Prediction of depth-change rates under raised and lowered weir conditions using Random Forest regression

Sangho Kim; Sungjung Kim

doi:10.3741/JKWRA.2025.58.S-2.1261

All Issue

2025 Vol.58, Issue 11S-2 Preview Page

Research Article

Prediction of depth-change rates under raised and lowered weir conditions using Random Forest regression 랜덤포레스트 회귀분석을 이용한 가동보 기립·전도 조건에서의 수심 증감률 예측

30 November 2025. pp. 1261-1275

PDF XML

Abstract

This study aims to quantitatively predict the depth-change rate associated with weir operations under raised and lowered conditions. In the preliminary analysis using a virtual channel, a simple linear regression model(SPSS-based) was established using the weir area ratio (AR) and bed slope (S) to examine the individual hydraulic influences and to define the basic structure of the regression model. For the real-river analysis, data from three rivers (Mangyeong, Geumho, and Musim) were integrated to develop a multiple linear regression (OLS) model focusing on AR, friction slope (FS), and site slope (SS), and the results were compared and verified with a Random Forest (RF) regression model. To perform the RF analysis, Group K-Fold (K=5) cross-validation was applied using river-weir GroupID, strictly separating the training (~80%) and validation (~20%) datasets. The partial dependence (PDP-1D/2D) method was used to interpret the mean effects and interactions of single and combined variables. As a result, the raised condition was best represented by an interaction-expanded model (AR×Fr, AR×FS, etc.), while the lowered condition was effectively explained by a single-variable model including Froude Number(Fr). From these results, a multi-variable regression equation(RF-2D) was developed. Although the RF-AR model using only AR showed limited explanatory power, the proposed RF-2D model exhibited a generalization performance comparable to that of the OLS model. The proposed regression equations enable rapid and consistent prediction of water-depth changes due to weir raising or lowering, using only limited input variables and without complex numerical simulations, and can thus serve as a decision-support tool for efficient weir operation and river management.

Keywords

Movable weir

Weir-raised/-lowered condition

Random Forest regression

HEC-RAS

본 연구는 보(weir)의 기립·전도 운영에 따른 수심 증감률을 정량적으로 예측하기 위해, 가상하도에 대한 사전 모의분석에서는 보면적비(AR)와 하상경사(S)를 이용하여 SPSS 기반 단순선형회귀식을 산정하고, 수리변수의 개별 영향을 파악하여 회귀 구조의 기초를 정립하였다. 실제 하천에서는 3개 하천(만경강·금호강·무심천) 자료를 통합 분석하여 보면적비(AR), 마찰경사(FS), 지점경사(SS) 등을 중심으로 다중선형회귀식(OLS)을 구축하고 랜덤포레스트(RF) 회귀모형과 비교·검증하였다. 랜덤포레스트(RF) 회귀분석을 위해 하천-보 GroupID로 Group K-Fold (K=5) OOF (Out-of-Fold)를 적용하여 학습(≈80%)·검증(≈20%)을 구분하고, 부분의존도(PDP-1D/2D)로 단일·복합 변수의 평균 영향과 상호작용을 해석하였다. 그 결과, 기립은 상호작용 확대형(AR×Fr, AR×FS 등), 전도는 푸르드수(Fr) 포함 단항형이 최적 구조로 선정되었으며, 이를 통해 다중선형회귀식(RF-2D)을 개발하였다. 보면적비(AR)만을 이용하는 RF-AR의 설명력은 제한적이었으나, RF-2D 개발식은 OLS와 유사한 수준의 일반화 성능을 보였다. 본 연구에서 개발된 식은 하천에서 복잡한 수치해석 없이도 제한된 입력자료만으로 보의 기립과 전도에 따른 수심 변화를 신속하고 간편하게 예측할 수 있어, 보 운영 및 하천관리의 사전 의사결정 지원 도구로 활용 가능할 것이다.

키워드

가동보

보의 기립과 전도

랜덤포레스트 기법

HEC-RAS

References

Barinas, G. (2025). Vegetation structure in hydrologic modeling: from interception loss to floodplain roughness. Ph.D. Dissertation, Oregon State University, Corvallis, OR, U.S.

Baruah, A., Zarrabi, R., and Johnson, M. (2024). “A data-driven approach for stage-discharge rating curve estimation across the contiguous United States.” AGU Fall Meeting, Washington, D.C., U.S.

Breiman, L. (2001). “Random forests.” Machine Learning, Vol. 45, No. 1, pp. 5-32. doi: 10.1023/A:1010933404324.

10.1023/A:1010933404324

Choi, Y.H., Lee, J.H., and Choi, H.S. (2016). “Hydrulic characteristics analysis of under flow in vertical lift weir.” Proceedings of the Korea Water Resources Association Conference, p. 464.

Erpicum, S., Pirotton, M., Archambeau, P., and Dewals, B.J. (2010). “Flow conditions in the vicinity of hydraulic jumps downstream from gates.” Journal of Hydraulic Research, Vol. 48, No. 2, pp. 200-208.

