Abstract
Objective merging of multiple forecasts to improve forecast accuracy is of large interest in many disciplines. Multiple linear regression (MLR) is an extremely attractive technique for this purpose because of its simplicity and interpretability. For modeling and prediction of extremes such as floods using MLR, however, attenuation bias is a very serious issue as it results in systematic under- and over-prediction in the upper and lower tails of the predictand, respectively. In this work, we introduce conditional bias-penalized multiple linear regression (CBP-MLR) which reduces attenuation bias by jointly minimizing mean squared error (MSE) and Type-II error squared. Whereas CBP-MLR improves prediction over tails, it degrades the performance near median. To retain MLR-like performance near median while exploiting the ability of CBP-MLR to improve prediction over tails, we employ composite MLR (CompMLR) which linearly weight-averages the MLR and CBP-MLR estimates. For comparative evaluation, we apply the proposed technique to multi-model streamflow prediction using several operationally produced streamflow forecasts as predictors. The results for multiple forecast groups in the US National Weather Service Middle Atlantic River Forecast Center’s service area show that the relative performance among different input forecasts varies most significantly with the range of the verifying observed streamflow, and that CompMLR is generally superior to the best performing forecasts in the mean squared error sense under widely varying conditions of predictability and predictive skill.
Similar content being viewed by others
References
Abel AB (2017) Classical measurement error with several regressors. Wharton School of the University of Pennsylvania, National Bureau of Economic Research
Adams T (2015) Verification of the NOAA/NWS MMEFS operational hydrologic ensemble forecasting system in the Ohio River Valley. World Environmental and Water Resources Congress, Austin
Adams TE (2016) Flood Forecasting in the United States NOAA/National Weather Service. In: Flood Forecasting. Elsevier, pp 249–310
Adnan RM, Liang Z, El-Shafie A, Zounemat-Kermani M, Kisi O (2019) Prediction of suspended sediment load using data-driven models. Water 11:2060. https://doi.org/10.3390/w11102060
Alizadeh B, Limon RA, Seo D-J et al (2020) Multiscale postprocessor for ensemble streamflow prediction for short to long ranges. J Hydrometeorol 21:265–285. https://doi.org/10.1175/JHM-D-19-0164.1
Anderson EA (1973) National Weather Service river forecast system: snow accumulation and ablation model. Silver Springs. https://www.wcc.nrcs.usda.gov/ftpref/wntsc/H&H/snow/AndersonHYDRO17.pdf
Anderson E (2006) Snow accumulation and ablation model—SNOW-17. https://www.wcc.nrcs.usda.gov/ftpref/wntsc/H&H/snow/AndersonSnow17.pdf
Baharvand S, Lashkar-Ara B (2021) Hydraulic design criteria of the modified meander C-type fishway using the combined experimental and CFD models. Ecol Eng 164:106207. https://doi.org/10.1016/j.ecoleng.2021.106207
Baharvand S, Jozaghi A, Fatahi-Alkouhi R et al (2020) Comparative study on the machine learning and regression-based approaches to predict the hydraulic jump sequent depth ratio. Iran J Sci Technol Trans Civ Eng. https://doi.org/10.1007/s40996-020-00526-2
Brown JD, Seo D-J (2013) Evaluation of a nonparametric post-processor for bias correction and uncertainty estimation of hydrologic predictions. Hydrol Process 27:83–105. https://doi.org/10.1002/hyp.9263
Brown JD, He M, Regonda S et al (2014a) Verification of temperature, precipitation, and streamflow forecasts from the NOAA/NWS Hydrologic Ensemble Forecast Service (HEFS): 2. Streamflow verification. J Hydrol 519:2847–2868. https://doi.org/10.1016/j.jhydrol.2014.05.030
Brown JD, Wu L, He M et al (2014b) Verification of temperature, precipitation, and streamflow forecasts from the NOAA/NWS Hydrologic Ensemble Forecast Service (HEFS): 1. Experimental design and forcing verification. J Hydrol 519:2869–2889. https://doi.org/10.1016/j.jhydrol.2014.05.028
Carl G, Kühn I (2008) Analyzing spatial ecological data using linear regression and wavelet analysis. Stoch Environ Res Risk Assess 22:315–324. https://doi.org/10.1007/s00477-007-0117-2
Chow VT, Maidment DR, Mays LW (1988) Applied hydrology. McGraw-Hill, New York
Conway DA, Roberts HV (1983) Reverse regression, fairness, and employment discrimination. J Bus Econ Stat 1:75. https://doi.org/10.2307/1391775
Cui B, Toth Z, Zhu Y, Hou D (2012) Bias correction for global ensemble forecast. Weather Forecast 27:396–410. https://doi.org/10.1175/WAF-D-11-00011.1
Danandeh Mehr A, Kahya E, Şahin A, Nazemosadat MJ (2015) Successive-station monthly streamflow prediction using different artificial neural network algorithms. Int J Environ Sci Technol. https://doi.org/10.1007/s13762-014-0613-0
Demargne J, Wu L, Regonda SK et al (2014) The science of NOAA’s operational hydrologic ensemble forecast service. Bull Am Meteorol Soc 95:79–98. https://doi.org/10.1175/BAMS-D-12-00081.1
Deutsch R (1965) Estimation theory. Prentice-Hall, Englewood Cliffs
Diks CGH, Vrugt JA (2010) Comparison of point forecast accuracy of model averaging methods in hydrologic applications. Stoch Environ Res Risk Assess 24:809–820. https://doi.org/10.1007/s00477-010-0378-z
Du J, McQueen J, DiMego G et al (2004) 21.3 The NOAA/NWS/NCEP short range ensemble forecast (SREF) system: evaluation of an initial condition vs multiple model physics ensemble approach. Bull Am Meteorol Soc 2329–2338
Duan Q, Ajami NK, Gao X, Sorooshian S (2007) Multi-model ensemble hydrologic prediction using Bayesian model averaging. Adv Water Resour 30:1371–1386. https://doi.org/10.1016/j.advwatres.2006.11.014
Fedora MA, Beschta RL (1989) Storm runoff simulation using an antecedent precipitation index (API) model. J Hydrol 112:121–133. https://doi.org/10.1016/0022-1694(89)90184-4
Frost C, Thompson SG (2000) Correcting for regression dilution bias: comparison of methods for a single predictor variable. J R Stat Soc Ser A Stat Soc 163:173–189. https://doi.org/10.1111/1467-985X.00164
Fuller W (1987) Measurement error models. Wiley, Chichester
Georgakakos KP, Seo D-J, Gupta H et al (2004) Towards the characterization of streamflow simulation uncertainty through multimodel ensembles. J Hydrol 298:222–241. https://doi.org/10.1016/j.jhydrol.2004.03.037
Gochis DJ, Barlage M, Dugger A et al (2018) The WRF-hydro modeling system technical description, (Version 5.0). NCAR technical note. https://ral.ucar.edu/sites/default/files/public/WRFHydroV5TechnicalDescription.pdf
Goldberger AS (1984) Reverse regression and salary discrimination. J Hum Resour 19:293–318. https://doi.org/10.2307/145875
Goodarzi E, Ziaei M, Hosseinipour EZ (2014) Introduction to optimization analysis in hydrosystem engineering. Springer, Cham
Graziano T, Clark E, Cosgrove B, Gochis D (2017) Transforming National Oceanic and Atmospheric Administration (NOAA) water resources prediction. In: 31st conference on hydrology, Seattle, WA, Amer. Meteor. Soc., 2A.2, https://ams.confex.com/ams/97Annual/webprogram/Paper314016.html
Green CA, Ferber MA (1984) Employment discrimination: an empirical test of forward versus reverse regression. J Hum Resour 19:557. https://doi.org/10.2307/145948
Hamill TM, Bates GT, Whitaker JS et al (2013) NOAA’s second-generation global medium-range ensemble reforecast dataset. Bull Am Meteorol Soc 94:1553–1565. https://doi.org/10.1175/BAMS-D-12-00014.1
Hassanzadeh Y, Ghazvinian M, Abdi A, Baharvand S, Jozaghi A (2020) Prediction of short and long-term droughts using artificial neural networks and hydro-meteorological variables. arXiv:2006.02581 [physics.ao-ph]
Hausman J (2001) Mismeasured variables in econometric analysis: problems from the right and problems from the left. J Econ Perspect 15:57–67. https://doi.org/10.1257/jep.15.4.57
Hoerl AE (1962) Application of ridge analysis to regression problems. Chem Eng Prog 58:54–59
Hoerl AE, Kennard RW (1970) Ridge regression: biased estimation for nonorthogonal problems. Technometrics. https://doi.org/10.1080/00401706.1970.10488634
Hoeting JA, Madigan D, Raftery AE et al (1999) Bayesian model averaging: a tutorial (with discussion). Stat Sci 14:382
Hughes MD (1993) Regression dilution in the proportional hazards model. Biometrics 49:1056. https://doi.org/10.2307/2532247
Jahan A, Edwards KL, Bahraminasab M (2016) Multi-criteria decision analysis for supporting the selection of engineering materials in product design. Butterworth-Heinemann Elsevier Ltd, Oxford
Jolliffe IT, Stephenson DB (eds) (2011) Forecast verification. Wiley, Chichester
Jozaghi A, Shamsai A (2017) Application of geospatial information system and technique for order preference by similarity to ideal solution for sitting water reservoirs case study: south of Sistan&Balouchestan Province. Sci Res Q Geogr Data 25(100):5–15. https://doi.org/10.22131/sepehr.2017.24802
Jozaghi A, Alizadeh B, Hatami M, Flood I, Khorrami M, Khodaei N, Ghasemi Tousi E (2018) A comparative study of the AHP and TOPSIS techniques for dam site selection using GIS: a case study of Sistan and Baluchestan Province. Iran Geosci 8:494. https://doi.org/10.3390/geosciences8120494
Jozaghi A, Nabatian M, Noh S et al (2019) Improving multisensor precipitation estimation via adaptive conditional bias-penalized merging of rain gauge data and remotely sensed quantitative precipitation estimates. J Hydrometeorol 20:2347–2365. https://doi.org/10.1175/JHM-D-19-0129.1
Jozaghi A, Ghazvinian M, Seo D et al (2020) Improving water forecasting with Bayesian averaging of multiple forecasts. In: 34th conference on hydrology, Boston, MA, Amer. Meteor. Soc., J26.3. https://ams.confex.com/ams/2020Annual/meetingapp.cgi/Paper/369034
Jozaghi A, Shen H, Seo D et al (2021) Improving flood forecasting via conditional bias-penalized bayesian model averaging. In: Amer. Meteor. Soc., 35th conference on hydrology, New Orleans, LA
Khan UT, Valeo C, He J (2013) Non-linear fuzzy-set based uncertainty propagation for improved DO prediction using multiple-linear regression. Stoch Environ Res Risk Assess 27:599–616. https://doi.org/10.1007/s00477-012-0626-5
Khanmohammadi N, Rezaie H, Montaseri M, Behmanesh J (2018) The application of multiple linear regression method in reference evapotranspiration trend calculation. Stoch Environ Res Risk Assess 32:661–673. https://doi.org/10.1007/s00477-017-1378-z
Kim B, Seo D-J, Noh SJ et al (2018) Improving multisensor estimation of heavy-to-extreme precipitation via conditional bias-penalized optimal estimation. J Hydrol 556:1096–1109. https://doi.org/10.1016/j.jhydrol.2016.10.052
Krzysztofowicz R (1999) Bayesian theory of probabilistic forecasting via deterministic hydrologic model. Water Resour Res. https://doi.org/10.1029/1999WR900099
Lashkar-Ara B, Baharvand S, Najafi L (2021) Study the performance of data-driven models to predict the scour depth caused by the aerated vertical jet. Irrig Sci Eng 43(4):79–89
Lee H, Shen H, Noh SJ et al (2019) Improving flood forecasting using conditional bias-penalized ensemble Kalman filter. J Hydrol 575:596–611. https://doi.org/10.1016/j.jhydrol.2019.05.072
Levi MD (1973) Errors in the variables bias in the presence of correctly measured variables. Econometrica. https://doi.org/10.2307/1913819
Liu Y, Ye L, Qin H, Hong X, Ye J, Yin X (2018) Monthly streamflow forecasting based on hidden Markov model and Gaussian Mixture Regression. J Hydrol. https://doi.org/10.1016/j.jhydrol.2018.03.057
Luo X, Yuan X, Zhu S, Xu Z, Meng L, Peng J (2019) A hybrid support vector regression framework for streamflow forecast. J Hydrol. https://doi.org/10.1016/j.jhydrol.2018.10.064
Madigan D, Raftery AE (1994) Model selection and accounting for model uncertainty in graphical models using occam’s window. J Am Stat Assoc. https://doi.org/10.1080/01621459.1994.10476894
Makkonen L (2006) Plotting positions in extreme value analysis. J Appl Meteorol Climatol. https://doi.org/10.1175/JAM2349.1
MARFC (2010) Understanding the River Forecast Process, NWS Middle Atlantic River Forecast Center, State College, PA. https://www.weather.gov/media/marfc/FactSheets/Fact_Sheet_Understanding_River_Forecast_Process_FINAL_singlepgs.pdf, Accessed 02 June 2021
Muhammad A, Stadnyk TA, Unduche F, Coulibaly P (2018) Multi-model approaches for improving seasonal ensemble streamflow prediction scheme with various statistical post-processing techniques in the Canadian Prairie Region. Water (Switzerland). https://doi.org/10.3390/w10111604
Murphy AH, Winkler RL (1987) A general framework for forecast verification. Mon Weather Rev. https://doi.org/10.1175/1520-0493(1987)115%3c1330:AGFFFV%3e2.0.CO;2
National Weather Service (2006) NWSRFS User Manual Documentation. Office of Hydrologic Development, Silver Spring, MD. https://www.nws.noaa.gov/oh/hrl/nwsrfs/users_manual/htm/warnpdf.php
National Weather Service (2008a) Single reservoir regulation (RES-SNGL) model. In: Office of Water Prediction (NWS OWP/NOAA). https://www.nws.noaa.gov/oh/hrl/general/chps/Models/Single_Reservoir_Regulation.pdf. Accessed 30 Jan 2017
National Weather Service (2008b) Joint reservoir regulation (RES-J) model. In: Office of Water Prediction (NWS OWP/NOAA). http://www.nws.noaa.gov/oh/hrl/general/chps/Models/Joint_Reservoir_Regulation.pdf. Accessed 30 Jan 2017
National Weather Service (2015) ensemble postprocessor (EnsPost) user’s manual. Office of Hydrologic Development, Silver Spring. https://www.nws.noaa.gov/oh/hrl/general/HEFS_doc/EnsPost_Users_Manual.pdf. Accessed 04 Apr 2015
National Weather Service (2016) meteorological ensemble forecast processor (MEFP) user’s manual. Office of Hydrologic Development, Silver Spring. https://www.nws.noaa.gov/oh/hrl/general/HEFS_doc/MEFP_Users_Manual.pdf
Nelson BR, Seo D-J, Kim D (2010) Multisensor precipitation reanalysis. J Hydrometeorol 11:666–682. https://doi.org/10.1175/2010JHM1210.1
Raftery AE, Gneiting T, Balabdaoui F, Polakowski M (2005) Using Bayesian model averaging to calibrate forecast ensembles. Mon Weather Rev. https://doi.org/10.1175/MWR2906.1
Raftery AE, Hoeting J, Volinsky CT et al (2015) BMA: Bayesina model averaging. http://cran.r-project.org/package=BMA
Raiffa H, Schlaifer R (1961) Applied statistical decision theory. Harvard University Press, Boston
Regonda SK, Seo DJ, Lawrence B et al (2013) Short-term ensemble streamflow forecasting using operationally-produced single-valued streamflow forecasts: a Hydrologic Model Output Statistics (HMOS) approach. J Hydrol. https://doi.org/10.1016/j.jhydrol.2013.05.028
Roe J, Dietz C, Restrepo P et al (2010) NOAA’s community hydrologic prediction system. In: 2th federal interagency hydrologic modeling conference, Las Vegas, NV. https://acwi.gov/sos/pubs/2ndJFIC/Contents/7E_Roe_12_28_09.pdf
Schaake J, Demargne J, Hartman R et al (2007) Precipitation and temperature ensemble forecasts from single-value forecasts. Hydrol Earth Syst Sci Discuss. https://doi.org/10.5194/hessd-4-655-2007
