HUSCAP logo Hokkaido Univ. logo

Hokkaido University Collection of Scholarly and Academic Papers >
農学院・農学研究院  >
雑誌発表論文等  >

Assessing the Suitability of Data from Sentinel-1A and 2A for Crop Classification

Manuscript_TGRS-2017-0042.docx.pdf1.51 MBPDF見る/開く

タイトル: Assessing the Suitability of Data from Sentinel-1A and 2A for Crop Classification
著者: Sonobe, Rei 著作を一覧する
Yamaya, Yuki 著作を一覧する
Tani, Hiroshi 著作を一覧する
Wang, Xiufeng 著作を一覧する
Kobayashi, Nobuyuki 著作を一覧する
Mochizuki, Kan-ichiro 著作を一覧する
キーワード: Agricultural fields
machine learning
発行日: 2017年 7月10日
出版者: Taylor & Francis
誌名: GIScience & Remote Sensing
巻: 54
号: 6
開始ページ: 918
終了ページ: 938
出版社 DOI: 10.1080/15481603.2017.1351149
抄録: Sentinel-1A C-SAR and Sentinel-2A MultiSpectral Instrument (MSI) provide data applicable to the remote identification of crop type. In this study, six crop types (beans, beetroot, grass, maize, potato, and winter wheat) were identified using five C-SAR images and one MSI image acquired during the 2016 growing season. To assess the potential for accurate crop classification with existing supervised learning models, the four different approaches of kernel-based extreme learning machine (KELM), multilayer feedforward neural networks, random forests, and support vector machine were compared. Algorithm hyperparameters were tuned using Bayesian optimization. Overall, KELM yielded the highest performance, achieving an overall classification accuracy of 96.8%. Evaluation of the sensitivity of classification models and relative importance of data types using data-based sensitivity analysis showed that the set of VV polarisation data acquired on 24 July (Sentinel-1A) and band 4 data (Sentinel-2A) had the greatest potential for use in crop classification.
Rights: This is an Accepted Manuscript of an article published by Taylor & Francis in GIScience & Remote Sensing on 10 Jul 2017, available online:
資料タイプ: article (author version)
出現コレクション:雑誌発表論文等 (Peer-reviewed Journal Articles, etc)

提供者: 山谷 祐貴


本サイトに関するご意見・お問い合わせは repo at へお願いします。 - 北海道大学