An integrated feature selection approach to high water stress yield prediction
Zongpeng Li, Xinguo Zhou, Qian Cheng, Weiguang Zhai, Bohan Mao, Yafeng Li, Zhen Chen · 2023
Read An integrated feature selection approach to high water stress yield prediction by Zongpeng Li, Xinguo Zhou, Qian Cheng, Weiguang Zhai, Bohan Mao, Yafeng Li, Zhen Chen (2023) 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-10726204.txt.
Description
Zongpeng Li and six co-authors published a study in 2023 on picking the right light-based clues for forecasting wheat yield under water stress. Drones carrying spectral cameras can compute dozens of vegetation indices, but not every index helps in every field. The team built a selection pipeline that keeps only the indices that earn their place.
They started with thirty-five candidate indices from flights over flowering and grain-filling wheat. Two ranking methods, one based on correlation and one on forest importance, each shortlisted features, and their union went through a final elimination round. Models fed the winning subset, in both a rule-based learner and a recurrent network, forecast yield better than fuller sets. Leaner inputs make drone forecasting cheaper to run at farm scale.
Catalog record
| CREATOR | Zongpeng Li, Xinguo Zhou, Qian Cheng, Weiguang Zhai, Bohan Mao, Yafeng Li, Zhen Chen |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 48 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |