首页 > 论文 > 激光与光电子学进展 > 57卷 > 15期(pp:153001--1)

结合分数阶微分技术与机器学习算法的土壤有机碳含量光谱估测

Combination of Fractional Order Differential and Machine Learning Algorithm for Spectral Estimation of Soil Organic Carbon Content

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

采集新疆渭干河-库车河典型绿洲96个表层土样,测量其光谱反射率和土壤有机碳(SOC)含量,采用分数阶微分技术(阶数的取值范围为0~2,步长为0.2)结合极限学习机、随机森林、多元自适应回归样条函数、弹性网络回归和梯度提升回归树(GBRT)5种机器学习算法,并对SOC含量进行高精度估算。实验结果表明:分数阶微分的预处理效果优于整数阶微分;特定波段处相关性得到明显提高,最大相关性提高了0.220;作为集成学习的GBRT(验证集中决定系数为0.878,相对分析误差为3.142)在不同阶数下均优于其他模型,建议使用基于1.6阶光谱反射率的GBRT估测干旱区绿洲SOC含量。总之,基于可见光-近红外(VIS-NIR)结合分数阶微分技术与机器学习算法,为提高估测干旱区绿洲SOC含量的模型精度提出新方案。

Abstract

In this study, 96 surface soil samples are obtained from the typical oasis of the Ugan-Kuqa River in the Xinjiang Uyghur Autonomous Region and their spectral reflectance and soil organic carbon (SOC) content are evaluated. Using fractional order differential technique (with an order value range of 0-2 and a step size of 0.2) is combined with five machine learning algorithms, including the extreme learning machine, random forest, multiple adaptive regression spline function, elastic network regression, and gradient lifting regression tree (GBRT) algorithms, and high-precision estimation of SOC content. The experimental results show that the pretreatment effect obtained using a fractional order differential is better than that obtained using an integer order differential. The correlation at a specific band is significantly improved, and the maximum correlation is enhanced by approximately 0.220. In case of the GBRT, the verification concentration determination coefficient is 0.878 and the relative analysis error is 3.142, indicating that this type of integrated learning is superior to other models of different orders. GBRT based on a 1.6-order spectral reflectance should be used to estimate the SOC content of the oasis in arid areas. Thus, a new scheme based on the combination of visible light-near infrared(VIS-NIR)with the fractional order differential technology and machine learning algorithms is proposed in this study to improve the accuracy of the model used for estimating the SOC content of the oasis in arid areas.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:O433

DOI:10.3788/LOP57.153001

所属栏目:光谱学

基金项目:国家自然科学基金;

收稿日期:2019-11-01

修改稿日期:2019-11-26

网络出版日期:2020-08-01

作者单位    点击查看

赵启东:新疆大学绿洲生态教育部重点实验室, 新疆 乌鲁木齐 830046新疆大学资源与环境科学学院智慧城市与环境建模自治区普通高校重点实验室, 新疆 乌鲁木齐 830046
葛翔宇:新疆大学绿洲生态教育部重点实验室, 新疆 乌鲁木齐 830046新疆大学资源与环境科学学院智慧城市与环境建模自治区普通高校重点实验室, 新疆 乌鲁木齐 830046
丁建丽:新疆大学绿洲生态教育部重点实验室, 新疆 乌鲁木齐 830046新疆大学资源与环境科学学院智慧城市与环境建模自治区普通高校重点实验室, 新疆 乌鲁木齐 830046
王敬哲:新疆大学绿洲生态教育部重点实验室, 新疆 乌鲁木齐 830046新疆大学资源与环境科学学院智慧城市与环境建模自治区普通高校重点实验室, 新疆 乌鲁木齐 830046广东省生态环境技术研究所, 广东 广州 510650
张振华:新疆大学绿洲生态教育部重点实验室, 新疆 乌鲁木齐 830046新疆大学资源与环境科学学院智慧城市与环境建模自治区普通高校重点实验室, 新疆 乌鲁木齐 830046
田美玲:新疆大学绿洲生态教育部重点实验室, 新疆 乌鲁木齐 830046新疆大学资源与环境科学学院智慧城市与环境建模自治区普通高校重点实验室, 新疆 乌鲁木齐 830046

联系人作者:赵启东(zhaoqidong1994@163.com); 丁建丽(watarid@xju.edu.cn);

备注:国家自然科学基金;

【1】Sakschewski B, von Bloh W, Boit A, et al. Resilience of Amazon forests emerges from plant trait diversity [J]. Nature Climate Change. 2016, 6(11): 1032-1036.

