融合特征优选与随机森林算法的GF-6影像东北一季稻遥感提取
Remote sensing extraction of paddy rice in Northeast China from GF-6 images by combining feature optimization and random forest
- 2023年27卷第9期 页码：2153-2164
纸质出版日期： 2023-09-07
DOI： 10.11834/jrs.20221338
扫 描 看 全 文
浏览全部资源
扫码关注微信
摘要
为寻求高效、高精度的东北一季稻种植面积提取方法，该研究以辽宁省盘锦市为研究区，利用覆盖水稻关键物候期的6景GF-6 WFV单时相影像和时序影像，构建光谱特征、植被指数、水体指数和红边指数4类特征变量，采用平均不纯度减少的方法进行重要性排序并通过袋外误差方法选择最优输入特征，建立基于特征优选的随机森林模型，对2020年盘锦市水稻种植分布进行提取。结果表明：（1）基于水稻不同物候期的单时相影像，总体分类精度均在94%以上，以处于水稻移栽期影像分类结果最佳，其总体精度、F1值（水稻）、Kappa系数与实地验证点精度分别为97.67%、98.84%、0.97和97.22%；（2）与单时相影像相比，利用时序影像进行土地覆被分类和水稻信息提取能够有效提高分类精度，其总体精度、F1值（水稻）、Kappa系数与实地验证点精度分别为99.33%、100.00%、0.99和97.22%；（3）对有无红边信息参与的水稻提取结果进行对比分析，红边波段和红边指数的引入可使分类精度有所提高；（4）引入紫边与黄边波段能够提高分类精度，但分类结果精度提高效果次于红边信息。该研究证明，基于特征优选的随机森林模型，利用水稻移栽期的单时相影像提取水稻种植分布可满足实际应用精度需求，但利用时序影像可进一步提高分类精度。此外，GF-6卫星的新增波段均能够提高水稻分类精度，显示出GF-6卫星在作物精细提取方面具有巨大应用潜力。
Abstract
Searching for an efficient
high-precision method for mapping paddy rice planting distribution in Northeast China has important implications for accurate paddy rice yield estimation and agricultural policy making.
In this paper
paddy rice planting distribution was mapped by feature optimization random forest method in Panjin City
Liaoning Province. Based on the land coverage types
2000 samples of 1000 paddy rice samples
250 water samples
300 wetland samples
150 dry land samples
and 300 construction land samples were acquired. Training samples and testing samples accounted for 70% and 30%
respectively. In addition
36 paddy rice field validation points were obtained through field surveys. The spectrum features
vegetation indexes
water index
and red edge indexes were constructed by using the GF-6 WFV images taken in the periods of May 11
May 25
June 1
June 6
July 20
and August 22 in 2020
and these images corresponded to the trefoil stage
transplanting stage
returning green stage
booting stage
and heading stage according to the phenological phase of paddy rice in Panjin City
respectively. The returning greening stage image was covered by June 1
and June 6. The feature importances of single temporal images and time series images were calculated
and out-of-bag (OOB) estimations on different feature combination models were performed based on OOB data. The optimal input features were selected after comprehensively considering the accuracy and complexity. Then
the feature optimization random forest model was established to extract the paddy rice planting area and spatial distribution information in Panjin City in 2020.
According to the testing samples and the paddy rice field validation points
the accuracy evaluation of classification results showed the following: (1) Based on the single temporal images with different phenological phases
all the classification accuracies were 94% and above. The classification result of the image in the paddy rice transplanting stage was the best that the overall accuracy
F1 score (paddy rice)
Kappa coefficient
and field validation point accuracy were 97.67%
98.84%
0.97
and 97.22%
respectively. (2) On the basis of comparison with the classification results of single temporal images
using time-series images for land coverage classification and paddy rice information extraction effectively improved the classification accuracy and reduced misclassification and omission
and the paddy rice classification map polygons were more regular. The overall accuracy
F1 score (paddy rice)
Kappa coefficient
and field validation points accuracy with time series images were 99.33%
100%
0.99
and 97.22%
respectively. (3) Through analyzing of the paddy rice extraction results with or without red edge bands and red edge indexes
the classification accuracy was improved by the introduction of red edge information. This paper proved that based on the feature optimization random forest model
the paddy rice information was accurately extracted by using the single temporal image of paddy rice transplanting stage. Compared with single temporal image
using time-series images improved the classification accuracy. Considering the complexity and running speed of the model
the single temporal image of paddy rice transplanting stage was used to extract paddy rice planting area to meet the accuracy requirement in practical applications. (4) Through analyzing the results of paddy rice extraction without purple band and the yellow band
this paper proved the introduction of purple and yellow bands can improve the classification accuracy
but the effect of improving the accuracy of the classification result was inferior to the red edge information.
Improving the classification accuracy of paddy rice and enhancing crop recognition capabilities by red edge information
purple band
and yellow band
showed the GF-6 satellite had broad application prospects in crop precise identification and area extraction.
关键词
遥感随机森林红边波段特征优选高分六号水稻紫边波段黄边波段
Keywords
remote sensingrandom forestred edge bandfeature optimizationGF-6paddy ricepurple bandyellow band
references
Breiman L. 1996. Bagging predictors. Machine Learning, 24(2): 123-140 [DOI: 10.1023/A:1018054314350http://dx.doi.org/10.1023/A:1018054314350]
Breiman L. 2001. Random forests. Machine Learning, 45(1): 5-32 [DOI: 10.1023/A:1010933404324http://dx.doi.org/10.1023/A:1010933404324]
Chen A X and Li Y C. 2020. Rice recognition of different growth stages based on Sentinel-2 images in mountainous areas of Southwest China. Transactions of the Chinese Society of Agricultural Engineering, 36(7): 192-199
陈安旭, 李月臣. 2020. 基于Sentinel-2影像对西南山区的不同生长期水稻识别. 农业工程学报, 36(7): 192-199 [DOI: 10.11975/j.issn.1002-6819.2020.07.022http://dx.doi.org/10.11975/j.issn.1002-6819.2020.07.022]
Chen J, Chen J, Liao A P, Cao X, Chen L J, Chen X H, He C Y, Han G, Peng S, Lu M, Zhang W W, Tong X H and Mills J. 2015. Global land cover mapping at 30 m resolution: a POK-based operational approach. ISPRS Journal of Photogrammetry and Remote Sensing, 103: 7-27 [DOI: 10.1016/j.isprsjprs.2014.09.002http://dx.doi.org/10.1016/j.isprsjprs.2014.09.002]
Clevers J G P W and Gitelson A A. 2013. Remote estimation of crop and grass chlorophyll and nitrogen content using red-edge bands on Sentinel-2 and -3. International Journal of Applied Earth Observation and Geoinformation, 23: 344-351 [DOI: 10.1016/j.jag.2012.10.008http://dx.doi.org/10.1016/j.jag.2012.10.008]
Dash J and Curran P J. 2004. The MERIS terrestrial chlorophyll index. International Journal of Remote Sensing, 25(23): 5403-5413 [DOI: 10.1080/0143116042000274015http://dx.doi.org/10.1080/0143116042000274015]
Elvidge C D and Chen Z K. 1995. Comparison of broad-band and narrow-band red and near-infrared vegetation indices. Remote Sensing of Environment, 54(1): 38-48 [DOI: 10.1016/0034-4257(95)00132-Khttp://dx.doi.org/10.1016/0034-4257(95)00132-K]
Fang F P and Cheng S H. 2018. The development of rice science, technology and industry in China. Journal of Agriculture, 8(1): 100-106
方福平, 程式华. 2018. 水稻科技与产业发展. 农学学报, 8(1): 100-106 [DOI: 10.11923/j.issn.2095-4050.Cjas2018-1-100http://dx.doi.org/10.11923/j.issn.2095-4050.Cjas2018-1-100]
Feng R, Yu W Y, Ji R P, Zhang Y S, Wu J W and Chen P S. 2017. Comparison and analysis of several extraction methods for lakes and reservoirs based on FY3B/MERSI. Science of Surveying and Mapping, 42(7): 147-152
