[1]张永亮,汪泓,肖玖军,等.基于高光谱的山区耕地土壤有机质含量估测[J].江苏农业学报,2024,(01):112-120.[doi:doi:10.3969/j.issn.1000-4440.2024.01.012]
　ZHANG Yong-liang,WANG Hong,XIAO Jiu-jun,et al.Estimation of soil organic matter content in mountain farmland based on hyperspectral data[J].,2024,(01):112-120.[doi:doi:10.3969/j.issn.1000-4440.2024.01.012]
点击复制

基于高光谱的山区耕地土壤有机质含量估测()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2024年01期
页码:
112-120
栏目:
农业信息工程
出版日期:
2024-01-30

文章信息/Info

Title:
Estimation of soil organic matter content in mountain farmland based on hyperspectral data
作者:
张永亮1; 汪泓1; 肖玖军2; 3; 李可相2; 3; 王宇1; 邢丹4
(1.贵州大学矿业学院,贵州贵阳550025；2.贵州省山地资源研究所,贵州贵阳550001；3.贵州省土地绿色整治工程研究中心,贵州贵阳550001；4.贵州省农业科学院辣椒研究所,贵州贵阳550009)
Author(s):
ZHANG Yong-liang1; WANG Hong1; XIAO Jiu-jun2; 3; LI Ke-xiang2; 3; WANG Yu1; XING Dan4
(1.Mining College of Guizhou University, Guiyang 550025, China;2.Guizhou Provincial Institute of Mountain Resources, Guiyang 550001,China;3.Guizhou Province Land Green Remediation Engineering Research Center, Guiyang 550001, China;4.Chili Research Institute, Guizhou Academy of Agricultural Sciences, Guiyang 550009, China)
关键词:
土壤有机质; 高光谱; 山区耕地; 一阶微分; BP神经网络
Keywords:
soil organic matter; hyperspectral; mountainous farmland; first-order differential; BP neural network
分类号:
S153
DOI:
doi:10.3969/j.issn.1000-4440.2024.01.012
文献标志码:
A
摘要:
以贵州省典型山区耕地土壤高光谱数据为研究对象,基于光谱变换法和机器学习原理构建贵州省山区耕地土壤有机质(SOM)含量估算模型。于2020年8月至2021年3月在贵州省13个县(区、市)采集了120个土壤样品,检测土壤可见光-近红外波段光谱信息,利用5种光谱数据变换(原始光谱、一阶微分、二阶微分、倒数对数的一阶微分、连续统去除)和4类模型(偏最小二乘回归、支持向量机、随机森林和BP神经网络)组合出不同土壤有机质含量的预测模型,按照3∶1选择训练样本和测试样本以估算山区SOM含量。结果表明,一阶微分数据变换与山区SOM含量的相关性较高,相关系数最高达到-0.635；反演模型中,基于一阶微分光谱变换构建的BP神经网络模型精度最高,训练集、测试集的决定系数(R2)分别为0.845、0.838,测试集均方根误差(RMSE)为3.452,相对分析误差(RPD)达到2.470,其次是RF、PLSR模型的RPD较高,SVM模型的RPD最低。光谱数据变换中一阶微分法能极大程度提取出山区耕地的SOM含量信息,BP神经网络模型是估算山区SOM含量的最优模型,本研究结果可为贵州省山区耕地土壤肥力的监测以及农业生产提供理论参考。
Abstract:
Taking the hyperspectral data of cultivated land in typical mountainous areas of Guizhou province as the research object, a model for estimating soil organic matter (SOM) content in mountainous areas of Guizhou province was established by using spectral transformation method and machine learning. From August 2020 to March 2021, 120 soil samples were collected from 13 counties and cities of Guizhou province, and the visible near-infrared spectral information of soil was detected. Five spectral data transformations (original spectra, first-order differential, second-order differential, first-order differential of reciprocal logarithm, continuum removal) and four types of models (partial least squares regression, support vector machine, random forest and BP neural network) were used to combine different soil organic matter content prediction models. The training samples and test samples were selected according to the ratio of 3∶1 to estimate the SOM content in mountain area. The correlation between the first-order differential data transformation and the SOM content in mountain area was high, and the highest correlation coefficient was -0.635. In the inversion model, the BP neural network model based on the first-order differential spectral transformation had the highest accuracy. The determination coefficients (R2) of the training set and the test set were 0.845 and 0.838, respectively. The root mean square error (RMSE) of the test set was 3.452. The relative analysis error (RPD) reached 2.470, followed by RF, PLSR and SVM. The first-order differential method in spectral data transformation could greatly extract the SOM content information of mountain cultivated land. The BP neural network model was the optimal model for estimating the SOM content in mountain areas. The results of this study can provide theoretical reference for the monitoring of soil fertility and agricultural production in mountainous areas of Guizhou province.

参考文献/References:

[1]贾文涛. 从土地整治向国土综合整治的转型发展[J]. 中国土地,2018(5):16-18.
[2]张霄羽,姚艳敏,颜祥照. 中红外光谱土壤有机质含量估测研究进展[J]. 中国土壤与肥料,2021(4):327-336.
[3]石朴杰,王世东,张合兵,等. 基于高光谱的复垦农田土壤有机质含量估测[J]. 土壤,2018,50(3):558-565.
[4]XIE R, XIAO H H. Application of remote sensing in the estimation of soil organic matter content[J]. Chemical Engineering Transactions,2018,66. DOI:10.3303/CET1866079.
[5]向红英,柳维扬,彭杰,等. 基于连续统去除法的南疆水稻土有机质含量预测[J]. 土壤,2016,48(2):389-394.
[6]韩兆迎,朱西存,刘庆,等. 黄河三角洲土壤有机质含量的高光谱反演[J]. 植物营养与肥料学报,2014,20(6):1545-1552.
[7]勾宇轩,赵云泽,李勇,等. 基于CWT-sCARS的东北旱作农田土壤有机质高光谱反演[J]. 农业机械学报,2022,53(3):331-337.
[8]南锋,朱洪芬,毕如田. 黄土高原煤矿区复垦农田土壤有机质含量的高光谱预测[J]. 中国农业科学,2016,49(11):2126-2135.
[9]NAWAR S, BUDDENBAUM H, HILL J, et al. Estimating the soil clay content and organic matter by means of different calibration methods of vis-NIR diffuse reflectance spectroscopy[J]. Soil and Tillage Research,2016,155:510-522.
[10]郑文博. 基于遥感数据的乐安河沿岸土壤有机质含量反演[D]. 淮南：安徽理工大学,2021.
[11]张娟娟,席磊,杨向阳,等. 砂姜黑土有机质含量高光谱估测模型构建[J]. 农业工程学报,2020,36(17):135-141.
[12]张森,卢霞,聂格格,等. SVM和BP检测滨海湿地土壤有机质[J]. 光谱学与光谱分析,2020,40(2):556-561.
[13]钟亮,郭熙,国佳欣,等. 基于不同卷积神经网络模型的红壤有机质高光谱估算[J]. 农业工程学报,2021,37(1):203-212.
[14]武彦清,张柏,宋开山,等. 松嫩平原土壤有机质含量高光谱反演研究[J]. 中国科学院研究生院学报,2011,28(2):187-194.
[15]陆龙妹,张平,卢宏亮,等. 淮北平原土壤高光谱特征及有机质含量预测[J]. 土壤,2019,51(2):374-380.
[16]文锡梅,兰安军,易兴松,等. 基于高光谱的喀斯特地区典型农田土壤有机质含量反演[J]. 西南农业学报,2018,31(8):1649-1654.
[17]王芳,刘林峰,冉秋霞,等. 施用秸秆炭对黄壤上小白菜生长及镉吸收的影响[J]. 绿色科技,2021,23(16):15-18.
[18]邸欣月,安显金,董慧,等. 贵州喀斯特区域土壤有机质的分布与演化特征[J]. 地球与环境,2015,43(6):697-708.
[19]郝冠军,黄懿珍,赵晓艺,等. 重铬酸钾外加热法测定土壤有机质的不确定度评定[J]. 上海农业学报,2011,27(3):103-109.
[20]肖艳,辛洪波,王斌,等. 基于小波变换和连续投影算法的黑土有机质含量高光谱估测[J]. 国土资源遥感,2021,33(2):33-39.
[21]郭云鹏,张弓,侯至丞,等. 采用SG平滑滤波的Stewart平台主从控制研究[J]. 自动化仪表,2019,40(2):30-33,38.
[22]XU P F, JIA Y J, JIANG M X. Blind audio source separation based on a new system model and the Savitzky-Golay filter[J]. Journal of Electrical Engineering,2021,72(3):208-212.
