[1]王文才,李绍稳,齐海军,等.土壤速效磷含量成像和非成像光谱预测差异性分析[J].江苏农业学报,2018,(04):811-817.[doi:doi:10.3969/j.issn.1000-4440.2018.04.014]
　WANG Wen-cai,LI Shao-wen,QI Hai-jun,et al.The diffference analysis of soil available phosphors content imaging and non-imaging spectra prediction[J].,2018,(04):811-817.[doi:doi:10.3969/j.issn.1000-4440.2018.04.014]
点击复制

土壤速效磷含量成像和非成像光谱预测差异性分析()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2018年04期
页码:
811-817
栏目:
耕作栽培·资源环境
出版日期:
2018-08-25

文章信息/Info

Title:
The diffference analysis of soil available phosphors content imaging and non-imaging spectra prediction
作者:
王文才; 李绍稳; 齐海军; 金秀; 王帅
（安徽农业大学信息与计算机学院/农业部农业物联网技术集成与应用重点实验室，安徽合肥230036）
Author(s):
WANG Wen-cai; LI Shao-wen; QI Hai-jun; JIN Xiu; WANG Shuai
(School of Information and Computer Science, Anhui Agricultural University/Key Laboratory of Technology Integration and Application in Agricultural Internet of Things, Ministry of Agriculture, Hefei 230036, China)
关键词:
成像光谱; 非成像光谱; 光谱分析; 土壤速效磷含量; 预测
Keywords:
imaging spectra; non-imaging spectra; spectral analysis; soil available phosphorus content; prediction
分类号:
S153.6
DOI:
doi:10.3969/j.issn.1000-4440.2018.04.014
文献标志码:
A
摘要:
以139个皖北砂姜黑土样品为研究对象，首先在室内采集土壤在 400～1 000 nm可见近红外光谱区域的成像和非成像2组光谱数据，再对光谱进行Savitaky-Golay 卷积平滑、标准正态变量变换（SNV）和一阶微分（FD）等一种或多种组合处理，最后利用偏最小二乘回归（PLSR）分别建立土壤速效磷（AP）含量回归模型。对2组光谱进行光谱特征分析和相似度分析，并对比模型预测效果，结果显示，成像和非成像光谱在形态上趋向一致，且非成像光谱的反射率值在每个波长点上均高于成像光谱；平滑处理后2种光谱的光谱相关拟合度得到提高；经预处理后，2种光谱建立的模型预测精度均有所提高；非成像光谱经预处理后建立的最优模型预测精度（验证集相对分析误差MRPD为2.02）高于成像光谱（验证集相对分析误差MRPD为1.85）。因此，成像光谱相对于非成像光谱在 400～1 000 nm波段建立的土壤速效磷含量回归模型预测能力稍差，但通过光谱预处理变换可以降低成像和非成像光谱的差异性并缩小成像与非成像光谱模型预测精度的差距。
Abstract:
In this study, 139 samples of Shajiang black soil in northern Anhui were used as materials. Firstly, imaging and non-imaging spectral data at 400-1 000 nm were collected indoorally. Then, a combination of Savitaky-Golay filtering algorithm, standard normal variate (SNV) and first derivative (FD) was performed on the spectrum. Finally, partial least squares regression (PLSR) was used to establish the regression model of soil available phosphorus (AP) content. The spectral feature analysis and similarity analysis of the two groups of spectra were conducted and the predictive effects of the models were compared. The results showed that the trend of imaging and non-imaging spectra in shape was consistent and the reflectance values of non-imaging spectra at each wavelength point were higher than those of imaging spectra. The spectral correlation fitting was improved after smoothing. After pretreatment, the prediction accuracy of the two spectra was improved. The prediction accuracy of the optimal model established after pretreatment of non-imaging spectra (the verification set relative analysis error MRPD was 2.02) was higher than that of the imaging spectra (verification set relative analysis error MRPD was 1.85). Therefore, prediction ability of the soil available phosphorus (AP) content regression model established in the 400-1 000 nm band of the imaging spectra was slightly worse than that of the non-imaging spectra. However, spectral preprocessing can reduce the difference between imaging and non-imaging spectra and reduce the accuracy difference of imaging and non-imaging spectral models.

参考文献/References:

[1]刘燕德,熊松盛,刘德力. 近红外光谱技术在土壤成分检测中的研究进展[J]. 光谱学与光谱分析, 2014, 34(10):2639-2644.
[2]张佳佳，郭熙，赵小敏．南方丘陵稻田土壤全磷、有效磷高光谱特征与反演模型[J]. 江苏农业科学，2016,44(7):522-525.
[3]SHEN J, YUAN L, ZHANG J, et al. Phosphorus dynamics: from soil to plant [J]. Plant Physiology, 2011, 156(3): 997-1005.
[4]贾生尧,杨祥龙,李光,等. 近红外光谱技术结合递归偏最小二乘算法对土壤速效磷与速效钾含量测定研究 [J]. 光谱学与光谱分析, 2015, 35(9): 2516-2520.
[5]SZEGEDY M, TARDOS G. Data fusion techniques for delineation of site-specific management zones in a field in UK[J]. Precision Agriculture, 2016, 17(2):200-217.
[6]吴茜,杨宇虹,徐照丽,等. 应用局部神经网络和可见/近红外光谱法估测土壤有效氮磷钾[J]. 光谱学与光谱分析, 2014, 34(8): 2102-2105.
[7]SHAO Y, HE Y. Nitrogen, phosphorus, and potassium prediction in soils, using infrared spectroscopy[J]. Soil Research, 2011, 49(2): 166-172.
[8]胡国田,何东健. 基于直接正交信号校正的土壤磷和钾 VNIR 测定研究[J]. 农业机械学报, 2015, 46(7): 139-145.
[9]PAZ-KAGAN T, ZAADY E, SALBACH C, et al. Mapping the spectral soil quality index (SSQI) using airborne imaging spectroscopy [J]. Remote Sensing, 2015, 7(11): 15748-15781.
[10]STENBERG B, VISCARRA R R A, MOUAZEN A, et al. Visible and near infrared spectroscopy in soil science[J]. Advances in Agronomy, 2010, 107:163-215.
[11]QI H, PAZ-KAGAN T, KARNIELI A, et al. Evaluating calibration methods for predicting soil available nutrients using hyperspectral VNIR data[J]. Soil & Tillage Research, 2018, 175:267-275.
[12]JUNG A, VOHLAND M, THIELEBRUHN S. Use of a portable camera for proximal soil sensing with hyperspectral image data[J]. Remote Sensing, 2015, 7(9):11434-11448.
[13]WIJEWARDANE N K, GE Y, MORGAN C L S. Prediction of soil organic and inorganic carbon at different moisture contents with dry ground VNIR: a comparative study of different approaches[J]. European Journal of Soil Science, 2016, 67(5):605-615.
[14]PAN T, ZHEN-TAO W U, CHEN H Z. Waveband optimization for near-infrared spectroscopic analysis of total nitrogen in soil[J]. Chinese Journal of Analytical Chemistry, 2012, 40(6):920-924.
[15]舒田,岳延滨,李莉婕,等. 基于高光谱遥感的农作物识别[J]. 江苏农业学报,2016,32(6):1310-1314.
[16]王坤,朱大洲,张东彦,等. 成像光谱技术在农作物信息诊断中的研究进展[J]. 光谱学与光谱分析, 2011, 31(3):589-594.
[17]覃泽林，谢国雪，李宇翔，等. 多时相高分一号影像在丘陵地区大宗农作物提取中的应用[J].南方农业学报，2017，48（1）：181-188.
[18]王尔美,李卫国,顾晓鹤,等. 基于光谱特征分异的玉米种植面积提取[J]. 江苏农业学报, 2017, 33(4):822-827.
[19]BRAY R, KURTZ L. Determination of total, organic, and available forms of phosphorus in soils[J]. Soil Science, 1945, 59(1): 39-46.
[20]CHU X L, YUAN H F, LU W Z. Progress and application of spectral data pretreatment and wavelength selection methods in NIR analytical technique[J]. Progress in Chemistry, 2004, 16(4):528-542.
[21]JI W, ROSSEL R A V, SHI Z. Accounting for the effects of water and the environment on proximally sensed vis-NIR soil spectra and their calibrations[J]. European Journal of Soil Science, 2015, 66(3):555-565.
[22]SAVITZKY A, GOLAY M J E. Smoothing and differentiation of data by simplified least squares procedures[J]. Analytical Chemistry, 1964, 36(8): 1627-1639.
[23]HELLAND I S, N S T, ISAKSSON T. Related versions of the multiplicative scatter correction method for preprocessing spectroscopic data [J]. Chemometrics and Intelligent Laboratory Systems, 1995, 29(2): 233-241.
[24]GHOLIZADEH A A, BORUVKA L A, SABERIOON M M B, et al. Comparing different data preprocessing methods for monitoring soil heavy metals based on soil spectral features [J]. Soil and Water Research, 2015, 10(4): 218-227.
[25]ASMUND R, BERG F V D, ENGELSEN S B. Review of the most common pre-processing techniques for near-infrared spectra[J]. Trac Trends in Analytical Chemistry, 2009, 28(10):1201-1222.
[26]KRUSE F A, LEFKOFF A B, BOARDMAN J W, et al. The spectral image processing system (SIPS)-interactive visualization and analysis of imaging spectrometer data[J]. Remote Sensing of Environment, 1993, 44(2/3):145-163.
[27]JI W, VISCARRA R R A, SHI Z. Improved estimates of organic carbon using proximally sensed vis-NIR spectra corrected by piecewise direct standardization[J]. European Journal of Soil Science, 2015, 66(4):670-678.
[28]KENNARD R W, STONE L A. Computer aided design of experiments [J]. Technometrics, 1969, 11(1): 137-148.
[29]ACKERSON J P, MORGAN C L S, GE Y. Penetrometer-mounted VisNIR spectroscopy: Application of EPO-PLS to in situ, VisNIR spectra[J]. Geoderma, 2017, 286:131-138.
[30]JI W, SHI Z, HUANG J, et al. In situ measurement of some soil properties in paddy soil using visible and near-infrared spectroscopy [J]. PLoS ONE, 2014, 9(8): e105708.
[31]ZHONG P, XU Y, ZHAO Y. Training twin support vector regression via linear programming[J]. Neural Computing and Applications, 2012, 21(2): 399-407.
[32]CHANG C W, LAIRD D A, MAUSBACH M J, et al. Near-Infrared reflectance spectroscopy-principal components regression analyses of soil properties [J]. Soil Science Society of America Journal, 2001, 65(2): 480-490.
[33]DOR E B, ONG C, LAU I C. Reflectance measurements of soils in the laboratory: Standards and protocols[J]. Geoderma, 2015, 245/246:112-124.

备注/Memo

备注/Memo:
收稿日期：2017-12-25 基金项目：农业部引进国际先进农业科学技术计划（“948”计划）项目(2015-Z44、2016-X34) 作者简介：王文才（1994-），男，安徽天长人，硕士研究生，主要从事土壤速效磷高光谱检测研究。（E-mail） wangwencai@ahau.edu.cn 通讯作者：李绍稳，（E-mail）shwli@ahau.edu.cn
更新日期/Last Update: 2018-09-04