What does this research mean for the field?

The proposed probabilistic runoff forecasting framework significantly improves deterministic and probabilistic forecasting performance, reducing RMSE by up to 73.2% and enhancing prediction reliability. Novelty: ClaimNovelty.NOVEL_FINDING. Consensus alignment: ConsensusAlignment.SUPPORTS_CONSENSUS.

What question did this study set out to answer?

The aim is to develop a robust framework for accurate runoff prediction, integrating advanced modeling techniques.

March 7, 2026Scientific ReportsOpen Access

Optimized decomposition and deep learning with bias correction for reliable runoff point-interval prediction

View Full Paper

Ask AI

Bookmark

Authors

HMHong MaUniversiti Sains Malaysia MMMuhammad Fadhil MarsaniUniversiti Sains Malaysia MMMohd. Asyraf Mansor

Discussion

Member takes

Implication

Demonstrates a probabilistic runoff forecasting framework, enhancing prediction reliability in flood management.

Key Points

The aim is to develop a robust framework for accurate runoff prediction, integrating advanced modeling techniques.
Employed variational mode decomposition optimized by the whale optimization algorithm for signal decomposition.
Used a hybrid temporal convolutional network and bidirectional gated recurrent unit for modeling.
Incorporated a bias correction strategy to enhance prediction accuracy.
Applied kernel density estimation to characterize error distribution and construct prediction intervals.
Bias correction reduced RMSE by 68.0% at Yichang and 73.2% at Jianli.
KDE based prediction intervals yielded approximately 5% improvement in the F score at the 90% confidence level.
The proposed framework significantly outperformed previous models in both deterministic and probabilistic forecasting.

Cite This Study

Ma et al. (2026) studied this question.

synapsesocial.com/papers/69abc1845af8044f7a4ea333 https://doi.org/10.1038/s41598-025-33713-0

View Full Paper

Ask AI

Bookmark