Yao Li

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.

The ridge–furrow plastic mulching technique has been widely applied due to its benefits of increasing temperature, conserving moisture, reducing evaporation, and boosting yields. Hydrus-2D is a computer model designed to simulate the two-dimensional movement of water in soil characterized by a low cost and high flexibility compared to field experiments. This study, based on field experiment data from Jianping County, Liaoning Province, China, during 2017–2018, developed Hydrus-2D models for two distinct field management practices: non-mulched flat cultivation (NM-FC) and mulched ridge tillage (M-RT). Furthermore, it simulated the dynamic changes in farmland water variations during the summer maize growth period (2021–2100) under climate change scenarios, specifically medium and high emission pathways (SSP2-4.5 and SSP5-8.5), based on the FGOALS-g3 model, which exhibits the highest similarity to the climate pattern of Jianping County in the Coupled Model Intercomparison Project Phase 6 (CMIP6) global climate models and the Shared Socioeconomic Pathways (SSPs). The results showed that in the future FGOALS-g3 model, net radiation exhibited a significant upward trend under the SSP2-4.5 scenario (Z = 2.38), while the average air temperature showed a highly significant increase under both SSP2-4.5 and SSP5-8.5 scenarios, with Z-values of 6.48 and 8.90, respectively. The Hydrus-2D model demonstrated high simulation accuracy in both NM-FC and M-RT treatments (R² ranging from 0.86 to 0.96, with RMSE not exceeding 0.011), accurately simulating the dynamic changes in soil water content (SWC) under future climate change. Compared to NM-FC, M-RT reduced evaporation, increased transpiration, and effectively decreased the leakage caused by increased future precipitation, resulting in a 0.04 and 0.01 cm³/cm³ increase in surface and deep soil SWC, respectively, during the summer maize growing season, significantly improving water use efficiency. Moreover, M-RT treatment reduced the impact coefficients of climate change on various water balance parameters, stabilizing changes in these parameters and SWC under future climate conditions. This study demonstrates the significant advantages of M-RT in coping with climate change, providing key scientific evidence for future agricultural water resource management. These findings offer valuable insights for policymakers and farmers, particularly in developing adaptive land management and irrigation strategies, helping to improve water use efficiency and promote sustainable agricultural practices.

Liaoning Province, a crucial agricultural region in Northeast China, has endured frequent drought disasters in recent years, significantly affecting both agricultural production and the ecological environment. Conducting drought research is of paramount importance for formulating scientific drought monitoring and prevention strategies, ensuring agricultural production and ecological safety. This study developed a Comprehensive Joint Drought Index (CJDI) using the empirical Copula function to systematically analyze drought events in Liaoning Province from 1981 to 2020. Through the application of MK trend tests, Morlet wavelet analysis, and run theory, the spatiotemporal variation patterns and recurrence characteristics of drought in Liaoning Province were thoroughly investigated. The results show that, compared to the three classic drought indices, Standardized Precipitation Index (SPI), Evaporative Demand Drought Index (EDDI), and Standardized Precipitation Evapotranspiration Index (SPEI), CJDI has the highest accuracy in monitoring actual drought events. From 1981 to 2020, drought intensity in all regions of Liaoning Province (east, west, south, and north) exhibited an upward trend, with the western region experiencing the most significant increase, as evidenced by an MK test Z-value of −4.53. Drought events in Liaoning Province show clear seasonality, with the most significant periodic fluctuations in spring (main cycles of 5–20 years, longer cycles of 40–57 years), while the frequency and variability of drought events in autumn and winter are lower. Mild droughts frequently occur in Liaoning Province, with joint and co-occurrence recurrence periods ranging from 1.0 to 1.8 years. Moderate droughts have shorter joint recurrence periods in the eastern region (1.2–1.4 years) and longer in the western and southern regions (1.4–2.2 years), with the longest co-occurrence recurrence period in the southern region (3.0–4.0 years). Severe and extreme droughts are less frequent in Liaoning Province. This study provides a scientific foundation for drought monitoring and prevention in Liaoning Province and serves as a valuable reference for developing agricultural production strategies to adapt to climate change.

Maize plays a crucial role in China’s grain production, with a cultivation area reaching 44.22 million hectares and an annual yield of 289 million tons in 2023. However, the challenge remains on how to further increase maize yield and water use efficiency (WUE) without adding to the environmental burden. To systematically evaluate the impact of straw incorporation under varying production conditions on maize yield and WUE, this study collected experimental data from multiple locations across China. A meta-analysis was conducted to compare the effects of straw incorporation versus no incorporation, and the main influencing factors were identified using correlation analysis and a random forest model. The results indicate that straw incorporation significantly enhances both maize yield and WUE, with the most pronounced improvements observed under conditions of an average growing season temperature of 19–23 °C, soil pH of 6.5–7.5, low initial soil organic matter content, and deep plowing for straw incorporation. Additionally, moderate nitrogen application rates and straw incorporation amounts (9000–15,000 kg·ha⁻²) also significantly boost maize yield and WUE. Field management practices and meteorological conditions are identified as the primary factors affecting maize yield and WUE under straw incorporation conditions. Therefore, straw incorporation stands out as an effective agricultural practice for achieving high maize yields and efficient resource utilization. The findings of this study provide valuable insights for global food security and the sustainable development of agriculture.