ارزیابی روش طیف‌سنجی امواج مرئی - مادون قرمز و روش‌های PLSR و SVMR در مدل‌سازی کربن آلی و کل مواد خنثی شوند خاک

نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه خاکشناسی، پردیس علوم و تحقیقات خوزستان، دانشگاه آزاد اسلامی، اهواز، ایران

2 گروه خاکشناسی، واحد اهواز، دانشگاه آزاد اسلامی، اهواز، ایران

3 گروه خاکشناسی، دانشکده کشاورزی، دانشگاه زنجان، زنجان، ایران

چکیده

برای مدیریت پایداری اراضی، اطلاع از فعالیت‌ها و خصوصیات خاک و تغییرات زمانی و مکانی آنها ضروری است. طیف‌سنجی امواج مرئی و مادون قرمز نزدیک به دلیل دقت و سرعت عمل بالا قابلیت ویژه‌ای در شناسایی و تعیین خصوصیات خاک دارد. هدف این مطالعه ارزیابی دقت روش طیف‌سنجی مرئی-مادون قرمز نزدیک در برآورد مقدار کربن آلی(OC) و کل مواد خنثی شونده خاک (TNV)  خاک است. به این منظور تعداد 110 نمونه خاک از استان‌های خوزستان، یزد و تهران تهیه و در آزمایشگاه طیف‌سنجی گردید. طیف به‌دست آمده از دستگاه طیف‌سنج با 5 روش پیش‌پردازش فیلتر ساویتزکی گولای (SG)، مشتق اول همراه با ساویتزکی گولای  (FD-SG)، مشتق دوم همراه با ساویتزکی گولای (SD-SG)، واریانس استاندارد نرمال (SNV)، تصحیح پخشیده چندگانه (MSC) اصلاح شد. همچنین عملکرد دو روش PLSR و SVMR در برآورد ویژگی‌های خاک مقایسه گردید. نتایج نشان دادند که مدل PLSR نسبت به مدل SVMR در برآورد OC و TNV دقت بالاتری دارد. دربرآود  OC، مدل PLSR و روش پیش‌پردازش MSC (47/1= RPDVAL و 19/0 = RMSEVAL ،59/0 =VAL R2) بهترین عملکرد و روش پیش‌پردازش SD-SG، ضعیف­ترین عملکرد (52/0= RPDVAL و 27/0 = RMSEVAL ،15/0 =VAL R2) را نشان داد. همچنین برای TNV روش پیش‌پردازش (FD-SG) بهترین عملکرد (01/2= RPDVAL و 70/5 = RMSEVAL ،78/0 =VAL R2) و روش پیش‌پردازش (SD-SG) ضعیف­ترین عملکرد (31/0= RPDVAL و 13/11 = RMSEVAL ،1/0 =VAL R2) را نشان داده است. طول موج کلیدی برای OC در محدوده 421 و 612 نانومتر و برای TNV در محدوده 2315 و 2151 نانومتر مشاهده گردید. این مطالعه نشان داد که روش طیف‌سنجی Vis-NIR به علت دارا بودن اساس فیزیکی و در نظر گرفتن فاکتورهای تاثیرگذار، به عنوان یک مدل بزرگ مقیاس، قابلیت مناسبی برای ارزیابی و پیش­بینی OC و TNV خاک دارد.

کلیدواژه‌ها


عنوان مقاله [English]

Assessing the Visible–Near-Infrared Spectroscopy Method and PLSR and SVMR Methods in Modeling Organic Carbon and Total Neutralizing Value of Soil

نویسندگان [English]

  • Rokhsar Akbarifazli 1 2
  • teimour babaeinejad 2
  • Navid Ghanavati 2
  • Akbar Hasani 3
  • Mohammad Sadegh Askari 3
1 Department of Soil Science. Khoozestan Science and Research Branch, Islamic Azad University, Ahvaz, Iran
2
3 Department of soil science, faculty of Agriculture, university of Zanjan, Zanjan, Iran
چکیده [English]

