Nitrogen is essential for rice growth and yield formation, but traditional methods for assessing nitrogen status are often labor-intensive and unreliable at high nitrogen levels due to saturation effects. This study evaluates the effectiveness of flavonoid content (Flav) and the Nitrogen Balance Index (NBI), measured using a Dualex sensor and combined with machine learning models, for precise nitrogen status estimation in rice. Field experiments involving 15 rice varieties under varying nitrogen application levels collected Dualex measurements of chlorophyll (Chl), Flav, and NBI from the top five leaves at key growth stages. Incremental analysis was performed to quantify saturation effects, revealing that chlorophyll measurements saturated at high nitrogen levels, limiting their reliability. In contrast, Flav and NBI remained sensitive across all nitrogen levels, accurately reflecting nitrogen status. Machine learning models, particularly random forest and extreme gradient boosting, achieved high prediction accuracy for leaf and plant nitrogen concentrations (R² > 0.82), with SHAP analysis identifying NBI and Flav from the top two leaves as the most influential predictors. By combining Flav and NBI measurements with machine learning, this approach effectively overcomes chlorophyll-based saturation limitations, enabling precise nitrogen estimation across diverse conditions and offering practical solutions for improved nitrogen management in rice cultivation.

This research was to examine the impacts of long-term integrated rice–crayfish farming on soil nutrients, carbon pools, and rice yields in paddy fields. The aim was to establish a scientific basis for the sustainable development of RS in the northern region of Zhejiang. The results showed that the change from rice monoculture (CK) to rice–crayfish coculture systems (RS) led to a 24.99% increase in the 5-year average of soil ammonium nitrogen (AN), while the soil nitrate nitrogen (NN), available potassium (AK), and available phosphorus content (AP) decreased by 28.02%, 16.05%, and 28.76%, respectively. Moreover, the total organic carbon (TOC), easily oxidizable organic carbon (EOC), dissolved organic carbon (DOC), and microbial biomass carbon (MBC) exhibited a reduction of 2.45%, 8.82%, 35.31%, and 65.84%, respectively. Correlation analysis revealed a significant positive correlation between NN, EOC, and MBC in the RS mode. In terms of rice yield, the 5-year average of rice yield in RS decreased by 8.40% compared to CK. The mean yield of early-maturing rice varieties was reduced by 13.16%, while that of late-maturing rice varieties was reduced by 6.00%. These results shed light on the annual variation in soil nutrients, carbon pools, and rice yield in the RS mode, providing insights for the sustainable development of RS in northern Zhejiang.

Microplastic might affect the crop yield, nitrogen (N) use efficiency and reactive N losses from agricultural soil systems. However, evaluation of these effects in infertile soil planted with different rice cultivars is lacking. We conducted a soil column experiment to determine the influence of a typical microplastic polyethylene (PE) input into an infertile soil with 270 kg N ha⁻¹ and planted with two rice cultivars, i.e., a common rice Nangeng 5055 (NG) and a hybrid rice Jiafengyou 6 (JFY). The results showed that JFY produced a significantly (p < 0.05) greater grain yield than NG (61.6–66.2 vs. 48.2–52.5 g pot⁻¹) but was not influenced by PE. Overall, PE hardly changed the N use efficiency of NG and JFY. Unexpectedly, PE significantly (p < 0.05) increased the total amino acid content of NG. Compared with JFY, NG volatilized significantly (p < 0.05) more ammonia (NH₃) (0.84–0.92 vs. 0.64–0.67 g N pot⁻¹) but emitted equal nitrous oxide (N₂O). PE exerted no effect on either NH₃ volatilization or the N₂O emission flux pattern and cumulative losses of the rice growth cycle, whether with NG or JFY. Some properties of tested soils changed after planting with different rice cultivars and incorporating with microplastic. In conclusion, the rice production, N use efficiency, NH₃ volatilization and N₂O emission from the N-fertilized infertile soil were pronouncedly influenced by the rice cultivar, but not the PE. However, PE influenced the grain quality of common rice and some properties of tested soils with both rice cultivars.

This research was to examine the impacts of long-term rice-crayfish coculture systems(RS) on soil nutrients, carbon pools, and rice yields in paddy fields , aiming to establish a scientific basis for the sustainable development of RS in the northern region of Zhejiang. The results showed that the change from rice monoculture (CK) to RS resulted in a 24.99% increase in the 5-year average of soil ammonium nitrogen(AN), while the soil nitrate nitrogen(NN), available potassium(AK), and available phosphorus content(AP) decreased by 28.02%, 16.05%, and 28.76% respectively. Moreover, the total organic carbon(TOC), easily oxidizable organic carbon(EOC), dissolved organic carbon(DOC), and microbial biomass carbon(MBC) decreased by 2.45%, 8.82%, 35.31%, and 65.84% respectively. Correlation analysis showed that there was a significant positive correlation between NN, EOC and MBC in the RS. In terms of rice yield, 5-year average of rice yield in RS has decreased by 8.4% compared to CK.The average yield of planting early-maturing varieties of rice was reduced by 13.16%, while the average yield of planting late-maturing varieties of rice was reduced by 6.00%. In conclusion, enhancing water and nutrient management and cultivating late maturing rice varieties are essential strategies for achieving the sustainable development of RS in northern Zhejiang.