Plastic-mulched Farmland Recognition in Loess Plateau Based on Sentinel-2 Remote-sensing Images
-
摘要: 及时、准确地获取覆膜农田的空间分布信息是防治地膜微塑料污染的基础。为准确地识别黄土高原地区的覆膜农田，本研究构建了基于Sentinel-2遥感影像和随机森林算法的适用于黄土高原覆膜农田遥感识别的特征集组合与多时相组合方案。以甘肃省临夏县、宁夏回族自治区彭阳县和山西省山阴县作为测试区，陕西省旬邑县作为验证区开展识别研究。首先，基于随机森林算法，针对3个不同的作物生育期(播期、生长旺盛期和收获期),在7种不同的特征集组合方案中优选出各时期识别精度最高的方案。然后，基于不同作物生育期的遥感影像及其对应的最优特征集组合方案，构建不同的多时相组合来进行覆膜农田识别并优选多时相组合。最后，利用旬邑县来验证构建的优选特征集组合与多时相组合识别覆膜农田的有效性，并绘制各研究区的覆膜农田空间分布图。结果表明：相比于其他遥感识别特征因子，Sentinel-2遥感影像光谱特征集中的可见光波段(B2、B3和B4)和短波红外波段(B11和B12),指数特征集中的归一化差值裸地与建筑用地指数(NDBBI)、归一化水体指数(NDWI)、裸土指数(BSI)、归一化建筑物指数(NDBI)和改进的归一化水体指数(MNDWI),纹理特征集中的和平均(savg)和相关性(corr)可以作为覆膜农田识别的优选输入特征变量。在7种特征集组合方案中，光谱+指数方案是播期和收获期识别覆膜农田的优选方案，在这两个时期对4个研究区的覆膜农田进行识别的F1值分别大于87%和57%,而光谱+指数+纹理方案是生长旺盛期识别覆膜农田的优选方案，该方案识别4个研究区覆膜农田的F1值均大于71%。基于多时相遥感影像的覆膜农田识别精度高于仅基于单时相遥感影像的精度，其中播期+生长旺盛期+收获期多时相组合可作为黄土高原覆膜农田识别的优选多时相组合，该组合在4个研究区识别覆膜农田的F1值均大于92%。总体而言，基于随机森林算法和本研究优选的特征集组合与多时相组合方案能够较为精准地识别黄土高原地区的覆膜农田。Abstract: Plastic film mulching has greatly increased crop yields in arid and semi-arid regions of China, but also caused a lot of environmental problems. Thus, timely and accurate mapping of plastic-mulched farmlands through remote sensing technology is helpful for governments to plan agricultural production and deal with micro-plastic pollutions. However, the existing recognition methods based on single-temporal remote-sensing images with low and medium resolutions are unable to accurately recognize the plastic-mulched farmlands in the Loess Plateau due to its complex terrain and fragmented agricultural landscapes. In order to accurately recognize plastic-mulched farmlands in the Loess Plateau, different feature set combination schemes and multi-temporal image combination schemes applicable to recognize plastic-mulched farmlands in the Loess Plateau were constructed based on Sentinel-2 remote-sensing images and random forest algorithm. Three testing areas were selected for constructing recognition schemes mentioned above, including Linxia County in Gansu Province, Pengyang County in Ningxia Hui Autonomous Region, and Shanyin County in Shanxi Province, and one validation area of Xunyi County in Shaanxi Province were chosen as the scheme validation area. Firstly, based on the random forest algorithm, the optimal feature set combination scheme with the highest recognition accuracy was selected from seven different feature set combination schemes for each growth stage（sowing stage, flourishing stage, and harvesting stage）. Then, based on the remote-sensing images of the three different crop growth stages and their corresponding optimal feature set combination schemes, different multi-temporal image combination schemes were constructed to recognize the plastic-mulched farmlands, and then the optimal multi-temporal image combination scheme was selected. Finally, the effectiveness of the optimal feature set combination scheme and multi-temporal image combination sheme for recognizing plastic-mulched farmlands was verified in Xunyi County, and the spatial distribution maps of plastic-mulched farmland in each research area were drawn. The results showed that the visible bands（B2, B3, and B4） and the short-wave infrared bands（B11 and B12） in the spectral feature set of Sentinel-2 remote-sensing images, the normalized difference bareness and built-up index（NDBBI）, normalized difference water index（NDWI）, bare soil index（BSI）, normalized difference built-up index（NDBI）, and modified normalized difference water index（MNDWI） in the index feature set, and the sum average（savg） and correlation（corr） in the textural feature set can be used as optimal input feature variables for recognizing plastic-mulched farmlands. Among the seven different feature set combination schemes, the “spectum + index” scheme was the optimal scheme for recognizing plastic-mulched farmlands during the sowing and harvesting stages. The F1-score for plastic-mulched farmland recognition in these two stages in the four study areas was greater than 87% and 57%, respectively. The “spctrum + index + texture” scheme was the optimal scheme for recognizing plastic-mulched farmlands during the flourishing stage with F1-score greater than 71% in the four study areas. Generally, the plastic-mulched farmland recognition accuracy based on multi-temporal remote-sensing images was higher than that based on single-temporal remote-sensing images. Among different multi-temporal image combination schemes, “sowing stage + flourishing stage + harvesting stage” can be used as the optimal scheme for plastic-mulched farmland recognition, and the F1-score for recognizing plastic-mulched farmlands in the four study areas was greater than 92%. In general, plastic-mulched farmlands in the Loess Plateau can be accurately recognized based on random forest algorithm and the optimal feature set combination schemes and multi-temporal image combination scheme.
-
-
[1] 黄明斌,李玉山.黄土塬区旱作冬小麦增产潜力研究[J].自然资源学报,2000,15(2):143-148.HUANG Mingbin,LI Yushan.On potential yield increase of dryland winter wheat on the loess tableland[J].Journal of Natural Resources,2000,15(2):143-148.(in Chinese) [2] 李玉山.苜蓿生产力动态及其水分生态环境效应[J].土壤学报,2002,39(3):404-411.LI Yushan.Productivity dynamic of alfalfa and its effect on water eco-environment[J].Acta Pedologica Sinica,2002,39(3):404-411.(in Chinese) [3] LI F M,WANG P,WANG J,et al.Effects of irrigation before sowing and plastic film mulching on yield and water uptake of spring wheat in semiarid Loess Plateau of China[J].Agricultural Water Management,2004,67(2):77-88.
[4] 严昌荣,刘恩科,舒帆,等.我国地膜覆盖和残留污染特点与防控技术[J].农业资源与环境学报,2014,31(2):95-102.YAN Changrong,LIU Enke,SHU Fan,et al.Review of agricultural plastic mulching and its residual pollution and prevention measures in China[J].Journal of Agricultural Resources and Environment,2014,31(2):95-102.(in Chinese) [5] 张德奇,廖允成,贾志宽.旱区地膜覆盖技术的研究进展及发展前景[J].干旱地区农业研究,2005,23(1):208-213.ZHANG Deqi,LIAO Yuncheng,JIA Zhikuan.Research advances and prospects of film mulching in arid and semi-arid areas[J].Agricultural Research in the Arid Areas,2005,23(1):208-213.(in Chinese) [6] LIU E K,HE W Q,YAN C R.‘White revolution’ to ‘white pollution’—agricultural plastic film mulch in China[J].Environmental Research Letters,2014,9(9):091001.
[7] LANORTE A,DE S F,NOLÈ G,et al.Agricultural plastic waste spatial estimation by Landsat 8 satellite images[J].Computers and Electronics in Agriculture,2017,141:35-45.
[8] GAO H H,YAN C R,LIU Q,et al.Effects of plastic mulching and plastic residue on agricultural production:a meta-analysis[J].Science of the Total Environment,2019,651:484-492.
[9] 贾坤,李强子,田亦陈,等.遥感影像分类方法研究进展[J].光谱学与光谱分析,2011,31(10):2618-2623.JIA Kun,LI Qiangzi,TIAN Yichen,et al.A review of classification methods of remote sensing imagery[J].Spectroscopy and Spectral Analysis,2011,31(10):2618-2623.(in Chinese) [10] 李长春,陈伟男,王宇,等.基于多源Sentinel数据的县域冬小麦种植面积提取[J].农业机械学报,2021,52(12):207-215.LI Changchun,CHEN Weinan,WANG Yu,et al.Extraction of winter wheat planting area in county based multi-sensor Sentinel data[J].Transactions of the Chinese Society for Agricultural Machinery,2021,52(12):207-215.(in Chinese) [11] 孙亚楠,李仙岳,史海滨,等.基于特征优选决策树模型的河套灌区土地利用分类[J].农业工程学报,2021,37(13):242-251.SUN Ya’nan,LI Xianyue,SHI Haibin,et al.Classification of land use in Hetao Irrigation District of Inner Mongolia using feature optimal decision trees[J].Transactions of the CSAE,2021,37(13):242-251.(in Chinese) [12] 田颖,陈卓奇,惠凤鸣,等.欧空局哨兵卫星Sentinel-2A/B数据特征及应用前景分析[J].北京师范大学学报(自然科学版),2019,55(1):57-65.TIAN Ying,CHEN Zhuoqi,HUI Fengming,et al.ESA Sentinel-2A/B satellite:characteristics and applications[J].Journal of Beijing Normal University (Natural Science),2019,55(1):57-65.(in Chinese) [13] SAMBERG L H,GERBER J S,RAMANKUTTY N,et al.Subnational distribution of average farm size and smallholder contributions to global food production[J].Environmental Research Letters,2016,11(12):124010.
[14] LU L Z,DI L P,YE Y M.A decision-tree classifier for extracting transparent plastic-mulched landcover from Landsat-5 TM images[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(11):4548-4558.
[15] LU L Z,HANG D W,DI L P.Threshold model for detecting transparent plastic-mulched landcover using moderate-resolution imaging spectroradiometer time series data:a case study in southern Xinjiang,China[J].Journal of Applied Remote Sensing,2015,9(1):097094.
[16] 郑文慧,王润红,曹银轩,等.基于Google Earth Engine的黄土高原覆膜农田遥感识别研究[J].农业机械学报,2022,53(1):224-234.ZHENG Wenhui,WANG Runhong,CAO Yinxuan,et al.Remote sensing recognition of plastic-film-mulched farmlands on Loess Plateau based on Google Earth Engine[J].Transactions of the Chinese Society for Agricultural Machinery,2022,53(1):224-234.(in Chinese) [17] 罗琪,刘晓龙,史正涛,等.基于GF-1与Sentinel-2融合数据的地膜识别方法研究[J].地理与地理信息科学,2021,37(1):39-46.LUO Qi,LIU Xiaolong,SHI Zhengtao,et al.Study on plastic mulch identification based on the fusion of GF-1 and Sentinel-2 images[J].Geography and Geo-Information Science,2021,37(1):39-46.(in Chinese) [18] HASITUYA,CHEN Z X.Mapping plastic-mulched farmland with multi-temporal Landsat-8 data[J].Remote Sensing,2017,9(6):557-583.
[19] 张家政,李崇贵,王涛.黄土高原植被覆盖时空变化及原因[J].水土保持研究,2022,29(1):224-230,241.ZHANG Jiazheng,LI Chonggui,WANG Tao.Dynamic change of vegetation coverage on the Loess Plateau and its factors[J].Research of Soil and Water Conservation,2022,29(1):224-230,241.(in Chinese) [20] 许尔琪.中国农业资源环境分区数据集[J].全球变化数据学报(中英文),2021,5(1):19-26.XU Erqi.Dataset of agricultural resource and environment zoning of China[J].Journal of Global Change Data & Discovery,2021,5(1):19-26.(in Chinese) [21] 郝玉红.甘肃和政春油菜品种对比试验初报[J].中国农技推广,2019,35(11):34-35. [22] 许青云,杨贵军,龙慧灵,等.基于MODIS NDVI多年时序数据的农作物种植识别[J].农业工程学报,2014,30(11):134-144.XU Qingyun,YANG Guijun,LONG Huiling,et al.Crop information identification based on MODIS NDVI time-series data[J].Transactions of the CSAE,2014,30(11):134-144.(in Chinese) [23] 张亚亚.基于GF-1遥感影像的农作物面积测量方法研究[D].长春:吉林大学,2017.ZHANG Yaya.Research on the method of crop area measurement based on remote sensed data[D].Changchun:Jilin University,2017.(in Chinese) [24] PHIRI D,SIMWANDA M,SALEKIN S,et al.Sentinel-2 data for land cover/use mapping:a review[J].Remote Sensing,2020,12(14):2291.
[25] HARALICK R M,SHANMUGAM K,DINSTEIN I H.Textural features for image classification[J].IEEE Transactions on Systems,Man,and Cybernetics,1973(6):610-621.
[26] TUCKER C J.Red and photographic infrared linear combinations for monitoring vegetation[J].Remote Sensing of Environment,1979,8(2):127-150.
[27] JORDAN C F.Derivation of leaf-area index from quality of light on the forest floor[J].Ecology,1969,50(4):663-666.
[28] BIRTH G S,MCVEY G R.Measuring the color of growing turf with a reflectance spectrophotometer[J].Agronomy Journal,1968,60(6):640-643.
[29] HUETE A R.A soil-adjusted vegetation index (SAVI)[J].Remote Sensing of Environment,1988,25(3):295-309.
[30] RIKIMARU A,ROY P S,MIYATAKE S.Tropical forest cover density mapping[J].Tropical Ecology,2002,43(1):39-47.
[31] ZHA Y,GAO J,NI S X.Use of normalized difference built-up index in automatically mapping urban areas from TM imagery[J].International Journal of Remote Sensing,2003,24(3):583-594.
[32] 吴志杰,赵书河.基于TM图像的“增强的指数型建筑用地指数”研究[J].国土资源遥感,2012,24(2):50-55.WU Zhijie,ZHAO Shuhe.A study of enhenced index-based build-up index based on Landsat TM imagery[J].Remote Sensing for Natural Resources,2012,24(2):50-55.(in Chinese) [33] XU H Q.Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery[J].International Journal of Remote Sensing,2006,27(14):3025-3033.
[34] MCFEETERS S K.The use of the normalized difference water index (NDWI) in the delineation of open water features[J].International Journal of Remote Sensing,1996,17(7):1425-1432.
[35] BREIMAN L.Random forests[J].Machine Learning,2001,45(1):5-32.
[36] 何云,黄翀,李贺,等.基于Sentinel-2A影像特征优选的随机森林土地覆盖分类[J].资源科学,2019,41(5):992-1001.HE Yun,HUANG Chong,LI He,et al.Land-cover classification of random forest based on Sentinel-2A image feature optimization[J].Resources Science,2019,41(5):992-1001.(in Chinese) [37] 何真,胡洁,蔡志文,等.协同多时相国产GF-1和GF-6卫星影像的艾草遥感识别[J].农业工程学报,2022,38(1):186-195.HE Zhen,HU Jie,CAI Zhiwen,et al.Remote sensing identification for Artemisia argyi integrating multi-temporal GF-1 and GF-6 images[J].Transactions of the CSAE,2022,38(1):186-195.(in Chinese) [38] ZHANG H,KANG J,XU X,et al.Accessing the temporal and spectral features in crop type mapping using multi-temporal Sentinel-2 imagery:a case study of Yi’an County,Heilongjiang Province,China[J].Computers and Electronics in Agriculture,2020,176:105618.
[39] 孔英会,景美丽.基于混淆矩阵和集成学习的分类方法研究[J].计算机工程与科学,2012,34(6):111-117.KONG Yinghui,JING Meili.Research of the classification method based on confusion matrixes and ensemble learning[J].Computer Engineering & Science,2012,34(6):111-117.(in Chinese) [40] 咸阳市统计局.咸阳统计年鉴[Z/OL].2021. http://tjj.xianyang.gov.cn/sjzx/xysj/202211/t20221117_1561847.html. [41] ZHANG H X,WANG Y J,SHANG J L,et al.Investigating the impact of classification features and classifiers on crop mapping performance in heterogeneous agricultural landscapes[J].International Journal of Applied Earth Observation and Geoinformation,2021,102:102388.
[42] HASITUYA,CHEN Z X,WANG L M,et al.Monitoring plastic-mulched farmland by Landsat-8 OLI imagery using spectral and textural features[J].Remote Sensing,2016,8(4):353.
[43] 哈斯图亚.基于多源数据的覆膜农田遥感识别研究[D].北京:中国农业科学院,2017.HASITUYA.Mapping plastic-mulched farmland with multi-source remote sensing data[D].Beijing:Chinese Academy of Agricultural Sciences,2017.(in Chinese) [44] BLICKENSDÖRFER L,SCHWIEDER M,PFLUGMACHER D,et al.Mapping of crop types and crop sequences with combined time series of Sentinel-1,Sentinel-2 and Landsat 8 data for Germany[J].Remote Sensing of Environment,2022,269:112831.
[45] 梁晨欣,黄启厅,王思,等.基于多时相遥感植被指数的柑橘果园识别[J].农业工程学报,2021,37(24):168-176.LIANG Chenxin,HUANG Qiting,WANG Si,et al.Identification of citrus orchard under vegetation indexes using multi-temporal remote sensing[J].Transactions of the CSAE,2021,37(24):168-176.(in Chinese) [46] 张荣群,王盛安,高万林,等.基于时序植被指数的县域作物遥感分类方法研究[J].农业机械学报,2015,46(增刊):246-252.ZHANG Rongqun,WANG Sheng’an,GAO Wanlin,et al.Remote-sensing classification method of county-level agricultural crops using time-series NDVI[J].Transactions of the Chinese Society for Agricultural Machinery,2015,46(Supp.):246-252.(in Chinese)
计量
- 文章访问数: 1
- HTML全文浏览量: 0
- PDF下载量: 1
下载:
