Precise estimation of rice leaf macro and micro nutrients from multi-spectral images using neural architecture search with polynomial approximation functions
Diksha Arora, Jhilik Bhattacharya, Chinmaya Panigrahy · 2026
Read Precise estimation of rice leaf macro and micro nutrients from multi-spectral images using neural architecture search with polynomial approximation functions by Diksha Arora, Jhilik Bhattacharya, Chinmaya Panigrahy (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/PMC13527141.txt.
Description
Diksha Arora, Jhilik Bhattacharya, and Chinmaya Panigrahy present, in a 2026 study, a deep learning method that reads rice leaf nutrient levels from drone multispectral images, instead of slow wet-lab chemistry. Knowing leaf nutrient levels guides fertilizer choices and yield. Their system searches for a good network design while using polynomial approximation functions and adaptive activations to cope with small training sets.
Field trials ran at Punjab Agricultural University across treatments and growth stages. The model read eleven macro and micro nutrients with low average errors in two review settings. Error ranges came with the predictions, and feature maps showed leaves with similar nutrient values grouping together. Ablation and cross checks by treatment and plot confirmed each part's role, and the method beat standard deep and machine learning baselines.
Catalog record
| CREATOR | Diksha Arora, Jhilik Bhattacharya, Chinmaya Panigrahy |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 150893 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |