Deep Learning Applications on Multitemporal SAR (Sentinel-1) Image Classification Using Confined Labeled Data: The Case of Detecting Rice Paddy in South Korea

Hyun Woo Jo, Sujong Lee, Eunbeen Park, Chul Hee Lim, Cholho Song, Halim Lee, Youngjin Ko, Sungeun Cha, Hoonjoo Yoon, Woo Kyun Lee

Research output: Contribution to journalArticlepeer-review

24 Citations (Scopus)


The applicability of deep learning to remote sensing is rapidly increasing in accordance with the improvement in spatiotemporal resolution of satellite images. However, unlike satellite images acquired in near-real-time over wide areas, there are limited amount of labeled data used for model training. In this article, three kinds of deep learning applications - data augmentation, semisupervised classification, and domain-adapted architecture - were tested in an effort to overcome the limitation of insufficient labeled data. Among the diverse tasks that can be used for classification, rice paddy detection in South Korea was performed for its ability to fully utilize the advantages of deep learning and high spatiotemporal image resolution. In the process of designing each application, the domain knowledge of remote sensing and rice phenology was integrated. Then, all possible combinations of the three applications were examined and evaluated with pixel-based comparisons in various environments and city-level comparisons using national statistics. The results of this article indicated that all combinations of the applications can contribute to increase classification performance, even though the uncertainty involved in imitating or utilizing unlabeled data remains. As the effectiveness of the proposed applications was experimentally confirmed, enhancement in the applicability of deep learning was expected in various remote sensing areas. In particular, the proposed applications would be significant when they are applied to a wide range of study areas and high-resolution images, as they tend to require a large amount of learning data from diverse environments, owing to high intra-class heterogeneity.

Original languageEnglish
Article number9063568
Pages (from-to)7589-7601
Number of pages13
JournalIEEE Transactions on Geoscience and Remote Sensing
Issue number11
Publication statusPublished - 2020 Nov

Bibliographical note

Funding Information:
Manuscript received August 7, 2019; revised February 12, 2020; accepted March 9, 2020. Date of publication April 10, 2020; date of current version October 27, 2020. This work was supported in part by the International Research and Development Program of the National Research Foundation of Korea (NRF) through the Ministry of Science, ICT, and Future Planning under Grant 2018K1A3A7A03089842, in part by Korea University Grant, and in part by the European Commission under Contract H2020-776019 EOPEN. (Corresponding author: Woo-Kyun Lee.) Hyun-Woo Jo, Sujong Lee, Eunbeen Park, Halim Lee, Youngjin Ko, Sungeun Cha, and Woo-Kyun Lee are with the Department of Environmental Science and Ecological Engineering, Korea University, Seoul 02841, South Korea (e-mail:

Publisher Copyright:
© 1980-2012 IEEE.


  • Data augmentation
  • data labeling
  • deep learning
  • domain adaptation
  • remote sensing
  • semisupervised classification

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • General Earth and Planetary Sciences


Dive into the research topics of 'Deep Learning Applications on Multitemporal SAR (Sentinel-1) Image Classification Using Confined Labeled Data: The Case of Detecting Rice Paddy in South Korea'. Together they form a unique fingerprint.

Cite this