affairs and Energy (BMWi) [50EE1908]

作者

  • R

    Russwurm, Marc (通讯) (第一作者)

  • K

    Koerner, Marco

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417