Economic and Environmental Geology (자원환경지질)

The Korean Society of Economic and Environmental Geology (대한자원환경지질학회)
권호 표지
DOI QR코드

DOI QR Code

Discussion on Detection of Sediment Moisture Content at Different Altitudes Employing UAV Hyperspectral Images

무인항공 초분광 영상을 기반으로 한 고도에 따른 퇴적물 함수율 탐지 고찰

  • Kyoungeun Lee (Department of Earth Environmental & Space Department of Earth, Environmental & Space Sciences Sciences, Chungnam National University) ;
  • Jaehyung Yu (Department of Earth Environmental & Space Department of Earth, Environmental & Space Sciences Sciences, Chungnam National University) ;
  • Chanhyeok Park (Department of Astronomy, Space Science, & Geology, Chungnam National University) ;
  • Trung Hieu Pham (Faculty of Geology, University of Science, Vietnam National University)
  • 이경은 (충남대학교 지구환경.우주융합과학과 ) ;
  • 유재형 (충남대학교 지구환경.우주융합과학과 ) ;
  • 박찬혁 (충남대학교 우주.지질학과) ;
  • Received : 2024.06.24
  • Accepted : 2024.08.07
  • Published : 2024.08.30
Download PDF
⟨ Previous Next ⟩

Abstract

This study examined the spectral characteristics of sediments according to moisture content using an unmanned aerial vehicle (UAV)-based hyperspectral sensor and evaluated the efficiency of moisture content detection at different flight altitudes. For this purpose, hyperspectral images in the 400-1000nm wavelength range were acquired and analyzed at altitudes of 40m and 80m for sediment samples with various moisture contents. The reflectance of the sediments generally showed a decreasing trend as the moisture content increased. Correlation analysis between moisture content and reflectance showed a strong negative correlation (r < -0.8) across the entire 400-900nm range. The moisture content detection model constructed using the Random Forest technique showed detection accuracies of RMSE 2.6%, R2 0.92 at 40m altitude and RMSE 2.2%, R2 0.95 at 80m altitude, confirming that the difference in accuracy between altitudes was minimal. Variable importance analysis revealed that the 600-700nm band played a crucial role in moisture content detection. This study is expected to be utilized in efficient sediment moisture management and natural disaster prediction in the field of environmental monitoring in the future.

본 연구는 무인항공기 기반 초분광 센서를 활용하여 퇴적물의 함수율에 따른 분광학적 반응 특성을 고찰하고, 비행 고도에 따른 함수율 탐지 효율성을 평가하였다. 이를 위해 다양한 함수율을 가진 퇴적물 시료를 대상으로 40m와 80m 고도에서 400~1000nm 파장 대역의 초분광 영상을 획득하고 분석하였다. 퇴적물의 반사도는 함수율이 증가함에 따라 전반적으로 감소하는 경향을 보였다. 함수율과 반사도 사이의 상관관계 분석 결과, 400~900nm 전 영역에서 강한 음의 상관관계(r < -0.8)를 보였다. 랜덤포레스트 기법을 활용한 함수율 탐지모델 구축 결과, 40m와 80m 고도에서의 탐지 정확도는 각각 RMSE 2.6%, R2 0.92와 RMSE 2.2%, R2 0.95로 나타나 고도 간 정확도 차이가 미미함을 확인하였다. 변수 중요도 분석 결과, 600~700nm 대역이 함수율 탐지에 주요한 역할을 하는 것으로 나타났다. 본 연구는 향후 환경 모니터링 분야에서 효율적인 퇴적물의 수분 관리와 자연재해 예측에 활용될 수 있을 것으로 기대된다.

Keywords

Acknowledgement

본 논문을 심사 해주신 심사위원님들께 감사드린다. 본 연구는 충남대학교 학술 연구비에 의해 지원되었다.

