Efficient Hyperparameter Tuning for Precise Precipitation Prediction Using EHPC Framework

Nivethitha K () and Lokeshkumar R ()
Additional contact information
Nivethitha K: Vellore Institute of Technology, School of Computer Science and Engineering
Lokeshkumar R: Vellore Institute of Technology, School of Computer Science and Engineering

Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA), 2025, vol. 39, issue 14, No 21, 7836 pages

Abstract: Abstract This study introduces an Enhanced Hyper-Parameter Configuration (EHPC) framework proposed to optimize hyperparameters of tree-based estimators for precipitation prediction models. The framework integrates Enhanced Bayesian optimization (EBO) approach, the Expected Improvement with Probability of Improvement acquisition function, and the simultaneous seeking strategy to enhance both efficiency and accuracy. The non-linear patterns and complex relationships within the meteorological features are captured using tree-based estimators such as Random forest and Gradient boosting. By modeling prediction performance, the EBO efficiently explores the hyperparameter space. EBO effectively explores the hyperparameter space using a surrogate model that iteratively selects promising configurations, minimizing the cost of evaluating the objective function. The EIPI function balances exploration and exploitation by combining the strengths of Probability of Improvement and Expected Improvement. The integration of EBO within the EHPC framework ensures that hyperparameters are chosen based on both predictive performance and computational efficiency. Overall, integrating EBO with tree-based estimators significantly improves the accuracy and reliability of precipitation prediction. The proposed strategy outperforms other existing approaches with a high prediction accuracy of 98.99% with an execution time of 28.99 s. This framework significantly improves prediction accuracy while reducing optimization time, making it a promising methodology for efficient precipitation prediction tasks.

Keywords: Bayesian optimization; Precipitation prediction; Balance parameter; Machine learning; Tree-based estimators (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11269-025-04319-y Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:waterr:v:39:y:2025:i:14:d:10.1007_s11269-025-04319-y

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/11269

DOI: 10.1007/s11269-025-04319-y

Access Statistics for this article

Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA) is currently edited by G. Tsakiris

More articles in Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA) from Springer, European Water Resources Association (EWRA)
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().