한국지반공학회논문집 (Journal of the Korean Geotechnical Society)

한국지반공학회 (Korean Geotechnical Society)
권호 표지
DOI QR코드

DOI QR Code

초분광 근적외선 영상 기술을 이용한 흙의 함수비 측정 기술

Soil Water Content Measurement Technology Using Hyperspectral Visible and Near-Infrared Imaging Technique

  • 임환희 (한국과학기술원 건설및환경공학과) ;
  • 전에녹 (한국과학기술원 건설및환경공학과) ;
  • 이득환 (한국과학기술원 건설및환경공학과) ;
  • 전준서 (한국건설기술연구원 건축안전연구센터 & 지진안전연구센터) ;
  • 이승래 (한국과학기술원 건설및환경공학과)
  • Lim, Hwan-Hui (Dept. of Civil and Environmental Engrg., KAIST) ;
  • Cheon, Enok (Dept. of Civil and Environmental Engrg., KAIST) ;
  • Lee, Deuk-Hwan (Dept. of Civil and Environmental Engrg., KAIST) ;
  • Jeon, Jun-Seo (Building Safety Research Center & Seismic Safety Research Center, Korea Institute of Civil Engineering and Building Technology) ;
  • Lee, Seung-Rae (Dept. of Civil and Environmental Engrg., KAIST)
  • 투고 : 2019.09.10
  • 심사 : 2019.11.11
  • 발행 : 2019.11.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 연구에서는 초분광 근적외선 영상을 이용하여 광역지역의 흙의 함수비 변화를 간편한 방법으로 예측하기 위해 수행되었다. 근적외선(VNIR) 영역대에서 변화되는 함수비 별로 모래, 화강풍화토(우면산, 구룡산, 대모산, 황령산), 카오리나이트를 초분광 카메라로 촬영하여 반사율을 추출하였고, 흙의 함수비와 가장 연관성 높은 매개변수를 찾기 위하여 선정된 매개변수와 함수비를 변수로하여 Partial Least Square Regression(PLSR) 분석을 이용하여 함수비 예측모델을 구축하였다. 함수비 예측모델을 구축한 결과, 흙의 종류에 관계없이 Area of reflectance(Near-infrared, NIR)의 매개변수가 흙의 함수비와 가장 연관성 높은 매개변수임을 확인하였고, 모든 흙에서 예측모델의 정확도(R2)는 0.9 이상임을 확인하였다. 또한 흙의 실제 함수비와 비교 검증해본 결과, 평균절대백분율(mean absolute percentage error, MAPE)이 15%이내로 확인되었다. 따라서 대상 흙들에서 50% 이내에서 변화되는 함수비 예측 가능성을 확인하였다. 본 연구를 통해 초분광 근적외선 영상을 이용하여 모래, 화강풍화토, 카오리나이트의 함수비 예측 가능성을 확인하였고, 모델의 정확도 개선 및 더 높은 범위의 함수비 예측을 위해서는 흙의 분류모델 개발이 추가적으로 필요하다고 판단된다.

In this study, a simple method to estimate the soil water content variation in a wide area was proposed using hyperspectral near-infrared images. The reflectance data of a sand, granite soils, and a kaolinite were measured by reflecting the soil samples with different wavelengths in the visible and near-infrared (VNIR) regions using hyperspectral cameras. The measured reflectances and parameters were used to build a water content prediction model using the Partial Least Square Regression (PLSR) analysis. In the water content prediction model, the Area of Reflectance (Near-infrared, NIR) parameter was the most suitable parameter to determine the water content. The parameter was applicable regardless of the soil type, as the coefficient of determination (R2) exceeded 0.9 for each soil sample. Additionally, the mean absolute percentage error (MAPE) was less than 15% when compared with the actual water content of the soil. Therefore, the predictability of water content variation for soils with water content lower than 50% was confirmed. Accordingly through this study, the predictability of water content variation in several soil types using the hyperspectral near-infrared images was confirmed. For further development, a model that incorporates soil classification would be required to improve the accuracy of the model and to predict higher range of water contents.

