Bayesian model averaging for river flow prediction
Tóm tắt
This paper explores the practical benefits of Bayesian model averaging, for a problem with limited data, namely future flow of five intermittent rivers. This problem is a useful proxy for many others, as the limited amount of data only allows tuning of small, simple models. Bayesian model averaging is theoretically a good way to cope with these difficulties, but it has not been widely used on this and similar problems. This paper uses real-world data to illustrate why. Bayesian model averaging can indeed give a better prediction, but only if the amount of data is small — if the data is so limited that it agrees a wide range of different models (instead of consistent with only a few near-identical models), then the weighted votes of those diverse models in Bayesian model averaging will (on average) give a better prediction than the single best model. In contrast, plenty of data can fit only one or a few very similar models; since they’ll vote the same way, Bayesian model averaging will give no practical improvement. Even with limited data that agrees with a range of models, the improvement is not very big large, but it is the direction of the improvement that stands out as a help for forecasting. Working around these caveats lets us better predict river floods, and similar problems with limited data.
Tài liệu tham khảo
Darwen PJ, Yao X (1997) Speciation as automatic categorical modularization. IEEE Trans Evol Comput 1(2):101–108
Duan Q, Ajami NK, Gao X, Sorooshian S (2007) Multi-model ensemble hydrologic prediction using Bayesian model averaging. Adv Water Resour 30:1371–1386
Gelman A, Carlin JB, Stern HS, Rubin DB (2004) Bayesian data analysis, 2 edn. Texts in statistical science series. Chapman-Hall, Boca Raton
Goldberg DE (1989) Genetic algorithms in search, optimization, and machine learning. Addison-Wesley, Reading
Halide H, Ridd P (2008) Complicated ENSO models do not significantly outperform very simple ENSO models. Int J Climatol 28:219–233
Haug EG (2007) Derivatives: models on models. Wiley, Hoboken
Hemri S, Fundel F, Zappa M (2013) Simultaneous calibration of ensemble river flow predictions over an entire range of lead times. Water Resour Res 49(10):6744–6755
Hoeting JA, Madigan D, Raftery AE, Volinsky CT (1999) Bayesian model averaging: a tutorial. Stat Sci 14(4):382–417
Madadgar S, Moradkhani H (2013) A Bayesian framework for probabilistic seasonal drought forecasting. J Hydrometeorol 14(6):1685–1705
Marshall L, Nott D, Sharma A (2007) Towards dynamic catchment modelling: a Bayesian hierarchical mixtures of experts framework. Hydrol Process 21(7):847–861
Mazzarella A, Giuliacci A, Liritzis I (2010) On the 60-month cycle of multivariate ENSO index. Theor Appl Climatol 100:23–27
Mitchell TM (1997) Machine learning. McGraw-Hill, New York
Najafi M, Moradkhani H, Jung I (2011) Assessing the uncertainties of hydrologic model selection in climate change impact studies. Hydrol Process 25(18):2814–2826
Parrish MA, Moradkhani H, DeChant CM (2012) Toward reduction of model uncertainty: integration of Bayesian model averaging and data assimilation. Water Resour Res 48(3):W03,519. https://doi.org/10.1029/2011WR011116
Qu B, Zhang X, Pappenberger F, Zhang T, Fang Y (2017) Multi-model grand ensemble hydrologic forecasting in the Fu River basin using Bayesian model averaging. Water 9(2):74
Raftery AE, Gneiting T, Balabdaoui F, Polakowski M (2005) Using Bayesian model averaging to calibrate forecast ensembles. Mon Weather Rev 133(5):1155–1174
Smith RE, Forrest S, Perelson AS (1992) Searching for diverse, cooperative populations with genetic algorithms. Evol Comput 1(2):127–149
Taleb N (1997) Dynamic hedging: managing vanilla and exotic options. Wiley Finance, New York
Xue B, Zhang M, Browne WN, Yao X (2016) A survey on evolutionary computation approaches to feature felection. IEEE Trans Evol Comput 20(4):606–626
Yan X, Su X (2009) Linear regression analysis: theory and computing. World Scientific