저수지 제체 월류수위 예측을 위한 Fuzzy Time Series법의적용성 비교 평가
Comparative Evaluation on Applicability of Fuzzy Time Series Method for Predicting Overtopping of Reservoir Embankment
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
An increasing pattern of extreme rainfall recently affected the rural infrastructures with catastrophic damage, especially the overtopping of a fill damembankment in the Republic of Korea. The overtopping was caused by the sudden increase in reservoir water level over the dam crest level, and itwas not easy work to predict a priori because of its non-linear behavior. Fuzzy time series (FTS) is a fuzzy-logic inference procedure and is suitedto apply to non-linear prediction methods such as machine learning. This study used the Wangshin reservoir and Goesan-dam cases, which experiencedovertopping in 2023 and 2022, respectively. Wangshin Reservoir was a typical agricultural fill dam and needed to stack more available data, with onlythe daily storage rate (water level) of 7 years, starting on 2 May 2016. Therefore, we used Goesan-dam data to select appropriate variables and comparethe analysis result, which was stacked with about 17 years of records. The analyses adapted LSTM to compare with FTS. As a result, the reservoirwater level was applied to predict the overtopping water level, and it was shown that the FTS method could predict the actual water levels effectivelyaccording to the result of comparison with LSTM. Then, the FTS method was expected to predict reservoir water level a priori to make appropriatecountermeasures on overtopping events as one of the alternatives.
Abstract
An increasing pattern of extreme rainfall recently affected the rural infrastructures with catastrophic damage, especially the overtopping of a fill damembankment in the Republic of Korea. The overtopping was caused by the sudden increase in reservoir water level over the dam crest level, and itwas not easy work to predict a priori because of its non-linear behavior. Fuzzy time series (FTS) is a fuzzy-logic inference procedure and is suitedto apply to non-linear prediction methods such as machine learning. This study used the Wangshin reservoir and Goesan-dam cases, which experiencedovertopping in 2023 and 2022, respectively. Wangshin Reservoir was a typical agricultural fill dam and needed to stack more available data, with onlythe daily storage rate (water level) of 7 years, starting on 2 May 2016. Therefore, we used Goesan-dam data to select appropriate variables and comparethe analysis result, which was stacked with about 17 years of records. The analyses adapted LSTM to compare with FTS. As a result, the reservoirwater level was applied to predict the overtopping water level, and it was shown that the FTS method could predict the actual water levels effectivelyaccording to the result of comparison with LSTM. Then, the FTS method was expected to predict reservoir water level a priori to make appropriatecountermeasures on overtopping events as one of the alternatives.
참고문헌 (36)
- Bae, J. H., "A study on time series cross-validation techniques for enhancing the accuracy of reservoir water level prediction using automated machine learning TPOT", Journal of Korean Society of Agricultural Engineering, 66(1), pp.1~13 (2024)
- Bárdossy, G., "Evaluation of uncertainties and risks in geology: New mathematical approaches for their handling" (2004), Springer
- Barrera-Animas, A. Y., "Rainfall prediction : A comparative analysis of modern machine learning algorithms for time-series forecasting", Machine Learning with Applications, 7, pp.100204~ (2024)
- Chen, S. M., "Forecasting enrollments based on fuzzy time series", Fuzzy Sets and Systems, 81, pp.311~319 (1996)
- Chen, S. M., "Temperature prediction using fuzzy time series", Systems, Management and Cybernetics, 30, pp.263~275 (2000)
- Chin, S. H., "Predicting climate change using an autoregression long short-term memory model", Frontiers in Environmental Science, 12, pp.1301343~ (2024)
- Choi, I. M., "A study on the capacity enhancement of flood damage: Measures to strengthen the safety of agricultural reservoirs in response to extreme floods", Proceeding of a Parliamentary Debate (2022)
- "Overflow at Goesan Dam... residents in low-lying areas are ordered to evacuate early in the morning" (2023)[URL]
- Kratzert, F., "Explainable AI: Interpreting, Explaining and Visualizing Deep Learning", pp.17~ (2019), Springer International Publishing
- "Google Colab®, version 3.10.12"[URL]
- Hochreiter, S., "Long short-term memory", Neural Computation, 9(8), pp.1735~1780 (1997)
- "Amazon stock forecasting in PyTorch with LSTM neural network (time series forecasting)" (2023)[URL]
- "World register of dams:General synthesis" (2020)[URL]
- Islam, M. S., "Current research trends and application areas of fuzzy and hybrid methods to the risk assessment of construction projects", Advanced Engineering Informatics, 33, pp.112~131 (2017)
- Jeong, C. S., "A study on the development of a dam operation table using the rainfall matrix", Journal of Korean Society for Disaster Security, 13(2), pp.39~51 (2020)
- Kecman, V., "Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models (Complex Adaptive Systems)" (2001), Bradford Book
- "Forecast with ARIMA in Python more easily with Scalecast" (2022)[URL]
- Kim, H. J., "Application of adaptive network-based fuzzy inference system(ANFIS)for modeling the hourly runoff in the Gapcheon watershed", KSCE Journal of Civil Engineering, 31(5B), pp.405~414 (2011)
- Kim, J. Y., "Stability analysis of embankment overtopping by initial fluctuating water level", Journal of Korean Geotechnical Society, 31(8), pp.51~62 (2015)
- "KOIS" (2023)[URL]
- Report on the overtopping accident cause analysis on Wangshin reservoir, "KRC", ~ (2022)
- Park, G. M., "Groundwater level prediction using ANFIS algorithm", Journal of the KIECS, 16(6), pp.1239~1248 (2021)
- PyTorch, "Copyright © 2024 The Linux Foundation®", ~ (2024)
- "RAWRIS"[URL]
- Shang, K., "Applying fuzzy logic to risk assessment and decision-making", CAS, SOA Joint Risk Management Section, pp.2013, ~
- Silva, P. C. L., "pyFTS: fuzzy time series for Python", Belo Horizonte (2018)[DOI]
- "the risk of collapse of Wangshin reservoir in Gangdong, Gyeongju... Resident evacuation order" (2022)[URL]
- Song, J. H., "Estimating reservoir inflow and outflow from water level observations using expert knowledge: Dealing with an ill-posed water balance equation in reservoir management", Water Resources Research, 58, pp.e2020WR028183~ (2022)[DOI]
- Song, Q., "Fuzzy time series and its model", Fuzzy Sets and Systems, 54(3), pp.269~277 (1993)[DOI]
- Song, Q., "Forecasting enrollments with fuzzy time series-part I", Fuzzy Sets and Systems, 54, pp.1~9 (1993)
- Song, Q., "Forecasting enrollments with fuzzy time series-part II", Fuzzy Sets and Systems, 62, pp.1~8 (1994)
- "WAMIS"[URL]
- Yang, K., "Fuzzy risk analysis of dam overtopping from snowmelt floods in the nonstationarity case of the Manas River catchment, China", Natural Hazards, 104, pp.27~49 (2020)
- Yu, H. K., "Weighted fuzzy time series models for TAIEX forecasting", Physica A, 349, pp.609~624 (2005)
- Zadeh, L. A., "Fuzzy sets", Information and Control, 8(3), pp.338~353 (1965)
- Zimmermann, H. J., "Fuzzy set theory", Advanced Review, 2, pp.317~332 (2010)