Maize is vital for global and Chinese food security. Yet, in Henan Province, a key maize-growing region in China, water scarcity, uneven rainfall, and inefficient irrigation and fertilization limit its yield and quality. This study combines a two-year field experiment (2023–2024) with the DSSAT model to optimize irrigation and fertilization for typical hydrological years (wet, normal, and dry). After calibration and validation with field data, the DSSAT model showed strong performance. Results indicate that optimal irrigation timing and volume vary with hydrological years: no irrigation is needed in wet years, one 30 mm irrigation at the tasseling (VT) stage in normal years, and three irrigations (total 90 mm) at the emergence (VE), jointing (VT), and grain filling (R2) stages in dry years. The optimal nitrogen fertilizer is 240 kg·ha⁻¹ in water-rich and normal years and 180 kg·ha⁻¹ in dry years. These optimized schemes can achieve 98–100% of maximum potential maize yields across hydrological years, offering practical insights for enhancing agricultural water and nutrient management in central Henan to support sustainable development and reduce environmental impacts.

Exploring the effects of different water and fertilizer irrigation systems on N₂O and CO₂ emissions is of great significance for promoting sustainable agricultural development. In this study, summer maize in Henan Province was selected as the research object, and field experiments were carried out from 2023 to 2024. A total of 12 water and fertilizer treatments were set up. In situ field measurements of N₂O and CO₂ in farmland were carried out using static chamber gas chromatography to study the effects of different water and fertilizer irrigation systems on N₂O and CO₂ emissions from farmland and the simulation performance of the DNDC model. The results were as follows: (1) Irrigation and fertilization significantly interacted to affect N₂O and CO₂ emissions. (2) The summer maize yield under the B2 treatment was the highest, and the total N₂O and CO₂ emissions under the C3 treatment were the highest. (3) Under the DNDC simulation scenario, the summer maize yields under the real-time irrigation system in 2023 and 2024 increased by 4.43% and 4.38% compared with those under full irrigation. The total N₂O emissions from farmland were reduced by 6.56% and 6.22%, while CO₂ emissions decreased by 14.49% and 14.79%, respectively. The results show that real-time water and fertilizer irrigation systems can promote the yield of summer maize and reduce greenhouse gas emissions. The research results provide a theoretical basis for reducing greenhouse gas emissions from farmland and are significant for promoting sustainable agricultural development.

Accurate and reliable estimation of reference crop evapotranspiration (ET₀) in the North Henan Plain is crucial for agricultural water resource management, production, and food supply in China. This study aims to evaluate the performance of deep learning (DL) methods in ET₀ estimation and assess the applicability of the developed DL model beyond the training domain. This study utilized historical meteorological data from Zhengzhou City, northern Henan, spanning 2010–2024. Meteorological variables were selected through correlation analysis and maximum information coefficient (MIC). A novel DL model—the TCN-Attention model (TA)—was constructed by incorporating a self-attention mechanism into the temporal convolutional network (TCN) model. This model was compared with two classical DL models—Long Short-Term Memory (LSTM) and TCN. Results indicate: (1) Sunshine duration ($n$), relative humidity ($\mathrm{R}\mathrm{H}$), and maximum temperature (T_max) are the three most significant features influencing summer maize evapotranspiration; (2) prediction accuracy under the same input scenarios: TA model > TCN model > LSTM model; (3) in scenarios where only temperature data is input, the TA model has the highest prediction accuracy, surpassing the H-S empirical method; and (4) for limited meteorological data, the combination of temperature and humidity was found to be most effective, showing good adaptability and accuracy at different time steps (hourly: R² = 0.982; daily: R² = 0.975; weekly: R² = 0.928). This study highlights the potential of the TA model for estimating reference crop evapotranspiration in the northern Henan Plain, which may provide theoretical guidance for crop irrigation management under future climate change.

Current agricultural irrigation management practices are often extensive, and traditional soil moisture content (SMC) monitoring methods are inefficient, so there is a pressing need for innovative approaches in precision irrigation. This study proposes a Multi-Feature Fusion Network (MFF-Net) for SMC inversion. The model uses a designed Channel-Changeable Residual Block (ResBlockCC) to construct a multi-branch feature extraction and fusion architecture. Integrating the Channel Squeeze and Spatial Excitation (sSE) attention module with U-Net-like skip connections, MFF-Net inverts root-zone SMC from summer maize leaf images. Field experiments were conducted in Zhengzhou, Henan Province, China, from 2024 to 2025, under three irrigation treatments: 60–70% θ_fc, 70–90% θ_fc, and 60–90% θ_fc (θ_fc denotes field capacity). This study shows that (1) MFF-Net achieved its smallest inversion error under the 60–70% θ_fc treatment, suggesting the inversion was most effective when SMC variation was small and relatively low; (2) MFF-Net demonstrated superior performance to several benchmark models, achieving an R² of 0.84; and (3) the ablation study confirmed that each feature branch and the sSE attention module contributed positively to model performance. MFF-Net thus offers a technological reference for real-time precision irrigation and shows promise for field SMC inversion in summer maize.