Interactions between carbon and nitrogen metabolism are essential for balancing source–sink dynamics in plants. Frequent cold stress disrupts these metabolic processes in rice and reduces grain yield. Two rice cultivars (DN428: cold-tolerant; SJ10: cold-sensitive) were subjected to 19 °C low-temperature stress at full-heading for varying lengths of time to analyze the effects on leaf and grain metabolism. The objective was to track carbon–nitrogen flow and identify factors affecting grain yield. Low-temperature stress significantly reduced the activity of nitrate reductase (NR), glutamine synthetase (GS), glutamate synthase (GOGAT), glutamate dehydrogenase (GDH), glutamic oxaloacetic transaminase (GOT), and glutamic pyruvic transaminase (GPT), in functional leaves compared to the control. This reduction decreased nitrogen accumulation, inhibited chlorophyll synthesis, and slowed photosynthesis. To preserve intracellular osmotic balance and lessen the effects of low temperatures, sucrose, fructose, and total soluble sugar levels, as well as sucrose synthase (SS) and sucrose phosphate synthase (SPS) activities, surged in response to low-temperature stress. However, low-temperature stress significantly reduced the activity of adenosine diphosphate glucose pyrophosphorylase (AGPase), granule-bound starch synthase (GBSS), soluble starch synthase (SSS), and starch branching enzyme (SBE). At the same time, low-temperature stress reduced the area of vascular bundles and phloem, making it difficult to transport carbon and nitrogen metabolites to grains on time. The response of grains to low-temperature stress differs from that of leaves, with prolonged low-temperature exposure causing a gradual decrease in carbon and nitrogen metabolism-related enzyme activities and product accumulation within the grains. The insufficient synthesis of starch precursors and carbon skeletons results in significantly lower thousand-grain weight and seed-setting rates, ultimately contributing to grain yield loss. This decline was more pronounced in inferior grains compared to superior grains. Compared to SJ10, DN428 exhibited higher values across various indicators and smaller declines under low-temperature stress, suggesting enhanced cold-tolerance and a greater capacity to maintain grain yield stability.

With the development of rice varieties and mechanized planting technology, reliable and efficient nitrogen and planting density status diagnosis and recommendation methods have become critical to the success of precise nitrogen and planting density management in crops. In this study, we combined population structure, plant shape characteristics, environmental weather conditions, and management information data using a machine learning model to simulate the responses of the yield and nitrogen nutrition index and developed an ensemble learning model-based nitrogen and planting density recommendation strategy for different varieties of rice types. In the third stage, the NNI and yield prediction effect of the ensemble learning model was more significantly improved than that of the other two stages. The scenario analysis results show that the optimal yields and nitrogen nutrition indices were obtained with a density and nitrogen amount of 100.1 × 10⁴ plant/ha and 161.05 kg·ha⁻¹ for the large-spike type variety of rice, 75.08 × 10⁴ plant/ha and 159.52 kg·ha⁻¹ for the intermediate type variety of rice, and 75.08 × 10⁴ plant/ha and 133.47 kg·ha⁻¹ for the panicle number type variety of rice, respectively. These results provide a scientific basis for the nitrogen application and planting density for a high yield and nitrogen nutrition index of rice in northeast China.