Automatic Framework of Mapping Impervious Surface Growth With Long-Term Landsat Imagery Based on Temporal Deep Learning Model

被引：13
|
作者：
Yin, Ranyu [1 ,2 ]
He, Guojin [1 ,2 ,3 ,4 ]
Wang, Guizhou [1 ,3 ,4 ]
Long, Tengfei [1 ]
Li, Hongfeng [5 ]
Zhou, Dengji [1 ,2 ]
Gong, Chengjuan [1 ,2 ]
机构：
[1] Chinese Acad Sci, Aerosp Informat Res Inst, Beijing 100094, Peoples R China
[2] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
[3] Key Lab Earth Observat Hainan Prov, Sanya 572029, Hainan, Peoples R China
[4] Chinese Acad Sci, Sanya Inst Aerosp Informat Res Inst, Sanya 572029, Hainan, Peoples R China
[5] Univ Technol Sydney, UTS Fac Engn & Informat Technol, Sydney, NSW 2008, Australia
来源：
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS | 2022年 / 19卷
基金：
中国国家自然科学基金;
关键词：
Earth; Remote sensing; Artificial satellites; Training; Deep learning; Charge coupled devices; Spatial resolution; Change detection; deep learning (DL); impervious surface (IS); Landsat; sample generation;
D O I：
10.1109/LGRS.2021.3135869
中图分类号：
P3 [地球物理学]; P59 [地球化学];
学科分类号：
0708 ; 070902 ;
摘要：
The impervious surface (IS) cover and its dynamics are key parameters in research about urban and ecology. This letter proposed an automatic framework to map the IS growth end-to-end based on the temporal deep learning (DL) model and long time-series Landsat imagery. First, the training and validating datasets were auto-generated by a joint strategy. Then, a DL network was designed, and the IS growth was predicted in temporal windows. Finally, the results from multi-temporal windows are combined to generate the IS growth map. The data around the core of Beijing, China, is tested, and the result shows that the proposed method could: 1) efficiently model the IS growth; 2) map IS growth with less salt-and-pepper noise and false alarm compared to existing products; and 3) be extended to future data easily.
引用
收藏
页数：5
相关论文
共 50 条
  • [21] CicadaNet: Deep learning based automatic cicada chorus filtering for improved long-term bird monitoring
    Zhang, Chengyun
    Jin, Nengting
    Xie, Jie
    Hao, Zezhou
    ECOLOGICAL INDICATORS, 2024, 158
  • [22] An SVM-Based Framework for Long-Term Learning Systems
    Benavides-Prado, Diana
    THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 9915 - 9916
  • [23] Location-based Human Activity Recognition Using Long-term Deep Learning Invariant Mapping
    Iabanzhi, Livii
    Astrakhan, Maria
    Tyshevskyi, Pavlo
    UBICOMP/ISWC '21 ADJUNCT: PROCEEDINGS OF THE 2021 ACM INTERNATIONAL JOINT CONFERENCE ON PERVASIVE AND UBIQUITOUS COMPUTING AND PROCEEDINGS OF THE 2021 ACM INTERNATIONAL SYMPOSIUM ON WEARABLE COMPUTERS, 2021, : 363 - 368
  • [24] A Deep Learning Based Approach for Long-Term Drought Prediction
    Agana, Norbert A.
    Homaifar, Abdollah
    SOUTHEASTCON 2017, 2017,
  • [25] A deep reinforcement learning based long-term recommender system
    Huang, Liwei
    Fu, Mingsheng
    Li, Fan
    Qu, Hong
    Liu, Yangjun
    Chen, Wenyu
    KNOWLEDGE-BASED SYSTEMS, 2021, 213
  • [26] DAFDM: A Discerning Deep Learning Model for Active Fire Detection Based on Landsat-8 Imagery
    Gao, Xu
    Shi, Wenzhong
    Zhang, Min
    Wang, Lukang
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2025, 18 : 7982 - 8000
  • [27] Inland lake indicator bacteria: Long-term impervious surface and weather influences and a predictive Bayesian model
    Uejio, Christopher K.
    Peters, Theodore W.
    Patz, Jonathan A.
    LAKE AND RESERVOIR MANAGEMENT, 2012, 28 (03): : 232 - 244
  • [28] Mapping of Sor Depressions and Solonchaks in the Northern Caspian Region Based on Long-Term Landsat Data
    Shinkarenko, S. S.
    Bartalev, S. A.
    COSMIC RESEARCH, 2024, 62 (SUPPL1) : S115 - S123
  • [29] A deep Learning Scheme for Automatic Seizure Detection from Long-Term Scalp EEG
    Yuvaraj, Rajamanickam
    Thomas, John
    Kluge, Tilmann
    Dauwels, Justin
    2018 CONFERENCE RECORD OF 52ND ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS, AND COMPUTERS, 2018, : 368 - 372
  • [30] Long-term Spatio-temporal Contrastive Learning framework for Skeleton Action Recognition
    Rustogi, Anshul
    Mukherjee, Snehasis
    2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,
12345