Farooq, M., Ahmad, I., and Khan, A. (2019). “Field observation and hydrodynamic modeling of gate operations in alluvial rivers.” Water Resources Management, Vol. 33, No. 5, pp. 1775-1790.

Friedman, J.H. (2001). “Greedy function approximation: A gradient boosting machine.” Annals of Statistics, Vol. 29, No. 5, pp. 1189-1232. doi: 10.1214/aos/1013203451.

10.1214/aos/1013203451

Ghaderi, A., Emami, A., and Ghodousi, J. (2021). “Experimental and numerical investigation of scouring downstream of a movable weir.” International Journal of Sediment Research, Vol. 36, No. 3, pp. 287-298.

Hydrologic Engineering Center (HEC) (2025). HEC-RAS user’s manual. U.S. Army Corps of Engineers, Davis, CA, U.S.

Kang, T.W., Hwangbo, B., and Kim, J.M. (2020). “Flow simulation according to the opening configuration of weirs using a numerical model.” Journal of the Korean Society for Ecological Infrastructure Engineering, Vol. 7, No. 3, pp. 8-15.

Kim, D.H., Lee, K.S., Hwangbo, J.G., Kim, H.S., and Kim, S.J. (2022). “Development of the method for flood water level forecasting and flood damage warning using an AI-based model.” Journal of the Korean Society of Hazard Mitigation, Vol. 22, No. 4, pp. 145-156. doi: 10.9798/KOSHAM.2022.22.4.145.

10.9798/KOSHAM.2022.22.4.145

Kim, H.I., Lee, Y.S., and Kim, B.H. (2021). “Real-time flood prediction applying random forest regression model in urban areas.” Journal of Korea Water Resources Association, Vol. 54, No. S-1, pp. 1119-1130. doi: 10.3741/JKWRA.2021.54.S-1.1119.

10.3741/JKWRA.2021.54.S-1.1119

Kim, Y.G., and Choi, K.W. (2014). “Experimental study on the energy dissipation effect downstream of a bottom-outlet type movable weir.” Proceedings of the Korean Society of Hazard Mitigation Conference, p. 87.

Lee, J.Y., Kim, K.Y., Son, S.H., and Shin, D.H. (2015). “Prediction of local scour behavior downstream according to movable- weir operation rules.” Journal of the Korean Society of Hazard Mitigation, Vol. 15, No. 4, pp. 289-297.

10.9798/KOSHAM.2015.15.4.221

Lee, K.S., and Jang, C.R. (2018). “Experimental analysis of the sedimentation processes in the movable weir by changing the channel slope considering weir operation.” Journal of Korea Water Resources Association, Vol. 51, No. 8, pp. 729-737. doi: 10.3741/JKWRA.2018.51.8.729.

10.3741/JKWRA.2018.51.8.729

Malik, M.H., and Rashid, R. (2024). “Streamflow prediction in the Jhelum River Basin using ensemble machine learning models and long-term hydro-meteorological data.” SSRN, SSRN preprint. doi: 10.2139/ssrn.5361454.

10.2139/ssrn.5361454

Park, J.S., Seol, M.S., and Lee, C.D. (2019). “Study on the characteristics of upstream flow by downstream weir with gates operation.” Proceedings of the Korea Water Resources Association Conference, p. 272.

Shiri, N., Kisi, O., Karimi, S., and Shiri, J. (2025). “Towards seasonal- based assessment of machine learning models in river dissolved oxygen simulations with different flow ranges.” ISH Journal of Hydraulic Engineering, Vol. 31, No. 3, pp. 461-482. doi: 10.1080/09715010.2025.2485301.

10.1080/09715010.2025.2485301

Singh, P., Bhargava, R., and Arora, G. (2017). “Numerical investigation of flow over radial gates under different opening ratios.” ISH Journal of Hydraulic Engineering, Vol. 23, No. 2, pp. 180-191. doi: 10.1080/09715010.2016.1182704.

10.1080/09715010.2016.1182704

Wang, X., Chen, Q., and Wu, Y. (2020). “Numerical simulation of flow characteristics in downstream of movable weirs under flood conditions.” Water, Vol. 12, No. 3, 750. doi: 10.3390/w12030750.

10.3390/w12030750

Information

Publisher :KOREA WATER RESOURECES ASSOCIATION
Publisher(Ko) :한국수자원학회
Journal Title :Journal of Korea Water Resources Association
Journal Title(Ko) :한국수자원학회 논문집
Volume : 58
No :11
Pages :1261-1275
Received Date : 2025-10-12
Revised Date : 2025-10-29
Accepted Date : 2025-10-30
DOI :https://doi.org/10.3741/JKWRA.2025.58.S-2.1261

Journal of Korea Water Resources Association ISSN:2799-8746(Print) 2799-8754(Online) 한국수자원학회 논문집

All Issue