All Issue

2026 Vol.59, Issue 8 Preview Page
Bed morphology measurement capability in large Korean rivers extending maximum measurable depth using CMR-OV hyperspectral bathymetry method

CMR-OV 초분광 수심 기법의 최대측정가능수심 확장을 통한 국내 대하천 정밀하상측정 가능성 평가

Dohyeon Kima
,
Dongsu Kimb
,
Hojun Youc
,
Seogyeong Leed*
,
Siyoon Kwone
김 도현a
,
김 동수b
,
유 호준c
,
이 서경d*
,
권 시윤e
aIntegrated M.S./Ph.D. Program, Department of Civil & Environmental Engineering, Dankook University, Yongin, Korea
bProfessor, Department of Civil & Environmental Engineering, Dankook University, Yongin, Korea
cSenior Researcher, Water Infrastructure Safety Research Center, K-water Research Institute, Daejeon, Korea
dPh.D. Student, Department of Civil & Environmental Engineering, Dankook University, Yongin, Korea
eAssistant Professor, Department of Civil and Infrastructure Engineering, Gyeongsang National University, Jinju, Korea
a단국대학교 인프라건설공학과 석박사통합과정
b단국대학교 인프라건설공학과 교수
cK-water 연구원 선임연구원
d단국대학교 인프라건설공학과 박사과정
e경상국립대학교 건설시스템공학과 조교수
*Corresponding Author
31 August 2026. pp. 907-920
PDF XML Citation
Abstract

River bathymetry varies spatially and temporally in response to discharge fluctuations and bed movement, making accurate depth estimation important for understanding and managing river systems. However, conventional field surveys and contact-based measurements are limited to point-based observations, making it difficult to obtain continuous bathymetric information over large river reaches. To address these limitations, this study applied the machine learning–based CMR-OV algorithm to hyperspectral image–based bathymetry and evaluated its potential to extend the maximum measurable depth. Depth data measured using an ADCP were grouped at 0.5 m intervals for model training, and the applicable depth range was evaluated based on the model showing the lowest RMSE. In addition, a bathymetric map was generated from hyperspectral imagery using the trained model, and its performance was evaluated by comparing predicted depths with observed depths along validation cross-sections. The results showed that, under low-turbidity conditions, CMR-OV achieved relatively good performance over a deeper depth range than the 2.5 m maximum measurable depth previously reported for the conventional OBRA approach. Cross-sectional comparison showed the best performance with an RMSE of 0.21 m and a coefficient of determination (R2) of 0.96. However, because in-situ observations in deeper water were limited, it was difficult to define the maximum measurable depth as a single fixed value. Further investigation using deeper-water observations and independent validation datasets is therefore needed.

Keywords
Remote sensing
Hyperspectral imagery
Bathymetry estimation
Maximum measurable depth

하천 수심은 유량 변화와 하상 이동에 따라 시·공간적으로 변동하므로 이를 정확히 파악하는 것은 하천의 이해와 관리에 중요하다. 그러나 기존 현장 측량과 접촉식 계측은 점 단위 자료에 한정되어 넓은 하천 구간의 연속적 수심 정보를 확보하는 데 한계가 있다. 이에 본 연구에서는 초분광 영상 기반 수심 산정 기법의 한계를 보완하기 위해 기계학습 기반 CMR-OV 알고리즘을 적용하고 최대측정가능수심의 확장 가능성을 평가하였다. ADCP로 계측한 수심 자료를 0.5 m 간격으로 구분하여 학습하였으며 RMSE가 가장 낮은 모델을 기준으로 적용 가능 범위를 검토하였다. 또한 구축된 모델로 초분광 영상에서 수심맵을 생성하고 검증 단면의 실측 수심과 비교하여 성능을 평가하였다. 그 결과, 저탁도 조건에서 CMR-OV는 기존 OBRA에서 제시된 최대측정가능수심 2.5 m보다 확장된 수심 범위에서 비교적 양호한 성능을 보였고 단면 검증을 통해 최적 결과가 RMSE 0.21 m, 결정계수(R2) 0.96으로 나타났다. 다만 깊은 수심대의 실측 자료가 제한적이어서 최대측정가능수심을 특정 값으로 단정하기에는 한계가 있었으며 향후 보다 깊은 수심대와 독립적인 검증자료를 포함한 추가 검토가 필요하다.

키워드
원격탐사
초분광 영상
수심 산정
최대측정가능수심
References
1

Belgiu, M., and Drăguţ, L. (2016). “Random forest in remote sensing: A review of applications and future directions.” ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 114, pp. 24-31.

10.1016/j.isprsjprs.2016.01.011
2

Brasington, J., Rumsby, B.T., and McVey, R. (2000). “Monitoring and modelling morphological change in braided river systems using the global positioning system.” Earth Surface Processes and Landforms, Vol. 25, pp. 973-990.

10.1002/1096-9837(200008)25:9<973::AID-ESP111>3.0.CO;2-Y
3

Chen, L., Liu, L., Liu, S., Shi, Z., and Shi, C. (2025). “The application of remote sensing technology in inland water quality monitoring and water environment science: Recent progress and perspectives.” Remote Sensing, Vol. 17, No. 4, 667.

10.3390/rs17040667
4

Gwon, Y., Kim, D., and You, H. (2023). “Evaluation for applicability of river depth measurement method depending on vegetation effect using drone-based spatial-temporal hyperspectral image.” Journal of Korea Water Resources Association, Vol. 56, No. 4, pp. 235-243.

10.3741/JKWRA.2023.56.4.235
5

Hestir, E.L., Brando, V.E., Bresciani, M., Giardino, C., Matta, E., Villa, P., and Dekker, A.G. (2015). “Measuring freshwater aquatic ecosystems: The need for a hyperspectral global mapping satellite mission.” Remote Sensing of Environment, Vol. 167, pp. 181-195.

