The paper introduces a flood detection system that is complete and makes use of the combination of wavelet transformation and deep learning, looking at different aspects of it, especially self-window modulation in this case, in the Cauvery Basin of Southern India. The research examines 4,971 daily samples from 2000 to 2013, consisting of 500 flood and 495 drought incidents. We put forward two models, wavelet–long short–term and wavelet–gated recurrent unit of with self-window modulation, which perform better than traditional methods by a significant margin. The wavelet-long-short term model that we have developed reaches 89.44% accuracy, 82.29% precision, 78.71% recall, and 84.67% F1-score, thereby also surpassing conventional long-short-term model by 7.1% accuracy. The method entails a combination of the discrete wavelet transform using the Daubechies-4 wavelet (energy: 1.37e+08, entropy: 21.43), feature extraction that points Flow_Mean14d (importance: 0.92) as the most informative and worthy feature to be selected, and selfwindow modulation technique asserting 48.2% input from window-1 in temporal study. A comparative study reveals that the integration of wavelets has improved the performance of the model by 6-9% on self-window modulation serent metrics, while self-window modulation contribution is an extra 3-5% boost. The system is capable of detecting floods in real–time with wavelet–long short–term and wavelet–gated recurrent units attaining AUC scores of 1.000 and 0.998, respectively, and at the same time providing large language model-generated safety advisories as support for operational decision-making.
Cauveri Basin flood detection hydrological forecasting GRU LSTM self-window modulation wavelet transform
| Primary Language | English |
|---|---|
| Subjects | Deep Learning, Classification Algorithms, Statistical Data Science, Stochastic Analysis and Modelling, Applied Statistics |
| Journal Section | Research Article |
| Authors | |
| Submission Date | January 4, 2026 |
| Acceptance Date | February 26, 2026 |
| Early Pub Date | April 17, 2026 |
| DOI | https://doi.org/10.15672/hujms.1855645 |
| IZ | https://izlik.org/JA29LA22NZ |
| Published in Issue | Year 2026 Issue: Advanced Online Publication |
Hacettepe Journal of Mathematics and Statistics (Formerly: Hacettepe Bulletin of Natural Sciences and Engineering - Series B) is an international, peer-reviewed, open-access journal that publishes high-quality original research articles and occasional comprehensive surveys in all areas of Mathematics and Statistics. The journal is committed to promoting the advancement of mathematical and statistical sciences by providing a platform for researchers to disseminate their findings to a global audience.
As an open-access journal, Hacettepe Journal of Mathematics and Statistics (HJMS) does not charge any article processing or publishing fees, ensuring that high-quality research remains freely accessible to the scientific community. The journal accepts submissions exclusively in English and upholds a rigorous peer-review process to maintain academic excellence.
The journal is widely recognized in the academic community and is indexed in leading databases such as Web of Science (Science Citation Index Expanded), Scopus, and Zentralblatt MATH. With its long-standing history and commitment to scholarly publishing, Hacettepe Journal of Mathematics and Statistics continues to serve as a valuable resource for researchers, academicians, and practitioners in the fields of Mathematics and Statistics.
Hacettepe Journal of Mathematics and Statistics (HJMS) is an international, peer-reviewed journal dedicated to publishing high-quality, original research. The journal accepts only manuscripts written in English and does not charge any submission or publication fees. Submitted articles must align with the journal’s scope and meet the required quality standards; otherwise, they will not be considered for review. Manuscripts that have been previously published or are under consideration for publication elsewhere will not be accepted.
Manuscript submissions for the journal are processed through the DergiPark system. Submissions must be made via the corresponding author's account. To submit your manuscript, please register and log in to the submission portal at DergiPark Login. (https://dergipark.org.tr/en/login).
The journal takes issues of copyright infringement, plagiarism, and other violations of best publishing practices very seriously. As part of the review process, manuscripts that lack proper form or exhibit a high similarity to existing sources, as detected by the iThenticate software (https://www.ithenticate.com/) will be immediately rejected by the editor.
It is essential to include all figure and table files, where applicable, along with the TeX file and class file during the submission process.
Option 2 (Employment of the Overleaf Template) For a collaborative and user-friendly environment, authors are encouraged to prepare their manuscripts using the official HJMS Overleaf template. The template includes all the necessary files and is accessible via the following link:
The online template provides all required files for manuscript preparation. Once the manuscript is completed, authors must download all files (including any figure and table files, where applicable) from Overleaf and upload them individually to the DergiPark system.
Note: The official Hacettepe University logo will be added later by the production editors of the journal. For both options, please ignore the following errors or warnings:
The following guidelines mut be adhered to when preparing manuscripts for submission to Hacettepe Journal of Mathematics and Statistics.
Abbreviations should be defined at first mention and used consistently thereafter.
Requirements Upon Acceptance
Hacettepe Journal of Mathematics and Statistics (HJMS) is committed to maintaining the highest standards of publication ethics and to supporting ethical research practices and strictly adheres to the Committee on Publication Ethics (COPE) Code of Conduct for Journal Publishers. We encourage journal editors to follow the COPE Code of Conduct for Journal Editors and to refer reviewers to the COPE Ethical Guidelines for Peer Reviewers as appropriate. In the development of the Policies and Ethics of HJMS, the following sources have been utilized:
Responsibilities of Authors
Responsibilities of Editors
Responsibilities of Reviewers
5. Limitations: The authors must notice that only two submissions per author per year will be considered. Once a paper is under review or has been accepted for publication, all co-authors need to wait 6 months from the submission date before submitting another paper to Hacettepe Journal of Mathematics and Statistics.
Copyright
.