冯锐, 于文颖, 纪瑞鹏, 张玉书, 武晋雯, 陈鹏狮. 2017. FY3B/MERSI数据的湖泊湿地面积提取对比分析. 测绘科学, 42(7): 147-152 [DOI: 10.16251/j.cnki.1009-2307.2017.07.024http://dx.doi.org/10.16251/j.cnki.1009-2307.2017.07.024]
He Y, Huang C, Li H, Liu Q S, Liu G H, Zhou Z C and Zhang C C. 2019. Land-cover classification of random forest based on Sentinel-2A image feature optimization. Resources Science, 41(5): 992-1001
何云, 黄翀, 李贺, 刘庆生, 刘高焕, 周振超, 张晨晨. 2019. 基于Sentinel-2A影像特征优选的随机森林土地覆盖分类. 资源科学, 41(5): 992-1001 [DOI: 10.18402/resci.2019.05.15http://dx.doi.org/10.18402/resci.2019.05.15]
Horler D N H, Dockray M and Barber J. 1983. The red edge of plant leaf reflectance. International Journal of Remote Sensing, 4(2): 273-288 [DOI: 10.1080/01431168308948546http://dx.doi.org/10.1080/01431168308948546]
Hou M J, Yin J P, Ge J, Li Y C, Feng Q S and Liang T G. 2020. Land cover remote sensing classification method of alpine wetland region based on random forest algorithm. Transactions of the Chinese Society for Agricultural Machinery, 51(7): 220-227
侯蒙京, 殷建鹏, 葛静, 李元春, 冯琦胜, 梁天刚. 2020. 基于随机森林的高寒湿地地区土地覆盖遥感分类方法. 农业机械学报, 51(7): 220-227 [DOI: 10.6041/j.issn.1000-1298.2020.07.025http://dx.doi.org/10.6041/j.issn.1000-1298.2020.07.025]
Huang J W, Li Z Y, Chen E X, Zhao L and Mo B P. 2021. Classification of plantation types based on WFV multispectral imagery of the GF-6 satellite. Journal of Remote Sensing, 25(2): 539-548
黄建文, 李增元, 陈尔学, 赵磊, 莫冰萍. 2021. 高分六号宽幅多光谱数据人工林类型分类. 遥感学报, 25(2): 539-548 [DOI: 10.11834/jrs.20219090http://dx.doi.org/10.11834/jrs.20219090]
Huang J X, Hou Y Z, Su W, Liu J M and Zhu D H. 2017. Mapping corn and soybean cropped area with GF-1 WFV data. Transactions of the Chinese Society of Agricultural Engineering, 33(7): 164-170
黄健熙, 侯矞焯, 苏伟, 刘峻明, 朱德海. 2017. 基于GF-1 WFV数据的玉米与大豆种植面积提取方法. 农业工程学报, 33(7): 164-170 [DOI: 10.11975/j.issn.1002-6819.2017.07.021http://dx.doi.org/10.11975/j.issn.1002-6819.2017.07.021]
Immitzer M, Vuolo F and Atzberger C. 2016. First experience with Sentinel-2 data for crop and tree species classifications in central Europe. Remote Sensing, 8(3): 166 [DOI: 10.3390/rs8030166http://dx.doi.org/10.3390/rs8030166]
Jia K, Li Q Z, Tian Y C and Wu B F. 2011. A review of classification methods of remote sensing imagery. Spectroscopy and Spectral Analysis, 31(10): 2618-2623
贾坤, 李强子, 田亦陈, 吴炳方. 2011. 遥感影像分类方法研究进展. 光谱学与光谱分析, 31(10): 2618-2623 [DOI: 10.3964/j.issn.1000-0593(2011)10-2618-06http://dx.doi.org/10.3964/j.issn.1000-0593(2011)10-2618-06]
Kim H O and Yeom J M. 2014. Effect of red-edge and texture features for object-based paddy rice crop classification using RapidEye multi-spectral satellite image data. International Journal of Remote Sensing, 35(19): 7046-7068 [DOI: 10.1080/01431161.2014.965285http://dx.doi.org/10.1080/01431161.2014.965285]
Li Q J, Liu J, Mi X F, Yang J and Yu T. 2021. Object-oriented crop classification for GF-6 WFV remote sensing images based on Convolutional Neural Network. National Remote Sensing Bulletin, 25(2): 549-558
李前景, 刘珺, 米晓飞, 杨健, 余涛. 2021. 面向对象与卷积神经网络模型的GF-6 WFV影像作物分类. 遥感学报, 25(2): 549-558 [DOI: 10.11834/jrs.20219347http://dx.doi.org/10.11834/jrs.20219347]
Li W J, Guo X L, Yang L B, Yan M, Zou C X, Fang Y H, Sun H and Huang J F. 2020. Accurate recognition of wine grapes using multi-feature optimization based on GF-6 satellite images. Transactions of the Chinese Society of Agricultural Engineering, 36(18): 165-173
李文杰, 郭晓雷, 杨玲波, 闫鸣, 邹晨曦, 方亚华, 孙涵, 黄敬峰. 2020. 基于GF-6卫星影像多特征优选的酿酒葡萄精准识别. 农业工程学报, 36(18): 165-173 [DOI: 10.11975/j.issn.1002-6819.2020.18.020http://dx.doi.org/10.11975/j.issn.1002-6819.2020.18.020]
Li Z P, Liu Z H, Li Z G, Tang P Q, Tan J Y and Yang P. 2014. Progress and prospect of application of remote sensing to rice spatial distribution. Chinese Journal of Agricultural Resources and Regional Planning, 35(6): 9-18
李志鹏, 刘珍环, 李正国, 唐鹏钦, 谭杰扬, 杨鹏. 2014. 水稻空间分布遥感提取研究进展与展望?. 中国农业资源与区划, 35(6): 9-18 [DOI: 10.7621/cjarrp.1005-9121.2014602http://dx.doi.org/10.7621/cjarrp.1005-9121.2014602]
Liang J, Zheng Z W, Xia S T, Zhang X T and Tang Y Y. 2020. Crop recognition and evaluation using red edge features of GF-6 satellite. Journal of Remote Sensing (Chinese), 24(10): 1168-1179
梁继, 郑镇炜, 夏诗婷, 张晓彤, 唐媛媛. 2020. 高分六号红边特征的农作物识别与评估. 遥感学报, 24(10): 1168-1179 [DOI: 10.11834/jrs.20209289http://dx.doi.org/10.11834/jrs.20209289]
Lu C L, Bai Z G, Li Y C, Wu B, Di G D and Dou Y F. 2021. Technical characteristic and new mode applications of GF-6 satellite. Spacecraft Engineering, 30(1): 7-14
陆春玲, 白照广, 李永昌, 武斌, 邸国栋, 窦毅芳. 2021. 高分六号卫星技术特点与新模式应用. 航天器工程, 30(1): 7-14 [DOI: 10.3969/j.issn.1673-8748.2021.01.002http://dx.doi.org/10.3969/j.issn.1673-8748.2021.01.002]
Lu D, Fu X J and Yue M J. 2020. Development status and policy suggestions of rice industry in Liaoning Province. Liaoning Agricultural Sciences, (6): 57-59
陆娣, 付雪娇, 岳铭鉴. 2020. 辽宁省水稻产业发展现状及政策建议. 辽宁农业科学, (6): 57-59 [DOI: 10.3969/j.issn.1002-1728.2020.06.014http://dx.doi.org/10.3969/j.issn.1002-1728.2020.06.014]
Mehdaoui R and Anane M. 2020. Exploitation of the red-edge bands of Sentinel 2 to improve the estimation of durum wheat yield in Grombalia region (Northeastern Tunisia). International Journal of Remote Sensing, 41(23): 8986-9008 [DOI: 10.1080/01431161.2020.1797217http://dx.doi.org/10.1080/01431161.2020.1797217]
Su W, Zhao X F, Sun Z P, Zhang M Z, Zou Z C, Wang W and Shi Y L. 2019. Estimating the corn canopy chlorophyll content using the Sentinel-2A image. Spectroscopy and Spectral Analysis, 39(5): 1535-1542
苏伟, 赵晓凤, 孙中平, 张明政, 邹再超, 王伟, 史园莉. 2019. 基于Sentinel-2A影像的玉米冠层叶绿素含量估算. 光谱学与光谱分析, 39(5): 1535-1542 [DOI: 10.3964/j.issn.1000-0593(2019)05-1535-08http://dx.doi.org/10.3964/j.issn.1000-0593(2019)05-1535-08]
Sun M X, Liu M, Sun Q Q, Zhang P, Jiao X, Sun D F and Shi Y Y. 2020. Response of new bands in GF-6 to land use/cover based on linear spectral mixture analysis model. Transactions of the Chinese Society of Agricultural Engineering, 36(3): 244-253
孙敏轩, 刘明, 孙强强, 张平, 焦心, 孙丹峰, 史云扬. 2020. 利用光谱混合分解模型分析GF-6新增波段对土地利用/覆被的响应. 农业工程学报, 36(3): 244-253 [DOI: 10.11975/j.issn.1002-6819.2020.03.030http://dx.doi.org/10.11975/j.issn.1002-6819.2020.03.030]
Wang L J, Kong Y R, Yang X D, Xu Y, Liang L and Wang S G. 2020. Classification of land use in farming areas based on feature optimization random forest algorithm. Transactions of the Chinese Society of Agricultural Engineering, 36(4): 244-250
王李娟, 孔钰如, 杨小冬, 徐艺, 梁亮, 王树果. 2020. 基于特征优选随机森林算法的农耕区土地利用分类. 农业工程学报, 36(4): 244-250 [DOI: 10.11975/j.issn.1002-6819.2020.04.029http://dx.doi.org/10.11975/j.issn.1002-6819.2020.04.029]
Yan L and Jiang W W. 2016. Progress in the study of vegetation cover classification of multispectral remote sensing imagery. Remote Sensing for Land and Resources, 28(2): 8-13
闫利, 江维薇. 2016. 多光谱遥感影像植被覆盖分类研究进展. 国土资源遥感, 28(2): 8-13 [DOI: 10.6046/gtzyyg.2016.02.02http://dx.doi.org/10.6046/gtzyyg.2016.02.02]
Yang J Y, Zhou Z X, Du Z R, Xu Q Q, Yin H and Liu R. 2019. Rural construction land extraction from high spatial resolution remote sensing image based on SegNet semantic segmentation model. Transactions of the Chinese Society of Agricultural Engineering, 35(5): 251-258
杨建宇, 周振旭, 杜贞容, 许全全, 尹航, 刘瑞. 2019. 基于SegNet语义模型的高分辨率遥感影像农村建设用地提取. 农业工程学报, 35(5): 251-258 [DOI: 10.11975/j.issn.1002-6819.2019.05.031http://dx.doi.org/10.11975/j.issn.1002-6819.2019.05.031]
Zhang P and Hu S G. 2019. Fine crop classification by remote sensing in complex planting areas based on field parcel. Transactions of the Chinese Society of Agricultural Engineering, 35(20): 125-134
张鹏, 胡守庚. 2019. 地块尺度的复杂种植区作物遥感精细分类. 农业工程学报, 35(20): 125-134 [DOI: 10.11975/j.issn.1002-6819.2019.20.016http://dx.doi.org/10.11975/j.issn.1002-6819.2019.20.016]
Zhang Q Y, Li Z, Xia C Z, Chen J and Peng D L. 2019. Tree species classification based on the new bands of GF-6 remote sensing satellite. Journal of Geo-Information Science, 21(10): 1619-1628
张沁雨, 李哲, 夏朝宗, 陈健, 彭道黎. 2019. 高分六号遥感卫星新增波段下的树种分类精度分析. 地球信息科学学报, 21(10): 1619-1628 [DOI: 10.12082/dqxxkx.2019.190116http://dx.doi.org/10.12082/dqxxkx.2019.190116]
文章被引用时，请邮件提醒。
提交
相关作者
暂无数据
相关机构
中国林业科学研究院荒漠化研究所
中国林业科学研究院资源信息研究所
中国科学院微电子研究所
山东科技大学 测绘与空间信息学院
湖州中核勘测规划设计有限公司
选择翻译语言
- 地址：北京市海淀区北四环西路19号 《遥感学报》编辑部 邮编：100190
- 联系电话：010-58887052 Email：nrsb@aircas.ac.cn
- 技术支持由北京北大方正电子有限公司提供 京ICP备20021838号-9
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies
0
回到顶部