10.1016/j.rse.2015.05.023
6

Kang, J.G., Lee, C.H., Yeo, H.K., and Kim, J.T. (2019). “Correlation analysis on the water depth and peak data value of hyperspectral imagery.” Ecology and Resilient Infrastructure, Vol. 6, No. 3, pp. 171-177.

10.17820/ERI.2019.6.3.171
7

Kim, D., Seo, Y., You, H., and Gwon, Y. (2023). “Performance evaluation of hyperspectral bathymetry method for morphological mapping in a large river confluence.” Journal of Korea Water Resources Association, Vol. 56, No. 3, pp. 195-210.

10.3741/JKWRA.2023.56.3.195
8

Koljonen, S., Huusko, A., Maki-Petays, A., Louhi, P., and Muotka, T. (2012). “Assessing habitat suitability for juvenile atlantic salmon in relation to in-stream restoration and discharge variability.” Restoration Ecology, Vol. 21, No. 3, pp. 344-352.

10.1111/j.1526-100X.2012.00908.x
9

Kwon, S., Passalacqua, P., Soloy, A., Jensen, D., and Simard, M. (2024). “Depth mapping in turbid and deep waters using AVIRIS-NG imagery: A study in Wax Lake Delta, Louisiana, USA.” Water Resources Research, Vol. 60, e2023WR036875.

10.1029/2023WR036875
10

Kwon, S., Seo, I.W., Noh, H., and Kim, B. (2022). “Hyperspectral retrievals of suspended sediment using cluster-based machine learning regression in shallow waters.” Science of the Total Environment, Vol. 833, 155168.

10.1016/j.scitotenv.2022.155168
11

Lee, Z., Carder, K.L., Mobley, C.D., Steward, R.G., and Patch, J.S. (1999). “Hyperspectral remote sensing for shallow waters: 2. Deriving bottom depths and water properties by optimization.” Applied Optics, Vol. 38, No. 18, pp. 3831-3843.

10.1364/AO.38.003831
12

Legleiter, C.J., Roberts, D.A., and Lawrence, R.L. (2009). “Spectrally based remote sensing of river bathymetry.” Earth Surface Processes and Landforms, Vol. 34, No. 8, pp. 1039-1059.

10.1002/esp.1787
13

Lyzenga, D.R. (1978). “Passive remote sensing techniques for mapping water depth and bottom features.” Applied Optics, Vol. 17, No. 3, pp. 379-383. doi: 10.1364/AO.17.000379.

10.1364/AO.17.000379
14

Marcus, W.A., and Fonstad, M.A. (2008). “Optical remote mapping of rivers at sub-meter resolutions and watershed extents.” Earth Surface Processes and Landforms, Vol. 33, No. 1, pp. 4-24.

10.1002/esp.1637
15

Melgani, F., and Bruzzone, L. (2004). “Classification of hyperspectral remote sensing images with support vector machines.” IEEE Transactions on Geoscience and Remote Sensing, Vol. 42, No. 8, pp. 1778-1790.

10.1109/TGRS.2004.831865
16

Morel, M., Booker, D.J., Gob, F., and Lamouroux, N. (2020). “Intercontinental predictions of river hydraulic geometry from catchment physical characteristics.” Journal of Hydrology, Vol. 582, 124292.

10.1016/j.jhydrol.2019.124292
17

Pan, Z., Glennie, C., Legleiter, C., and Overstreet, B. (2015). “Estimation of water depths and turbidity from hyperspectral imagery using support vector regression.” IEEE Geoscience and Remote Sensing Letters, Vol. 12, No. 10, pp. 2165-2169.

10.1109/LGRS.2015.2453636
18

Paoletti, M.E., Haut, J.M., Plaza, J., and Plaza, A. (2019). “Deep learning classifiers for hyperspectral imaging: A review.” ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 158, pp. 279-317.

10.1016/j.isprsjprs.2019.09.006
19

Stumpf, R.P., Holderied, K., and Sinclair, M. (2003). “Determination of water depth with high-resolution satellite imagery over variable bottom types.” Limnology and Oceanography, Vol. 48, No. 1, pp. 547-556. doi: 10.4319/lo.2003.48.1_part_2.0547.

10.4319/lo.2003.48.1_part_2.0547
20

Wu, J., Li, W., Du, H., Wan, Y., Yang, S., and Xiao, Y. (2023). “Estimating river bathymetry from multisource remote sensing data.” Journal of Hydrology, Vol. 620, 129567.

10.1016/j.jhydrol.2023.129567
21

You, H., Kim, D., and Gwon, Y. (2024). “Morphological dune mapping in shallow alluvial stream using UAV-based hyperspectral images.” KSCE Journal of Civil Engineering, Vol. 28, No. 4, pp. 1594-1606.

10.1007/s12205-024-1278-y
22

You, H.J. (2018). Development of riverine bathymetry survey technique using drone-based hyperspectral image. Ph. D. dissertation, Dankook University, pp. 124-152.

Information
  • Publisher :KOREA WATER RESOURECES ASSOCIATION
  • Publisher(Ko) :한국수자원학회
  • Journal Title :Journal of Korea Water Resources Association
  • Journal Title(Ko) :한국수자원학회 논문집
  • Volume : 59
  • No :8
  • Pages :907-920
  • Received Date : 2026-04-07
  • Revised Date : 2026-06-19
  • Accepted Date : 2026-06-30
  • DOI :https://doi.org/10.3741/JKWRA.2026.59.8.907
Journal Informaiton Journal of Korea Water Resources Association Journal of Korea Water Resources Association
Online Submission
Archives
  • scopus
  • KCI-수자원
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close