For sustainable land management, it is necessary to understand the functions and characteristics of soils, and their spatial and temporal changes. Visible and near-infrared spectroscopy has a specific capability to identify and determine soil properties due to high accuracy and high-performance speed. The purpose of this study is to evaluate the accuracy of visible and near-infrared spectroscopy method in estimating soil organic matter and total neutralizing value. Therefore, 110 soil samples were collected from Khuzestan, Yazd and Tehran provinces, and spectral reflectance was performed using ASD FieldSpec3. The spectra obtained from the spectrometer were pre-processed using five methods including Savitzky-Golay filter (SG), the first derivative with the Savitzky-Golay filter (FD-SG), the second derivative with the Savitzky-Golay filter (SD-SG), the standard normal variate (SNV), and Multiplicative scatter correction (MSC). Also, the performance of PLSR and SVMR methods was compared in terms of soil organic carbon and total neutralizing value estimation. The results indicated that the PLSR model in estimating both organic carbon properties and total neutralizing value had higher accuracy compared to the SVR model. In estimation of soil organic carbon, PLSR method and MSC preprocessing method had the best performance (R2VAL=0.59, RMSEVAL=0.19 and PRDVAL=1.47) and the second derivative method had the least performance (R2VAL=0.15, RMSEVAL=0.27 and PRDVAL=0.52). Also for estimation of total neutralizing value, the first derivative preprocessing method had the best performance (R2VAL=0.78, RMSEVAL=5.70 and PRDVAL=2.01) and the second derivative method had the least performance (R2VAL=0.1, RMSEVAL=11.13, and PRDVAL=0.31). The key wavelengths were observed for soil organic matter in the range of 421- 612 nm and for total neutralizing value in the range of 2315- 2151 nm. This study showed that the Vis-NIR spectroscopy method, due to its physical basis and considering the influencing factors, as a large-scale model, makes it possible to evaluate and predict soil OC and TNV.

کلیدواژه‌ها [English]

