ITPCAS OpenIR  > 图书馆
Evaluation of Three Deep Learning Models for Early Crop Classification Using Sentinel-1A Imagery Time Series-A Case Study in Zhanjiang, China
Zhao, HW (Zhao, Hongwei)1,2; Chen, ZX (Chen, Zhongxin)1,2; Jiang, H (Jiang, Hao)3,4,5; Jing, WL (Jing, Wenlong)3,4,5; Sun, L (Sun, Liang)1,2; Feng, M (Feng, Min)6
Source PublicationREMOTE SENSING
2019
Volume11Issue:22Pages:2673
DOI10.3390/rs11222673
Abstract

Timely and accurate estimation of the area and distribution of crops is vital for food security. Optical remote sensing has been a key technique for acquiring crop area and conditions on regional to global scales, but great challenges arise due to frequent cloudy days in southern China. This makes optical remote sensing images usually unavailable. Synthetic aperture radar (SAR) could bridge this gap since it is less affected by clouds. The recent availability of Sentinel-1A (S1A) SAR imagery with a 12-day revisit period at a high spatial resolution of about 10 m makes it possible to fully utilize phenological information to improve early crop classification. In deep learning methods, one-dimensional convolutional neural networks (1D CNNs), long short-term memory recurrent neural networks (LSTM RNNs), and gated recurrent unit RNNs (GRU RNNs) have been shown to efficiently extract temporal features for classification tasks. However, due to the complexity of training, these three deep learning methods have been less used in early crop classification. In this work, we attempted to combine them with an incremental classification method to avoid the need for training optimal architectures and hyper-parameters for data from each time series. First, we trained 1D CNNs, LSTM RNNs, and GRU RNNs based on the full images' time series to attain three classifiers with optimal architectures and hyper-parameters. Then, starting at the first time point, we performed an incremental classification process to train each classifier using all of the previous data, and obtained a classification network with all parameter values (including the hyper-parameters) at each time point. Finally, test accuracies of each time point were assessed for each crop type to determine the optimal time series length. A case study was conducted in Suixi and Leizhou counties of Zhanjiang City, China. To verify the effectiveness of this method, we also implemented the classic random forest (RF) approach. The results were as follows: (i) 1D CNNs achieved the highest Kappa coefficient (0.942) of the four classifiers, and the highest value (0.934) in the GRU RNNs time series was attained earlier than with other classifiers; (ii) all three deep learning methods and the RF achieved F measures above 0.900 before the end of growth seasons of banana, eucalyptus, second-season paddy rice, and sugarcane; while, the 1D CNN classifier was the only one that could obtain an F-measure above 0.900 for pineapple before harvest. All results indicated the effectiveness of the solution combining the deep learning models with the incremental classification approach for early crop classification. This method is expected to provide new perspectives for early mapping of croplands in cloudy areas.

Subject AreaRemote Sensing
WOS IDWOS:000502284300078
Language英语
Indexed BySCI
KeywordRandom Forest System Fields Area
WOS Research AreaRemote Sensing
WOS SubjectRemote Sensing
Cooperation Status国内
Department大陆碰撞与高原隆升重点实验室
URL查看原文
PublisherMDPI
Citation statistics
Document Type期刊论文
Identifierhttp://ir.itpcas.ac.cn/handle/131C11/9095
Collection图书馆
Corresponding AuthorJiang, H (Jiang, Hao)
Affiliation1.CAAS, Inst Agr Resources & Reg Planning, Beijing 100081, Peoples R China;
2.Minist Agr & Rural Affairs, Key Lab Agr Remote Sensing, Beijing 100081, Peoples R China;
3.Key Lab Guangdong Utilizat Remote Sensing & Geog, Guangzhou 510070, Guangdong, Peoples R China;
4.Guangdong Open Lab Geospatial Informat Technol &, Guangzhou 510070, Guangdong, Peoples R China;
5.Guangzhou Inst Geog, Guangzhou 510070, Guangdong, Peoples R China;
6.Chinese Acad Sci, Inst Tibetan Plateau Res, Beijing 100101, Peoples R China.
Recommended Citation
GB/T 7714
Zhao, HW ,Chen, ZX ,Jiang, H ,et al. Evaluation of Three Deep Learning Models for Early Crop Classification Using Sentinel-1A Imagery Time Series-A Case Study in Zhanjiang, China[J]. REMOTE SENSING,2019,11(22):2673.
APA Zhao, HW ,Chen, ZX ,Jiang, H ,Jing, WL ,Sun, L ,&Feng, M .(2019).Evaluation of Three Deep Learning Models for Early Crop Classification Using Sentinel-1A Imagery Time Series-A Case Study in Zhanjiang, China.REMOTE SENSING,11(22),2673.
MLA Zhao, HW ,et al."Evaluation of Three Deep Learning Models for Early Crop Classification Using Sentinel-1A Imagery Time Series-A Case Study in Zhanjiang, China".REMOTE SENSING 11.22(2019):2673.
Files in This Item:
File Name/Size DocType Version Access License
2019059.pdf(4487KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhao, HW (Zhao, Hongwei)]'s Articles
[Chen, ZX (Chen, Zhongxin)]'s Articles
[Jiang, H (Jiang, Hao)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhao, HW (Zhao, Hongwei)]'s Articles
[Chen, ZX (Chen, Zhongxin)]'s Articles
[Jiang, H (Jiang, Hao)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhao, HW (Zhao, Hongwei)]'s Articles
[Chen, ZX (Chen, Zhongxin)]'s Articles
[Jiang, H (Jiang, Hao)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 2019059.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.