All Issue

2024 Vol.11, Issue 4 Preview Page

Original Article

Improvement of Sediment Discharge Estimation Models using Data Mining Techniques and Prediction of River Environmental Changes

데이터 마이닝 기반 유사량 추정 모델의 성능 개선 및 하천 환경 변화 예측

Eun-kyung Jang1
,
Woochul Kang2*
장 은경1
,
강 우철2*
1Research Specialist, Department of Hydro Science and Engineering Research, Korea Institute of Civil Engineering and Building Technology, Goyang 10223, Korea
2Assistant Professor, Department of Smart Infrastructure Engineering, Kongju National University, Cheonan 31080, Korea
1한국건설기술연구원 수자원하천연구본부 전임연구원
2국립공주대학교 스마트인프라공학과 조교수
*Corresponding Author
31 December 2024. pp. 135-144
PDF XML Citation
Abstract

This study aimed to improve the accuracy of sediment discharge estimation models in river environments using data mining techniques, contributing to river management and environmental change assessment. The performance of an existing model tree-based sediment estimation model was enhanced by incorporating the latest data from 2021 to 2023, and the improved model was analyzed by comparing it with actual observation data. The enhanced model showed high coefficients of determination in most river systems, with improved prediction accuracy compared to the existing model. Notably, it demonstrated excellent fit in the Yeongsan and Nakdong rivers, and improved performance was also observed in the lower sediment discharge range of the Han River. Furthermore, the study analyzed watershed environmental changes and erosion-deposition patterns by utilizing sediment rating curves, proving the potential for predicting river environmental changes. This study highlights the importance of continuous model improvement using the latest data to increase the reliability of sediment discharge estimation. It demonstrates the potential application of the enhanced model in various fields, such as river management, flood control, and sediment management.

Keywords
Data mining
Model tree
Sediment estimation model
Sediment rating curve
Total sediment discharge

본 연구는 데이터 마이닝 기법을 활용하여 하천 환경에서 유사량을 추정하는 모델의 정확성을 개선하고, 이를 통해 하천 관리와 환경 변화 평가에 기여하고자 하였다. 기존의 모델 트리 기반 유사량 추정 모델에 2021년부터 2023년까지의 최신 데이터를 추가하여 모델의 성능을 개선하였으며, 이를 실제 관측 데이터와 비교하여 분석하였다. 개선된 모델은 대부분의 수계에서 높은 결정 계수를 보이며, 기존 모델 대비 예측 정확성이 향상된 결과를 나타냈다. 특히 영산강과 낙동강에서는 우수한 적합도를 보였으며, 한강의 저유사량 범위에서도 개선된 성능을 확인할 수 있었다. 추가적으로 유사량 관계식을 활용하여 유역 환경 변화와 침식·퇴적 패턴을 분석함으로써, 하천 환경 변화 예측의 가능성을 입증하였다. 본 연구는 최신 데이터를 활용한 지속적인 모델 개선이 유사량 추정의 신뢰성을 높이는 데 중요함을 제시하며, 개선된 모델이 하천 관리, 홍수 및 퇴적물 관리 등 다양한 응용 분야에서 활용 가능성을 보여주었다.

키워드
데이터 마이닝
Model Tree
유사량 추정 모델
유사량 관계식
총 유사량
References
1

Asselman, N.E.M. 2000. Fitting and interpretation of sediment rating curves. Journal of Hydrology 234(3-4): 228-248.

10.1016/S0022-1694(00)00253-5
2

Atieh, M., Mehltretter, S.L., Gharabaghi, B., and Rudra, R. 2015. Integrative neural networks model for prediction of sediment rating curve parameters for ungauged basins. Journal of Hydrology 531: 1095-1107.

10.1016/j.jhydrol.2015.11.008
3

Breiman, L. 2001. Random forests. Machine Learning 45(1): 5-32.

10.1023/A:1010933404324
4

Campbell, F.B. and Bauder, H.A. 1940. A rating-curve method for determining silt-discharge of streams. Transactions, American Geophysical Union 21: 603-607.

10.1029/TR021i002p00603
5

Cisty, M., Soldanova, V., Cyprich, F., Holubova, K., and Simor, V. 2021. Suspended sediment modelling with hydrological and climate input data. Journal of Hydroinformatics 23(1): 192-210.

10.2166/hydro.2020.116
6

Gupta, D., Hazarika, B.B., Berlin, M., Sharma, U.M., and Mishra, K. 2021. Artificial intelligence for suspended sediment load prediction: a review. Environmental Earth Sciences 80(9): 346.

10.1007/s12665-021-09625-3
7

Horowitz, A.J. 2003. An evaluation of sediment rating curves for estimating suspended sediment concentrations for subsequent flux calculations. Hydrological Processes 17(17): 3387-3409.

10.1002/hyp.1299
8

Jang, E.K. 2017. Sediment discharge assessment for rivers using model tree in data mining. Doctoral dissertation, Myongji University. (in Korean)

9

Jang, E.K. and Kang, W. 2020. Model development for the estimation of specific degradation using classification and prediction of data mining. Journal of Korea Water Resources Association 53(3): 215-223.

10

Jang, E.K., Ji, U., and Ahn, M. 2018. Sediment discharge assessment and stable channel analysis using Model Tree of data mining for Naesung Stream. Journal of Korea Water Resources Association 51(11): 999-1009.

11

Jang, E.K., Ji, U., and Yeo, W. 2023. Estimation of sediment discharge using a tree-based model. Hydrological Sciences Journal 68(11): 1513-1528.

10.1080/02626667.2023.2221790
12

Kang, W., Jang, E.K., Yang, C.Y., and Julien, P.Y. 2021. Geospatial analysis and model development for specific degradation in South Korea using model tree data mining. Catena 200: 105142.

10.1016/j.catena.2021.105142
13

Kang, W., Lee, K., and Jang, E.K. 2022. Evaluation and validation of estimated sediment yield and transport model developed with model tree technique. Applied Sciences 12(3): 1119.

10.3390/app12031119
14

Kang, W., So, B.J., Kim, S., Lee, J.H., Jang, E.K., and Kim, H.S. 2024. Update of Empirical Models for Predicting Specific Degradation in South Korea and Future Sediment Management Considering Climate Change. KSCE Journal of Civil Engineering 28(1): 186-196.

10.1007/s12205-023-0220-z
15

Kim, S.W. and Suh, K.D. 2013. Development of a Stability Formula for Tetrapod by Using M5' Model Tree. Journal of Korean Society of Coastal and Ocean Engineers 25(3): 138-146.

10.9765/KSCOE.2013.25.3.138
16

Korea Water Resources Survey Technology Institute. 2022. 2021 Hydrological survey report. Seoul, South Korea: Korea Water Resources Survey Technology Institute.

17

Korea Water Resources Survey Technology Institute. 2023. 2022 Hydrological survey report. Seoul, South Korea: Korea Water Resources Survey Technology Institute.

18

Korea Water Resources Survey Technology Institute. 2024. 2023 Hydrological survey report. Seoul, South Korea: Korea Water Resources Survey Technology Institute.

19

Mulyono, T., Jumi, J., and Azizah, A. 2021. Sediments discharge analysis using tank model for disaster mitigation. IOP Conference Series: Materials Science and Engineering 1108(1): 012014.

10.1088/1757-899X/1108/1/012014
20

Quinlan, J.R. 1986. Induction of decision trees. Machine Learning 1: 81-106.

10.1007/BF00116251
21

Rezaei, K. and Vadiati, M. 2020. A comparative study of artificial intelligence models for predicting monthly river suspended sediment load. Journal of Water and Land Development 45: 107-118.

10.24425/jwld.2020.133052
22

Rezaei, M., Kafaei, R., Mahmoodi, M., Sanati, A.M., Vakilabadi, D.R., Arfaeinia, H., ... and Boffito, D.C. 2021. Heavy metals concentration in mangrove tissues and associated sediments and seawater from the north coast of Persian Gulf, Iran: Ecological and health risk assessment. Environmental Nanotechnology, Monitoring & Management 15: 100456.

10.1016/j.enmm.2021.100456
23

Seo, J., Woo, C., Lee, C., and Kim, D. 2018. Characteristics of sediment discharge based on GIS spatial analysis of area damaged by debris flow. Journal of the Korean Society of Hazard Mitigation 18(5): 89-96.

10.9798/KOSHAM.2018.18.5.89
24

Walling, D.E. 1977. Assessing the accuracy of suspended sediment rating curves for a small basin. Water Resources Research 13(3): 531-538.

10.1029/WR013i003p00531
25

Walling, D.E. and Webb, B.W. 1981. The reliability of suspended sediment load data. IAHS Publication 133: 177-194.

26

Wang, Y. and Witten, I.H. 1996. Induction of model trees for predicting continuous classes. Machine Learning Working paper 96/23.

Information
  • Publisher :Korean Society of Ecology and Infrastructure Engineering
  • Publisher(Ko) :응용생태공학회
  • Journal Title :Ecology and Resilient Infrastructure
  • Journal Title(Ko) :응용생태공학회 논문집
  • Volume : 11
  • No :4
  • Pages :135-144
  • Received Date : 2024-11-08
  • Revised Date : 2024-11-30
  • Accepted Date : 2024-12-02
  • DOI :https://doi.org/10.17820/eri.2024.11.4.135
Journal Informaiton Ecology and Resilient Infrastructure Ecology and Resilient Infrastructure
Online Submission
  • NRF
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close