Leaf nitrogen content (LNC) is a vital agronomic parameter in rice, commonly used to evaluate photosynthetic capacity and diagnose crop nutrient levels. Nitrogen deficiency can significantly reduce yield, underscoring the importance of accurate LNC estimation for practical applications. This study utilizes hyperspectral UAV imagery to acquire rice canopy data, applying various machine learning regression algorithms (MLR) to develop an LNC estimation model and create a nitrogen concentration distribution map, offering valuable guidance for subsequent field nitrogen management. The analysis incorporates four types of spectral data extracted throughout the rice growth cycle: original reflectance bands (OR bands), vegetation indices (VIs), first-derivative spectral bands (FD bands), and hyperspectral variable parameters (HSPs) as model inputs, while measured nitrogen concentration serves as the output. Results demonstrate that the random forest regression (RFR) and gradient boosting decision tree (GBDT) algorithms performed effectively, with the GBDT achieving the highest average R² of 0.76 across different nitrogen treatments. Among the nitrogen estimation models for various rice varieties, RFR exhibited superior accuracy, achieving an R² of 0.95 for the SuXiangJing100 variety, while the GBDT reached 0.93. Meanwhile, the support vector machine regression (SVMR) showed slightly lower accuracy, and partial least-squares regression (PLSR) was the least effective. This study developed an LNC estimation method applicable to the whole growth stage of common rice varieties. The method is suitable for estimating rice LNC across different growth stages, varieties, and nitrogen treatments, and it also provides a reference for nitrogen estimation and fertilization planning at flight altitudes other than the 120 m used in this study.

Developing modern circular agriculture is one of the important ways to promote agricultural sustainable development, facilitating the achievement of the Sustainable Development Goals adopted by the United Nations. However, when agricultural production operators constructed particular systems, they often lacked accurate data support and parameter matching. Consequently, problems such as unknown input and output, low circulation efficiency, and lack of comprehensive evaluation occurred, increasing challenges for efficient circulation of the systems. Therefore, based on sufficient data collection and field investigation, this research integrated emergy analysis and life cycle assessment to conduct sustainability evaluation on the modern Straw–Sheep–Cropland agro-pastoral circular system. Then the system was optimized by means of coupling parameter adjustment and key technology regulation. The results showed that the whole system required lower total emergy input after optimization. And the total weighted value of potential environmental impacts of the optimized system was 47.12% of that of the original system. Meanwhile, annual environmental service emergy in air, water, and soil was reduced significantly compared with the original one. In general, the optimized system had good performance in reduction, reuse, and controllability, so its sustainability was also high. This research formed a systematic method suitable for evaluating and optimizing the modern agro-pastoral circular system, which provided accurate guidance for the scientific construction and sustainable development of circular agriculture systems.

Water availability is one of the most limiting factors in crop production, and understanding crop water use efficiency is especially important in environments where changes in crop performance are driven by water availability. The stable isotope δ¹³C has been proposed to evaluate the water management and physiological water use efficiency (WUE) for upland crops. However, this technique has rarely been used for rice, especially for water-saving management systems such as the Ground Cover Rice Production System (GCRPS), which can significantly improve WUE. Therefore, a two-year lowland rice field experiment was conducted to evaluate the effects of sampling time, plant organ and yearly climatic changes on δ¹³C and its relationship to WUE. Our study revealed the following: (1) Significant differences in shoot and leaf δ¹³C were found between paddy and GCRPS plants only at the maximum tillering stage but not at the flowering stage. (2) The shoot δ¹³C at maximum tillering showed a significant positive correlation with irrigation (WUE_i) and total water use efficiency (WUE_t), but there was no such relationship at the flowering stage. (3) Shoot δ¹³C was significantly higher in 2013 than in 2014, most likely related to higher solar radiation from transplanting to maximum tillering in 2013, as there were no significant differences between the years in other climatic factors and soil water content. Our results suggest that the δ¹³C of rice shoots sampled at the maximum tillering stage shows the best correlation with crop water use efficiency.

Surface water quality is critical to ecosystem health and sustainable development, yet conventional monitoring falls short of spatiotemporally continuous assessment. Remote sensing coupled with machine learning has become a powerful paradigm for large-scale quantitative retrieval of water quality parameters (WQPs). This review examines the progress and prospects of machine-learning-driven multi-source remote sensing for surface WQP retrieval. A systematic literature review following PRISMA 2020 guidelines, covering 437 Web of Science Core Collection publications (2000–2025), reveals exponential growth, with China and the United States contributing 70.3% of total output. A critical synthesis covers four dimensions: (1) characteristics and fusion strategies of satellite, airborne, and ground-based remote sensing data; (2) modeling features of traditional machine learning (SVR, RF, GBDT), deep learning (CNN, RNN, Transformer), and hybrid approaches; and (3) retrieval advances for optically active versus non-optically active parameters—the former approaches operational readiness while the latter remains constrained by weak indirect spectral correlations; and (4) uncertainty sources and mitigation strategies across the data–model–parameter chain. Five key challenges are identified: limited model generalizability, insufficient physical interpretability, optical heterogeneity and parameter coupling, scarce in situ data, and multi-source fusion bottlenecks. Five future directions are proposed—transfer learning, physically informed explainable machine learning, non-optically active parameter retrieval, benchmark dataset development, and intelligent multi-source fusion—offering a roadmap toward operational surface water quality monitoring.

The ridge culture place planting system (RCPPS) is a promising technique for planting rapeseed that can promote the growth of rapeseed by late rice stubble, which has been widely adopted in the Yangtze River delta. To determine the optimum planting date for rape (Brassica napus L.) forage and grain yield in an intensive rice–rape rotation system, a field experiment was conducted with five transplantation dates (from 20 October to 30 November at 10 day intervals) in RCPPS. The forage/grain yield, nutrition, and growth parameters were analyzed. At podding, rape biomass yield was highest, and no significant differences were found among treatments. It was around 12.0% crude protein, 11.4% ether extract, 38.8% neutral detergent fiber, and 34.9% acid detergent fiber. In the treatments of 20 and 30 November, crude protein content increased and acid detergent fiber content decreased significantly. Compared with 20 October, the grain yield of rape transplanted in November decreased significantly by 17.2% to 22.5%. The grain yield was significantly correlated with the number of secondary branches, pods, and seeds. At the final flowering stage, rape transplanted in November had noticeably reduced leaf growth, rhizome width, and yield than 20 and 30 October. Overall, for multiple uses of rapeseed in the Yangtze River delta belt with RCPPS, it is optimal to plant in mid to late November for forage use with higher nutritional value, being coordinated with the previous rice crop, whereas late October is the appropriate planting time to obtain a higher grain yield.