A study of multi parameter optimization for rainfall-runoff model (monthly runoff assessment tool) using machine learning

JaeEun Yoo; SeJin Jeung; ByungSik Kim; SeungKwon Jung

doi:10.3741/JKWRA.2025.58.7.537

All Issue

2025 Vol.58, Issue 7 Preview Page Next Page

Research Article

A study of multi parameter optimization for rainfall-runoff model (monthly runoff assessment tool) using machine learning 머신러닝 기반의 강우-유출모형(M-RAT) 매개변수 최적화 기법

31 July 2025. pp. 537-551

PDF XML

Abstract

Recently, the flow rate has been decreased from the reservoirs and small streams due to climate change. The reduction of stream flow cause the stream desiccation and lead to the various adverse effects such as ecosystem degradation and loss of self-purification capacity. In watersheds where have low flow due to drought, considering the runoff characteristics is important. The runoff of stream can be estimated and predicted by the simulations using rainfall-runoff model such as M-RAT (Monthly Runoff Assessment Tool) model is a widely-used tool. Based on a simple monthly water-budget equation, M-RAT estimates monthly runoff through the analysis. With the M-RAT model, the accuracy of the runoff simulations show the improved results by calibrating the model parameters using hydrological and meteorological data from the watershed. This study proposed the parameter optimization method using the machine learning models to calibrate and optimize the M-RAT model parameters for 13 watersheds, and simulated monthly runoff using the optimized parameters. The proposed methods showed the improved accuracy compared to the traditional parameter optimization methods.

Keywords

Machine learning

Rainfall-runoff model

M-RAT

Parameter

Optimization

최근 기후변화, 기후변동으로 인해 저수지 및 소하천의 유량이 감소하는 추세이다. 이와 같은 하천 유량 감소는 건천화 현상을 발생시켜 하천의 생태계 파괴, 자정기능 상실, 친수 기능 상실 등 각종 부작용의 원인이 될 수 있다. 가뭄으로 인해 하천 및 저수지에 저유량이 유지되는 유역은 유출량의 특성 파악이 중요한 요소로 작용한다. 강우-유출 모형을 활용한 유출량 모의를 통해 하천의 유량을 파악할 수 있으며, 그 중 M-RAT (Monthly Runoff Assessment Tool) 모형은 일반적이고 간단한 월 물수지 방정식을 기반으로 유출 분석을 통해 월 유출량을 추정한다. M-RAT 모형을 활용한 유출량 모의 시 하천 유역의 수문 및 기상자료를 사용하여 모형의 매개변수를 보정하는 과정을 통해 모의의 정확도를 높일 수 있다. 본 연구는 머신러닝 기법을 활용하여 13개 유역을 대상으로 M-RAT 모형의 매개변수를 검보정 및 최적화하고, 획득한 매개변수를 활용하여 M-RAT 모형을 통한 월 유출량을 모의하였다. 모형 성능 검증을 위해 미호강, 합천댐, 홍천강 3개 유역에 적용하여 정확성을 검토한 결과, 머신러닝 기반의 매개변수 최적화 기법을 활용했을 때 기존에 수행된 기법에 비해 개선된 결과를 확인할 수 있었다.

키워드

머신러닝

강우-유출모형

M-RAT

매개변수

최적화

References

Ahn, S.R, Lee, J.W, Jang, S.S, and Kim, S.J. (2016). “Large scale SWAT watershed modeling considering multi- purpose dams and multi-function weirs operation: For Namhan River basin.” Journal of the Korean Society of Agricultural Engineers, Vol. 58, No. 4, pp. 21-35. doi: 10.5389/KSAE.2016.58.4.021.

10.5389/KSAE.2016.58.4.021

Arnold, J.G., and Allen, P.M. (1996). “Estimating hydrologic budgets for three Illinois watersheds.” Journal of Hydrology, Vol. 176, No. 1, pp. 57-77. doi: 10.1016/0022-1694(95)02782-3.

10.1016/0022-1694(95)02782-3

Chang, H.J., Lee, H.J., and Lee, H.S. (2019), “Regionalization of conceptual rainfall-runoff model to simulate runoff induced by Typhoons.” Journal of Korean Society of Disaster and Security, Vol. 12, pp. 63-72. doi: 10.21729/ksds.2019.12.4.63.

10.21729/ksds.2019.12.4.63

Choi, H.H., and Lee, H.S. (2012). “Assessment of conceptual rainfall runoff models for regionalisation at Miho catchment.” Journal of the Korean Society of Hazard Mitigation, Vol. 12, No. 1, pp. 193-203. doi: 10.9798/KOSHAM.2012.12.1.193.

10.9798/KOSHAM.2012.12.1.193

Choi, J.R., Chung, I.M., Jeung, S.J., Choo, K.S., Oh, C.H., Kim, B.S. (2021). “Development and verification of the available number of water intake days in ungauged local water source using the SWAT model and flow recession.” Water, Vol. 13, No. 11, 1511, doi: 10.3390/w13111511.

10.3390/w13111511

Choo, K.-S. (2021). A study on the estimation of thresholdrainfall using machine learning. Master Thesis, Kangwon National University.

Cortes, C., and Vapnik, V. (1995). “Support-vector networks.” Machine Learning, Vol. 20, No. 3, pp.273-297.

10.1023/A:1022627411411

Ho, T.K. (1995). “Random decision forests.” Proceedings of 3rd International Conference on Document Analysis and Recognition, Vol. 1, pp. 278-282.

10.1109/ICDAR.1995.598994

Hong, J., Choi, Y., and Yi, J. (2021) “Parameter optimization of agricultural reservoir long-term runoff model based on historical data.” Journal of Korea Water Resources Association, KWRA, Vol. 54, No. 2, pp. 93-104. doi: 10.3741/JKWRA.2021.54.2.93.

10.3741/JKWRA.2021.54.2.93

Jeung, S.J. (2019a). Impact assessments of climate and hydrological cycle changes in North Korea based on RCP climate change scenarios. Ph. D. Dissertation, Kangwon National University.

Jeung, S.J., Kang, D.H., and Kim, B.S. (2019b). “Impacts assessment of Climate change on hydrologic cycle changes in North Korea based on RCP climate change scenarios I. Development of long-term runoff model parameter estimation for ungauged basins.” Journal of Wetlands Research, Vol.21, No. 1, pp. 28-38. doi: 10.17663/JWR.2019.21.s-1.28.

10.17663/JWR.2019.21.s-1.28

Jeung, S.J., Kang, D.H., and Kim, B.S. (2019c). “Impacts assessment of climate changes in North Korea based on RCP climate change scenarios II. Impacts assessment of hydrologic cycle changes in Yalu River.” Journal of Wetlands Research, Vol. 21, No. spc, pp. 39-50. doi: 10.17663/JWR.2019.21.s-1.39.

10.17663/JWR.2019.21.s-1.39

Kim, H.J., and Jung, H.W. (2018). “A study on seasonal runoff characteristics of small streams using SWAT.” Proceedings of the Korean Society of Agricultural Engineers Conference, Vol. 2018, pp. 283-283.

Lee, J.-Y., Ryu, J.H., Park, K.W., Kang, D., and Kim, T.-W. (2020). “Estimating design floods at ungaugaed watersheds using machine learning.” KSCE 2020 Convention, pp 154-155.

Nash, J.E., and Sutcliffe, J.V. (1970). “River flow forecasting through conceptual models part I - A discussion of principles.” Journal of Hydrology, Vol. 10, No. 3, pp. 282-290.

10.1016/0022-1694(70)90255-6

Rokach, L., and Maimon, O. (2005). “Decision trees.” Data Mining and Knowledge Discovery Handbook, Edited by Maimon, O., and Rokach, L., Springer, Boston, MA, U.S., pp. 165-192. doi: 10.1007/0-387-25465-X_9.

10.1007/0-387-25465-X_9

Schapire, R.E. (2013). “Explaining AdaBoost.” Empirical Inference, Edited by Schölkopf, B., Luo, Z., and Vovk, V., Springer- Verlag, Berlin Heidelberg, pp. 37-52. doi: 10.1007/978-3-642-41136-6_5

10.1007/978-3-642-41136-6_5

Vandewiele, G.L., Xu, C-Y., and Win, N.-L. (1992). “Methodlogy and comparative study of monthly water balance models in Belguim, China and Burma.” Journal of Hydrology, Vol. 134, pp. 315-347. doi: 10.1016/0022-1694(92)90041-S.

10.1016/0022-1694(92)90041-S

Yoon, K., Beom, J., Jeong, J., Jeung, M., and Park, M. (2022). “Development of reinforcement learning algorithm for auto- calibration of SWMM model parameters.” Proceedings of the Korean Society of Agricultural Engineers Conference, Vol. 2022, p. 308.

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 :7
Pages :537-551
Received Date : 2024-09-13
Revised Date : 2025-04-18
Accepted Date : 2025-05-08
DOI :https://doi.org/10.3741/JKWRA.2025.58.7.537

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

All Issue