Accurate estimation of reference evapotranspiration (ETo) is key to agricultural irrigation scheduling and water resources management in arid and semiarid areas. This study evaluates the capability of coupling a Bat algorithm with the XGBoost method (i.e., the BAXGB model) for estimating monthly ETo in the arid and semiarid regions of China. Meteorological data from three stations (Datong, Yinchuan, and Taiyuan) during 1991–2015 were used to build the BAXGB model, the multivariate adaptive regression splines (MARS), and the gaussian process regression (GPR) model. Six input combinations with different sets of meteorological parameters were applied for model training and testing, which included mean air temperature (Tmean), maximum air temperature (Tmax), minimum air temperature (Tmin), wind speed (U), relative humidity (RH), and solar radiation (Rs) or extraterrestrial radiation (Ra, MJ m⁻²·d⁻¹). The results indicated that BAXGB models (RMSE = 0.114–0.412 mm·d⁻¹, MAE = 0.087–0.302 mm·d⁻¹, and R² = 0.937–0.996) were more accurate than either MARS (RMSE = 0.146–0.512 mm·d⁻¹, MAE = 0.112–0.37 mm·d⁻¹, and R² = 0.935–0.994) or GPR (RMSE = 0.289–0.714 mm·d⁻¹, MAE = 0.197–0.564 mm·d⁻¹, and R² = 0.817–0.980) model for estimating ETo. Findings of this study would be helpful for agricultural irrigation scheduling in the arid and semiarid regions and may be used as reference in other regions where accurate models for improving local water management are needed.

Atmospheric nitrogen (N) deposition greatly affects ecosystem processes and properties. However, few studies have simultaneously examined the responses of both the above‐ and belowground communities to N deposition. Here, we investigated the effects of 8 years of simulated N deposition on soil microbial communities and plant diversity in a subtropical forest. The quantities of experimental N added (g of N m⁻² year⁻¹) and treatment codes were 0 (N0, control), 6 (N1), 12 (N2), and 24 (N3). Phospholipid fatty acids (PLFAs) analysis was used to characterize the soil microbial community while plant diversity and coverage were determined in the permanent field plots. Microbial abundance was reduced by the N3 treatment, and plant species richness and coverage were reduced by both N2 and N3 treatments. Declines in plant species richness were associated with decreased abundance of arbuscular mycorrhizal fungi, increased bacterial stress index, and reduced soil pH. The plasticity of soil microbial community would be more related to the different responses among treatments when compared with plant community. These results indicate that long‐term N deposition has greater effects on the understory plant community than on the soil microbial community and different conservation strategies should be considered.