Physiology-informed LSTM framework integrating crop model and Sentinel-2 time series for rice nitrogen status estimation
Jinpeng Yang, Zhaopeng Fu, Ke Zhang, Bohuai Shi, Jiang Wang, Weizhe Zhao, Qiang Cao, Yongchao Tian, Yan Zhu, Weixing Cao, Xiaojun Liu · 2026
Read Physiology-informed LSTM framework integrating crop model and Sentinel-2 time series for rice nitrogen status estimation by Jinpeng Yang, Zhaopeng Fu, Ke Zhang, Bohuai Shi, Jiang Wang, Weizhe Zhao, Qiang Cao, Yongchao Tian, Yan Zhu, Weixing Cao, Xiaojun Liu (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-13293751.txt.
Description
Jinpeng Yang and colleagues design a smarter way to judge how much nitrogen rice plants hold, in a 2026 agricultural study. Fertilizer decisions depend on plant dry matter and nitrogen uptake, yet field measurements are too sparse to guide whole regions. Their framework first teaches a deep learning model how rice grows, using a crop simulator run across thousands of virtual fields, then fine-tunes it with satellite image sequences and real field data.
The trained model estimated dry matter and nitrogen uptake more accurately than standard machine learning methods. From those estimates it classified nitrogen status with reasonable accuracy and computed how much fertilizer each field still needed. Field trials at seven sites cut nitrogen use noticeably while holding or raising yields. The authors offer the system as decision support for precise, lower-waste fertilization.
Catalog record
| CREATOR | Jinpeng Yang, Zhaopeng Fu, Ke Zhang, Bohuai Shi, Jiang Wang, Weizhe Zhao, Qiang Cao, Yongchao Tian, Yan Zhu, Weixing Cao, Xiaojun Liu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 57 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |