Accurate prediction of photovoltaic power is of great significance to the safe operation of power grids. In order to improve the prediction accuracy, a similar day clustering convolutional neural network (CNN)–informer model was proposed to predict the photovoltaic power. Based on correlation analysis, it was determined that global horizontal radiation was the meteorological factor that had the greatest impact on photovoltaic power, and the dataset was divided into four categories according to the correlation between meteorological factors and photovoltaic power fluctuation characteristics; then, a CNN was used to extract the feature information and trends of different subsets, and the features output by CNN were fused and input into the informer model. The informer model was used to establish the temporal feature relationship between historical data, and the final photovoltaic power generation power prediction result was obtained. The experimental results show that the proposed CNN–informer prediction method has high accuracy and stability in photovoltaic power generation prediction and outperforms other deep learning methods.

Nitrous oxide (N₂O) is a potent greenhouse gas (GHG) with agricultural soils representing its largest anthropogenic source. However, the mechanisms involved in the N₂O emission and factors affecting N₂O emission fluxes in response to various nitrogenous fertilizer applications remain uncertain. We conducted a four-year (2012–2015) field experiment to assess how fertilization scheme impacts N₂O emissions from a rice-wheat cropping system in eastern China. The fertilizer treatments included Control (CK), Conventional fertilizer (CF), CF with shallow-irrigation (CF+SI), CF with deep-irrigation system (CF+DI), Optimized fertilizer (OF), OF with Urease inhibitor (OF+UI), OF with conservation tillage (OF+CT) and Slow-release fertilizer (SRF). N₂O emissions were measured by a closed static chamber method. N₂O emission fluxes ranged from 0.61 μg m^-2 h^-1 to 1707 μg m^-2 h^-1, indicating a significant impact of nitrogen fertilizer and cropping type on N₂O emissions. The highest crop yields for wheat (3515–3667 kg ha^-1) and rice (8633–8990 kg ha^-1) were observed under the SRF and OF+UI treatments with significant reduction in N₂O emissions by 16.94–21.20% and 5.55–7.93%, respectively. Our findings suggest that the SRF and OF+UI treatments can be effective in achieving maximum crop yield and lowering N₂O emissions for the rice-wheat cropping system in eastern China.

This study aimed to investigate the impacts of straw and biochar on greenhouse gas (GHG) emissions and grain yield in a double rice cropping system under optimal N fertilizer reduction. Conventional fertilization (CF) was used as the control group, and treatments included optimal fertilization and 15% less nitrogen (OF), together with straw (S) or biochar (B) applied under different fertilization conditions, namely CF + S, CF + B, OF + S, and OF + B. The effects of treatments on soil CH₄ and N₂O emissions were studied, and changes in soil physicochemical properties were analyzed. The results showed that relative to CF, CF + S and OF + S increased the cumulative CH₄ emissions by 11.80% and 2.35%, respectively, while CF + B and OF + B resulted in significant reductions in cumulative CH₄ emissions by 27.80% and 28.46%, respectively. Biochar was effective in reducing N₂O emissions, and OF further increased the potential, with CF + B and OF + B achieving the best N₂O reductions of 30.56% and 32.21%, respectively. Although OF reduced yields by 0.16%, this difference was within reasonable limits; the remaining treatments increased grain yields by 2.55% to 3.47%. CF + B and OF + B reduced the global warming potential (GWP) by 27.93% and 28.63%, respectively, and ultimately reduced the greenhouse gas emission intensity (GHGI) by 30.42% and 30.97%. Both straw and biochar increased the soil organic matter, NH₄⁺-N, and NO₃⁻-N contents, and biochar increased the soil pH, which may be the potential mechanism regulating soil GHG emissions. Overall, OF + B is beneficial for reducing GHG emissions and may be a better agronomic cropping pattern in double season rice growing areas.

Soil moisture, as an important variable affecting water–heat exchange between land and atmosphere, is an important feedback to climate change. Soil moisture is of great concern in Northern China, where arable land is extensive, but water resources are distributed unevenly and extremely sensitive to climate change. Using measured soil moisture data collected by the China Meteorological Administration from 164 stations during 1980–2021, we explored the drivers of soil moisture variation by analyzing its spatiotemporal variability using linear regression, partial correlation analysis, and geostatistical methods. The results indicated that (1) soil moisture increased from northwest to southeast in Northern China, with the lowest soil moisture in the IM; (2) the overall trend of soil moisture in most regions decreased, especially in the arid northwest and northeast China. However, soil moisture in some regions began to increase gradually in recent years, such as in northwestern Xinjiang and the central-eastern part of IM; and (3) soil moisture in the whole region was negatively correlated with temperature and sunshine duration and positively correlated with precipitation and relative humidity. The results of the study can provide valuable guidance for timely agricultural irrigation and the adjustment of cropping structures, thereby ensuring agricultural production and food security.