A field experiment was conducted for the purpose of examining the effects of different combinations of water and fertilizer applications on the water consumption and yields of alfalfa under subsurface drip irrigation (SDI). The results showed that the jointing and branching stages were the key stages for alfalfa water requirement. The water consumption had varied greatly (from 130 to 170 mm) during the growth period of each alfalfa crop. The water consumption during the whole growth period was approximately 500 mm, and the maximum water consumption intensity was 3.64 mm·d^-1. The overall changes in water consumption and yields during the growth period of the alfalfa displayed trends of first increasing and then decreasing. The sensitivities of the yields to water changes were much higher than that of fertilizer. The water use efficiency (WUE) of the alfalfa was determined to range from 1.68 to 3.20 kg·m^-3, and the rate of growth had ranged from 4.85% to 51.77%. The WUE and rate of growth of the alfalfa indicated the following trend: second crop > third crop > first crop. The results of frequency analysis based on the water‐nitrogen‐yield regression equation are the following: irrigation amounts of 142~165 mm and nitrogen application of 61~80 kg·hm^-2 have a 95% probability of obtaining a hay yield of alfalfa of more than 11903 kg·hm^-2. These results suggest that SDI is a promising irrigation method, which can increase the WUE and hay yield of alfalfa under the condition of SDI within an appropriate amount of water and nitrogen fertilizer, and too low or too high water and nitrogen fertilizer will adversely affect the WUE and hay yield of alfalfa.

Terrestrial ecosystems depend heavily on their vegetation; it is possible to forecast future growth trends of regional vegetation by keeping an eye on changes in vegetation dynamics. To circumvent the potential reduction in prediction accuracy caused by the non-stationarity of meteorological changes, we analyzed the characteristics of NDVI (Normalized Difference Vegetation Index) spatial and temporal changes and the influencing factors over the past 20 years in the Maowusu Sandland of China via attribution analysis. We also constructed a comprehensive analysis system for vegetation pre-restoration. Moreover, we combined meteorological data from 2000 to 2018 and presented a deep-learning NDVI-Informer prediction model with a self-attentive mechanism. We also used distillation operation and fusion convolutional neural network for NDVI prediction. Incorporating a probsparse self-attention method successfully overcomes Transformer weaknesses by lowering the memory use and complexity of large time series. It significantly accelerates the inference speed of long time series prediction and works well with non-smooth data. The primary findings were: (1) the Maowusu Sandland’s 20-year average showed a consistent increasing trend in the NDVI at 0.0034 a⁻¹, which was mostly caused by climate change, with a relative contribution rate of 55.47%; (2) The Informer-based model accurately forecasted the NDVI in the research region based on meteorological elements and conducted a thorough analysis of the MAPE (mean absolute percentage error) (2.24%). This suggests that it can effectively lower the data’s volatility and increase prediction accuracy. The anticipated outcomes indicate that the trend will stabilize during the following ten years. To attain more sustainable and efficient agricultural production, the results of this study may be used to accurately estimate future crop yields and NDVI using previous data.

Currently, there is a limited supply of freshwater on a worldwide scale, and finding effective ways to use agricultural freshwater resources has become a widely discussed subject. To investigate the most suitable crops and the efficient use of water resources in dry regions, we performed a comparison study of water consumption between two common crops, maize and sunflowers, in the irrigation area located on the south bank of the Yellow River in Northwest China. Both sunflowers and maize have diverse water sources at various reproductive phases. We discovered that sunflower predominantly consumes 0–50 cm soil water throughout the reproductive cycle, whereas maize mostly utilizes 0–50 cm soil water in the early reproductive phase and 50–90 cm soil water in the late reproductive period. The comparison of yield sustainability between sunflowers and maize demonstrated that sunflowers exhibited more resilience than maize when subjected to the same level of water decrease. Sunflowers’ yield sustainability score stayed consistently over 0.95, while maize had a lowest score of 0.84. We observed via correlation analysis that it was the fraction of subsurface water contribution and the water contribution of the 50~70 cm soil layer that impacted the yield of sunflowers and maize, with coefficients of 0.88 or higher. Ultimately, sunflowers exhibited a lower level of responsiveness to water scarcity compared to maize. Sunflowers have greater drought tolerance compared to maize since they rely less on soil layers replenished by a limited water supply. Based on our findings, sunflowers are well suited to arid conditions and limited spaces that do not have access to irrigation, while maize is better suited to well-watered conditions and expansive cultivation areas.