[an error occurred while processing this directive] 世界地质 2020, 39(3) 706-713 DOI:   10.3969/j.issn.1004-5589.2020.03.022  ISSN: 1004-5589 CN: 22-1111/P
本期目录 | 下期目录 | 过刊浏览 | 高级检索                                                            [打印本页]   [关闭]
水文·遥感
扩展功能
本文信息
Supporting info
PDF(4150KB)
[HTML全文]
参考文献[PDF]
参考文献
服务与反馈
把本文推荐给朋友
加入我的书架
加入引用管理器
引用本文
Email Alert
文章反馈
浏览反馈信息
本文关键词相关文章
时间序列
Sentinel-1
Google Earth Engine
随机森林
本文作者相关文章
韩冰冰
陈圣波
PubMed
Article by Han B
Article by Chen S
基于GEE时间序列遥感影像分类方法研究
韩冰冰, 陈圣波
吉林大学地球探测科学与技术学院, 长春 130026
摘要： 为探究不同时间序列密度影像对地物分类影响，笔者以敦化市为研究区，基于Google Earth Engine云平台，以Sentinel-1为数据源，建立10 d、15 d、20 d、30 d等不同时间间隔的时间序列数据集，对建立的时间序列数据集采用随机森林、分类回归树和最小距离3种分类方法进行分类实验，探究3种分类方法的识别能力。结果表明，与分类回归树和最小距离相比随机森林更能准确识别作物，时间序列密度的增加能提高分类精度。选取随机森林分类器对10 d时间间隔的时间序列数据集总体分类精度达到了98.04%。
关键词： 时间序列   Sentinel-1   Google Earth Engine   随机森林  
Time series remote sensing image classification method based on GEE
HAN Bing-bing, CHEN Sheng-bo
College of Geo-exploration Science and Technology, Jilin University, Changchun 130026, China
Abstract: In order to study the impact of different time series density images on the feature classification, Dunhua is used as research area based on Google Earth Engine cloud platform. The time series data collections with different time intervals of 10 d, 15 d, 20 d and 30 d are established by using Sentinel-1 images as data source. Three classification methods of random forest, classification regression tree and minimum distance are used to conduct classification experiments for the established time series data collections to explore the recognition ability of three methods. The results show that random forest can identify crops more accurately than classification regression tree and minimum distance, and the increase of time series density can enhance classification accuracy. Using random forest classifier for time series data collections with 10 d interval, the overall classification accuracy reaches 98.04%.
Keywords: time series   Sentinel-1   Google Earth Engine   random forest  
收稿日期 2020-04-04 修回日期 2020-04-21 网络版发布日期  
DOI: 10.3969/j.issn.1004-5589.2020.03.022
基金项目:

国家发改委东北地区培育和发展新兴产业三年行动计划中央预算内投资计划项目（吉发改投资[2016]512号）

通讯作者: 陈圣波(1967-),教授,主要从事空间遥感研究。E-mail:chensb@jlu.edu.cn
作者简介:
作者Email: chensb@jlu.edu.cn
参考文献：
[1] 吴田军,骆剑承,夏列钢,等.迁移学习支持下的遥感影像对象级分类样本自动选择方法[J].测绘学报,2014,43(9):908-916. WU Tian-jun, LUO Jian-cheng, XIA Lie-gang, et al. Object-level classification sample automatic selection method for remote sensing image based on transfer learning[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(9):908-916.
[2] Vintrou E, Desbrosse A, Bégué A, et al. Crop area mapping in West Africa using landscape stratification of MODIS time series and comparison with existing global land products[J]. International Journal of Applied Earth Observation and Geoinformation, 2012, 14(1):83-93.
[3] Xiao X, Boles S, Frolking S, et al. Mapping paddy rice agriculture in south and southeast Asia using multi-temporal MODIS images[J]. Remote Sensing of Environment, 2006, 100(1):95-113.
[4] 李晓慧, 王宏, 李晓兵, 等. 基于多时相Landsat 8 OLI影像的农作物遥感分类研究[J]. 遥感技术与应用, 2019, 34(2):389-397. LI Xiao-hui, WANG Hong, LI Xiao-bing, et al. Research on remote sensing classification of crops based on multi-temporal Landsat 8 OLI images[J]. Remote Sensing Technology and Application, 2019, 34(2):389-397.
[5] 刘佳, 王利民, 杨福刚, 等. 基于HJ时间序列数据的农作物种植面积估算[J]. 农业工程学报, 2015, 31(3):199-206. LIU Jia, WANG Li-min, YANG Fu-gang, et al. Estimation of crop planting area based on HJ time series data[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(3):199-206.
[6] Liu J, Feng Q, Gong J, et al. Winter wheat mapping using a random forest classifier combined with multi-temporal and multi-sensor data[J]. International Journal of Digital Earth, 2018, 11(8):783-802.
[7] 李俐, 孔庆玲, 王鹏新, 等. 基于时间序列Sentinel-1A数据的玉米种植面积监测研究[J].资源科学, 2018, 40(8):1608-1621. LI Li, KONG Qing-ling, WANG Peng-xin, et al. Monitoring of corn planting area based on time series Sentiel-1A data[J]. Resources Science, 2018, 40(8):1608-1621.
[8] Hoekman D H, Vissers M A M. A new polarimetric classification approach evaluated for agricultural crops[J]. IEEE Transactions on Geoscience and Remote Sensing, 2003, 41(12):2881-2889.
[9] McNairn H, Shang J, Jiao X, et al. The contribution of ALOS PALSAR multipolarization and polarimetric data to crop classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(12):3981-3992.
[10] 杨魁, 杨建兵, 江冰茹. Sentinel-1卫星综述[J]. 城市勘测, 2015(2):24-27. YANG Kui, YANG Jian-bing, JIANG Bing-ru. Sentinel-1 satellite overview[J]. Urban Geotechnical Investigation & Surveying, 2015(2):24-27.
[11] Gong P, Liu H, Zhang M, et al. Stable classification with limited sample:transferring a 30-m resolution sample set collected in 2015 to mapping 10-m resolution global land cover in 2017[J]. Science Bulletin, 2019, 64(6):370-373.
[12] 张亮, 宁芊. CART决策树的两种改进及应用[J]. 计算机工程与设计, 2015, 36(5):1209-1213. ZHANG Liang, NING Qian. Improvement and application of CART decision tree[J]. Computer Engineering and Design, 2015, 36(5):1209-1213.
[13] Breiman L. Random forests[J]. Machine Learning, 2001, 45(1):5-32.
[14] Loosvelt L, Peters J, Skriver H, et al. Impact of reducing polarimetric SAR input on the uncertainty of crop classifications based on the random forests algorithm[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(10):4185-4200.
本刊中的类似文章
1．康乾坤, 路来君.随机森林算法在测井岩性分类中的应用[J]. 世界地质, 2020,39(2): 398-405
2．吴真玮, 曾昭发, 潘隆武.基于CEEMD和自适应中值滤波的大地电磁数据去噪研究[J]. 世界地质, 2017,36(3): 970-975
3．赵春艳, 郝哲, 朱浮声.大跨度公路隧道围岩变形的时间序列分析[J]. 世界地质, 2009,28(3): 361-366
Copyright by 世界地质