基于分数阶微分联合光谱指数估算银川平原土壤有机质含量

doi:10.13287/j.1001-9332.202303.020

摘要/Abstract

摘要： 土壤有机质是评价土壤肥力的重要指标。为探讨分数阶微分联合不同光谱指数所建模型对较低土壤有机质含量的估算效果,本研究利用银川平原土壤野外高光谱反射率,结合室内实测有机质含量,对反射率原始数据进行倒数对数变换后进行0～2阶(间隔0.20)的分数阶微分处理,构建差值指数(DI)、比值指数(RI)、亮度指数(BI)、归一化指数(NDI)、再归一化指数(RDI)和广义指数(GDI),分析6个指数与土壤有机质含量间的二维相关性,筛选出最优光谱指数,分别建立主成分回归(PCR)、偏最小二乘回归(PLSR)、反向神经网络(BPNN)、支持向量机(SVM)和地理加权回归(GWR)模型估算土壤有机质含量。结果表明: DI、RI、NDI、BI、GDI、RDI与土壤有机质含量间的最大相关系数绝对值(MACC)整体呈现先上升后下降的规律,分别在1.0、0.6、1.4和1.6阶处MACC最高。基于分数阶微分变化下的0.2～2.0阶RDI可用于后续模型构建,其中,MACC值最佳组合波段主要集中在400～600和1300～1700 nm。在单一光谱指数RDI所建不同模型中,SVM模型估算精度最高,其建模决定系数、验证决定系数和相对分析误差分别达到0.86、0.87和2.32。研究结果可为低有机质含量地区的土壤有机质快速、准确估算及制图提供科学依据。

关键词: 土壤有机质, 分数阶微分, 光谱指数, 支持向量机, 地理加权回归

Abstract: Soil organic matter (SOM) is a crucial indicator of soil fertility. Field hyperspectral reflectance and laboratory SOM data of soil samples from the Yinchuan Plain were used to explore the performance of models based on fractional derivative combined with different spectral indices. Following reciprocal and logarithmic transformation, the reflectance data were processed using fractional derivative from 0 to 2 orders (interval 0.20). Then, the difference index (DI), ratio index (RI), brightness index (BI), normalized difference index (NDI), renormalized difference index (RDI), and generalized difference index (GDI) were constructed. The two-dimensional correlation between the six indices and SOM content were analyzed. The optimal spectral indices were selected to establish SOM estimation models with principal component regression (PCR), partial least square regression (PLSR), back propagation neural network (BPNN), support vector machine (SVM), and geographically weighted regression (GWR). Results showed that the maximum absolute correlation coefficient (MACC) values between DI, RI, NDI, BI, GDI, RDI, and SOM contents increased firstly and then decreased, with the highest values observed at 1.0, 0.6, 1.4, and 1.6 orders. The 0.2-2.0 order RDI under fractional derivative variation could be used for subsequent model construction, in which the optimal combinations of bands for MACC values were mainly concentrated at 400-600 nm and 1300-1700 nm. Among the different models based on the single spectral index RDI, the model based on SVM achieved the highest estimation accuracy, whose modeling determination coefficient, verification determination coefficient and relative percentage difference reached 0.86, 0.87 and 2.32. Our results would provide a scientific reference for quick and accurate SOM assessment and mapping in areas with relatively low SOM content.

Key words: soil organic matter, fractional order derivative, spectral index, support vector machine, geographically weighted regression

尚天浩, 陈睿华, 张俊华, 王怡婧. 基于分数阶微分联合光谱指数估算银川平原土壤有机质含量[J]. 应用生态学报, 2023, 34(3): 717-725.

SHANG Tianhao, CHEN Ruihua, ZHANG Junhua, WANG Yijing. Estimation of soil organic matter content in Yinchuan Plain based on fractional derivative combined with spectral indices.[J]. Chinese Journal of Applied Ecology, 2023, 34(3): 717-725.

