대한지리학회지 (Journal of the Korean Geographical Society)

대한지리학회 (The Korean Geographical Society)
권호 표지

산지토양의 탄소와 질소 예측을 위한 가시 근적외선 분광반사특성 분석의 전처리 방법 비교

Evaluating Spectral Preprocessing Methods for Visible and Near Infrared Reflectance Spectroscopy to Predict Soil Carbon and Nitrogen in Mountainous Areas

  • 정관용 (바이로이트대학 지구과학과)
  • 투고 : 2016.08.30
  • 발행 : 2016.08.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

토양 예측은 지속가능한 산지관리 측면에서 필요한 토양특성자료를 제공할 수 있다. 이중 가시 근적외선 분광반사 특성을 이용한 토양 예측은 저비용, 빠른 분석과 비파괴 측정, 비교적 높은 정확도로 관심을 받고 있다. 일반적으로 토양 분광반사특성 측정 과정에서 잡음이 나타날 수 있어 전처리 과정이 필요하다. 하지만 이러한 전처리 방법을 비교하고 평가하는 작업이 거의 이루어지지 못 했다. 본 연구에서는 토양 탄소와 질소 예측을 위해 5가지 전처리 방법을 비교하였다. 이는 연속체 제거, Savitzky-Golay 변환, 이산 웨이블렛(wavelet) 변환, 1차와 2차 도함수 변환이다. 토양예측 모델로 부분 최소제곱 회귀모형을 사용하였고, 총 153개 시료 중에서 검증을 위해 122개 훈련자료와 31개의 검증자료로 나누어 평가하였다. 전반적으로 토양시료의 탄소 함량이 높을수록 토양에 대한 입사 에너지의 흡수가 커지는 특성을 보였다. 파장별로는 가시광선 영역(650nm와 700nm)이 토양 탄소 그리고 질소와 가장 높은 상관관계를 보였다. 전처리 비교에서 연속체 제거가 토양 탄소(9.53mg/g)와 질소(0.79mg/g)에 대해 가장 높은 정확도(Root Mean Square Error)를 보였다. 따라서 토양 탄소와 질소 예측을 위해 연속체 제거가 가장 효과적인 분광반사특성 분석의 전처리 방법으로 판단되었다. 시각적인 평가에서 웨이블릿 변환이나 Savitzky-Golay 변환은 차이가 거의 없었고, 평가 결과도 유사했다. 따라서 다소 계산과정이 간단한 Savitzky-Golay 변환이 선호될 수 있다.

The soil prediction can provide quantitative soil information for sustainable mountainous ecosystem management. Visible near infrared spectroscopy, one of soil prediction methods, has been applied to predict several soil properties with effective costs, rapid and nondesctructive analysis, and satisfactory accuracy. Spectral preprocessing is a essential procedure to correct noisy spectra for visible near infrared spectroscopy. However, there are no attempts to evaluate various spectral preprocessing methods. We tested 5 different pretreatments, namely continuum removal, Savitzky-Golay filter, discrete wavelet transform, 1st derivative, and 2nd derivative to predict soil carbon(C) and nitrogen(N). Partial least squares regression was used for the prediction method. The total of 153 soil samples was split into 122 samples for calibration and 31 samples for validation. In the all range, absorption was increased with increasing C contents. Specifically, the visible region (650nm and 700nm) showed high values of the correlation coefficient with soil C and N contents. For spectral preprocessing methods, continuum removal had the highest prediction accuracy(Root Mean Square Error) for C(9.53mg/g) and N(0.79mg/g). Therefore, continuum removal was selected as the best preprocessing method. Additionally, there were no distinct differences between Savitzky-Golay filter and discrete wavelet transform for visual assessment and the methods showed similar validation results. According to the results, we also recommended Savitzky-Golay filter that is a simple pre-treatment with continuum removal.

키워드

참고문헌

  1. 강신규.John Tenhunen, 2010, "산지복잡지형과 생태적 비균질성: 산지경관의 생산성과 수자원/수질에 관한 생태계 서비스 평가," 한국농림기상학회지, 12(4), 307-316. https://doi.org/10.5532/KJAFM.2010.12.4.307
  2. 박수진.손연규.홍석영.박찬원.장용선, 2010, "한국 주요 토양유형의 공간적 분포와 토양형성요인을 이용한 예측가능성 평가," 대한지리학회지, 45(1), 95-118.
  3. 박형동.현창욱.오승찬, 2011, 에너지자원 원격탐사, 씨아이알.
  4. 정관용, 2011, "산지토양특성의 공간적 분포와 예측가능성," 지리학논총, 57, 21-42.
  5. 정관용.박수진, 2015, "지형분류를 이용한 산지 토양 예측가능성," 한국지형학회지, 22(3), 43-61.
  6. 정진현.구교상.이충화.김춘식, 2002, "우리나라 산림 토양의 지역별 이화학적 특성," 한국임학회지, 91(6), 694-700.
  7. 최은영.홍석영.김이현.송관철.장용선, 2009, "가시.근적외 분광 스펙트럼을 이용한 토양 이화학성 추정," 한국토양비료학회지, 42(6), 522-528.
  8. 최은영.홍석영.김이현.장용선, 2010, "분광학을 이용한 토양 유기물 추정 및 분포도 작성," 한국토양비료학회지, 43(6), 968-974.
  9. Adamchuk, V. I. and Rossel, R. A. V., 2010, Development of On-the-Go Proximal Soil Sensor Systems, In R. A. V. Rossel, A. B. McBratney and B. Minasny (eds.), Proximal Soil Sensing, Springer, Dordrecht, 15-28.
  10. Akansu, A. N. and Haddad, R. A., 2001. Multiresolution Signal Decomposition: Transforms, Subbands, and Wavelets, Academic Press, San Diego.
  11. Breiman, L., 2001, Random forests. Machine learning, 45(1), 5-32. https://doi.org/10.1023/A:1010933404324
  12. Chang, C. W., Laird, D. A., Mausbach, M. J. and Hurburgh, C. R., 2001, Near-Infrared Reflectance Spectroscopy-Principal Components Regression Analyses of Soil Properties, Soil Science Society of America Journal, 65(2), 480-490. https://doi.org/10.2136/sssaj2001.652480x
  13. Chang, C. W. and Laird, D. A., 2002, Near-infrared reflectance spectroscopic analysis of soil C and N, Soil Science, 167(2), 110-116. https://doi.org/10.1097/00010694-200202000-00003
  14. Choe, E., van de Meer, F., van Ruitenbeek, F., van der Werff, H., de Smeth, B. and Kim, K., 2008, Mapping of heavy metal pollution in stream sediments using combined geochemistry, field spectroscopy, and hyperspectral remote sensing: A case study of the Rodalquilar mining area, SE Spain, Remote Sensing of Environment, 112, 3222-3233. https://doi.org/10.1016/j.rse.2008.03.017
  15. Chun, H. C., Hong, S. Y., Song, K. C. and Kim, Y., 2012, Predicting Organic Matter content in Korean Soils Using Regression rules on Visible-Near Infrared Diffuse Reflectance Spectra, Korean Journal of Soil Science and Fertilizer, 45(4), 497-502. https://doi.org/10.7745/KJSSF.2012.45.4.497
  16. Clark, R. N. and Roush, T. L., 1984, Reflectance spectroscopy: Quantitative analysis techniques for remote sensing applications, Journal of Geophysical Research: Solid Earth, 89(B7), 6329-6340. https://doi.org/10.1029/JB089iB07p06329
  17. Dayal, B. S. and MacGregor, J. F., 1997, Improved PLS Algorithms. Journal of Chemometrics, 11, 73-85. https://doi.org/10.1002/(SICI)1099-128X(199701)11:1<73::AID-CEM435>3.0.CO;2-#
  18. Dematte, J. A. M. and da Silva Terra, F., 2014, Spectral pedology: A new perspective on evaluation of soils along pedogenetic alterations, Geoderma, 217-218, 190-200. https://doi.org/10.1016/j.geoderma.2013.11.012
  19. Donoho, D. L. and Johnstone, I. M., 1994, Ideal spatial adapatation by wavelet shrinkage, Biometrika, 81(3), 425-455. https://doi.org/10.1093/biomet/81.3.425
  20. Hartemink, A. E. and Minasny, B., 2016, Digital soil morphometrics, Springer International Publishing, Switzerland.
  21. Hong, S. Y., Lee, K., Minasny, B., Kim, Y. and Hyun, B. K., 2014, Predicting Soil Chemical Properties with Regression Rules from Visible-near Infrared Reflectance Spectroscopy, Korean Journal of Soil Science and Fertilizer, 47(5), 319-323. https://doi.org/10.7745/KJSSF.2014.47.5.319
  22. Jensen, J. R., 2006, Remote sensing of the environment: An earth resource perspective, Pearson education.
  23. Lal, R., 2004, Soil Carbon Sequestration Impacts on Global Climate Change and Food Security, Science, 304(5677), 1623-1627. https://doi.org/10.1126/science.1097396
  24. McBratney, A. B., Mendonca Santos, M. L. and Minasny, B., 2003, On digital soil mapping, Geoderma, 117, 3-52. https://doi.org/10.1016/S0016-7061(03)00223-4
  25. McKay, M. D., Beckman, R. J. and Conover, W. J., 1979, A compa rison of three method s for selec ting values of input variables in the analysis of output from a computer code, Technometrics, 21(2), 239-245. https://doi.org/10.1080/00401706.1979.10489755
  26. Minasny, B. and McBratney, A. B., 2006, A conditioned Latin hypercube method for sampling in the presence of ancillary information, Computers & Geosciences, 32(9), 1378-1388. https://doi.org/10.1016/j.cageo.2005.12.009