[23]ZHAO L, HU Y, ZHOU W, et al. Estimation methods for soil mercury content using hyperspectral remote sensing[J]. Sustainability, 2018, 10(7): 2474.
[24]高颖,王延仓,顾晓鹤,等. 基于微分变换定量反演土壤有机质及全氮含量[J]. 江苏农业科学,2020,48(24):220-225.
[25]ClOUTIS E A. Hyperspectral geological remote sensing: evaluation of analytical techniques[J]. International Journal of Remote Sensing,1996,17(12):2215-2242.
[26]徐明星,周生路,丁卫,等. 苏北沿海滩涂地区土壤有机质含量的高光谱预测[J]. 农业工程学报,2011,27(2):219-223.
[27]于雷,洪永胜,耿雷,等. 基于偏最小二乘回归的土壤有机质含量高光谱估算[J]. 农业工程学报,2015,31(14):103-109.
[28]ZHAO H Q, ZHAO X S. Nonlinear unmixing of minerals based on the log and continuum removal model[J]. European Journal of Remote Sensing,2019,52(1):277-293.
[29]MEVIK B H, WEHRENS R. The PLS package: principal component and partial least squares regression in R[J]. Journal of Statistical Software,2007,18(2):1-23.
[30]郄欣,齐雁冰,刘姣姣,等. 基于室内高光谱数据的多种类型土壤有机质估算模型比较[J]. 干旱地区农业研究,2021,39(4):109-116,124.
[31]孙玉婷,杨红云,王映龙,等. 基于支持向量机的水稻叶面积测定[J]. 江苏农业学报,2018,34(5):1027-1035.
[32]于欢,刘健,刘亚秋,等. 丘陵区耕地土壤有机质含量高光谱估测研究[J]. 山东农业大学学报(自然科学版),2021,52(4):648-653.
[33]孟亚琼. 改进的Adaboost算法在基因表达数据中的应用[D]. 杭州：中国计量大学,2018.
[34]江叶枫,郭熙,叶英聪,等. 应用集成BP神经网络模型预测土壤有机质空间分布[J]. 江苏农业学报,2017,33(5):1044-1050.
[35]刘清,关榆君. 电梯群控系统节能优化调度控制[J]. 计算机仿真,2018,35(10):340-344.
[36]孙浩然,赵志根,赵佳星,等. 珠海一号高光谱遥感的表层土壤有机质含量反演方法[J]. 遥感信息,2020,35(4):40-46.
[37]于雷,洪永胜,周勇,等. 高光谱估算土壤有机质含量的波长变量筛选方法[J]. 农业工程报,2016,32(13):95-102.
[38]陈祯. 基于近红外光谱分析的土壤水分信息的提取与处理[D]. 武汉：华中科技大学,2010.
[39]韩陈,唐强,韦杰. 紫色土和黄壤含水率的室内光谱反演[J]. 水土保持通报,2021,41(5):174-180,190.
[40]玉米提·买明,王雪梅. 连续小波变换的土壤有机质含量高光谱估测[J]. 光谱学与光谱分析,2022,42(4):1278-1284.
[41]周伟,谢利娟,杨晗,等. 基于高光谱的三江源区土壤有机质含量反演[J]. 土壤通报,2021,52(3):564-574.
[42]奉国和. SVM分类核函数及参数选择比较[J]. 计算机工程与应用,2011,47(3):123-124,128.
[43]卢志宏,刘辛瑶,常书娟,等. 基于BP神经网络的草原矿区表层土壤N/P高光谱反演模型[J]. 草业科学,2018,35(9):2127-2136.

