Accurate and real-time monitoring of root soil water content (RSWC) is key in optimizing field irrigation decisions and enhancing crop water productivity. However, relying only on the vegetation index as the input to the inversion model may result in lower inversion accuracy due to the canopy spectral saturation effect. To break through the limitation of a single data source, this study constructed an integrated network model (ATT-LSTM) incorporating the attention mechanism based on the long and short-term memory network (LSTM) to enhance the inversion performance by integrating heterogeneous data from multiple sources. The experiment used canopy spectral data based on UAV remote sensing and weather station monitoring data as input features. A control group was set up for cross-validation to realize the accurate inversion of RSWC in kiwifruit plants. The results show that the coefficient of determination (R²) of the ATT-LSTM model on the test set reaches 0.868. This study confirms that the multi-source data fusion framework effectively overcomes vegetation index saturation, improves rhizosphere moisture monitoring accuracy, supports precision irrigation decisions in kiwifruit orchards, and provides a reference for smart agriculture water management optimization.

Fertilization is a critical measure for vegetation restoration and ecological reconstruction in degraded grasslands. However, little is known about the long-term effects of different combinations of nitrogen (N), phosphorus (P), potassium (K) on plant and microbial communities in degraded grasslands. This study conducted a four-year (2017–2020) N, P, K addition experiment in the Khorchin Grassland, a degraded typical grassland located in Zhalute Banner, Tongliao City, Inner Mongolia, to investigate the effects of fertilization treatment on plant functional groups and microbial communities after grazing exclusion. Our results showed that the addition of P, NP, and NPK compound fertilizers significantly increased aboveground biomass of the plant community, which is mainly related to the improvement of nutrient availability to promote the growth of specific plant functional groups, especially annual and biennial plants and perennial bunchgrasses. However, the addition of N, P, and NP fertilizers significantly reduced the species diversity of the plant community. At the same time, the addition of N, P, and NP fertilizers and the application of N and NP significantly reduced fungal species diversity but had no significant effect on soil bacteria. Our study provides new insights into the relationships between different types of fertilization and plant community productivity and biodiversity in degraded grasslands over four years of fertilization, which is critical for evaluating the effect of fertilization on the restoration of degraded grassland.

Pollinator health depends critically on gut microbiome composition, yet species-specific responses to agricultural environments remain unclear. We compared gut microbiome dynamics and dietary shifts in Osmia excavata, Megachile rotundata, and Apis cerana during alfalfa pollination using 16S rRNA sequencing and rbcL metabarcoding. Alpha diversity revealed distinct patterns: O. excavata showed reduced richness but increased evenness after foraging, M. rotundata exhibited reduced diversity, while A. cerana remained stable. Beta diversity demonstrated microbiome convergence among species after release, indicating environmental filtering. Dietary analysis revealed polylectic foraging dominated by Citrullus lanatus, Peganum nigellastrum, and Zea mays, with minimal alfalfa consumption. Pseudomonadota and Bacillota predominated, with species-specific signatures: Gilliamella in A. cerana, Lactobacillus in M. rotundata, and Bacillus in O. excavata. These findings demonstrate that microbiome assembly reflects host sociality–environment interactions, with solitary bees showing greater plasticity. This study provides a microbial foundation for pollinator conservation in agricultural systems.