키워드

참고문헌

  1. Bae, H., Seo, Y., Kim, D., Lohumi, S., Park, E., and Cho, B. (2016), "Development of Non-Destructive Sorting Technique for Viability of Watermelon Seed by Using Hyperspectral Image Processing", Journal of the Korean Society for Nondestructive Testing, Vol.36(1), pp.35-44. https://doi.org/10.7779/JKSNT.2016.36.1.35
  2. Berney, E., Kyzar, J., and Oyelami, L. (2012), "Device comparison for determining field soil moisture content", U.S. Army Engineering Research and Development Center, ERDC/GSL TR-11-42.
  3. Bowers, S. and Hanks, R. (1965), "Reflection of Radiant Energy from Soils", Soil Science, Vol.100(2), pp.130-138. https://doi.org/10.1097/00010694-196508000-00009
  4. Jia, S., Li, H., Wang, Y., Tong, R., and Li, Q. (2017), "Hyperspectral Imaging Analysis for the Classification of Soil Types and the Determination of Soil Total Nitrogen", Sensors, Vol.17(10), pp.2252 https://doi.org/10.3390/s17102252
  5. Kim, D., Seo, J., Lee, C., and Woo, C. (2016), "Analysis on the Behaviors of Soil Water Characteristic Sensors through Rainfall- Induced Landslide Flume Experiments", Journal of the Korean Society of Hazard Mitigation, Vol.16, pp.209-218.
  6. Kim, J., Lee, K., Oh, M., Choi, K., Yang, S., Kim, W., and Park, H. (2019), "Evaluation of Moisture and Feed Values for Winter Annual Forage Crops Using Near Infrared Reflectance Spectroscopy", Journal of The Korean Society of Grassland and Forage Science, Vol.39(2), pp.114-120. https://doi.org/10.5333/KGFS.2019.39.2.114
  7. Kim, K. and Hwang, K. (2012), "A Study on the Demand Forecasting and Efficient Operation of Jeju National Airport using seasonal ARIMA model", Journal of the Korea Academia-Industrial cooperation Society, Vol.13(8), pp.3381-3388. https://doi.org/10.5762/KAIS.2012.13.8.3381
  8. Njoku, E.G and Entekhabi, D. (1996), "Passive microwave remote sensing of soil moisture", Journal of Hydrology, Vol.184, pp.101-129. https://doi.org/10.1016/0022-1694(95)02970-2
  9. Park, S., Kim, J., and LEE, S. (2017), "A Study on Speedy Water Content Measurement Method for Soils", Journal of The Korean Geotechnical Society, Vol.33, pp.57-65. https://doi.org/10.7843/kgs.2017.33.1.57
  10. Specim.fi. (2019). Datacube. [online] Availavle at : https://www.specim.fi/iq/manual/software/iq/topics/data-cube.html [Accessed 9 Sep.2019]
  11. Ulaby, F., Dubois, P., and Zyl, J. (1996), "Rader Mapping of Surface Soil Moisture", Journal of Hydrology, Vol.184, pp.57-84. https://doi.org/10.1016/0022-1694(95)02968-0
  12. Wang, F., Gao, J., and Zha, Y. (2018), "Hyperspectral Sensing of Heavy Metals in Soil and Vegetation: Feasibility and Challenges", ISPRS Journal of Photogrammetry and Remote Sensing, Vol.136, pp.73-84. https://doi.org/10.1016/j.isprsjprs.2017.12.003
  13. Zhang, X., Younan, N., and O'Hara, C. (2005), "Wavelet Domain Statistical Hyperspectral Soil Texture Classification", IEEE Transactions on Geoscience and Remote Sensing, Vol.43(3), pp.615-618. https://doi.org/10.1109/TGRS.2004.841476