  • Organic Carbon
  • Preprocessing
  • Regression
  • Spectroscopy
  • Total neutralizing value
Bashour, I. I. and Sayegh, A. H. (2007). Methods of analysis for soils of arid and semi-arid regions (p. 119). Rome, Italy: Food and Agriculture Organization of the United Nations.
Ben-Dor, E. and Banin, A. (1994). Visible and near-infrared (0.4–1.1 μm) analysis of arid and semiarid soils. Remote Sensing of Environment, 48(3), 261-274.
Ben‐Dor, E. and Banin, A. (1995). Near‐infrared analysis as a rapid method to simultaneously evaluate several soil properties. Soil Science Society of America Journal, 59(2), 364-372.
Chaternour, M., Landi A., Farrokhian firouzi A., Noroozi A., and Bahrami, H. (2020). Application of hyperspectral images in quantification of soil gypsum in center areas of Khuzestan province prone to dust generation. Applied Soil Research, 8(3):1-13.(In Farsi)
Chatrenour, M., Landi, A., Farrokhian Firouzi, A., Noroozi, A. and Bahrami, H. (2019a). ModelingSoil Salinity in Khuzestan Lands Susceptible for Dust ProductionUsing Visible-Near Infrared Spectroscopic Method. Iranian Journal of Soil Water Research, 50(8), 1951-1962.(In Farsi)
Chatrenour, M., Landi, A., Farrokhian Firouzi, A., Noroozi, A. and Bahrami, H. (2019b). Investigating soil Properties in susceptible areas of dust production in Khuzestan province by visible and wave-near infrared spectroscopy. Journal of Watershed Engineering and Management, 12(3), 670-685.(In Farsi)
Coutinho, M. F. B., Alari, F.O., Ferreira, M. C., Amaral, R. (2019). Green methodology for soil organic matter analysis using a national near infrared spectral library in tandem with learning machine.Geoderma , 338, 401–409.
De Santana, F. B., de Giuseppe, L.O., de Souza,M. A., Poppi, R. J. (2019). Green methodology for soil organic matter analysis using a national near infrared spectral library in tandem with learning machine. . Science of the Total Environment, 658, 895–900.
Farifteh, J., Van der Meer, F., Atzberger, C. and Carranza, E.J.M. (2007). Quantitative analysis of salt-affected soil reflectance spectra: A comparison of two adaptive methods (PLSR and ANN). Remote Sensing of Environment, 110, 59–78.
Florinsky, I.V., Eilers, R.G., Manning, G.R. and Fuller, L.G. (2002). Prediction of soil properties by digital terrain. Environmental Modelling and Software, 17, 295–311.
Geladi, P. and Kowalski, B.R. (1986). Partial least-squares regression: a tutorial. Analytica Chimica Acta, 185, 1–17.
Han, Y., Tang, Z., Sun, J., Xing, X., Zhang, M. and Cheng, J. (2019). Heavy metals in soil contaminated through e-waste processing activities in a recycling area: Implications for risk management. Process Safety and Environmental Protection, 125, 189-196.
Harrison, T.N. (2012). Experimental VNIR reflectance spectroscopy of gypsum dehydration: Investigating the gypsum to bassanite transition. American Mineralogist, 97(4), 598-609.
Hassani, A., Bahrami, H., Noroozi, A. and Oustan, S. (2014). Visible-near infrared reflectance spectroscopy for assessment of soil properties in gypseous and calcareous soils. Journal of Watershed Engineering and Management, 6(2),125-138.
Hong, Y., Chen, S., Liu, Y., Zhang, Y., Yu, L., Chen, Y., Cheng, H. and Liu, Y. (2019a). 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, 174, 104-116.
Hong, Y., Liu, Y., Chen, Y., Liu, Y., Yu, L., Liu, Y. and Cheng, H. (2019b). Application of fractional-order derivative in the quantitative estimation of soil organic matter content through visible and near-infrared spectroscopy. Geoderma, 337, 758-769.
Hu, X.Y. (2013). Application of visible/near-infrared spectra in modeling of soil total phosphorus. Pedosphere, 23(4), 417-421.
Khayamim, F., Khademi, H. and Ayoubi, S. (2018). Capability and limitations of clay minerals estimation in surface soils of the Isfahan province by Vis-NIR Spectroscopy. Iranian Journal of Soil Research, 32, 129–140.
Khayamim, F., Khademi, H., Stenberg, B. and Wetterlind, J. (2015). Capability of vis-NIR spectroscopy to predict selected chemical soil properties in Isfahan province. Isfahan University of Technology, 19(72), 81-92. (In Farsi)
Kuang, B. and Mouazen, A.M. (2011). Calibration of visible and near infrared spectroscopy for soil analysis at the field scale on three European farms. European Journal of Soil Science, 62(4), 629-636.
Mousavi, F., Abdi, E., Ghalandarzadeh, A., Bahrami, H., Majnounian, B. and Mirzaei, S. (2018). Estimate of soil cation exchange capacity using reflectance spectrometry. Journal of Forest Research and Development,  4, 347–361.
Nawar, S.,  Buddenbaum, H., Hill, J., Kozak, J.and Mouazen, A.M., (2016). Estimating the soil clay content and organic matter by means of different calibration methods of vis-NIR diffuse reflectance spectroscopy. Soil Tillage Reserach, 155, 510–522.
