Integration of Hydrological Model and Time Series Model for Improving the Runoff Simulation: A Case Study on BTOP Model in Zhou River Basin, China
Source abstract
Abstract
Improving the accuracy of runoff simulations is a significant focus of hydrological science for multiple purposes such as water resources management, flood and drought prediction, and water environment protection. However, the simulated runoff has limitations that cannot be eliminated. This paper proposes a method that integrates the hydrological and time series models to improve the reliability and accuracy of simulated runoffs. Specifically, the block-wise use of TOPMODEL (BTOP) is integrated with three time series models to improve the simulated runoff from a hydrological model of the Zhou River Basin, China. Unlike most previous research that has not addressed the influence of runoff patterns while correcting the runoff, this study manually adds the hydrologic cycle to the machine learning-based time series model. This also incorporates scenario-specific knowledge from the researcher’s area of expertise into the prediction model. The results show that the improved Prophet model proposed in this study, that is, by adjusting its holiday function to a flow function, significantly improved the Nash–Sutcliffe efficiency (NSE) of the simulated runoff by 53.47% (highest) and 23.93% (average). The autoregressive integrated moving average (ARIMA) model and long short-term memory (LSTM) improved the runoff but performed less well than the improved Prophet model. This paper presents an effective method to improve the runoff simulation by integrating the hydrological and time series models.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Hydrology and Watershed Management Studies · Flood Risk Assessment and Management · Hydrological Forecasting Using AI
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
State Key Laboratory of Hydraulics and Mountain River Engineering, College of Water Resource and Hydropower, Sichuan University, No. 24 South Section 1, Yihuan Road, Chengdu 610065, China
Institute for Disaster Management and Reconstruction, Sichuan University-Hong Kong Polytechnic University, Chengdu 610065, China
College of Water Resources and Hydropower, Sichuan Agricultural University, Ya’an 625014, China
Funding
the Regional Innovation Cooperation Program · the Science& Technology Department of Sichuan Province · the Science and Technology Department of Tibet
References (62)
Show source-provided references
1. Surface Water Resources, Climate Change and Simulation Modeling10.1016/j.aqpro.2015.02.094 ↗
2. Distributed-Parameter Large Basin Runoff Model. I: Model Development10.1061/(ASCE)1084-0699(2005)10:3(173) ↗
3. How much runoff originates as snow in the western United States, and how will that change in the future?10.1002/2017GL073551 ↗
4. Hydrological modelling of urbanized catchments: A review and future directions10.1016/j.jhydrol.2015.06.028 ↗
5. Liu, C., and Shan, Y. (2021). Impact of an emergent model vegetation patch on flow adjustment and velocity. Water Management, Thomas Telford Ltd.
6. An open channel with an emergent vegetation patch: Predicting the longitudinal profiles of velocities based on exponential decay10.1016/j.jhydrol.2019.124429 ↗
7. Zhou, L., Zhang, X., Liu, L., Chen, T., Liu, X., Ren, Y., Zhang, H., Li, X., and Ao, T. (2020). An Approach to Evaluate Non-Point Source Pollution in An Ungauged Basin: A Case Study in Xiao'anxi River Basin, China, IWA Publishing.10.2166/ws.2020.216 ↗
8. Time-Series Data Mining
9. Box, G.E.P., and Jenkins, G.M. (1970). Time Series Analysis Forecasting and Control, Holden-Day.
10. A review of unsupervised feature learning and deep learning for time-series modeling10.1016/j.patrec.2014.01.008 ↗
11. Recent advances in SAR interferometry time series analysis for measuring crustal deformation
12. Applications of hybrid wavelet-Artificial Intelligence models in hydrology: A review10.1016/j.jhydrol.2014.03.057 ↗
13. A new method for runoff prediction error correction based on LS-SVM and a 4D copula joint distribution10.1016/j.jhydrol.2021.126223 ↗
14. A stochastic approach for assessing the uncertainty of rainfall-runoff simulations10.1029/2003WR002540 ↗
15. Cheng, C., Li, Y., and Liu, L. (2021, January 11–12). Study on real-time flood prediction in Xijiang River Basin based on ArMA-GARCH Model. Proceedings of the Chinese Society of Dam Engineering 2021 Annual Conference, Guangzhou, China.
16. Bayesian probabilistic flood forecasting system
17. Jiao, W., and Long, H. (2015). Prediction correction of distributed hydrological model based on autoregressive model. J. Water Resour. Water Eng., 6.
18. (2022, March 25). The Data Set Is Provided by Geospatial Data Cloud Site, Computer Network Information Center, Chinese Academy of Sciences. Available online: http://www.gscloud.cn.
19. (2022, March 25). LP DAAC-MCD12Q1, Available online: https://lpdaac.usgs.gov/products/mcd12q1v006/.
20. (2022, March 25). FAO Digital Soil Map of the World (DSMW). Available online: http://www.fao.org/land-water/land/land-governance/land-resources-planning-toolbox/category/details/en/c/1026564/.
21. GLEAM v3: Satellite-based land evaporation and root-zone soil moisture10.5194/gmd-10-1903-2017 ↗
22. (2022, March 25). The Potential Evapotranspiration (EP) from the Climatic Research Unit (CRU) of the School of Environmental Sciences (ENV) at the University of East Anglia (UEA). Available online: http://www.cru.uea.ac.uk/.
23. (2022, March 25). The Leaf Area Index (LAI) of the National Centers for Environmental Information, Available online: https://www.ncei.noaa.gov/data/avhrr-land-leaf-area-index-and-fapar/access/.
24. Zhu, Y., Liu, L., Qin, F., Zhou, L., Zhang, X., Chen, T., Li, X., and Ao, T. (2021). Application of the Regression-Augmented Regionalization Approach for BTOP Model in Ungauged Basins. Water, 13.10.3390/w13162294 ↗
25. Gusyev, M.A., Magome, J., Kiem, A., and Takeuchi, K. (2017). The BTOP Model with Supplementary Tools User Manual, Public Works Research Institute (PWRI).
26. Introduction of block-wise use of TOPMODEL and Muskingum-Cunge method for the hydroenvironmental simulation of a large ungauged basin10.1080/02626669909492258 ↗
27. Development and application of a new algorithm for automated pit removal for grid DEMs10.1623/hysj.48.6.985.51423 ↗
28. A BTOP model to extend TOPMODEL for distributed hydrological simulation of large basins10.1002/hyp.6910 ↗
29. Screening and Optimizing the Sensitive Parameters of BTOPMC Model Based on UQ-PyL Software: Case Study of a Flood Event in the Fuji River Basin, Japan10.1061/(ASCE)HE.1943-5584.0001970 ↗
30. Zhou, L., Rasmy, M., Takeuchi, K., Koike, T., Selvarajah, H., and Ao, T. (2021). Adequacy of Near Real-Time Satellite Precipitation Products in Driving Flood Discharge Simulation in the Fuji River Basin, Japan. Appl. Sci., 11.10.3390/app11031087 ↗
31. A study on availability of ground observations and its impacts on bias correction of satellite precipitation products and hydrologic simulation efficiency10.1016/j.jhydrol.2022.127595 ↗
32. Investigation of the Mekong River basin hydrology for 1980–2000 using the YHyM10.1002/hyp.6934 ↗
33. Studies on the Mekong River Basin-Modelling of Hydrology and Water Resources10.1002/hyp.6933 ↗
34. Comprehensive evaluation of parameter importance and optimization based on the integrated sensitivity analysis system: A case study of the BTOP model in the upper Min River Basin, China10.1016/j.jhydrol.2022.127819 ↗
35. The assessment of spatial and temporal transferability of a physically based distributed hydrological model parameters in different physiographic regions of Nepal10.1016/j.jhydrol.2007.09.016 ↗
36. Relating BTOPMC model parameters to physical features of MOPEX basins10.1016/j.jhydrol.2005.07.006 ↗
37. Shuffled complex evolution approach for effective and efficient global minimization10.1007/BF00939380 ↗
38. Applications of the ARIMA model for time series data analysis
39. Day-ahead wind speed forecasting using f-ARIMA models10.1016/j.renene.2008.09.006 ↗
40. Cong, M., and Li, Y. (2017). Improving Forecasting Accuracy of Annual Runoff Time Series Using RBFN Based on EEMD Decomposition. DEStech Trans. Eng. Technol. Res.
41. Autoregressive Integrated Moving Average (ARIMA) Model of Forecast Demand in Distribution Centre10.1088/1757-899X/598/1/012071 ↗
42. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
43. A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures10.1162/neco_a_01199 ↗
44. Alom, M.Z., Taha, T.M., Yakopcic, C., Westberg, S., Sidike, P., Nasrin, M.S., Hasan, M., Essen, B.V., Awwal, A., and Asari, V.K. (2019). A State-of-the-Art Survey on Deep Learning Theory and Architectures. Electronics, 8.10.3390/electronics8030292 ↗
45. Duarte, D., Walshaw, C., and Ramesh, N. (2021). A Comparison of Time-Series Predictions for Healthcare Emergency Department Indicators and the Impact of COVID-19. Appl. Sci., 11.10.3390/app11083561 ↗
46. Forecasting at Scale
47. Time series analysis and forecasting of coronavirus disease in Indonesia using ARIMA model and PROPHET10.1016/j.procs.2021.01.036 ↗
48. Prophet, a web-based tool for class prediction using microarray data10.1093/bioinformatics/btl602 ↗
49. An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision10.1109/TPAMI.2004.60 ↗
50. Forecasting of COVID-19 cases using Deep learning models: Is it reliable and practically significant?10.1016/j.rinp.2021.103817 ↗
51. Automatic forecasting software: A survey and evaluation10.1016/0169-2070(91)90055-Z ↗
52. Efficient Tests for an Autoregressive Unit Root10.2307/2171846 ↗
53. Gep, B., and Gm, J. (1976). Times Series Analysis—Forecasting and Control, Prentice-Hall.
54. Mitic, P. (November, January 30). Is a Reputation Time Series White Noise?. Proceedings of the International Conference on Intelligent Data Engineering and Automated Learning, Guilin, China.
55. The use of the Durbin–Watsondstatistic in Rietveld analysis10.1107/S0021889887086485 ↗
56. Daily wind speed forecasting through hybrid KF-ANN model based on ARIMA10.1016/j.renene.2014.11.084 ↗
57. Short-term traffic flow prediction using seasonal ARIMA model with limited input data10.1007/s12544-015-0170-8 ↗
58. Application of a hybrid ARIMA-LSTM model based on the SPEI for drought forecasting10.1007/s11356-021-15325-z ↗
59. Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networks
60. Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network10.1016/j.physd.2019.132306 ↗
61. LSTM: A Search Space Odyssey10.1109/TNNLS.2016.2582924 ↗
62. Effectiveness of water infrastructure for river flood management: Part 1—Flood Hazard Assessment using hydrological models in Bangladesh