[1]张传波,李卫国,王晶,等.波段反射率和植被指数结合的作物生长季农田土壤水分估测[J].江苏农业学报,2022,38(01):111-118.[doi:doi:10.3969/j.issn.1000-4440.2022.01.013]
　ZHANG Chuan-bo,LI Wei-guo,WANG Jing,et al.Estimation of farmland soil moisture in crop growing season based on combination of band reflectance and vegetation index[J].,2022,38(01):111-118.[doi:doi:10.3969/j.issn.1000-4440.2022.01.013]
点击复制

波段反射率和植被指数结合的作物生长季农田土壤水分估测()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
38
期数:
2022年01期
页码:
111-118
栏目:
农业信息工程
出版日期:
2022-02-28

文章信息/Info

Title:
Estimation of farmland soil moisture in crop growing season based on combination of band reflectance and vegetation index
作者:
张传波1; 2; 李卫国1; 2; 王晶2; 李伟3; 马廷淮4
（1.江苏大学农业工程学院，江苏镇江212013；2.江苏省农业科学院农业信息研究所，江苏南京210014；3.江苏大学流体机械工程技术研究中心，江苏镇江212013；4.南京信息工程大学，江苏南京210044）
Author(s):
ZHANG Chuan-bo1; 2; LI Wei-guo1; 2; WANG Jing2; LI Wei3; MA Ting-huai4
（1.College of Agricultural Engineering, Jiangsu University，Zhenjiang 212013，China；2.Institute of Agricultural Information，Jiangsu Academy of Agricultural Sciences，Nanjing 210014，China；3.Fluid Machinery Engineering Technology Research Center，Jiangsu University，Zhenjiang 212013，China；4.Nanjing University of Information Science and Technology，Nanjing 210044，China）
关键词:
农田土壤水分含量; 作物生长; 多光谱波段反射率; 植被指数; 神经网络
Keywords:
soil moisture content in farmland; crop growth; multi-spectral band reflectance; vegetation index; neural network
分类号:
S127
DOI:
doi:10.3969/j.issn.1000-4440.2022.01.013
文献标志码:
A
摘要:
为了建立快速、有效的农田土壤水分含量（SMCF）遥感估测方法，在江苏省连云港市东海县、泰州市兴化市和盐城市大丰区布设SMCF遥感估测试验。在获取作物冠层近红外波段反射率（Near-infrared bandreflectance，Rnir）、红光波段反射率（Red bandreflectance，Rred）以及SMCF的基础上，通过分析波段反射率和植被指数多个遥感光谱特征指标与SMCF之间的相关性，构建基于BP神经网络的SMCF遥感估测模型，并与多元线性回归模型估测精度进行比较。结果表明，Rnir、Rred、差值植被指数（DVI）和比值植被指数（RVI）与SMCF间呈正相关关系，归一化差值植被指数（NDVI）和SMCF间呈负相关关系，各指标与SMCF的相关性从高到低依次为Rnir> DVI>Rred> NDVI>RVI，其中Rnir与SMCF相关性最高，相关系数为0.765。利用BP神经网络建立的SMCF估测模型的决定系数（R2）为0.928，均方根误差（RMSE）为3.61%，平均相对误差（ARE）为9.07%。利用多元线性回归方法建立的SMCF估测模型的R2为0.660，RMSE为7.65%，ARE为21.43%。二者相比可以看出，BP神经网络SMCF估测模型的估测效果明显优于多元线性回归模型，说明将神经网络算法与波段反射率和植被指数结合建模，可以有效提高SMCF的估测精度。
Abstract:
To set up a fast and effective remote sensing estimation method for soil moisture content in farmland (SMCF), remote sensing estimation experiments of SMCF were designed in Donghai County of Lianyungang City, Xinghua City of Taizhou City and Dafeng District of Yancheng City, Jiangsu province. After acquisition of canopy near-infrared band reflectance (Rnir) and red band reflectance (Rred) of crops and SMCF, correlation between multiple indicators of remote sensing spectral features such as band reflectance, vegetation index and SMCF were analyzed, and a remote sensing estimation model of SMCF based on back propagation (BP) neural network was constructed. Besides, the estimation accuracy was compared with multiple linear regression model. The results showed that, Rnir, Rred, difference vegetation index (DVI) and ratio vegetation index (RVI) were in positive relationships with SMCF. The correlation coefficients between different indexes and SMCF were sequenced as follows: Rnir>DVI>Rred>NDVI>RVI. Among them, Rnir had the highest correlation with SMCF, with a correlation coefficient of 0.765. The determination coefficient (R2) of SMCF estimation model established by BP neural network was 0.928, the root mean square error (RMSE) was 3.61%, and the average relative error (ARE) was 9.07%. R2, RMSE and ARE of the SMCF estimation model established by multiple linear regression method were 0.660, 7.65% and 21.43%, respectively. By comparing the two models, it can be seen that the estimation effect of BP neural network model on SMCF is obviously better than multiple linear regression model, which shows that the estimation accuracy of SMCF can be effectively improved by combining the neural network algorithm with band reflectivity and vegetation index.