References

  1. A.I. de Castro, J. Torres-Sanchez, J.M. Pena, F.M. Jimenez-Brenes, O. Csillik and F. Lopez-Granados (2018) An automatic random forest-OBIA algorithm for early weed mapping between and within crop rows using UAV imagery. Remote Sens., v.10, n.2, p.1-21. doi: 10.3390/rs10020285 
  2. Andrew W Western, Sen-Lin Zhou, Rodger B Grayson, Thomas A McMahon, Gunter Bloschl, David J Wilson (2004) Spatial correlation of soil moisture in small catchments and its relationship to dominant spatial hydrological processes. Journal of Hydrology, v.286(1-4), p.113-134, ISSN 0022-1694, https://doi.org/10.1016/j.jhydrol.2003.09.014. 
  3. Breiman, L. (2001) Random forests. Machine Learning, v.45, p.5-32. doi: 10.1023/A:1010933404324 
  4. C. Nolet, A. Poortinga, P. Roosjen, H. Bartholomeus and G. Ruessink (2014) Measuring and modeling the effect of surface moisture on the spectral reflectance of coastal beach sand. PLoS One, v.9, p.e112151-9. doi: 10.1371/journal.pone.0112151 
  5. Choe, E.Y., Hong, S.Y., Kim, K.W., Kim, Y.H. and Zhang, Y.S. (2010) Monitoring of Soil Properties using VNIR Spectroscopy. Korean Society of Soil Science and Fertilizer, p.94-103 (in Korean). 
  6. D.B. Lobell and G.P. Asner (2002) Moisture effects on soil reflectance. Soil Sci. Soc. Am. J., v.66, p.722-727. doi: 10.2136/sssaj2002.7220 
  7. Ditzler, C., K. Scheffe, and H.C. Monger (2017) Soil science division staff. Soil Survey Manual, 603. 
  8. Dopper, V., Rocha, A.D., Berger, K., Granzig, T., Verrelst, J., Kleinschmit, B. and Forster, M. (2022) Estimating soil moisture content under grassland with hyperspectral data using radiative transfer modelling and machine learning. International Journal of Applied Earth Observation and Geoinformation, v.110, 102817. doi: 10.1016/j.jag.2022.102817 
  9. E.J.M. Carranza and A.G. Laborte (2015) Random forest predictive modeling of mineral prospectivity with small number of prospects and data with missing values in Abra (Philippines). Comput. Geosci., v.74, p.60-70. doi: 10.1016/j.cageo.2014.10.004 
  10. Fushiki, T. (2011) Estimation of prediction error by using K-fold cross-validation. Statistics and Computing, v.21, p.137-146. doi:10.1007/s11222-009-9153-8 
  11. Ge, X., Ding, J., Jin, X., Wang, J., Chen, X., Li, X., Liu, J. and Xie, B. (2021) Estimating Agricultural Soil Moisture Content through UAV-Based Hyperspectral Images in the Arid Region. Remote Sens., v.13, 1562. https://doi.org/10.3390/rs13081562. 
  12. Guo, L., Chehata, N., Mallet, C. and Boukir, S. (2011) Relevance of airborne lidar and multispectral image data for urban scene classification using Random Forests. ISPRS J. Photogramm. Remote Sens., v.66, p.56-66. doi: 10.1016/j.isprsjprs.2010.08.007 
  13. H. Kim, J. Yu, L. Wang, C. Park, H.S. Han and S.-G. Jang (2022) Analysis on Effective UAS Survey Conditions for Classification of Coastal Sediments. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, v.15, p.1163-1173. doi: 10.1109/JSTARS.2021.3136228. 
  14. H. Shin, J. Yu, Y. Jeong, L. Wang and D.-Y. Yang (2017) Casebased regression models defining the relationships between moisture content and shortwave infrared reflectance of beach sands. IEEE J. Sel. Topics Appl. Earth Observat. Remote Sens., v.10, n.10, p.4512-4521. doi: 10.1109/JSTARS.2017.2723912 
  15. Haein Shin, Jaehyung Yu, Jieun Kim, Dongyoon Yang and Gilljae Lee (2015). Mapping the moisture content of coastal sediments using ASTER data for spectroscopic and mineralogical analyses: a case study in South Korea. Remote Sensing Letters, v.6(6), p.488-497. doi:10.1080/2150704X.2015.1049379. 
  16. J. Shin, J. Yu, L. Wang, J. Seo, H.H. Huynh and G. Jeong (2023) Spectral Indices to Assess Pollution Level in Soils: Case-Adaptive and Universal Detection Models for Multiple Heavy Metal Pollution Under Laboratory Conditions. IEEE Transactions on Geoscience and Remote Sensing, v.61, p.1-16, n.4504516. doi: 10.1109/TGRS.2023.3297126. 
  17. Jeon, E., Kim, K., Cho, S. and Kim, S. (2019) A Comparative Study of Absolute Radiometric Correction Methods for Drone-borne Hyperspectral Imagery. Korean Journal of Remote Sensing, v.35(2), p.203-215. https://doi.org/10.7780/KJRS.2019.35.2.1. 
  18. Kokaly, R.F. and Clark, R.N. (1999) Spectroscopic determination of leaf biochemistry using band-depth analysis of absorption features and stepwise multiple linear regression. Remote Sensing of Environment, v.67(3), p.267-287. doi: 10.1016/S0034-4257(98)00084-4 
  19. Lee, K.Y., K.C. Lee, J.E. Kim, S. Kim, J.M. Ahn and T.H. Im (2015) A study on the nutrient release characteristics from sediments in Nak-dong River. Journal of Korean Society on Water Environment, v.31(6), p.644-652. doi: 10.15681/KSWE.2015.31.6.644 
  20. Lobell, D.B. and Asner, G.P. (2002) Moisture effects on soil reflectance. Soil Science Society of America Journal, v.66(3), p.722-727. doi: 10.2136/sssaj2002.7220 
  21. Luo, W., Xu, X., Liu, W., Liu, M., Li, Z., Peng, T., Xu, C., Zhang, Y. and Zhang, R. (2019) UAV based soil moisture remote sensing in a karst mountainous catchment. Catena, v.174, p.478-489. https://doi.org/10.1016/j.catena.2018.11.017. 
  22. Mccoll, K.A., Alemohammad, S.H., Akbar, R., Konings, A.G., Yueh, S. and Entekhabi, D. (2017) The global distribution and dynamics of surface soil moisture. Nat. Geosci., v.10(2), p.100-104. https://doi.org/10.1038/ngeo2868. 
  23. Minghan Cheng, Xiyun Jiao, Yadong Liu, Mingchao Shao, Xun Yu, Yi Bai, Zixu Wang, Siyu Wang, Nuremanguli Tuohuti, Shuaibing Liu, Lei Shi, Dameng Yin, Xiao Huang, Chenwei Nie, and Xiuliang Jin (2022) Estimation of soil moisture content under high maize canopy coverage from UAV multimodal data and machine learning. Agricultural Water Management, v.264, 107530, ISSN 0378-3774. https://doi.org/10.1016/j.agwat.2022.107530. 
  24. Peretyazhko, T. and Sposito, G. (2005) Iron(III) reduction and phosphorous solubilization in humid tropical forest soils. Geochimica et Cosmochimica Acta, v.69(14), p.3643-3652. doi:10.1016/j.gca.2005.03.045 
  25. Robinson, D.A., Jones, S.B., Wraith, J.M., Or, D. and Friedman, S.P. (2003) A Review of Advances in Dielectric and Electrical Conductivity Measurement in Soils Using Time Domain Reflectometry. Vadose Zone Journal, v.2, p.444-475. https://doi.org/10.2136/vzj2003.4440. 
  26. Rodriguez, J.D., Perez, A. and Lozano, J.A. (2009) Sensitivity analysis of k-fold cross validation in prediction error estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, v.32(3), p.569-575. doi: 10.1109/TPAMI.2009.187 
  27. Rodriguez-Galiano, V.F., Ghimire, B., Rogan, J., Chica-Olmo, M. and Rigol-Sanchez, J.P. (2012) An assessment of the effectiveness of a random forest classifier for land-cover classification. ISPRS J. Photogramm. Remote Sens., v.67, p.93-104. doi: 10.1016/j.isprsjprs.2011.11.002 
  28. Rosa Agliata, Thom A. Bogaard, Roberto Greco, Aldo Minardo, Luigi Mollo and Susan C. (2019) Steele-Dunne, Non-invasive water content estimation in a tuff wall by DTS. Construction and Building Materials, v.197, p.821-829. ISSN 0950-0618. https://doi.org/10.1016/j.conbuildmat.2018.11.250. 
  29. Sherman, D.M. and Waite, T.D. (1985) Electronic spectra of Fe3+ oxides and oxide hydroxides in the near IR to near UV. American Mineralogist, v.70, p.1262-1269. 
  30. Topp, G.C., J.L. Davis, and A.P. Annan (1980) Electromagnetic determination of soil water content: Measurements in coaxial transmission lines. Water Resour. Res., v.16(3), p.574-582. doi:10.1029/WR016i003p00574. 
  31. Tsai, F. and Philpot, W. (1998) Derivative analysis of hyperspectral data. Remote Sensing of Environment, v.66(1), p.41-51. doi:10.1016/S0034-4257(98)00032-7 
  32. Weidong, L., F. Baret, G. Xingfa, T. Qingxi, Z. Lanfen, and Z. Bing (2002) Relating Soil Surface Moisture to Reflectance. Remote Sensing of Environment, v.81(2-3), p.238-246. doi:10.1016/S0034-4257(01)00347-9. 
  33. Z. Yin, T. Lei, Q. Yan, Z. Chen and Y. Dong (2013) A near-infrared reflectance sensor for soil surface moisture measurement. Comput. Electron. Agriculture, v.99, p.101-107. doi: 10.1016/j.compag.2013.08.029