Skip to main content

Integrating Hydrological and Machine Learning Models for Enhanced Streamflow Forecasting via Bayesian Model Averaging in a Hydro-Dominant Power System

Publication ,  Journal Article
Torres, FLR; Lima, LMM; Reboita, MS; de Queiroz, AR; Lima, JWM
Published in: Water (Switzerland)
February 1, 2024

Streamflow forecasting plays a crucial role in the operational planning of hydro-dominant power systems, providing valuable insights into future water inflows to reservoirs and hydropower plants. It relies on complex mathematical models, which, despite their sophistication, face various uncertainties affecting their performance. These uncertainties can significantly influence both short-term and long-term operational planning in hydropower systems. To mitigate these effects, this study introduces a novel Bayesian model averaging (BMA) framework to improve the accuracy of streamflow forecasts in real hydro-dominant power systems. Designed to serve as an operational tool, the proposed framework incorporates predictive uncertainty into the forecasting process, enhancing the robustness and reliability of predictions. BMA statistically combines multiple models based on their posterior probability distributions, producing forecasts from the weighted averages of predictions. This approach updates weights periodically using recent historical data of forecasted and measured streamflows. Tested on inflows to 139 reservoirs and hydropower plants in Brazil, the proposed BMA framework proved to be more skillful than individual models, showing improvements in forecasting accuracy, especially in the South and Southeast regions of Brazil. This method offers a more reliable tool for streamflow prediction, enhancing decision making in hydropower system operations.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Water (Switzerland)

DOI

EISSN

2073-4441

Publication Date

February 1, 2024

Volume

16

Issue

4
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Torres, F. L. R., Lima, L. M. M., Reboita, M. S., de Queiroz, A. R., & Lima, J. W. M. (2024). Integrating Hydrological and Machine Learning Models for Enhanced Streamflow Forecasting via Bayesian Model Averaging in a Hydro-Dominant Power System. Water (Switzerland), 16(4). https://doi.org/10.3390/w16040586
Torres, F. L. R., L. M. M. Lima, M. S. Reboita, A. R. de Queiroz, and J. W. M. Lima. “Integrating Hydrological and Machine Learning Models for Enhanced Streamflow Forecasting via Bayesian Model Averaging in a Hydro-Dominant Power System.” Water (Switzerland) 16, no. 4 (February 1, 2024). https://doi.org/10.3390/w16040586.
Torres, F. L. R., et al. “Integrating Hydrological and Machine Learning Models for Enhanced Streamflow Forecasting via Bayesian Model Averaging in a Hydro-Dominant Power System.” Water (Switzerland), vol. 16, no. 4, Feb. 2024. Scopus, doi:10.3390/w16040586.

Published In

Water (Switzerland)

DOI

EISSN

2073-4441

Publication Date

February 1, 2024

Volume

16

Issue

4