  27. Minasny, B. and McBratney, A. B., 2008, Regression rules as a tool for predicting soil properties from infrared reflectance spectroscopy, Chemometrics and Intelligent Laboratory Systems, 94(1), 72-79. https://doi.org/10.1016/j.chemolab.2008.06.003
  28. Nason, G., 2008, Wavelet methods in statistics with R, Springer Science & Business Media, New York.
  29. Park, S. J., Ruecker, G. R., Agyare, W. A., Akramhanov, A., Kim, D. and Vlek, P. L. G., 2009, Influence of Grid Cell Size and Flow Routing Algorithm on Soil-Landform Modeling, Journal of the Korean Geographical Society, 44(2), 122-145.
  30. Quinlan, J. R., 1992, C4. 5: Programming for machine learning, Morgan Kauffmann, California.
  31. Ramirez-Lopez, L. and Stevens, A., 2014, Pre-processing, sampling and modelling (soil) vis-IR data using the 'prospectr' and 'resemble' packages, Pedometron, 34, 9-14.
  32. Rossel, R. A. V., Walvoort, D. J. J., McBratney, A. B., Janik, L. J. and Skjemstad, J. O., 2006, Visible, near infrared, mid infrared or combined diffuse reflectance spectroscopy for simultaneous assessment of various soil properties, Geoderma, 131(1-2), 59-75. https://doi.org/10.1016/j.geoderma.2005.03.007
  33. Rossel, R. A. V. and Lark, R. M., 2009, Improved analysis and modelling of soil diffuse reflectance spectra using wavelets, European Journal of Soil Science, 60(3), 453-464. https://doi.org/10.1111/j.1365-2389.2009.01121.x
  34. Rossel, R. A. V. and Behrens, T., 2010, Using data mining to model and interpret soil diffuse reflectance spectra, Geoderma, 158(1-2), 46-54. https://doi.org/10.1016/j.geoderma.2009.12.025
  35. Rossel, R. A. V., Rizzo, R., Demattê, J. A. M. and Behrens, T., 2010a, Spatial Modeling of a Soil Fertility Index using Visible-Near-Infrared Spectra and Terrain Attributes, Soil Science Society of America Journal, 74(4), 1293-1300. https://doi.org/10.2136/sssaj2009.0130
  36. Rossel, R. A. V., McBratney, A. B. and Minasny, B., 2010b, Proximal soil sensing, Springer Science & Business Media, Dordrecht.
  37. Savitzky, A. and Golay, M. J. E., 1964, Smoothing and Differentiation of Data by Simplified Least Squares Procedures, Analytical Chemistry, 36(8), 1627-1639. https://doi.org/10.1021/ac60214a047
  38. Schoenholtz, S. H., Van Miegroet, H. and Burger, J. A., 2000, A review of chemical and physical properties as indicators of forest soil quality: Challenges and opportunities, Forest Ecology and Management, 138(1-3), 335-356. https://doi.org/10.1016/S0378-1127(00)00423-0
  39. Scull, P., Franklin, J., Chadwick, and O. A., McArthur, D., 2003, Predictive soil mapping: a review, Progress in Physical Geography, 27(2), 171-197. https://doi.org/10.1191/0309133303pp366ra
  40. Shukla, M. K., 2011, Soil hydrology, land use and agriculture: measurement and modelling, CABI, Oxfordshire.
  41. Soriano-Disla, J. M., Janik, L. J., Rossel, R. A. V., Macdonald, L. M. and McLaughlin, M. J., The performance of visible, near-, and mid-infrared reflectance spectroscopy for prediction of soil physical, chemical and biological properties, Applied Spectroscopy Reviews, 49(2), 139-186. https://doi.org/10.1080/05704928.2013.811081
  42. Stenberg, B., Rossel, R. A. V., Mouazen, A. M. and Wetterlind, J., 2010, Visible and Near Infrared Spectroscopy in Soil Science, Advances in agronomy, 107, 163-215.
  43. Stenberg, B. and Rossel, R. A. V., 2010, Diffuse reflectance spectroscopy for high-resolution soil sensing, In R. A. V. Rossel, A. B. McBratney and B. Minasny (eds.), Proximal Soil Sensing, Springer, Dordrecht, 29-47.
  44. Stevens, A., Nocita, M., Toth, G., Montanarella, L. and van Wesemael, B., 2013, Prediction of Soil Organic Carbon at the European Scale by Visible and Near InfraRed Reflectance Spectroscopy, PLoS ONE, 8(6).
  45. Sweeney, K. E., Roering, J. J., Almond, P. and Reckling, T., 2012, How steady are steady-state landscapes? Using visible-near-infrared soil spectroscopy to quantify erosional variability, Geology, 40, 807-810. https://doi.org/10.1130/G33167.1
  46. Vapnik, V., 1995, The Nature of Statistical Learning Theory, Springer Verlag, New York.
  47. Vitousek, P. M., Hattenschwiler, S., Olander, L. and Allison, S., 2002, Nitrogen and Nature, Ambio: A Journal of the Human Environment, 31(2), 97-101. https://doi.org/10.1579/0044-7447-31.2.97
  48. Wold, S., Ruhe, A., Wold, H. and Dunn III, W. J., 1984, The collinearity problem in linear regression, the partial least squares (PLS) approach to generalized inverses, SIAM Journal on Scientific and Statistical Computing, 5(3), 735-743. https://doi.org/10.1137/0905052