基于时序PolSAR影像与决策树模型的油菜物候期识别

doi:10.3969/j.issn.1004-1524.2021.11.14

浙江农业学报 ›› 2021, Vol. 33 ›› Issue (11): 2116-2127.DOI: 10.3969/j.issn.1004-1524.2021.11.14

基于时序PolSAR影像与决策树模型的油菜物候期识别

李诗涛^a(), 张王菲^b^,^*(), 赵丽仙^b, 王熙媛^b

a.西南林业大学地理与生态旅游学院,云南昆明 650224
b.西南林业大学林学院,云南昆明 650224

收稿日期:2020-12-15 出版日期:2021-11-25 发布日期:2021-11-26
作者简介:*张王菲,E-mail: mekmzwf@163.com
李诗涛(1994—),男,湖南吉首人,硕士,主要从事农业微波遥感应用研究。E-mail: lst_123@163.com
通讯作者: 张王菲
基金资助:
国家自然科学基金(31860240);国家自然科学基金(42161059);云南省万人计划青年拔尖人才(80201444);云南省教育厅科学研究基金(2019J0182)

Phenological period identification of oilseed rape based on time-series PolSAR image and decision tree model

LI Shitao^a(), ZHANG Wangfei^b^,^*(), ZHAO Lixian^b, WANG Xiyuan^b

a. School of Geography and Ecotourism, Southwest Forestry University, Kunming 650224, China
b. Forest College, Southwest Forestry University, Kunming 650224, China

Received:2020-12-15 Online:2021-11-25 Published:2021-11-26
Contact: ZHANG Wangfei

摘要/Abstract

摘要：

作物物候期识别是农情遥感监测的重要内容,及时准确识别作物物候期,对有效评估作物生长趋势、提高农情信息化管理水平有重要意义。提出了基于时间序列全极化合成孔径雷达(polarimetric synthetic aperture radar, PolSAR)数据结合决策树模型的油菜物候期识别方法。首先,采用3种极化分解方法提取PolSAR极化参数,并分析各极化参数对油菜物候期的动态响应规律;其次,基于各极化分解方法提取的参数建立决策树模型,并对油菜物候期进行分类识别;最后,采用基于混淆矩阵的方法对油菜物候期识别结果进行精度评价。采用5期Radarsat-2 PolSAR数据和地面物候观测数据进行实验验证。结果表明:提取的PolSAR参数中对物候期变化较为敏感的参数有H/A/alpha分解中的散射角(Alpha)、特征值(L2、L3)、伪熵(P2)、目标方位角(Beta1)参数,Freeman-Durden分解中的地面散射(Ground)和奇次散射(Odd)参数,Yamaguchi分解中的奇次散射(Odd_Y)和螺旋体散射(Helix)参数;决策树模型对油菜物候期识别结果较为准确,识别结果中组合3种极化分解方法提取参数建立的原始决策树模型分类总体精度最高,达94%。总体上,PolSAR极化分解参数对油菜物候期变化比较敏感,决策树模型能有效识别油菜物候期。

关键词: 油菜, 物候期识别, Radarsat-2, 极化分解, 决策树

Abstract:

Crop phenological period identification plays an important role in agricultural condition monitoring. Timely and accurate crop phenological period identification is of great significance for evaluating crop growth trend and improving the agricultural information management level effectively.In this study, we selected oilseed rape as an example and proposed a crop phenological period identification method through polarimetric synthetic aperture radar (PolSAR) data and decision tree algorithms. First, polarimetric SAR parameters were extracted through three popular polarimetric decomposition methods. Their dynamic responses to oilseed rape phenological periods were also analyzed. Then, the parameters extracted by the three polarimetric decomposition methods were used to train and validate the decision tree models, five oilseed rape phenological periods were identified. Finally, confusion matrices were used to verify feasibility of the constructed decision models.The results showed that polarimetric SAR decomposition parameters, including scattering angle(Alpha), eigenvalue(L2, L3), pseudo-entropy(P2) and target azimuth (Beta1) parameters from H/A/alpha decomposition method; ground scattering (Ground) and odd scattering (Odd) parameters from Freeman-Durden decomposition method; odd scattering (Odd_Y) and helix scattering (Helix) parameters from Yamaguchi decomposition method showed great sensitivity to changes of oilseed rape phenological period.The decision tree models were more accurate to classify the phenology of rapeseed. Among the results, primitive decision tree model established based on the combination of extracted parameters from three polarimetric decomposition methods had the highest classification accuracy, the overall classification accuracy was 94%. The results also showed the sensitivity of PolSAR parameters to phenological changes of oilseed rape and the effectiveness of decision tree model in identification of oilseed rape phenological period.

Key words: rape, phenological identification, Radarsat-2, polarimetric decomposition, decision-tree

中图分类号:

S565.4
TP75

李诗涛, 张王菲, 赵丽仙, 王熙媛. 基于时序PolSAR影像与决策树模型的油菜物候期识别[J]. 浙江农业学报, 2021, 33(11): 2116-2127.

LI Shitao, ZHANG Wangfei, ZHAO Lixian, WANG Xiyuan. Phenological period identification of oilseed rape based on time-series PolSAR image and decision tree model[J]. Acta Agriculturae Zhejiangensis, 2021, 33(11): 2116-2127.

图/表 10

参考文献 27

[1]	王汉中. 我国油菜产需形势分析及产业发展对策[J]. 中国油料作物学报, 2007, 29(1):101-105.
	WANG H Z. Strategy for rapeseed industry development based on the analysis of rapeseed production and demand in China[J]. Chinese Journal of Oil Crop Sciences, 2007, 29(1):101-105.(in Chinese with English abstract)
[2]	李颖, 陈怀亮, 李耀辉, 等. 一种利用MODIS数据的夏玉米物候期监测方法[J]. 应用气象学报, 2018, 29(1):111-119.
	LI Y, CHEN H L, LI Y H, et al. A method for summer maize phenology monitoring by MODIS data[J]. Journal of Applied Meteorological Science, 2018, 29(1):111-119.(in Chinese with English abstract)
[3]	张晓萱, 崔耀平, 刘素洁, 等. 自然植被物候遥感提取精度评估[J]. 生态学杂志, 2019, 38(5):1589-1599.
	ZHANG X X, CUI Y P, LIU S J, et al. Evaluation of the accuracy of phenology extraction methods for natural vegetation based on remote sensing[J]. Chinese Journal of Ecology, 2019, 38(5):1589-1599.(in Chinese with English abstract)
[4]	MATTIA F, LE TOAN T, PICARD G, et al. Multitemporal C-band radar measurements on wheat fields[J]. IEEE Transactions on Geoscience and Remote Sensing, 2003, 41(7):1551-1560. DOI URL
[5]	ADAMS J R, BERG A A, MCNAIRN H, et al. Sensitivity of C-band SAR polarimetric variables to unvegetated agricultural fields[J]. Canadian Journal of Remote Sensing, 2013, 39(1):1-16. DOI URL
[6]	CLOUDE S. Polarisation: applications in remote sensing[M]. Oxford: Oxford University Press, 2009.
[7]	LE TOAN T, BEAUDOIN A, RIOM J, et al. Relating forest biomass to SAR data[J]. IEEE Transactions on Geoscience and Remote Sensing, 1992, 30(2):403-411. DOI URL
[8]	LIU C, SHANG J L, VACHON P W, et al. Multiyear crop monitoring using polarimetric RADARSAT-2 data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(4):2227-2240. DOI URL
[9]	XU J, LI Z, TIAN B S, et al. Polarimetric analysis of multi-temporal RADARSAT-2 SAR images for wheat monitoring and mapping[J]. International Journal of Remote Sensing, 2014, 35(10):3840-3858. DOI URL
[10]	LOPEZ-SANCHEZ J M, VICENTE-GUIJALBA F, BALLESTER-BERMAN J D, et al. Polarimetric response of rice fields at C-band: analysis and phenology retrieval[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(5):2977-2993. DOI URL
[11]	杨浩. 基于时间序列全极化与简缩极化SAR的作物定量监测研究[D]. 北京: 中国林业科学研究院, 2015.
	YANG H. Study on quantitative crop monitoring by time series of fully polarimetric and compact polarimetric SAR imagery[D]. Beijing: Chinese Academy of Forestry, 2015. (in Chinese with English abstract)
[12]	YANG Z, LI K, LIU L, et al. Rice growth monitoring using simulated compact polarimetric C band SAR[J]. Radio Science, 2014, 49(12):1300-1315. DOI URL
[13]	MCNAIRN H, JIAO X F, PACHECO A, et al. Estimating canola phenology using synthetic aperture radar[J]. Remote Sensing of Environment, 2018, 219:196-205. DOI URL
[14]	DEY S, BHATTACHARYA A, RATHA D, et al. Novel clustering schemes for full and compact polarimetric SAR data: an application for rice phenology characterization[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 169:135-151. DOI URL
[15]	SATALINO G, BALENZANO A, MATTIA F, et al. C-band SAR data for mapping crops dominated by surface or volume scattering[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(2):384-388. DOI URL
[16]	张亚红, 张王菲, 姬永杰, 等. 油菜简缩极化参数响应及其长势参数反演[J]. 江苏农业科学, 2018, 46(15):170-175.
	ZHANG Y H, ZHANG W F, JI Y J, et al. Reduced polarization parameter response of rapeseed and its inversion of growth parameters[J]. Jiangsu Agricultural Sciences, 2018, 46(15):170-175.(in Chinese)
[17]	ERTEN E, ROSSI C, YUZUGULLU O, et al. Phenological growth stages of paddy rice according to the BBCH scale and SAR images[C/OL]// [2020-12-15].2014 IEEE Geoscience and Remote Sensing Symposium. IEEE, 2014.https://www.researchgate.net/publication/269286721_Phenological_growth_stages_of_paddy_rice_according_to_the_BBCH_scale_and_SAR_images.
[18]	孙丹, 马久云. 各向异性自适应滤波在合成孔径雷达图像中对斑点噪声的去除[J]. 计算机光盘软件与应用, 2014, 17(12):133-135.
	SUN D, MA J Y. Anisotropic adaptive filtering for speckle noise removal in synthetic aperture radar images[J]. Computer CD Software and Applications, 2014, 17(12):133-135.(in Chinese)
[19]	李坤, 邵芸, 张风丽. 基于RadarSat-2全极化数据的水稻识别[J]. 遥感技术与应用, 2012, 27(1):86-93.
	LI K, SHAO Y, ZHANG F L. Extraction of rice based on quad-polarization RadarSat-2 data[J]. Remote Sensing Technology and Application, 2012, 27(1):86-93.(in Chinese with English abstract)
[20]	FREEMAN A, DURDEN S L. A three-component scattering model for polarimetric SAR data[J]. IEEE Transactions on Geoscience and Remote Sensing, 1998, 36(3):963-973. DOI URL
[21]	CLOUDE S R, POTTIER E. An entropy based classification scheme for land applications of polarimetric SAR[J]. IEEE Transactions on Geoscience and Remote Sensing, 1997, 35(1):68-78. DOI URL
[22]	YAMAGUCHI Y, MORIYAMA T, ISHIDO M, et al. Four-component scattering model for polarimetric SAR image decomposition[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(8):1699-1706. DOI URL
[23]	HAN J W. Data mining: concepts and techniques[M]. San Francisco: Morgan Kaufmann Publishers Inc. 2005.
[24]	张继超, 周沛希, 张永红. 面向对象的多种特征极化SAR决策树分类方法[J]. 测绘科学, 2019, 44(10):181-189.
	ZHANG J C, ZHOU P X, ZHANG Y H. Object-oriented decision tree classification method of multi-feature polarimetric SAR[J]. Science of Surveying and Mapping, 2019, 44(10):181-189.(in Chinese with English abstract)
[25]	WANG H Q, MAGAGI R, GOÏTA K, et al. Crop phenology retrieval via polarimetric SAR decomposition and random forest algorithm[J]. Remote Sensing of Environment, 2019, 231:111234. DOI URL
[26]	CANISIUS F, SHANG J L, LIU J G, et al. Tracking crop phenological development using multi-temporal polarimetric Radarsat-2 data[J]. Remote Sensing of Environment, 2018, 210:508-518. DOI URL
[27]	LOPEZ-SANCHEZ J M, CLOUDE S R, BALLESTER-BERMAN J D. Rice phenology monitoring by means of SAR polarimetry at X-band[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(7):2695-2709. DOI URL

生长发育时期 Growth period	播后时间 Days after sowing/d	物候阶段 Phenological phase
苗期Growth period	1-15	S1
蕾薹期Grey moss period	16-39	S2
花期Flowering period	40-63	S3
角果成熟期Ripening stage of pod	64-87	S4
成熟衰落期Maturity and decay period	88-110	S5

生长发育时期 Growth period	播后时间 Days after sowing/d	物候阶段 Phenological phase
苗期Growth period	1-15	S1
蕾薹期Grey moss period	16-39	S2
花期Flowering period	40-63	S3
角果成熟期Ripening stage of pod	64-87	S4
成熟衰落期Maturity and decay period	88-110	S5

分解方法 Decomposition methods	分解参数 Decomposition parameters	描述 Description
H/A/alpha分解 H/A/alpha decomposition	Alpha、Anisotropy、Entropy、 Lambda (Span)	基于H/A/alpha的参数:目标散射角、反熵、散射熵、散射特征值(功率) Parameters based on H/A/alpha: target scattering angle, inverse entropy, scattering entropy, scattering eigenvalue (power)
	Alpha1、Alpha2、Alpha3;Beta1、 Beta2、Beta3;Delta1、Delta2、 Delta3;Gamma1、Gamma2、 Gamma3	基于特征向量的参数:3种散射机制对应的散射角,目标方位角,相位角差 Parameters based on eigenvectors: scattering angles corresponding to the three scattering mechanisms, target azimuth, phase angle difference
	L1、L2、L3;P1、P2、P3;Pedestal; RVI	基于特征值的参数:3种散射机制对应的特征值,3种散射机制对应的熵,极化特征的基准高度,雷达植被指数 Parameters based on eigenvalues: eigenvalues corresponding to the three scattering mechanisms, entropy corresponding to the three scattering mechanisms, reference height of the polarization characteristics, radar vegetation index (RVI)
Freeman-Durden 二、三分量分解 Freeman-Durden two-and three-component decomposition	Ground、Canopy、Odd、Dbl、Vol	地面散射、冠层散射分量、奇次散射、偶次散射与体散射分量 Ground scattering, canopy scattering component, odd scattering, even scattering and volume scattering component
Yamaguchi四分量分解 Yamaguchi four- component decomposition	Odd_Y、Dbl_Y、Vol_Y、Helix	奇次散射、偶次散射、体散射与螺旋体散射分量 Odd scattering, even scattering, volume scattering and helix scattering components

分解方法 Decomposition methods	分解参数 Decomposition parameters	描述 Description
H/A/alpha分解 H/A/alpha decomposition	Alpha、Anisotropy、Entropy、 Lambda (Span)	基于H/A/alpha的参数:目标散射角、反熵、散射熵、散射特征值(功率) Parameters based on H/A/alpha: target scattering angle, inverse entropy, scattering entropy, scattering eigenvalue (power)
	Alpha1、Alpha2、Alpha3;Beta1、 Beta2、Beta3;Delta1、Delta2、 Delta3;Gamma1、Gamma2、 Gamma3	基于特征向量的参数:3种散射机制对应的散射角,目标方位角,相位角差 Parameters based on eigenvectors: scattering angles corresponding to the three scattering mechanisms, target azimuth, phase angle difference
	L1、L2、L3;P1、P2、P3;Pedestal; RVI	基于特征值的参数:3种散射机制对应的特征值,3种散射机制对应的熵,极化特征的基准高度,雷达植被指数 Parameters based on eigenvalues: eigenvalues corresponding to the three scattering mechanisms, entropy corresponding to the three scattering mechanisms, reference height of the polarization characteristics, radar vegetation index (RVI)
Freeman-Durden 二、三分量分解 Freeman-Durden two-and three-component decomposition	Ground、Canopy、Odd、Dbl、Vol	地面散射、冠层散射分量、奇次散射、偶次散射与体散射分量 Ground scattering, canopy scattering component, odd scattering, even scattering and volume scattering component
Yamaguchi四分量分解 Yamaguchi four- component decomposition	Odd_Y、Dbl_Y、Vol_Y、Helix	奇次散射、偶次散射、体散射与螺旋体散射分量 Odd scattering, even scattering, volume scattering and helix scattering components

精度Accuracy	S1	S2	S3	S4	S5
制图精度	90.28	95.79	94.74	94.74	89.47
Mapping accuracy
用户精度	94.20	92.86	90.90	97.83	90.42
User accuracy

基于时序PolSAR影像与决策树模型的油菜物候期识别

Phenological period identification of oilseed rape based on time-series PolSAR image and decision tree model

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 27

相关文章 15

编辑推荐

Metrics

本文评价

物候期 Phenological phase	S1	S2	S3	S4	S5	总计 Total
S1	65	7	0	0	0	72
S2	4	91	0	0	0	95
S3	0	0	90	0	5	95
S4	0	0	1	90	4	95
S5	0	0	8	2	85	95
总计Total	69	98	99	92	94

决策树模型 Decision tree model	极化分解方法Polarization decomposition method
决策树模型 Decision tree model	Freeman-Durden分解 Freeman decomposition	Yamaguchi分解 Yamaguchi decomposition	H/A/alpha分解 H/A/alpha decomposition	3种分解组合 Three kinds of decomposition synthesis
原始决策树Primitive decision tree	89.45	89.34	93.40	94.00
minleaf决策树Minleaf decision tree	82.96	84.87	88.63	89.54
剪枝决策树Pruning decision tree	86.13	87.83	92.21	91.61

[1]	董智超, 岳宁燕, 吕魏, 余晓燚, 郑凯文, 宋海星, 陈海飞. 高、低含油量油菜品种的产量、品质和氮利用效率对施氮量的响应差异[J]. 浙江农业学报, 2025, 37(5): 998-1008.
[2]	裴大妹, 赵洪平, 王龙, 李华欣, 赵志, 肖麓. 白菜型油菜分枝角度主基因+多基因混合遗传模型分析[J]. 浙江农业学报, 2025, 37(4): 745-753.
[3]	陈威, 朱怡航, 顾清, 林宝刚, 张小斌. 基于机器视觉和YOLOv5的油菜角果表型参数分析[J]. 浙江农业学报, 2024, 36(6): 1379-1388.
[4]	沈宇峰, 罗海峰, 吴明亮, 官春云. 油菜脱出物双向切流喂入式旋风分离清选装置的设计与试验[J]. 浙江农业学报, 2023, 35(5): 1178-1186.
[5]	姚彦林, 马骊, 刘丽君, 蒲媛媛, 李学才, 王旺田, 方彦, 孙万仓, 武军艳. 白菜型油菜开花调控基因BrFT的生物信息学特性和表达分析[J]. 浙江农业学报, 2023, 35(5): 992-1000.
[6]	徐洋, 任奕林, 王浩杰, 黄秋航, 邢博源, 曹红亮. 不同制备条件下油菜秸秆生物炭用作缓释载体的综合评价[J]. 浙江农业学报, 2023, 35(4): 893-902.
[7]	许耀照, 曾秀存, 王振朝, 党仕卓, 刘永晶. NaCl胁迫对冬油菜种子萌发和生理特性的影响[J]. 浙江农业学报, 2023, 35(3): 499-508.
[8]	郎春秀, 刘仁虎, 郑滔, 王伏林, 石江华, 胡张华, 吴关庭. 化学诱变获得甘蓝型油菜矮秆突变新种质[J]. 浙江农业学报, 2023, 35(11): 2516-2524.
[9]	李虹桥, 赖莹, 母娜, 严红梅, 汤维群, 蒋小灵, 高雯, 吴永成. 密度对不同株高油菜冠层结构与群体光合能力的影响[J]. 浙江农业学报, 2022, 34(3): 419-427.
[10]	周欣兴, 赵林, 张文杰, 谭昌伟, 李刚波, 石梦云, 张婷, 杨峰. 基于Sentinel-2多时相影像的果树种植区遥感提取[J]. 浙江农业学报, 2022, 34(12): 2767-2777.
[11]	冯玮, 李朋朋, 宋鹏. 甘蓝型油菜Kunitz蛋白酶抑制剂的异源表达与理化特征分析[J]. 浙江农业学报, 2022, 34(1): 112-119.
[12]	陈纪鹏, 刘小林, 李生强, 刘显军, 胡月清, 陈桃. 白菜型油菜黄芽白与甘蓝型油菜湘油15种间杂交及其杂种后代的遗传学特征[J]. 浙江农业学报, 2021, 33(7): 1170-1176.
[13]	练华山, 李欣欣, 林立金, 廖明安. 表油菜素内酯对夏黑葡萄幼苗生长的影响[J]. 浙江农业学报, 2021, 33(10): 1889-1896.
[14]	熊廷浩, 黄益国, 周旋, 鲁艳红, 资涛, 胡宇倩, 宋海星. 湖南省油菜主产区土壤养分含量与重金属污染风险评价[J]. 浙江农业学报, 2021, 33(10): 1904-1912.
[15]	张金然, 李存超, 李询, 孙国峻, 何瑞银, 魏清. 基于GIS的油菜播种控制系统设计与试验[J]. 浙江农业学报, 2020, 32(3): 518-526.