자동기계학습 TPOT 기반 저수위 예측 정확도 향상을 위한 시계열 교차검증 기법 연구
A Study on Time Series Cross-Validation Techniques for Enhancing the Accuracy of Reservoir Water Level Prediction Using Automated Machine Learning TPOT
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
This study assessed the efficacy of improving the accuracy of reservoir water level prediction models by employing automated machine learning models and efficient cross-validation methods for time-series data. Considering the inherent complexity and non-linearity of time-series data related to reservoir water levels, we proposed an optimized approach for model selection and training. The performance of twelve models was evaluated for the Obong Reservoir in Gangneung, Gangwon Province, using the TPOT (Tree-based Pipeline Optimization Tool) and four cross-validation methods, which led to the determination of the optimal pipeline model. The pipeline model consisting of Extra Tree, Stacking Ridge Regression, and Simple Ridge Regression showed outstanding predictive performance for both training and test data, with an R2 (Coefficient of determination) and NSE (Nash-Sutcliffe Efficiency) exceeding 0.93. On the other hand, for predictions of water levels 12 hours later, the pipeline model selected through time-series split cross-validation accurately captured the change pattern of time-series water level data during the test period, with an NSE exceeding 0.99. The methodology proposed in this study is expected to greatly contribute to the efficient generation of reservoir water level predictions in regions with high rainfall variability.
Abstract
This study assessed the efficacy of improving the accuracy of reservoir water level prediction models by employing automated machine learning models and efficient cross-validation methods for time-series data. Considering the inherent complexity and non-linearity of time-series data related to reservoir water levels, we proposed an optimized approach for model selection and training. The performance of twelve models was evaluated for the Obong Reservoir in Gangneung, Gangwon Province, using the TPOT (Tree-based Pipeline Optimization Tool) and four cross-validation methods, which led to the determination of the optimal pipeline model. The pipeline model consisting of Extra Tree, Stacking Ridge Regression, and Simple Ridge Regression showed outstanding predictive performance for both training and test data, with an R2 (Coefficient of determination) and NSE (Nash-Sutcliffe Efficiency) exceeding 0.93. On the other hand, for predictions of water levels 12 hours later, the pipeline model selected through time-series split cross-validation accurately captured the change pattern of time-series water level data during the test period, with an NSE exceeding 0.99. The methodology proposed in this study is expected to greatly contribute to the efficient generation of reservoir water level predictions in regions with high rainfall variability.
참고문헌 (29)
- Bae, J. H., "A study on regularization methods to evaluate the sediment trapping efficiency of vegetative filter strips", Journal of the Korean Society of Agricultural Engineers, 61(6), pp.9~19 (2019)[DOI]
- Bergmeir, C., "A note on the validity of cross-validation for evaluating autoregressive time series prediction", Computational Statistics & Data Analysis, 120, pp.70~83 (2018)[DOI]
- Brockwell, P. J., "Introduction to time series and forecasting" (2002), Springer
- Castillo-Botón, C., "Analysis and prediction of dammed water level in a hydropower reservoir using machine learning and persistence-based techniques", Water, 12(6), pp.1528~ (2020)[DOI]
- Chang, F. -J., "Adaptive neuro-fuzzy inference system for prediction of water level in reservoir", Advances in Water Resources, 29(1), pp.1~10 (2006)[DOI]
- Chen, T., "Xgboost : A scalable tree boosting system", Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2016)
- Das, M., "A probabilistic nonlinear model for forecasting daily water level in reservoir", Water Resources Management, 30, pp.3107~3122 (2016)[DOI]
- Doke, A., "Survey on automated machine learning(AutoML)and meta learning", 2021 12th International Conference on Computing Communication and Networking Technologies(ICCCNT) (2021)
- Elliott, G., "Complete subset regressions", Journal of Econometrics, 177(2), pp.357~373 (2013)[DOI]
- Feurer, M., "Efficient and robust automated machine learning", Advances in Neural Information Processing Systems, 28 (2015)
- Ferreira, L., "A comparison of AutoML tools for machine learning, deep learning and XGBoost", 2021International Joint Conference on Neural Networks (IJCNN) (2021)
- Fu, W., "Asymptotics for lasso-type estimators", The Annals of Statistics, 28(5), pp.1356~1378 (2000)[DOI]
- Gal, Y., "A theoretically grounded application of dropout in recurrent neural networks", Advances in Neural Information Processing Systems, 29 (2016)
- Geurts, P., "Extremely randomized trees", Machine Learning, 63, pp.3~42 (2006)[DOI]
- Hamilton, J., "Time series econometrics" (1994), Princeton University Press
- Hipni, A., "Daily forecasting of dam water levels: comparing a support vector machine (SVM)model with adaptive neuro fuzzy inference system (ANFIS)", Water Resources Management, 27(10), pp.3803~3823 (2013)
- Hochreiter, S., "Long short-term memory", Neural Computation, 9(8), pp.1735~1780 (1997)[DOI]
- Hoerl, A. E., "Ridge regression : Biased estimation for nonorthogonal problems", Technometrics, 12(1), pp.55~67 (1970)[DOI]
- Hutter, F., "Automated machine learning: methods, systems, challenges" (2019), Springer Nature
- Hyndman, R. J., "Forecasting : principles and practice" (2018), OTexts
- Kim, S., "Assessment of pan evaporation modeling using bootstrap resampling and soft computing methods", Journal of Computing in Civil Engineering, 29(5), pp.04014063~ (2015)[DOI]
- Li, F., "An ensemble modeling approach to forecast daily reservoir inflow using bidirectional long-and short-term memory(Bi-LSTM), variational mode decomposition(VMD), and energy entropy method", Water Resources Management, 35, pp.2941~2963 (2021)[DOI]
- Loi, N. K., "Automated procedure of real-time flood forecasting in Vu Gia–Thu Bon river basin, Vietnam by integrating SWAT and HEC-RAS models", Journal of Water and Climate Change, 10(3), pp.535~545 (2019)[DOI]
- Ogutu, J. O., "Genomic selection using regularized linear regression models: ridge regression, lasso, elastic net and their extensions", BMC Proceedings (2012)
- Olson, R. S., "TPOT: A tree-based pipeline optimization tool for automating machine learning", Workshop on Automatic Machine Learning (2016)
- Rajaee, T., "River suspended sediment load prediction : application of ANN and wavelet conjunction model", Journal of Hydrologic Engineering, 16(8), pp.613~627 (2011)[DOI]
- Sapitang, M., "Machine learning application in reservoir water level forecasting for sustainable hydropower generation strategy", Sustainability, 12(15), pp.6121~ (2020)[DOI]
- Seo, Y., "Reservoir water level forecasting using machine learning models", Journal of the Korean Society of Agricultural Engineers, 59(3), pp.97~110 (2017)[DOI]
- Shumway, R. H., "ARIMA models", Time Series Analysis and Its Applications : With R Examples, 75~163 (2017)