Schweppe FC (1973) Uncertain dynamic systems. Prentice Hall, Englewood Cliffs
Seber GAF, Wild CJ (1989) Nonlinear regression. Wiley, Hoboken
Seo DJ (2013) Conditional bias-penalized kriging (CBPK). Stoch Environ Res Risk Assess. https://doi.org/10.1007/s00477-012-0567-z
Seo D-J, Herr HD, Schaake JC (2006) A statistical post-processor for accounting of hydrologic uncertainty in short-range ensemble streamflow prediction. Hydrol Earth Syst Sci Discuss. https://doi.org/10.5194/hessd-3-1987-2006
Seo DJ, Siddique R, Zhang Y, Kim D (2014) Improving real-time estimation of heavy-to-extreme precipitation using rain gauge data via conditional bias-penalized optimal estimation. J Hydrol. https://doi.org/10.1016/j.jhydrol.2014.09.055
Seo D-J, Saifuddin MM, Lee H (2018a) Conditional bias-penalized Kalman filter for improved estimation and prediction of extremes. Stoch Environ Res Risk Assess 32:183–201. https://doi.org/10.1007/s00477-017-1442-8
Seo D-J, Saifuddin MM, Lee H (2018b) Correction to: Conditional bias-penalized Kalman filter for improved estimation and prediction of extremes. Stoch Environ Res Risk Assess. https://doi.org/10.1007/s00477-018-1626-x
Shen H, Lee H, Seo D-J (2019) Adaptive conditional bias-penalized kalman filter for improved estimation of extremes and its approximation for reduced computation. arXiv:1908.00482
Siddique R, Mejia A, Brown J et al (2015) Verification of precipitation forecasts from two numerical weather prediction models in the Middle Atlantic Region of the USA: a precursory analysis to hydrologic forecasting. J Hydrol. https://doi.org/10.1016/j.jhydrol.2015.08.042
Sittner WT, Schauss CE, Monro JC (1969) Continuous hydrograph synthesis with an API-type hydrologic model. Water Resour Res. https://doi.org/10.1029/WR005i005p01007
Theil H (1961) Economic forecasts and policy. North-Holland Pub. Co., Amsterdam
Tibshirani R (1996) Regression shrinkage and selection via the lasso. J R Stat Soc Ser B. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x
Tibshirani R (1997) The lasso method for variable selection in the cox model. Stat Med. https://doi.org/10.1002/(SICI)1097-0258(19970228)16:4%3c385::AID-SIM380%3e3.0.CO;2-3
Tikhonov AN, Arsenin VY (1977) Solutions of ill-posed problems. Winston and Sons, Washington
Tikhonov AN, Goncharsky AV, Stepanov VV, Yagola AG (1995) Numerical methods for the solution of ill-posed problems
Toth Z, Kalnay E (1997) Ensemble forecasting at NCEP and the breeding method. Mon Weather Rev. https://doi.org/10.1175/1520-0493(1997)125%3c3297:EFANAT%3e2.0.CO;2
Wilks DS (2005) Statistical methods in the atmospheric sciences, 2nd edn. Academic Press, London
Wu L, Seo DJ, Demargne J et al (2011) Generation of ensemble precipitation forecast from single-valued quantitative precipitation forecast for hydrologic ensemble prediction. J Hydrol. https://doi.org/10.1016/j.jhydrol.2011.01.013
Zeugner S (2011) Bayesian model averaging with BMS. WwwCranR-ProductOrg
Zhu Y, Toth Z (2008) NAEFS and NCEP global ensemble. Presentation for National DOH Workshop. https://www.nws.noaa.gov/oh/hrl/hsmb/docs/hep/events_announce/NAEFS_Yuejian_Zhu.pdf
Acknowledgements
This material is based upon work supported in part by the NOAA’s Joint Technology Transfer Initiative Program (Grant NA16OAR4590232). This support is gratefully acknowledged.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Jozaghi, A., Shen, H., Ghazvinian, M. et al. Multi-model streamflow prediction using conditional bias-penalized multiple linear regression. Stoch Environ Res Risk Assess 35, 2355–2373 (2021). https://doi.org/10.1007/s00477-021-02048-3
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00477-021-02048-3