相似文献/References:

[1]江叶枫,郭熙,叶英聪,等.应用集成BP神经网络模型预测土壤有机质空间分布[J].江苏农业学报,2017,(05):1044.[doi:doi:10.3969/j.issn.1000-4440.2017.05.013]
　JIANG Ye-feng,GUO Xi,YE Ying-cong,et al.Spatial distribution of soil organic matter predicted by BP neural network ensemble model[J].,2017,(01):1044.[doi:doi:10.3969/j.issn.1000-4440.2017.05.013]
[2]刘志刚,徐勤超.基质破碎度对光谱法检测基质含水率的影响[J].江苏农业学报,2017,(05):1051.[doi:doi:10.3969/j.issn.1000-4440.2017.05.014]
　LIU Zhi-gang,XU Qin-chao.Influences of substrate fragmentation degree on substrate water contents detected by hyper-spectral technology[J].,2017,(01):1051.[doi:doi:10.3969/j.issn.1000-4440.2017.05.014]
[3]王卓卓,何英彬,罗善军,等.基于冠层高光谱数据与马氏距离的马铃薯品种识别[J].江苏农业学报,2018,(05):1036.[doi:doi:10.3969/j.issn.1000-4440.2018.05.010]
　WANG Zhuo-zhuo,HE Ying-bin,LUO Shan-jun,et al.Variety identification of potatoes based on canopy hyperspectral data and Mahalanobis distance[J].,2018,(01):1036.[doi:doi:10.3969/j.issn.1000-4440.2018.05.010]
[4]芦兵,孙俊,毛罕平,等.高光谱和图像特征相融合的生菜病害识别[J].江苏农业学报,2018,(06):1254.[doi:doi:10.3969/j.issn.1000-4440.2018.06.008]
　LU Bing,SUN Jun,MAO Han-ping,et al.Disease recognition of lettuce with feature fusion based on hyperspectrum and image[J].,2018,(01):1254.[doi:doi:10.3969/j.issn.1000-4440.2018.06.008]
[5]徐丽华,谢德体.土壤有机质含量预测精度对光谱预处理和特征波段的响应[J].江苏农业学报,2019,(06):1340.[doi:doi:10.3969/j.issn.1000-4440.2019.06.010]
　XU Li-hua,XIE De-ti.Response of soil organic matter content prediction accuracy to preprocessing of spectra and feature bands[J].,2019,(01):1340.[doi:doi:10.3969/j.issn.1000-4440.2019.06.010]
[6]王婷,刘振华,彭一平,等.华南地区土壤有机质含量高光谱反演[J].江苏农业学报,2020,(02):350.[doi:doi:10.3969/j.issn.1000-4440.2020.02.014]
　WANG Ting,LIU Zhen-hua,PENG Yi-ping,et al.Predicting soil organic matter content in South China based on hyperspectral reflectance[J].,2020,(01):350.[doi:doi:10.3969/j.issn.1000-4440.2020.02.014]
[7]朱淑鑫,杨宸,顾兴健,等.K均值算法结合连续投影算法应用于土壤速效钾含量的高光谱分析[J].江苏农业学报,2020,(02):358.[doi:doi:10.3969/j.issn.1000-4440.2020.02.015]
　ZHU Shu-xin,YANG Chen,GU Xing-jian,et al.K-means algorithm combined with successive projection algorithm for hyperspectral analysis of soil available potassium content[J].,2020,(01):358.[doi:doi:10.3969/j.issn.1000-4440.2020.02.015]
[8]苗梦珂,王宝山,李长春,等.基于连续小波变换的冬小麦叶片最大净光合速率遥感估算[J].江苏农业学报,2020,(03):544.[doi:doi:10.3969/j.issn.1000-4440.2020.03.003]
　MIAO Meng-ke,WANG Bao-shan,LI Chang-chun,et al.Remote sensing estimation of maximum net photosynthetic rate of winter wheat leaves based on continuous wavelet transform[J].,2020,(01):544.[doi:doi:10.3969/j.issn.1000-4440.2020.03.003]
[9]陶惠林,冯海宽,徐良骥,等.基于无人机高光谱遥感数据的冬小麦生物量估算[J].江苏农业学报,2020,(05):1154.[doi:doi:10.3969/j.issn.1000-4440.2020.05.012]
　TAO Hui-lin,FENG Hai-kuan,XU Liang-ji,et al.Winter wheat biomass estimation based on hyperspectral remote sensing data of unmanned aerial vehicle(UAV)[J].,2020,(01):1154.[doi:doi:10.3969/j.issn.1000-4440.2020.05.012]
[10]赵懿,杜建军,张振华,等.秸秆还田方式对土壤有机质积累与转化影响的研究进展[J].江苏农业学报,2021,(06):1614.[doi:doi:10.3969/j.issn.1000-4440.2021.05.032]
　ZHAO Yi,DU Jian-jun,ZHANG Zhen-hua,et al.Research progress on the effects of straw returning on soil organic matter accumulation and transformation[J].,2021,(01):1614.[doi:doi:10.3969/j.issn.1000-4440.2021.05.032]
[11]郑曼迪,熊黑钢,乔娟峰,等.基于综合光谱指数的不同程度人类干扰下土壤有机质含量预测[J].江苏农业学报,2018,(05):1048.[doi:doi:10.3969/j.issn.1000-4440.2018.05.012]
　ZHENG Man-di,XIONG Hei-gang,QIAO Juan-feng,et al.Prediction of soil organic matter content based on comprehensive spectral index at different levels of human disturbance[J].,2018,(01):1048.[doi:doi:10.3969/j.issn.1000-4440.2018.05.012]

备注/Memo

备注/Memo:
收稿日期：2022-11-18基金项目：贵州科学院青年基金项目[黔科院J字(2018)25号];贵州省科技支撑计划项目[黔科合支撑(2020)1Y172号];贵州省科技支撑计划项目[黔科合支撑(2021)一般496号]；国家重点研发计划项目(2022YDF1100307)；贵州省基础研究计划项目[黔科合基础-ZK(2021)一般100号、黔科合基础-ZK(2022)一般276号]作者简介：张永亮(1995-),男,贵州都匀人,硕士研究生,主要从事土壤高光谱遥感方面的研究。(E-mail)17864159359@163.com通讯作者：汪泓,(E-mail)7653606@qq.com
更新日期/Last Update: 2024-03-17