Ng, H. Y., Loka, V., Pooi, C. K. (2019). Treatment and hybrid modeling of domestic reverse osmosis concentrate using biological activated carbon. Desalination, 468, 114047.
Nocita, M., Stevens, A., Toth, G., Panagos, P., van Wesemael, B. and Montanarella, L. (2014). Prediction of soil organic carbon content by diffuse reflectance spectroscopy using a local partial least square regression approach. Soil Biology and Biochemistry, 68, 337-347.
Powlson, D.S., Brookes, P.C., Whitmore, A.P., Goulding, K.W.T., Hopkins, D.W. (2011). Soil Organic Matters. European Journal of Soil Science, 62, 1–4.
Rasooli, N., Farpoor, M.H., Khayamim, F. and Ranjbar, H. (2018). Prediction of selected soil properties using visible and near infrared spectroscopy in bardsir area, Kerman province. Iranian Journal of Soil Research, 32, 231–243.
Rial, M., Cortizas, A. M. and  Rodríguez-Lado, L. (2017). Understanding the spatial distribution of factors controlling topsoil organic carbon content in European soils. Science of the Total Environment, 609, 1411-1422.
Rossel, R. V. and Behrens, T. (2010). Using data mining to model and interpret soil diffuse reflectance spectra. Geoderma, 158(1-2), 46-54.
Rossel, R.V.,  Behrens, T.,  Ben-Dor, E., Brown, D.J.,  Demattê, J.A.M.,  Shepherd, K.D., ... and Aïchi, H. (2016). A global spectral library to characterize the world's soil. Earth-Science Reviews, 155, 198-230.
Rossel, R.V., Cattle, S.R., Ortega, A. and Fouad, Y. (2009). In situ measurements of soil colour, mineral composition and clay content by vis–NIR spectroscopy. Geoderma, 150(3-4), 253-266.
Smola, A. J. and Scholkopf, B. (2004). A tutorial on support vector regression, Statistics and Computing, 14, 199-222.
Stenberg, B., Viscarra Rossel, R.A.,  Mouazen,  A.M. and Wetterlind, J. (2010). Visible and Near Infrared Spectroscopy in Soil Science, In Donald L. Sparks, editor: Advances in Agronomy, Vol. 107, Burlington: Academic Press, 2010, pp. 163-215.
Stoner, E.R. and  Baumgardner,  M.F. (1981). Characteristic variations in reflectance of surface soils. Soil Science Society of America Journal, 45(6), 1161-1165.
Tumsavas, Z., Tekin, Y., Ulusoy, Y. and Mouazen, A.M. (2019). Prediction and mapping of soil clay and sand contents using visible and near-infrared spectroscopy. Biosystems Engineering, 177, 90-100.
Vapnik,V.N.(1998). Statistical learning theory. Adaptive and learning systems for signal processing. Commmunications and Control, 2, 1-740.
Viscarra Rossel, R.A., Behrens, T., Ben-Dor, E., Brown, D.J.,…and Ji, W. (2016). A global spectral library to characterize the world’s soil. Earth-Science Reviews, 155, 198–230.
Viscarra Rossel, R.A., Cattle, S.R., Ortega, A., Fouad, Y., (2009). In situ measurements of soil colour, mineral composition and clay content by vis-NIR spectroscopy. Geoderma, 150, 253–266.
Walkly, A. and Black, I.A. (1934). An examination of the Dugtijaraff method for determining soil organic matter and proposed modification of the chronic and titration method. Soil Science, 37, 23-38.
Wan, M., Qu, M., Hu, W., Li, W., Zhang, C., Cheng, H. and Huang, B. (2019). Estimation of soil pH using PXRF spectrometry and Vis-NIR spectroscopy for rapid environmental risk assessment of soil heavy metals. Process Safety and Environmental Protection, 132,73–81.
Wang, J., He, T., Lv, C., Chen, Y. and Jian, W. (2010). Mapping soil organic matter based on land degradation spectral response units using Hyperion images. International Journal of Applied Earth Observation and Geoinformation, 12, 171-180.
Wilding, L.P. (1985). Spatial variability: its documentation, accomodation and implication to soil surveys. In Soil spatial variability, Las Vegas NV, 30 November-1 December 1984 (pp. 166-194).
Wold, S. (2001a). M. Sj ostrom, L. Eriksson. Chemom. Intell. Lab. Syst, 58, 109-130.Wu, Y., Vapnik, V.N., 1999. Statistical Learning Theory, Technometrics.
Wold, S., Sjostrom, M., Eriksson, L., (2001b). PLS-regression: A basic tool of chemometrics. Chemom. Intell. Lab. Syst. 58, 109–130.
Xie, X. L. and Li, A.B. (2018). Identification of soil profile classes using depth-weighted visible–near-infrared spectral reflectance. Geoderma, 325, 90-101.
 Xu, C., Zeng, W., Huang, J., Wu, J. and Van Leeuwen, W. J. (2016). Prediction of soil moisture content and soil salt concentration from hyperspectral laboratory and field data. Remote Sensing, 8(1), 42.
Xuemei, L., and L. Jianshe. (2013). Measurement of soil properties using visib le and short wave-near infrared spectroscop y and multivariate calibration. Measurement. 46(10):3808 -3814.