【2】Zhang Z P, Ding J L, Wang J Z. Spectral characteristics of oasis soil in arid area based on harmonic analysis algorithm [J]. Acta Optica Sinica. 2019, 39(2): 0228003.
张子鹏, 丁建丽, 王敬哲. 基于谐波分析算法的干旱区绿洲土壤光谱特性研究 [J]. 光学学报. 2019, 39(2): 0228003.

【3】Viscarra Rossel R A, Behrens T, Ben-Dor E, et al. A global spectral library to characterize the world''''s soil [J]. Earth-Science Reviews. 2016, 155: 198-230.

【4】Fang X, Guo X L, Zhang C, et al. Contributions of climate change to the terrestrial carbon stock of the arid region of China: a multi-dataset analysis [J]. Science of the Total Environment. 2019, 668: 631-644.

【5】O''''Rourke S M. Stockmann U, Holden N M, et al. An assessment of model averaging to improve predictive power of portable VIS-NIR and XRF for the determination of agronomic soil properties [J]. Geoderma. 2016, 279: 31-44.

【6】Cambou A, Cardinael R, Kouakoua E, et al. Prediction of soil organic carbon stock using visible and near infrared reflectance spectroscopy (VNIRS) in the field [J]. Geoderma. 2016, 261: 151-159.

【7】Ding J L, Yang A X, Wang J Z, et al. Machine-learning-based quantitative estimation of soil organic carbon content by VIS/NIR spectroscopy [J]. PeerJ. 2018, 6: e5714.

【8】Dotto A C. Dalmolin R S D, Caten A T, et al. A systematic study on the application of scatter-corrective and spectral-derivative preprocessing for multivariate prediction of soil organic carbon by VIS-NIR spectra [J]. Geoderma. 2018, 314: 262-274.

【9】Liu Y F, Song Y L, Guo L, et al. Geostatistical models of soil organic carbon density prediction based on soil hyperspectral reflectance [J]. Transactions of the Chinese Society of Agricultural Engineering. 2017, 33(2): 183-191.
刘艳芳, 宋玉玲, 郭龙, 等. 结合高光谱信息的土壤有机碳密度地统计模型 [J]. 农业工程学报. 2017, 33(2): 183-191.

【10】Filippi P, Cattle S R. Bishop T F A, et al. Combining ancillary soil data with VIS-NIR spectra to improve predictions of organic and inorganic carbon content of soils [J]. MethodsX. 2018, 5: 551-560.

【11】Hong Y S, Chen S C, Liu Y L, 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 [J]. CATENA. 2019, 174: 104-116.

【12】Va?át R, Kode?ová R, Klement A, et al. Simple but efficient signal pre-processing in soil organic carbon spectroscopic estimation [J]. Geoderma. 2017, 298: 46-53.

【13】Delwiche S R, Reeves J B. A graphical method to evaluate spectral preprocessing in multivariate regression calibrations: example with Savitzky-Golay filters and partial least squares regression [J]. Applied Spectroscopy. 2010, 64(1): 73-82.

【14】Wang J Z, Ding J L, Abulimiti A, et al. Quantitative estimation of soil salinity by means of different modeling methods and visible-near infrared (VIS-NIR) spectroscopy, Ebinur Lake Wetland, Northwest China [J]. PeerJ. 2018, 6: e4703.

【15】Wang X P, Zhang F, Ding J L, et al. Estimation of soil salt content (SSC) in the Ebinur Lake Wetland National Nature Reserve (ELWNNR), Northwest China, based on a Bootstrap-BP neural network model and optimal spectral indices [J]. Science of the Total Environment. 2018, 615: 918-930.

【16】Hong Y S, Chen Y Y, Yu L, et al. Combining fractional order derivative and spectral variable selection for organic matter estimation of homogeneous soil samples by VIS-NIR spectroscopy [J]. Remote Sensing. 2018, 10(3): 479.

【17】Ge X Y, Ding J L, Wang J Z, et al. Estimation of soil moisture content based on competitive adaptive reweighted sampling algorithm coupled with machine learning [J]. Acta Optica Sinica. 2018, 38(10): 1030001.
葛翔宇, 丁建丽, 王敬哲, 等. 基于竞争适应重加权采样算法耦合机器学习的土壤含水量估算 [J]. 光学学报. 2018, 38(10): 1030001.

【18】Bao Q L, Ding J L, Wang J Z. Prediction of soilmoisture content by selecting spectral characteristics using random forest method [J]. Laser & Optoelectronics Progress. 2018, 55(11): 113002.
包青岭, 丁建丽, 王敬哲. 利用随机森林方法优选光谱特征预测土壤水分含量 [J]. 激光与光电子学进展. 2018, 55(11): 113002.

【19】Wang F, Yang S T, Ding J L, et al. Environmental sensitive variable optimization and machine learning algorithm using in soil salt prediction at oasis [J]. Transactions of the Chinese Society of Agricultural Engineering. 2018, 34(22): 102-110.
王飞, 杨胜天, 丁建丽, 等. 环境敏感变量优选及机器学习算法预测绿洲土壤盐分 [J]. 农业工程学报. 2018, 34(22): 102-110.

【20】Nawar S, Mouazen A M. On-line VIS-NIR spectroscopy prediction of soil organic carbon using machine learning [J]. Soil and Tillage Research. 2019, 190: 120-127.

【21】Lu R K. Soil agricultural chemical analysis methods[M]. Beijing: China Agriculture Science and Technology Press, 2000.
鲁如坤. 土壤农业化学分析方法[M]. 北京: 中国农业科技出版社, 2000.

【22】Ge X Y, Wang J Z, Ding J L, et al. Combining UAV-based hyperspectral imagery and machine learning algorithms for soil moisture content monitoring [J]. PeerJ. 2019, 7: e6926.

【23】Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: theory and applications [J]. Neurocomputing. 2006, 70(1/2/3): 489-501.

【24】Belgiu M, Dragut L. Random forest in remote sensing: a review of applications and future directions [J]. ISPRS Journal of Photogrammetry and Remote Sensing. 2016, 114: 24-31.

【25】Du P J, Samat A, Waske B, et al. Random Forest and Rotation Forest for fully polarized SAR image classification using polarimetric and spatial features [J]. ISPRS Journal of Photogrammetry and Remote Sensing. 2015, 105: 38-53.

【26】Rossel R A V, Behrens T. Using data mining to model and interpret soil diffuse reflectance spectra [J]. Geoderma. 2010, 158(1/2): 46-54.

【27】Zheng N N, Luan X L, Liu F. Elastic Net modeling for near infrared spectroscopy [J]. Spectroscopy and Spectral Analysis. 2018, 38(10): 3096-3100.
郑年年, 栾小丽, 刘飞. 近红外光谱Elastic Net建模方法与应用 [J]. 光谱学与光谱分析. 2018, 38(10): 3096-3100.

【28】Ogutu J O, Schulz-Streeck T, Piepho H P. Genomic selection using regularized linear regression models: ridge regression, lasso, elastic net and their extensions [J]. BMC Proceedings. 2012, 6(s2): s10.

【29】Liu L F, Ji M, Buchroithner M F. Combining partial least squares and the gradient-boosting method for soil property retrieval using visible near-infrared shortwave infrared spectra [J]. Remote Sensing. 2017, 9(12): 1299.

【30】Tian M L, Ge X Y, Ding J L, et al. Coupled machine learning and unmanned aerial vehicle based hyperspectral data for soil moisture content estimation [J]. Laser & Optoelectronics Progress. 2020, 57(9): 093002.
田美玲, 葛翔宇, 丁建丽, 等. 耦合机器学习和机载高光谱数据的土壤含水量估算 [J]. 激光与光电子学进展. 2020, 57(9): 093002.

【31】Wang J Z, Tiyip T, Ding J L, et al. Quantitative estimation of organic matter content in arid soil using VIS-NIR spectroscopy preprocessed by fractional derivative [J]. Journal of Spectroscopy. 2017, 2017: 1375158.

【32】Hong Y S, Liu Y L, Chen Y Y, et al. Application of fractional-order derivative in the quantitative estimation of soil organic matter content through visible and near-infrared spectroscopy [J]. Geoderma. 2019, 337: 758-769.

【33】Shi Z, Wang Q L, Peng J, et al. Development of a national VNIR soil-spectral library for soil classification and prediction of organic matter concentrations [J]. Scientia Sinica (Terrae). 2014, 44(5): 978-988.
史舟, 王乾龙, 彭杰, 等. 中国主要土壤高光谱反射特性分类与有机质光谱预测模型 [J]. 中国科学(地球科学). 2014, 44(5): 978-988.

【34】Shi Z, Ji W J. Viscarra Rossel R A, et al. Prediction of soil organic matter using a spatially constrained local partial least squares regression and the Chinese VIS-NIR spectral library [J]. European Journal of Soil Science. 2015, 66(4): 679-687.

引用该论文

Zhao Qidong,Ge Xiangyu,Ding Jianli,Wang Jingzhe,Zhang Zhenhua,Tian Meiling. Combination of Fractional Order Differential and Machine Learning Algorithm for Spectral Estimation of Soil Organic Carbon Content[J]. Laser & Optoelectronics Progress, 2020, 57(15): 153001

赵启东,葛翔宇,丁建丽,王敬哲,张振华,田美玲. 结合分数阶微分技术与机器学习算法的土壤有机碳含量光谱估测[J]. 激光与光电子学进展, 2020, 57(15): 153001

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF