Enhancing drought forecasting with CNN-TQWT and metaheuristic hybrids: evidence from Norway
Sertaç Oruç, Türker Tuğrul, Mehmet Ali Hınıs · 2026
Read Enhancing drought forecasting with CNN-TQWT and metaheuristic hybrids: evidence from Norway by Sertaç Oruç, Türker Tuğrul, Mehmet Ali Hınıs (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13478465.txt.
Description
Sertaç Oruç and two colleagues improved in 2026 drought forecasts for Norway with hybrid neural models. They used monthly rain records from 1970 to 2025 for Bergen, Kristiansand, Oslo, and Tromsø, scored with a standard 12-month dryness index.
They paired a convolutional neural network with a signal-splitting method called TQWT, plus random forest and tuning methods, and tested four input setups. The CNN-TQWT hybrids beat the other models at all four sites, with the best correlation scores above 0.97 and the best fit scores above 0.91 at every site. The results point to the TQWT split as the key gain, offering planners a steadier base for farm and water plans.
Catalog record
| CREATOR | Sertaç Oruç, Türker Tuğrul, Mehmet Ali Hınıs |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 71 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |