All Issue

2024 Vol.66, Issue 1
A Study on Time Series Cross-Validation Techniques for Enhancing the Accuracy of Reservoir Water Level Prediction Using Automated Machine Learning TPOT

자동기계학습 TPOT 기반 저수위 예측 정확도 향상을 위한 시계열 교차검증 기법 연구

Joo-Hyun Baea
,
Woon-Ji Parkb
,
Seoro Leec
,
Tae-Seon Parkd
,
Sang-Bin Parke
,
Jonggun Kimf
,
Kyoung-Jae Limg†
배 주현a
,
박 운지b
,
이 서로c
,
박 태선d
,
박 상빈e
,
김 종건f
,
임 경재g†
aResearch Professor, Agriculture and Life Sciences Research Institute, Kangwon National University
bPostdoctoral Research Fellow, Agriculture and Life Sciences Research Institute, Kangwon National University
cPostdoctoral Research Fellow, Agriculture and Life Sciences Research Institute, Kangwon National University
dExecutive Director, Agricultural Infrastructure Development, Korea Rural Community Corporation
eDirector, Water Resources System Department, Korea Rural Community Corporation
fAssistant Professor, Department of Regional Infrastructure Engineering, Kangwon National University
gProfessor, Department of Regional Infrastructure Engineering, Kangwon National University
a강원대학교 농업생명과학연구소 연구교수
b강원대학교 농업생명과학연구소 박사후 연구위원
c강원대학교 농업생명과학연구소 박사후 연구위원
d한국농어촌공사 농업기반시설개발본부장
e한국농어촌공사 수자원시스템부 부장
f강원대학교 지역인프라공학부 조교수
g강원대학교 지역기반공학부 교수
†Corresponding author Tel.: +82-33-250-6468, Fax: +82-33-259-5560 E-mail: kyoungjaelim@gmail.com
2024. pp. 1-13
PDF XML Citation
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.

Keywords
Machine learning
reservoir water level prediction
Tree-based Pipeline Optimization Tool (TPOT)
cross-validation
pipeline model
References

REFERENCES

1
J. H. Bae, J. Han, J. E. Yang, J. Kim, K. J. Lim and W. S. Jang, Journal of the Korean Society of Agricultural Engineers, A study on regularization methods to evaluate the sediment trapping efficiency of vegetative filter strips, 61(6); 9-19, (in Korean) (2019)10.5389/KSAE.2019.61.6.009
2
C. Bergmeir, R. J. Hyndman and B. Koo, Computational Statistics & Data Analysis, A note on the validity of cross-validation for evaluating autoregressive time series prediction, 120; 70-83 (2018)10.1016/j.csda.2017.11.003
3
P. J. Brockwell and R. A. Davis, Introduction to time series and forecasting: Springer (2002)
4
C. Castillo-Botón, D. Casillas-Pérez, C. Casanova-Mateo, L. Moreno-Saavedra, B. Morales-Díaz, J. Sanz-Justo, P. A. Gutiérrez and S. Salcedo-Sanz, Water, Analysis and prediction of dammed water level in a hydropower reservoir using machine learning and persistence-based techniques, 12(6); 1528 (2020)10.3390/w12061528
5
F.-J. Chang and Y.-T. Chang, Advances in Water Resources, Adaptive neuro-fuzzy inference system for prediction of water level in reservoir, 29(1); 1-10 (2006)10.1016/j.advwatres.2005.04.015
6
T. Chen and C. Guestrin, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningXgboost: A scalable tree boosting system (2016)
7
M. Das, S. K. Ghosh, V. Chowdary, A. Saikrishnaveni and R. Sharma, Water Resources Management, A probabilistic nonlinear model for forecasting daily water level in reservoir, 30; 3107-3122 (2016)10.1007/s11269-016-1317-7
8
A. Doke and M. Gaikwad, 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT)Survey on automated machine learning (AutoML) and meta learning (2021)
9
G. Elliott, A. Gargano and A. Timmermann, Journal of Econometrics, Complete subset regressions, 177(2); 357-373 (2013)10.1016/j.jeconom.2013.05.004
10
M. Feurer, A. Klein, K. Eggensperger, J. Springenberg, M. Blum and F. Hutter, Advances in Neural Information Processing Systems, Efficient and robust automated machine learning, 28 (2015)
11
L. Ferreira, A. Pilastri, C. M. Martins, P. M. Pires and P. Cortez, 2021 International Joint Conference on Neural Networks (IJCNN)A comparison of AutoML tools for machine learning, deep learning and XGBoost (2021)
12
W. Fu and K. Knight, The Annals of Statistics, Asymptotics for lasso-type estimators, 28(5); 1356-1378 (2000)10.1214/aos/1015957397
13
Y. Gal and Z. Ghahramani, Advances in Neural Information Processing Systems, A theoretically grounded application of dropout in recurrent neural networks, 29 (2016)
14
P. Geurts, D. Ernst and L. Wehenkel, Machine Learning, Extremely randomized trees, 63; 3-42 (2006)10.1007/s10994-006-6226-1
15
J. Hamilton, Time series econometrics, NJ. Princeton University Press Princeton. (1994)
16
A. Hipni, A. El-Shafie, A. Najah, O. A. Karim, A. Hussain and M. Mukhlisin, Water Resources Management, Daily forecasting of dam water levels: comparing a support vector machine (SVM) model with adaptive neuro fuzzy inference system (ANFIS), 27(10); 3803-3823 (2013)10.1007/s11269-013-0382-4
17
S. Hochreiter and J. Schmidhuber, Neural Computation, Long short-term memory, 9(8); 1735-1780 (1997)10.1162/neco.1997.9.8.1735
18
A. E. Hoerl and R. W. Kennard, Technometrics, Ridge regression: Biased estimation for nonorthogonal problems, 12(1); 55-67 (1970)10.1080/00401706.1970.10488634
19
F. Hutter, L. Kotthoff and J. Vanschoren, Springer Nature, Automated machine learning: methods, systems, challenges (2019)
20
R. J. Hyndman and G. Athanasopoulos, Otexts, Forecasting: principles and practice (2018)
21
S. Kim, Y. Seo and V. P. Singh, Journal of Computing in Civil Engineering, Assessment of pan evaporation modeling using bootstrap resampling and soft computing methods, 29(5); 04014063 (2015)10.1061/(asce)cp.1943-5487.0000367
22
F. Li, G. Ma, S. Chen and W. Huang, Water Resources Management, 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, 35; 2941-2963 (2021)10.1007/s11269-021-02984-2
23
N. K. Loi, N. D. Liem, L. H. Tu, N. T. Hong, C. D. Truong, V. N. Q. Tram, T. T. Nhat, T. N. Anh and J. Jeong, Journal of Water and Climate Change, Automated procedure of real-time flood forecasting in Vu Gia–Thu Bon river basin, Vietnam by integrating SWAT and HEC-RAS models, 10(3); 535-545 (2019)10.2166/wcc.2018.015
24
J. O. Ogutu, T. Schulz-Streeck and H.-P. Piepho, BMC ProceedingsGenomic selection using regularized linear regression models: ridge regression, lasso, elastic net and their extensions (2012)
25
R. S. Olson and J. H. Moore, Workshop on Automatic Machine Learning, TPOT: A tree-based pipeline optimization tool for automating machine learning (2016)
26
T. Rajaee, V. Nourani, Z. K. Mohammad and O. Kisi, Journal of Hydrologic Engineering, River suspended sediment load prediction: application of ANN and wavelet conjunction model, 16(8); 613-627 (2011)10.1061/(asce)he.1943-5584.0000347
27
M. Sapitang, W. M. Ridwan, K. Faizal Kushiar, A. Najah Ahmed and A. El-Shafie, Sustainability, Machine learning application in reservoir water level forecasting for sustainable hydropower generation strategy, 12(15); 6121 (2020)10.3390/su12156121
28
Y. Seo, E. Choi and W. Yeo, Journal of the Korean Society of Agricultural Engineers, Reservoir water level forecasting using machine learning models, 59(3); 97-110, (in Korean) (2017)10.5389/ksae.2017.59.3.097
29
R. H. Shumway, D. S. Stoffer, R. H. Shumway and D. S. Stoffer, Time Series Analysis and Its Applications: With R Examples, ARIMA models; 75-163 (2017)10.1007/978-3-319-52452-8_3
Information
  • Publisher :The Korean Society of Agricultural Engineers
  • Publisher(Ko) :한국농공학회
  • Journal Title :Journal of Korean Society of Agricultural Engineers
  • Journal Title(Ko) :한국농공학회논문집
  • Volume : 66
  • No :1
  • Pages :1-13
  • Received Date : 2023-07-19
  • Revised Date : 2023-09-08
  • Accepted Date : 2023-10-11
  • DOI :https://doi.org/10.5389/KSAE.2024.66.1.001
Journal Informaiton Journal of Korean Society of Agricultural Engineers Journal of Korean Society of Agricultural Engineers
  • NRF
  • KOFST
  • crossref crossmark
  • crossref cited-by
  • crossref funder-registry
  • crosscheck
  • orcid
  • open access
Journal Informaiton Journal Informaiton - close