参考文献

[1] Kim K, Daly EJ, Gorzelak M, et al. Soil organic matter pools response to perennial grain cropping and nitrogen fertilizer. Soil and Tillage Research, 2022, 220: 105376
[2] Meng XT, BaoYL, Zhang XL, et al. Prediction of soil organic matter using different soil classification hierarchical level stratification strategies and spectral characteristic parameters. Geoderma, 2022, 411: 115696
[3] 尼加提·卡斯木, 茹克亚·萨吾提, 师庆东, 等. 基于优化光谱指数的土壤有机质含量估算. 农业机械学报, 2018, 49(11): 155-163
[4] 杨帆, 徐洋, 崔勇, 等. 近30年中国农田耕层土壤有机质含量变化. 土壤学报, 2017, 54(5): 1047-1056
[5] Zhang ZP, Ding JL, Zhu CM, et al. Strategies for the efficient estimation of soil organic matter in salt-affected soils through Vis-NIR spectroscopy: Optimal band combination algorithm and spectral degradation. Geoderma, 2021, 382: 114729
[6] 朱阿星, 杨琳, 樊乃卿, 等. 数字土壤制图研究综述与展望. 地理科学进展, 2018, 37(1): 66-78
[7] 方少文, 杨梅花, 赵小敏, 等. 红壤区土壤有机质光谱特征与定量估算——以江西省吉安县为例. 土壤学报, 2014, 51(5): 1003-1010
[8] Zeraatpisheh M, Ayoubi S, Mirbagheri Z, et al. Spatial prediction of soil aggregate stability and soil organic carbon in aggregate fractions using machine learning algorithms and environmental variables. Geoderma Regional, 2021, 27: e00440
[9] Reis AS, Rodrigues M, dos Santos GLAA, et al. Detection of soil organic matter using hyperspectral imaging sensor combined with multivariate regression modeling procedures. Remote Sensing Applications: Society and Environment, 2021, 22: 100492
[10] Munnaf MA, Mouazen AM, Removal of external influences from on-line vis-NIR spectra for predicting soil organic carbon using machine learning. Catena, 2022, 211: 106015
[11] 唐海涛, 孟祥添, 苏循新, 等. 基于CARS算法的不同类型土壤有机质高光谱预测. 农业工程学报, 2021, 37(2): 105-113
[12] 洪永胜, 朱亚星, 苏学平, 等. 高光谱技术联合归一化光谱指数估算土壤有机质含量. 光谱学与光谱分析, 2017, 37(11): 3537-3542
[13] 张子鹏, 丁建丽, 王敬哲, 等. 利用三维光谱指数定量估算土壤有机质含量:以新疆艾比湖流域为例. 光谱学与光谱分析, 2020, 40(5): 1514-1522
[14] Baumgardner MF, Silval RF, Biehl LL, et al. Reflectance properties of soils. Advances in Agronomy, 1986, 38: 1-44
[15] Ben-Dor E, Banin A. Near-infrared analysis as a rapid method to simultaneously evaluate several soil properties. Soil Science of America Journal, 1995, 59: 364-372
[16] Schmitt M. Fractional derivative analysis of diffuse reflectance spectra. Applied Spectroscopy, 1998, 52: 840-846
[17] Cui SC, Zhou KF, Ding RF, et al. Estimation of soil copper content based on fractional-order derivative spectroscopy and spectral characteristic band selection. Spectrochemical Acta Part A: Molecular and Biomolecular Spectroscopy, 2022, 275: 121190
[18] Rinnan R, Rinnan A. Application of near infrared reflectance (NIR) and fluorescence spectroscopy to analysis of microbiological and chemical properties of arctic soil. Soil Biology & Biochemistry, 2007, 39: 1664-1673
[19] Chen Y, Ma LX, Yu DS, et al. Comparison of feature selection methods for mapping soil organic matter in subtropical restored forests. Ecological Indicators, 2022, 135: 108545
[20] Peng XT, Shi TZ, Song AH, et al. Estimating soil organic carbon using VIS/NIR spectroscopy with SVMR and SPA methods. Remote Sensing, 2014, 6: 2699-2717
[21] Meng XT, Bao YL, Liu JG, et al. Regional soil organic carbon prediction model based on a discrete wavelet analysis of hyperspectral satellite data. International Journal of Applied Earth Observation and Geoinformation, 2020, 89: 102111
[22] 贾萍萍, 尚天浩, 张俊华, 等. 利用多源光谱信息反演宁夏银北地区干湿季土壤含盐量. 农业工程学报, 2020, 36(17): 125-134
[23] 尚天浩, 毛鸿欣, 张俊华, 等. 基于PCA敏感波段筛选与SVM建模的银川平原土壤有机质高光谱估算. 生态学杂志, 2021, 40(12): 4128-4136
[24] 何彤慧, 程志, 张玉峰, 等. 银川平原沟渠植物多样性特征及影响因素. 湿地科学, 2013, 11(3): 352-358
[25] Hong YS, Cheng SC, Liu YL, et al. Combination of fractional order derivative and memory based learning algorithm to improve the estimation accuracy of soil organic matter by visible and near infrared spectroscopy. Catena, 2019, 214: 104-116
[26] Hong YS, Shen RL Chen H, et al. Estimating lead and zinc concentrations in periurban agricultural soils through reflectance spectroscopy: Effects of fractional order derivative and random forest. Science of the Total Environment, 2019, 165: 1969-1982
[27] Ihuoma SO, Madramootoo CA. Narrow-band reflectance indices for mapping the combined effects of water and nitrogen stress in field grown tomato crops. Biosystems Engineering, 2020, 192: 133-143
[28] Kennard W, Stone LA. Computer aided design of experiments. Technimetrics, 1969, 11: 137-148
[29] Viscarra RRA, Behrens T. Using data mining to model and interpret soil diffuse reflectance spectral. Geoderma, 2010, 158: 46-54
[30] Vicente LE, Filho C. Identification of mineral components in tropical soils using reflectance spectroscopy and advanced spaceborne thermal emission and reflection radiometer (ASTER) data. Remote Sensing of Environment, 2011, 115: 1824-1836
[31] 张智韬, 劳聪聪, 王海峰, 等. 基于FOD和SVMDA-RF的土壤有机质含量高光谱预测. 农业机械学报, 2020, 51(1): 156-167
[32] 尚天浩, 陈睿华, 张俊华, 等. 基于实测高光谱与Sentinel-2B数据的银北土壤Na⁺含量估测. 应用生态学报, 2021, 32(3): 1023-1032
[33] 赵明松, 谢毅, 陆龙妹, 等. 基于高光谱特征指数的土壤有机质含量建模. 土壤学报, 2021, 58(1): 42-54
[34] Vahid K, Faramarz DA, Saeed Y, et al. Monitoring soil lead and zinc contents via combination of spectroscopy with extreme learning machine and other data mining methods. Geoderma, 2018, 318: 29-41
[35] Wang XP, Zhang F, Kuan HT, et al. New methods for improving the remote sensing estimation of soil organic matter content in the Ebinur Lake wetland national nature reserve in northwest China. Remote Sensing of Environment, 2018, 218: 104-118
[36] 郭燕, 纪文君, 吴宏海, 等. 基于野外VIS-NIR光谱的土壤有机质预测与制图. 光谱与光谱分析, 2013, 33(4): 1135-1140
[37] Stenberg B, ViscarraRossel RA, Mouazen MA, et al. Visible and near infrared spectroscopy in soil science. Advances in Agronomy, 2010, 107: 163-215
[38] Shi TZ, Chen YY, Liu HZ, et al. Soil organic carbon content estimation with laboratory-based visible-near-infrared reflectance spectroscopy: Feature selection. Applied Spectroscopy, 2014, 68: 831-837
[39] 纪文君, 李曦, 李成学, 等. 基于全谱数据挖掘技术的土壤有机质高光谱预测建模研究. 光谱学与光谱分析, 2012, 32(9): 2393-2398
[40] 刁淑娟, 刘春玲, 张涛, 等. 基于SVM的湖泊咸度等级遥感信息提取方法——以内蒙古巴丹吉林沙漠为例. 国土资源遥感, 2016, 28(4): 114-118