Please wait a minute...
img

官方微信

遥感技术与应用  2021, Vol. 36 Issue (2): 324-331    DOI: 10.11873/j.issn.1004-0323.2021.2.0324
农业遥感专栏     
基于多时相Sentinel-2影像的黑河中游玉米种植面积提取研究
陈彦四1,2(),黄春林1(),侯金亮1,韩伟孝1,2,冯娅娅1,2,李翔华1,2,王静3
1.中国科学院西北生态环境资源研究院 甘肃省遥感重点实验室,甘肃 兰州 730000
2.中国科学院大学,北京 100049
3.甘肃省食品检验研究院,甘肃 兰州 730000
Extraction of Maize Planting Area based on Multi-temporal Sentinel-2 Imagery in the Middle Reaches of Heihe River
Yansi Chen1,2(),Chunlin Huang1(),Jinliang Hou1,Weixiao Han1,2,Yaya Feng1,2,Xianghua Li1,2,Jing Wang3
1.Key Laboratory of Remote Sensing of Gansu Province,Northwest Institute of Eco-Environment and Resources,Chinese Academy of Sciences,Lanzhou 730000,China
2.University of Chinese Academy of Sciences,Beijing 100049,China
3.Gansu Food Inspection and Research Institute,Lanzhou 730000,China
 全文: PDF(3912 KB)   HTML
摘要:

玉米是黑河中游种植面积最大的农作物,生长期需水量大、蒸散量高。准确获取玉米种植面积对该区域农作物种植结构调整、水资源合理规划有重要参考意义。基于2019年4月至9月Sentinel-2多时相影像,采用随机森林算法开展了黑河中游玉米种植面积提取研究。研究方法分为两类—直接提取法和两步提取法。进一步探讨了多时间信息量对玉米种植面积提取精度的影响以及各输入特征参数在玉米面积提取过程中的重要性表现。结果表明:基于Sentinel-2多时相影像,直接提取法和两步提取法均可高精度地提取研究区玉米种植面积,特别是两步提取法,玉米分类总体精度可达85.03%,F1_Score为0.70,Kappa系数为0.83;与单幅影像相比,多时相影像可获取不同作物的物候信息,有效减少作物错分/漏分,提高作物分类精度。该方法对基于高分辨率光学影像结合机器学习方法获取具有高度异质性的作物信息具有重要的参考价值。

关键词: 玉米种植面积多时相卫星影像Sentinel-2随机森林    
Abstract:

Maize is the crop with the largest planting area in the middle reaches of the Heihe River, with large water requirements and high evapotranspiration during the growing period. Accurately obtaining the maize planting area has important significances for the adjustment of crop planting structure and reasonable planning of water resources in the region. The object of this paper is to assess the value of multi-temporal Sentinel-2 data for extraction of maize planting area in the middle reaches of the Heihe River from April to September 2019. The random forest algorithm was adopted in this work. The research methods were divided into two categories: extraction directly and two-step extraction. Further discussed the impact of multi- temporal information as input on the classification accuracy, and analyzed the importance of the input feature parameters of the model in the extraction process. The results showed that the two-step extraction method based on Sentinel-2 multi-temporal images could accurately extract the maize planting area in the study area with the overall classification accuracy of 85.03%, F1_Score of 0.70, and Kappa coefficient of 0.83. Compared with single image, multi-temporal images could effectively improve the accuracy of crop classification, obtaining differently crop phenology information. The research demonstrates the value of obtaining highly heterogeneous crop information based on high-resolution optical image combined with machine learning method.

Key words: Maize planting area    Time series satellite imagery    Sentinel-2    Random forest
收稿日期: 2020-06-18 出版日期: 2021-05-24
ZTFLH:  TP79  
基金资助: 中国科学院战略性先导科技专项(A类)(XDA19040500);甘肃省重点研发计划项目(17YF1FA134)
通讯作者: 黄春林     E-mail: chenyansi@lzb.ac.cn;huangcl@lzb.ac.cn
作者简介: 陈彦四(1992-),女,山西吕梁人,硕士研究生,主要从事农业遥感研究。E?mail: chenyansi@lzb.ac.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
陈彦四
黄春林
侯金亮
韩伟孝
冯娅娅
李翔华
王静

引用本文:

陈彦四,黄春林,侯金亮,韩伟孝,冯娅娅,李翔华,王静. 基于多时相Sentinel-2影像的黑河中游玉米种植面积提取研究[J]. 遥感技术与应用, 2021, 36(2): 324-331.

Yansi Chen,Chunlin Huang,Jinliang Hou,Weixiao Han,Yaya Feng,Xianghua Li,Jing Wang. Extraction of Maize Planting Area based on Multi-temporal Sentinel-2 Imagery in the Middle Reaches of Heihe River. Remote Sensing Technology and Application, 2021, 36(2): 324-331.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2021.2.0324        http://www.rsta.ac.cn/CN/Y2021/V36/I2/324

图1  研究区概况审图号:GS(2019)1823
地物类型采样点分类总计来源
玉米玉米623623野外采集

非玉米

植被

蔬菜、麦子等157731野外采集
大棚种植241Google Earth
草地、林地333Google Earth
非植被建设用地5291 542Google Earth
水体333Sentinel-2
其他677Google Earth
表1  野外采集数据以及其他辅助数据
图2  技术路线图
植被区提取结果OAKappaF1_Score
方案一植被非植被
植被3931996.78%0.940.97
非植被9448
方案二植被非植被
植被2521596.32%0.930.97
非植被8283
玉米种植面积提取结果OAKappaF1_Score
方案一玉米非玉米
玉米1903484.48%0.680.82
非玉米27142
方案二玉米非玉米
玉米1883785.03%0.700.83
非玉米22147
表2  黑河中游玉米种植面积提取精度评估
图3  研究区玉米种植面积分布图(左图)以及局部放大Sentinel-2 RGB影像(右上)与分类结果比较(右下)
图4  玉米种植面积提取总体精度
图5  随机森林模型输入指数的频次和重要性排序
1 Chen Y, Lu D, Luo L, et al. Detecting Irrigation Extent, Frequency, and Timing in a Heterogeneous Arid Agricultural Region Using Modis Time Series, Landsat Imagery, and Ancillary Data [J].Remote Sensing of Environment,2018,204: 197-211.
2 Lu Ling, Cheng Guodong, Li Xin. Study on the Landscape Pattern of Zhangye Oasis in the Middle Reaches of Heihe River Basin [J] .Journal of Applied Ecology, 2001,12(1): 68-74.
2 卢玲,程国栋,李新.黑河流域中游地区景观变化研究[J].应用生态学报,2001,12(1):68-74.
3 Wang Shuguo,Ma Chunfeng,Zhao Zebin,et al. Estimation of Soil Moisture of Agriculture Field in the Middle Reaches of the Heihe River Basin based on Sentinel-1 and Landsat 8 Imagery [J]. Remote Sensing Technology and Application,2020,35(1):13-22.
3 王树果,马春锋,赵泽斌,等.基于Sentinel-1及Landsat 8数据的黑河中游农田土壤水分估算[J].遥感技术与应用,2020,35(1):13-22.
4 Jiao Yuanmei, Ma Mingguo, Xiao Duning. Study on the Landscape Pattern of Zhangye Oasis in the Middle Reaches of Heihe River Basin [J]. Glacier and Frozen Soil, 2003,25(1): 94-99.
4 角媛梅,马明国,肖笃宁.黑河流域中游张掖绿洲景观格局研究[J].冰川冻土,2003,25(1):94-99.
5 Zheng Luqian,Tan Minghong. A Comparative Study of Water Use Efficiency of Different Crops in the Middle Reaches of Hei-he River and Its Implications for Planting Structure Adjustment[J].Journal of Geo-information Science,2016,18(7):977-986.
5 郑璐倩,谈明洪.黑河中游地区作物用水效率比较及种植结构调整方向研究[J].地球信息科学学报,2016,18(7):977-986.
6 Cabral A I R, Costa F L. Land Cover Changes and Landscape Pattern Dynamics in Senegal and Guinea Bissau Borderland [J]. Applied Geography, 2017, 82: 115-128.
7 Esmail M, Ali M, Negm A. Monitoring Land Use/Land Cover Changes Around Damietta Promontory, Egypt, Using RS/GIS[C]∥12th International Conference on Hydroinformatics (HIC)-Smart Water for the Future,South Korea,2016,154: 936-942.
8 Pea M A, Brenning A. Assessing Fruit-Tree Crop Classification from Landsat-8 Time Series for the Maipo Valley, Chile [J]. Remote Sensing of Environment, 2015, 171:234-244.
9 Skakun S, Franch B, Vermote E, et al. Early Season Large-Area Winter Crop Mapping Using Modis NDVI Data, Growing Degree Days Information and a Gaussian Mixture Model [J]. Remote Sensing of Environment, 2017, 195(15):244-258.
10 Son N T, Chen C F, Chen C R, et al. Classification of Multitemporal Sentinel-2 Data for Field-Level Monitoring of Rice Cropping Practices in Taiwan [J]. Advances in Space Research, 2020, 65(8):1910-1921.
11 Kamthonkiat D, Honda K, Turral H, et al. Discrimination of Irrigated and Rainfed Rice in a Tropical Agricultural System Using Spot Vegetation Ndvi and Rainfall Data [J]. International Journal of Remote Sensing, 2007, 26(12): 2527-2547.
12 Ozdogan M, Gutman G. A New Methodology to Map Irrigated Areas Using Multi-temporal Modis and Ancillary Data: An Application Example in the Continental Us [J]. Remote Sensing of Environment, 2008, 112(9): 3520-3537.
13 Basukala A K, Oldenburg C, Schellberg J, et al. Towards Improved Land Use Mapping of Irrigated Croplands: Performance Assessment of Different Image Classification Algorithms and Approaches [J]. European Journal of Remote Sensing,2017,50(1): 187-201.
14 Ragettli S, Herberz T, Siegfried T. An Unsupervised Classification Algorithm for Multi-temporal Irrigated Area Mapping in Central Asia [J].Remote Sensing,2018,10(11).
15 Gomez C, White J C, Wulder M A. Optical Remotely Sensed Time Series Data for Land Cover Classification: A Review [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 116:55-72.
16 Mitsopoulos I, Chrysafi I, Bountis D, et al. Assessment of Factors Driving High Fire Severity Potential and Classification in a Mediterranean Pine Ecosystem [J]. Journal of Environmental Management, 2019, 235: 266-275.
17 Hao P, Zhan Y, Wang L,et al. Feature Selection of Time Series MODIS Data for Early Crop Classification Using Random Forest: A Case Study in Kansas, USA[J]. Remote Sensing, 2015, 7(5): 5347-5369.
18 Panda S S, Ames D P, Panigrahi S. Application of Vegetation Indices for Agricultural Crop Yield Prediction Using Neural Network Techniques [J]. Remote Sensing. 2010, 2(3): 673–696.
19 Reed B C, Brown J F, VanderZee D, et al. Measuring Phenological Variability from Satellite Imagery [J]. Journal of Vegetation Science, 1994, 5(5):703–714.
20 Huemmrich K F, Privette J L, Mukelabai M, et al. Time-Series Validation of Modis Land Biophysical Products in a Kalahari Woodland, Africa[J]. International Journal Of Remote Sensing,2005, 26(9): 4381-4398.
21 Jeong S, Kang S, Jang K, et al. Development of Variable Threshold Models for Detection of Irrigated Paddy Rice Fields and Irrigation Timing in Heterogeneous Land Cover[J]. Agricultural Water Management, 2012, 115:83-91.
22 Huete A R, Liu H Q, Batchily K, et al. A Comparison of Vegetation Indices over a Global set of TM Images for EOS-MODIS[J]. Remote Sensing of Environment, 1997, 59(3):440-451.
23 Huete A, Didan K, Miura T, et al. Overview of the Radiometric and Biophysical Performance of the Modis Vegetation Indices [J]. Remote Sensing of Environment, 2002, 83(1-2):195-213.
24 Deventer A P, Ward A D, Gowda P H, et al. Using Thematic Mapper Data to Identify Contrasting Soil Plains and Tillage Practices[J]. Photogrammetric Engineering & Remote Sensing,1997,63(1):87-93.
25 Congalton R G. A Review of Assessing of the Accuracy of Classifications of Remotely Sensed Data[J]. Remote Sensing of Environment, 1991, 37(1): 35-46.
26 You N, Dong J. Examining Earliest Identifiable Timing of Crops Using all Available Sentinel 1/2 Imagery and Google Earth Engine[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 161: 109-123.
[1] 王崇阳,田昕. 基于GF⁃1 PMS数据的森林覆盖变化检测[J]. 遥感技术与应用, 2021, 36(1): 208-216.
[2] 付甜梦,张丽,陈博伟,闫敏. 基于GEE平台的海岛地表覆盖提取及变化监测—以苏拉威西岛为例[J]. 遥感技术与应用, 2021, 36(1): 55-64.
[3] 马腾耀,肖鹏峰,张学良,马威,郭金金. 基于特征优选的GF-3全极化数据积雪识别[J]. 遥感技术与应用, 2020, 35(6): 1292-1302.
[4] 王一帆,徐涵秋. 基于客观阈值与随机森林Gini指标的水体遥感指数对比[J]. 遥感技术与应用, 2020, 35(5): 1089-1098.
[5] 牟昱璇,邬明权,牛铮,黄文江,杨尽. 南方地区复杂条件下的耕地面积遥感提取方法[J]. 遥感技术与应用, 2020, 35(5): 1127-1135.
[6] 王明,刘正佳,陈元琰. 基于Sentinel-2波段/产品的图像云检测效果对比研究[J]. 遥感技术与应用, 2020, 35(5): 1167-1177.
[7] 李宏达,高小红,汤敏. 基于CNN的不同空间分辨率影像土地覆被分类研究[J]. 遥感技术与应用, 2020, 35(4): 749-758.
[8] 李萌,年雁云,边瑞,白艳萍,马金辉. 基于多源遥感影像的青海云杉和祁连圆柏分类[J]. 遥感技术与应用, 2020, 35(4): 855-863.
[9] 张坤,刘乃文,高帅,赵书慧. 数据驱动的植被总初级生产力估算方法研究[J]. 遥感技术与应用, 2020, 35(4): 943-949.
[10] 董超,赵庚星. 时序数据集构建质量对土地覆盖分类精度的影响研究[J]. 遥感技术与应用, 2020, 35(3): 558-566.
[11] 李净,温松楠. 基于3种机器学习法的太阳辐射模拟研究[J]. 遥感技术与应用, 2020, 35(3): 615-622.
[12] 柴旭荣,李明,周义,王金风,田庆春. 影像的土地覆被快速分类[J]. 遥感技术与应用, 2020, 35(2): 315-325.
[13] 唐廷元,付波霖,何素云,娄佩卿,闭璐. 基于GF-1和Sentinel-1A的漓江流域典型地物信息提取[J]. 遥感技术与应用, 2020, 35(2): 448-457.
[14] 刘培,余志远,马威,韩瑞梅,陈正超,王涵,杨磊库. 基于地形信息的Landsat与Radarsat-2遥感数据协同分类研究[J]. 遥感技术与应用, 2019, 34(6): 1269-1275.
[15] 李哲,张沁雨,彭道黎. 基于高分二号遥感影像的树种分类方法[J]. 遥感技术与应用, 2019, 34(5): 970-982.