Physiology-informed LSTM framework integrating crop model and Sentinel-2 time series for rice nitrogen status estimation.

Abstract

Accurate assessment of plant dry matter (PDM) and plant N accumulation (PNA) provides essential indicators for precision nitrogen (N) management in rice production. However, purely data-driven models struggle to generalize due to the spatial scarcity of ground-truth physiological data. To address this, a physiology-informed long short-term memory (PI-LSTM) framework was developed for robust regional N diagnosis and variable-rate fertilization. First, the model was pretrained to internalize crop growth dynamics using a DSSAT-based simulation library, which spanned 2000 representative fields and 700 management scenarios to provide physiologically consistent pseudo-labels. Subsequently, the framework was fine-tuned using multi-year field observations (2020, 2023, 2024), Sentinel-2 time-series data, and meteorological inputs. The proposed LSTM framework outperformed conventional machine learning approaches in estimating PDM and PNA, achieving five-fold cross-validation R 2 values of 0.87 and 0.83, respectively. Based on these biophysical estimations, the N nutrition index (NNI) diagnosis achieved a 67.3% overall classification accuracy. Furthermore, by integrating the critical N dilution curve, the critical PNA and accumulated N deficiency (AND) were quantified, which served as the basis for developing the AND-based N recommendation algorithm (ANDA). Finally, variable-rate topdressing field experiments conducted across seven sites in 2024 and 2025 demonstrated that the ANDA reduced N input by 13.4% compared with farmers' practices, while maintaining or increasing yield and improving N partial factor productivity by 18.6%. This study provides a reliable, physically consistent decision-support framework for regional-scale precision N management.

Plant phenotyping relevance

Sentinel-2時系列とLSTMにより、イネの乾物量および窒素蓄積量という植物形質を推定する方法の開発・検証が研究の中心であり、施肥管理への応用も技術評価として記述されている。

Code and data availability

The supplied blocks describe field phenotyping (PDM/PNA destructive sampling), Sentinel-2 time series, DSSAT pseudo-labels, and a PI-LSTM model, but no public deposit of the paper's datasets, imagery, or code is shown. The 'Data and Code Availability' section is truncated before any availability statement or URL. The C

No evidence-backed public reproduction asset is currently recorded.