Document is current

Article History

Received: 11 March 2026

Accepted: 7 August 2026

First Online: 16 August 2026

Declarations

Ethics approval and consent to participate: Not applicable. This study did not involve human participants.

Consent for publication: Not applicable. This manuscript does not contain any individual person’s data in any form.

Program language: Python Source code: The complete source code for data preprocessing, feature engineering, model training (LSTM, Prophet, Random Forest), ensemble learning (weighted averaging and stacking), and evaluation is openly available at .

Documentation: Detailed instructions for installation, dataset formatting, model training, ensemble construction, and reproduction of results are provided in the project README file:

Source code repository: The source codes are available for download at . Archived version for citation: A fixed, citable version of the code is archived on Zenodo at: https://doi.org/10.5281/zenodo.18345316.

Competing interests: The authors declare no competing interests.