Impact of Bias-Correction Type and Conditional Training on Bayesian Model Averaging over the Northeast United States

Abstract The performance of a multimodel ensemble over the northeast United States is evaluated before and after applying bias correction and Bayesian model averaging (BMA). The 13-member Stony Brook University (SBU) ensemble at 0000 UTC is combined with the 21-member National Centers for Environmental Prediction (NCEP) Short-Range Ensemble Forecast (SREF) system at 2100 UTC. The ensemble is verified using 2-m temperature and 10-m wind speed for the 2007–09 warm seasons, and for subsets of days with high ozone and high fire threat. The impacts of training period, bias-correction method, and BMA are explored for these potentially hazardous weather events using the most recent consecutive (sequential training) and most recent similar days (conditional training). BMA sensitivity to the selection of ensemble members is explored. A running mean difference between forecasts and observations using the last 14 days is better at removing temperature bias than is a cumulative distribution function (CDF) or linear regression approach. Wind speed bias is better removed by adjusting the modeled CDF to the observation. High fire threat and ozone days exhibit a larger cool bias and a greater negative wind speed bias than the warm-season average. Conditional bias correction is generally better at removing temperature and wind speed biases than sequential training. Greater probabilistic skill is found for temperature using both conditional bias correction and BMA compared to sequential bias correction with or without BMA. Conditional and sequential BMA results are similar for 10-m wind speed, although BMA typically improves probabilistic skill regardless of training.

Download Full-text

Short Term Wind Speed Forecasting Based on Bayesian Model Averaging Method

Volume 6: Emerging Technologies: Alternative Energy Systems; Energy Systems: Analysis, Thermodynamics and Sustainability ◽

10.1115/imece2009-13055 ◽

2009 ◽

Author(s):

Gong Li ◽

Jing Shi ◽

Junyi Zhou

Keyword(s):

Wind Speed ◽

Power System ◽

Wind Energy ◽

Statistical Models ◽

Bayesian Model ◽

Bayesian Model Averaging ◽

Model Averaging ◽

Short Term ◽

Goodness Of Fit Test ◽

Wind Speed Forecasting

Wind energy has been the world’s fastest growing source of clean and renewable energy in the past decade. One of the fundamental difficulties faced by power system operators, however, is the unpredictability and variability of wind power generation, which is closely connected with the continuous fluctuations of the wind resource. Good short-term wind speed forecasting methods and techniques are urgently needed since it is important for wind energy conversion systems in terms of the relevant issues associated with the dynamic control of the wind turbine and the integration of wind energy into the power system. This paper proposes the application of Bayesian Model Averaging (BMA) method in combining the one-hour-ahead short-term wind speed forecasts from different statistical models. Based on the hourly wind speed observations from one representative site within North Dakota, four statistical models are built and the corresponding forecast time series are obtained. These data are then analyzed by using BMA method. The goodness-of-fit test results show that the BMA method is superior to its component models by providing a more reliable and accurate description of the total predictive uncertainty than the original elements, leading to a sharper probability density function for the probabilistic wind speed predictions.

Download Full-text

Probabilistic wind speed forecasting using Bayesian model averaging with truncated normal components

Computational Statistics & Data Analysis ◽

10.1016/j.csda.2014.02.013 ◽

2014 ◽

Vol 75 ◽

pp. 227-238 ◽

Cited By ~ 49

Author(s):

Sándor Baran

Keyword(s):

Wind Speed ◽

Bayesian Model ◽

Bayesian Model Averaging ◽

Model Averaging ◽

Wind Speed Forecasting ◽

Truncated Normal

Download Full-text

Application of Bayesian model averaging in modeling long-term wind speed distributions

Renewable Energy ◽

10.1016/j.renene.2009.09.003 ◽

2010 ◽

Vol 35 (6) ◽

pp. 1192-1202 ◽

Cited By ~ 44

Author(s):

Gong Li ◽

Jing Shi

Keyword(s):

Wind Speed ◽

Bayesian Model ◽

Bayesian Model Averaging ◽

Model Averaging

Download Full-text

A Comparison between Raw Ensemble Output, (Modified) Bayesian Model Averaging, and Extended Logistic Regression Using ECMWF Ensemble Precipitation Reforecasts

Monthly Weather Review ◽

10.1175/2010mwr3285.1 ◽

2010 ◽

Vol 138 (11) ◽

pp. 4199-4211 ◽

Cited By ~ 57

Author(s):

Maurice J. Schmeits ◽

Kees J. Kok

Keyword(s):

Logistic Regression ◽

Bias Correction ◽

Bayesian Model ◽

Bayesian Model Averaging ◽

Model Averaging ◽

Ensemble Prediction ◽

Ensemble Forecasts ◽

Ensemble Prediction System ◽

The Difference ◽

Model Output Statistics

Abstract Using a 20-yr ECMWF ensemble reforecast dataset of total precipitation and a 20-yr dataset of a dense precipitation observation network in the Netherlands, a comparison is made between the raw ensemble output, Bayesian model averaging (BMA), and extended logistic regression (LR). A previous study indicated that BMA and conventional LR are successful in calibrating multimodel ensemble forecasts of precipitation for a single forecast projection. However, a more elaborate comparison between these methods has not yet been made. This study compares the raw ensemble output, BMA, and extended LR for single-model ensemble reforecasts of precipitation; namely, from the ECMWF ensemble prediction system (EPS). The raw EPS output turns out to be generally well calibrated up to 6 forecast days, if compared to the area-mean 24-h precipitation sum. Surprisingly, BMA is less skillful than the raw EPS output from forecast day 3 onward. This is due to the bias correction in BMA, which applies model output statistics to individual ensemble members. As a result, the spread of the bias-corrected ensemble members is decreased, especially for the longer forecast projections. Here, an additive bias correction is applied instead and the equation for the probability of precipitation in BMA is also changed. These modifications to BMA are referred to as “modified BMA” and lead to a significant improvement in the skill of BMA for the longer projections. If the area-maximum 24-h precipitation sum is used as a predictand, both modified BMA and extended LR improve the raw EPS output significantly for the first 5 forecast days. However, the difference in skill between modified BMA and extended LR does not seem to be statistically significant. Yet, extended LR might be preferred, because incorporating predictors that are different from the predictand is straightforward, in contrast to BMA.

Download Full-text

Bayesian Model Averaging of Climate Model Projections Constrained by Precipitation Observations over the Contiguous United States

Journal of Hydrometeorology ◽

10.1175/jhm-d-19-0258.1 ◽

2020 ◽

Vol 21 (10) ◽

pp. 2401-2418 ◽

Cited By ~ 2

Author(s):

E. C. Massoud ◽

H. Lee ◽

P. B. Gibson ◽

P. Loikith ◽

D. E. Waliser

Keyword(s):

United States ◽

Bayesian Model ◽

Bayesian Model Averaging ◽

Climate Model ◽

Model Averaging ◽

Daily Rainfall ◽

Climate Projections ◽

Total Uncertainty ◽

Model Average ◽

Ensemble Mean

AbstractThis study utilizes Bayesian model averaging (BMA) as a framework to constrain the spread of uncertainty in climate projections of precipitation over the contiguous United States (CONUS). We use a subset of historical model simulations and future model projections (RCP8.5) from the Coupled Model Intercomparison Project phase 5 (CMIP5). We evaluate the representation of five precipitation summary metrics in the historical simulations using observations from the NASA Tropical Rainfall Measuring Mission (TRMM) satellites. The summary metrics include mean, annual and interannual variability, and maximum and minimum extremes of precipitation. The estimated model average produced with BMA is shown to have higher accuracy in simulating mean rainfall than the ensemble mean (RMSE of 0.49 for BMA versus 0.65 for ensemble mean), and a more constrained spread of uncertainty with roughly a third of the total uncertainty than is produced with the multimodel ensemble. The results show that, by the end of the century, the mean daily rainfall is projected to increase for most of the East Coast and the Northwest, may decrease in the southern United States, and with little change expected for the Southwest. For extremes, the wettest year on record is projected to become wetter for the majority of CONUS and the driest year to become drier. We show that BMA offers a framework to more accurately estimate and to constrain the spread of uncertainties of future climate, such as precipitation changes over CONUS.

Download Full-text

Calibrated Surface Temperature Forecasts from the Canadian Ensemble Prediction System Using Bayesian Model Averaging

Monthly Weather Review ◽

10.1175/mwr3347.1 ◽

2007 ◽

Vol 135 (4) ◽

pp. 1364-1385 ◽

Cited By ~ 76

Author(s):

Laurence J. Wilson ◽

Stephane Beauregard ◽

Adrian E. Raftery ◽

Richard Verret

Keyword(s):

Surface Temperature ◽

Bias Correction ◽

Bayesian Model ◽

Bayesian Model Averaging ◽

Model Averaging ◽

Training Sample ◽

Ensemble Prediction ◽

Ensemble Forecasts ◽

Modest Improvement ◽

Component Models

Abstract Bayesian model averaging (BMA) has recently been proposed as a way of correcting underdispersion in ensemble forecasts. BMA is a standard statistical procedure for combining predictive distributions from different sources. The output of BMA is a probability density function (pdf), which is a weighted average of pdfs centered on the bias-corrected forecasts. The BMA weights reflect the relative contributions of the component models to the predictive skill over a training sample. The variance of the BMA pdf is made up of two components, the between-model variance, and the within-model error variance, both estimated from the training sample. This paper describes the results of experiments with BMA to calibrate surface temperature forecasts from the 16-member Canadian ensemble system. Using one year of ensemble forecasts, BMA was applied for different training periods ranging from 25 to 80 days. The method was trained on the most recent forecast period, then applied to the next day’s forecasts as an independent sample. This process was repeated through the year, and forecast quality was evaluated using rank histograms, the continuous rank probability score, and the continuous rank probability skill score. An examination of the BMA weights provided a useful comparative evaluation of the component models, both for the ensemble itself and for the ensemble augmented with the unperturbed control forecast and the higher-resolution deterministic forecast. Training periods around 40 days provided a good calibration of the ensemble dispersion. Both full regression and simple bias-correction methods worked well to correct the bias, except that the full regression failed to completely remove seasonal trend biases in spring and fall. Simple correction of the bias was sufficient to produce positive forecast skill out to 10 days with respect to climatology, which was improved by the BMA. The addition of the control forecast and the full-resolution model forecast to the ensemble produced modest improvement in the forecasts for ranges out to about 7 days. Finally, BMA produced significantly narrower 90% prediction intervals compared to a simple Gaussian bias correction, while achieving similar overall accuracy.

Download Full-text