The ongoing global warming and changing patterns of precipitation have significant implications for crop yields. Process-based models are the most commonly used method to assess the impacts of projected climate changes on crop yields. In this study, the crop-environment resource synthesis (CERES)-Maize 4.6.7 model was used to project the maize crop yield in the Shaanxi Province of China over future periods. In this context, the downscaled ensemble projections of 17 general circulation models (GCMs) under four representative concentration pathways (RCP 2.6, RCP 4.5, RCP 6.0, and RCP 8.5) were used as input for the calibrated CERES-Maize model. Results showed a negative correlation between temperature and maize yield in the study area. It is expected that each 1.0 °C rise in seasonal temperature will cause up to a 9% decrease in the yield. However, the influence of CO₂ fertilization showed a positive response, as witnessed by the increase in the crop yield. With CO₂ fertilization, the average increase in the maize crop yield compared to without CO₂ fertilization per three decades was 10.5%, 11.6%, TA7.8%, and 6.5% under the RCP2.6, RCP4.5, RCP6.0, and RCP8.5 scenarios, respectively. An elevated CO₂ concentration showed a pronounced positive impact on the rain-fed maize yield compared to the irrigated maize yield. The average water use efficiency (WUE) was better at elevated CO₂ concentrations and improved by 7–21% relative to the without CO₂ fertilization of the WUE. Therefore, future climate changes with elevated CO₂ are expected to be favorable for maize yields in the Shaanxi Province of China, and farmers can expect further benefits in the future from growing maize.

With the advancement of modern agriculture and increasing scarcity of water and fertilizer resources, determining optimal water and nitrogen (N) management strategies for intercropping systems is critical for ensuring system productivity and enhancing resource-use efficiency. This study employed field experiments to investigate the effects of different water and N treatments on grain yield, aboveground biomass, leaf area index (LAI), photosynthetic parameters, chlorophyll fluorescence characteristics, and radiation use efficiency (RUE) in a maize–soybean intercropping system. The experiment consisted of three cropping systems (maize monoculture, soybean monoculture, and maize–soybean intercropping), two irrigation regimes (rain-fed and supplemental irrigation), and three N-application rates for maize (240, 180, and 120 kgN ha⁻¹). The results demonstrated that supplementary irrigation significantly enhanced the LAI and photosynthetic capacity of both maize and soybean during critical growth stages, thereby promoting increases in grain yield and aboveground biomass. Intercropping significantly improved the productivity and photosynthetic performance of maize compared to monoculture, whereas soybean exhibited a reduction under intercropping conditions. Furthermore, irrigation regime and N rate had significant interactive effects on the photosynthetic performance of maize at the tasseling stage. In the intercropping system, a 25% reduction in the conventional application rate of N for maize maintained system productivity, whereas a 50% reduction substantially decreased maize yield and photosynthetic performance. The intercropping system achieved land equivalent ratios (LERs) ranging from 1.06 to 1.11 and RUE advantages (ΔRUE) of 1.52 to 1.64, demonstrating significant superiority in land and light resource utilization. Considering both productivity and resource-use efficiency, supplemental irrigation combined with 180 kgN ha⁻¹ N application for maize represents the optimal water and N management strategy for achieving high yield and efficiency in maize–soybean intercropping systems in the Guanzhong plain.

Gross primary productivity (GPP) is a key indicator for assessing carbon uptake capacity and photosynthetic productivity in agricultural ecosystems, playing a crucial role in regional carbon cycle evaluation and sustainable agriculture development. However, traditional mechanistic light use efficiency (LUE) models exhibit variable accuracy under different climatic conditions and crop types. Machine learning models, while demonstrating strong fitting capabilities, heavily depend on the selection of input features and data availability. This study focuses on winter wheat in the Guanzhong region, utilizing continuous field observation data from the 2020–2022 growing seasons to develop five machine learning models: Ridge Regression (Ridge), Random Forest (RF), Support Vector Regression (SVR), Gradient Boosting Regression (GB), and a stacking-based ensemble learning model (LSM). These models were compared with the LUE model under two scenarios, excluding and including solar-induced chlorophyll fluorescence (SIF), to evaluate the contribution of SIF to GPP estimation accuracy. The results indicate significant differences in GPP estimation performance among the machine learning models, with LSM outperforming others in both scenarios. Without SIF, LSM achieved an average R² of 0.87, surpassing individual models (0.72–0.83), demonstrating strong stability and generalization ability. With SIF inclusion, all machine learning models showed marked accuracy improvements, with LSM’s average R² rising to 0.91, highlighting SIF’s critical role in capturing photosynthetic dynamics. Although the LUE model approached machine learning model accuracy in some growth stages, its overall performance was limited by structural constraints. This study demonstrates that ensemble learning methods integrating multi-source observations offer significant advantages for high-precision winter wheat GPP estimation, and that incorporating SIF as a physiological indicator further enhances model robustness and predictive capacity. The findings validate the potential of combining ensemble learning and photosynthetic physiological parameters to improve GPP retrieval accuracy, providing a reliable technical pathway for agricultural ecosystem carbon flux estimation and informing strategies for climate change adaptation.

Against the backdrop of intensifying global climate change, continuous population growth, and increasing pressure on natural resources and the environment, traditional extensive agricultural practices are no longer sustainable