参考文献/References:

[1]刘凯，张耗，张慎凤，等. 结实期土壤水分和灌溉方式对水稻产量与品质的影响及其生理原因[J]. 作物学报，2008，34(2)：268-276.
[2]陈超,李荣,李芬,等.不同沟垄覆盖下土壤水热效应对旱作马铃薯生长及产量的影响[J].排灌机械工程学报,2020,38(11):1160-1166.
[3]王斌,何文寿,耿世杰.粉垄耕作对土壤水分利用效率和马铃薯产量的影响[J].江苏农业科学,2020,48(21):93-96.
[4]高佳,张宏斌,张恒嘉,等.绿洲灌区膜下滴灌调亏对辣椒品质及产量的影响[J].排灌机械工程学报,2021,39(4):404-409.
[5]王唯逍，刘小军，田永超，等. 不同土壤水分处理对水稻光合特性及产量的影响[J]. 生态学报，2012，32(22)：7053-7060.
[6]赵嘉涛,马玉诏,范艳丽,等.生物可降解地膜对棉花产量及水分利用效率的影响[J].排灌机械工程学报,2021,39(1):96-101.
[7]MANABE S，SMAGORINSKY J，STRICKLER R F. Simulated climatology of a general circulation model with a hydrologic CYCLE1[J]. Monthly Weather Review，1965，93(12)：155-169.
[8]BAIER W，ROBERTSON G W. A new versatile soil moisture budget[J]. Canadian Journal of Plant Science，1966，46(3)：299-315.
[9]徐梅，隋吉东，刘振忠.土壤水分含量的理论分析及预测模型[J]. 生物数学学报，1999, 14 (1)：95-99.
[10]邵晓梅，严昌荣，徐振剑.土壤水分监测与模拟研究进展[J]. 地理科学进展，2004(3)：58-66.
[11]尹健康，陈昌华，邢小军，等. 基于BP神经网络的烟田土壤水分预测[J]. 电子科技大学学报，2010，39(6)：891-895.
[12]刘建栋，王馥棠，于强，等. 华北地区冬小麦叶片光合作用模型在农业干旱预测中的应用研究[J]. 应用气象学报，2003，14(4)：469-478.
[13]ARMAND R，WAMBEKE V. The Newhall simulation model for estimating soil moisture & temperature regimes [D].New York：Cornell University，Ithaca，2000.
[14]尚松浩，雷志栋，杨诗秀. 冬小麦田间墒情预报的经验模型[J].农业工程学报，2000, 16 (5)：31-33.
[15]GONG Y S，CAO Q H，SUN Z J. The effects of soil bulk density，clay content and temperature on soil water content measurement using time-domain reflectometry[J].Hydrological Processes，2003，17(18)：3601-3614.
[16]熊世为，李卫国，贾天山，等.基于HJ卫星数据的土壤含水量反演及其旱情预测[J].江苏农业学报，2014，30(5)：1044-1050.
[17]WHALLEY W R，LEEDS-HARRISON P B，BOWMAN G E. Estimation of soil moisture status using near infrared reflectance[J]. Hydrological Processes，1991，5(3)：321-327.
[18]HOSSEINI M，SARADJIAN M R. Multi-index-based soil moisture estimation using MODIS images[J]. International Journal of Remote Sensing，2011，32(21)：6799-6809.
[19]刘洪斌，武伟，魏朝富. 基于神经网络的土壤水分预测建模研究[J]. 水土保持学报，2003，17(5)：59-62.
[20]尚松浩，毛晓敏，雷志栋，等. 冬小麦田间墒情预报的BP神经网络模型[J]. 水利学报，2002，33(4)：60-63.
[21]ELSHORBAGY A，PARASURAMAN K. On the relevance of using artificial neural networks for estimating soil moisture content[J]. Journal of Hydrology，2008，362(1/2)：1-18.
[22]ADEYEMI O，GROVE I，PEETS S，et al. Dynamic neural network modelling of soil moisture content for predictive irrigation scheduling[J]. Sensors，2018，18(10)：1-22.
[23]LI W G，LIU Y，CHEN H，et al. Estimation model of winter wheat disease based on meteorological factors and spectral information[J]. Food Production Processing and Nutrition，2020，2(1)：77-82.
[24]李卫国，王纪华，赵春江，等. 冬小麦抽穗期长势遥感监测的初步研究[J]. 江苏农业学报，2007，23(5)：499-500.
[25]JORDAN C F. Derivation of leaf‐area index from quality of light on the forest floor[J]. Ecology，1969，50(4)：663-666.
[26]林子晶，李卫国，申双和，等. HJ星和GF1号数据在水稻种植面积提取中的应用[J].江苏农业学报，2016，32(1)：111-117.
[27]王嵘冰，徐红艳，李波，等. BP神经网络隐含层节点数确定方法研究[J].计算机技术与发展，2018，28(4)：31-35.
[28]汪四水，张孝羲.基于神经网络的稻纵卷叶螟长期预测[J].植物保护学报，2000, 27(4)：313-316.
[29]李卫国，黄文江，董莹莹，等.基于温湿度与遥感植被指数的冬小麦赤霉病估测[J].农业工程学报，2017，33(23)：203-210.
[30]刘平. 人工神经网络用于化学数据解析的研究(Ⅰ)：逼近规律与过拟合[J]. 高等学校化学学报，1996，20(6)：861-865.
[31]李俭川，秦国军，温熙森，等. 神经网络学习算法的过拟合问题及解决方法[J]. 振动，测试与诊断，2002(4)：16-20,76.
[32]ZHANG R H，SUN X M，ZHU Z L，et al. A remote sensing model for monitoring soil evaporation based on differential thermal inertia and its validation[J]. Science in China. Series D，Earth sciences，2003，46(4)：342-355.
[33]余涛，田国良. 热惯量法在监测土壤表层水分变化中的研究[J]. 遥感学报，1997，1(1)：24-31.
[34]GOWARD S N，XUE Y，CZAJKOWSKI K P. Evaluating land surface moisture conditions from the remotely sensed temperature/vegetation index measurements：an exploration with the simplified simple biosphere model[J]. Remote Sensing of Environment，2002，79(2/3)：225-242.
[35]MALLICK K，BHATTACHARYA B K，PATEL N K. Estimating volumetric surface moisture content for cropped soils using a soil wetness index based on surface temperature and NDVI[J]. Agricultural & Forest Meteorology，2009，149(8)：1327-1342.
[36]WIGNERON J P，WALDTEUFEL P，CHANZY A，et al. Two-dimensional microwave interferometer retrieval capabilities over land surfaces (SMOS Mission)[J]. Remote Sensing of Environment，2017，73(3)：270-282.
[37]NOTARNICOLA C，ANGIULLI M，POSA F. Soil moisture retrieval from remotely sensed data：neural network approach versus Bayesian method[J]. IEEE Transactions on Geoscience & Remote Sensing，2008，46(2)：547-557.
[38]张坤,刘永强,阿依尼格尔·亚力坤,等.塔克拉玛干沙漠腹地土壤热通量的陆面过程与卫星遥感研究[J].江苏农业科学,2020,48(20):256-264.

备注/Memo

备注/Memo:
收稿日期：2021-05-13基金项目：国家重点研发计划项目（2021YFE0104400）；江苏省农业科技自主创新资金项目[CX（20）2037]作者简介：张传波（1993-），男，安徽蚌埠人，硕士研究生，研究方向为农业遥感应用研究。（E-mail）1003176295@qq.com通讯作者：李卫国,（E-mail）jaaslwg@126.com
更新日期/Last Update: 2022-03-04