Deep Learning for Land Cover Change Detection

被引:76
|
作者
Sefrin, Oliver [1 ]
Riese, Felix M. [1 ]
Keller, Sina [1 ]
机构
[1] Karlsruhe Inst Technol, Inst Photogrammetry & Remote Sensing, D-76131 Karlsruhe, Germany
关键词
machine learning; multi-class classification; long short-term memory network (LSTM); fully convolutional neural network (FCN); multitemporal; time series; Sentinel-2; TIME-SERIES; CLASSIFICATION; IMAGERY; ATTENTION; AREA;
D O I
10.3390/rs13010078
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Land cover and its change are crucial for many environmental applications. This study focuses on the land cover classification and change detection with multitemporal and multispectral Sentinel-2 satellite data. To address the challenging land cover change detection task, we rely on two different deep learning architectures and selected pre-processing steps. For example, we define an excluded class and deal with temporal water shoreline changes in the pre-processing. We employ a fully convolutional neural network (FCN), and we combine the FCN with long short-term memory (LSTM) networks. The FCN can only handle monotemporal input data, while the FCN combined with LSTM can use sequential information (multitemporal). Besides, we provided fixed and variable sequences as training sequences for the combined FCN and LSTM approach. The former refers to using six defined satellite images, while the latter consists of image sequences from an extended training pool of ten images. Further, we propose measures for the robustness concerning the selection of Sentinel-2 image data as evaluation metrics. We can distinguish between actual land cover changes and misclassifications of the deep learning approaches with these metrics. According to the provided metrics, both multitemporal LSTM approaches outperform the monotemporal FCN approach, about 3 to 5 percentage points (p.p.). The LSTM approach trained on the variable sequences detects 3 p.p. more land cover changes than the LSTM approach trained on the fixed sequences. Besides, applying our selected pre-processing improves the water classification and avoids reducing the dataset effectively by 17.6%. The presented LSTM approaches can be modified to provide applicability for a variable number of image sequences since we published the code of the deep learning models. The Sentinel-2 data and the ground truth are also freely available.
引用
收藏
页码:1 / 27
页数:27
相关论文
共 50 条
  • [21] DEEP LEARNING NEURAL NETWORKS FOR LAND USE LAND COVER MAPPING
    Storie, Christopher D.
    Henry, Christopher J.
    IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2018, : 3445 - 3448
  • [22] Land Use and Land Cover Classification Meets Deep Learning: A Review
    Zhao, Shengyu
    Tu, Kaiwen
    Ye, Shutong
    Tang, Hao
    Hu, Yaocong
    Xie, Chao
    SENSORS, 2023, 23 (21)
  • [23] Investigation for Land Use and Land Cover Change Detection Using GIS
    Shivpuje, Prakash
    Deshmukh, Nilesh
    Bhalchandra, Parag
    Khamitkar, Santosh
    Lokhande, Sakharam
    Jondhale, Vijay
    Bahuguna, Vijay
    PROCEEDINGS OF THE INTERNATIONAL CONGRESS ON INFORMATION AND COMMUNICATION TECHNOLOGY, ICICT 2015, VOL 2, 2016, 439 : 393 - 399
  • [24] Land use/land cover change detection based on canonical transformation
    Zhang, L
    Liao, MS
    Sheng, H
    IMAGE PROCESSING AND PATTERN RECOGNITION IN REMOTE SENSING, 2003, 4898 : 303 - 311
  • [25] On the detection of land cover change using fraction images
    Haertel, V
    Shimabukuro, YE
    Almeida, R
    IGARSS 2003: IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOLS I - VII, PROCEEDINGS: LEARNING FROM EARTH'S SHAPES AND SIZES, 2003, : 3350 - 3352
  • [26] The experience of land cover change detection by satellite data
    Lev Spivak
    Irina Vitkovskaya
    Madina Batyrbayeva
    Alexey Terekhov
    Frontiers of Earth Science, 2012, 6 : 140 - 146
  • [27] Methodologies and approaches for automated land cover change detection
    Comber, AJ
    Law, ANR
    Lishman, JR
    SPATIAL INFORMATION AND THE ENVIRONMENT, 2001, 8 : 37 - 51
  • [28] The experience of land cover change detection by satellite data
    Spivak, Lev
    Vitkovskaya, Irina
    Batyrbayeva, Madina
    Terekhov, Alexey
    FRONTIERS OF EARTH SCIENCE, 2012, 6 (02) : 140 - 146
  • [29] Change detection for Finnish CORINE land cover classification
    Torma, Markus
    Harma, Pekka
    Hatunen, Suvi
    Teiniranta, Riitta
    Kallio, Minna
    Jarvenpaa, Elise
    EARTH RESOURCES AND ENVIRONMENTAL REMOTE SENSING/GIS APPLICATIONS II, 2011, 8181
  • [30] CHANGE DETECTION OF THE NATIONAL LAND COVER DATASET OF MAXICO
    Colditz, Rene R.
    Llamas, Ricardo M.
    Ressl, Rainer A.
    2012 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2012, : 6181 - 6184