A hybrid deep learning approach for winter wheat yield prediction: evidence from leveraging multi-source data
Manogna R. L, Shaanil Punglia, Siddhant Tushar Joshi · 2026
Read A hybrid deep learning approach for winter wheat yield prediction: evidence from leveraging multi-source data by Manogna R. L, Shaanil Punglia, Siddhant Tushar Joshi (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/PMC13572458.txt.
Description
Manogna R. L, with two colleagues, benchmarks 2026 computer models for winter wheat yield forecasts across India. District-level forecasts guide food plans and policy in the world's second largest wheat producer. The team tested nine model types on 23 years of data from 275 districts in seven states.
The data joined soil depth profiles with weather and satellite series from 2001 to 2023. A hybrid model that routes each data kind through its own path won, with a mean error of 273.2 kilograms per hectare. That cut error by 43.8 percent against a random forest base model. A plain forecast that just repeats last year's yield nearly tied it, though. The hybrid pulled ahead in the dry 2023 season, and its edge centred on the February to March grain-filling window.
Catalog record
| CREATOR | Manogna R. L, Shaanil Punglia, Siddhant Tushar Joshi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 93147 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |