The accurate estimation of leaf chlorophyll content (LCC) is a significant foundation in assessing litchi photosynthetic activity and possible nutrient status. Hyperspectral remote sensing data have been widely used in agricultural quantitative monitoring research for the non-destructive assessment of LCC. Variable selection approaches are crucial for analyzing high-dimensional datasets due to the high danger of overfitting, time-intensiveness, or substantial computational requirements. In this study, the performance of five machine learning regression algorithms (MLRAs) was investigated based on the hyperspectral fractional order derivative (FOD) reflection of 298 leaves together with the variable combination population analysis (VCPA)-genetic algorithm (GA) hybrid strategy in estimating the LCC of Litchi. The results showed that the correlation coefficient (r) between the 0.8-order derivative spectrum and LCC had the highest correlation coefficients (r = 0.9179, p < 0.01). The VCPA-GA hybrid strategy fully utilizes VCPA and GA while compensating for their limitations based on a large number of variables. Moreover, the model was developed using the selected 14 sensitive bands from 0.8-order hyperspectral reflectance data with the lowest root mean square error in prediction (RMSEP = 5.04 $\mathsf{\mu }\mathrm{g}·{\mathrm{cm}}^{-2}$). Compared with the five MLRAs, validation results confirmed that the ridge regression (RR) algorithm derived from the 0.2 order was the most effective for estimating the LCC with the coefficient of determination (R² = 0.88), mean absolute error (MAE = 3.40$\mathsf{\mu }\mathrm{g}·{\mathrm{cm}}^{-2}$), root mean square error (RMSE = 4.23$\mathsf{\mu }\mathrm{g}·{\mathrm{cm}}^{-2}$), and ratio of performance to inter-quartile distance (RPIQ = 3.59). This study indicates that a hybrid variable selection strategy (VCPA-GA) and MLRAs are very effective in retrieving the LCC through hyperspectral reflectance at the leaf scale. The proposed methods could further provide some scientific basis for the hyperspectral remote sensing band setting of different platforms, such as an unmanned aerial vehicle (UAV) and satellite.

Chlorophyll is an essential pigment for photosynthesis in tea plants, and fluctuations in its content directly impact the growth and developmental processes of tea trees, thereby influencing the final quality of the tea. Therefore, achieving rapid and non-destructive real-time monitoring of leaf chlorophyll content (LCC) is beneficial for precise management in tea plantations. In this study, derivative transformations were first applied to preprocess the tea hyperspectral data, followed by the use of the Stable Competitive Adaptive Reweighted Sampling (SCARS) algorithm for feature variable selection. Finally, multiple individual machine learning models and stacking models were constructed to estimate tea LCC based on hyperspectral data, with a particular emphasis on analyzing how the selection of base models and meta-models affects the predictive performance of the stacking models. The results indicate that derivative processing enhances the sensitivity of hyperspectral data to tea LCC; furthermore, compared with individual machine learning models, the stacking models demonstrate superior predictive accuracy and generalization ability. Among the 17 constructed stacking configurations, when the meta-model is fixed, the predictive performance of the stacking model improves continuously with an increase in the number and accuracy of the base models and with a decrease in the structural similarity among the selected base models. Therefore, when constructing stacking models, the base model combination should comprise various models with minimal structural similarity while ensuring robust predictive performance, and the meta-model should be chosen as a simple linear or nonlinear model.

Understanding how soil arthropod communities respond to nutrient enrichment is important for assessing grassland ecosystem health, but such knowledge remains limited for degraded Sophora alopecuroides grasslands. To address this gap, a two-year field experiment was conducted in the Tuhulusu grassland (Xinjiang, China) with four treatments: nitrogen (N) addition, phosphorus (P) addition, combined N and P (NP) addition, and an unamended control (CK). Soil arthropod communities and environmental variables were monitored during the flowering, maturity, and senescence stages of S. alopecuroides. Across all treatments, three taxa—Oppiidae, Hypoaspidae, and Rhagidiidae—remained dominant, indicating wide ecological tolerance. Nutrient addition significantly altered arthropod individual density (response variable) and soil properties, including total phosphorus, available phosphorus, nitrate−N, ammonium−N, and pH (all p < 0.001), and these effects were strongly linked to plant phenology. The dominance, evenness, and Shannon diversity indices ranked as NP > CK > P > N. The key environmental drivers varied by treatment: total phosphorus and soil moisture under N addition, soil moisture under P and NP addition, and pH and electrical conductivity under CK. Collectively, these findings provide evidence that soil arthropod communities in S. alopecuroides grasslands are sensitive to nutrient enrichment in a phenology−dependent manner, with soil moisture content emerging as a critical limiting factor under nutrient−added conditions.

Grassland degradation, exacerbated by climate change and anthropogenic disturbances, poses a substantial barrier to ecological restoration, largely due to the invasion of toxic weeds. In the degraded grasslands of the Ili River Valley, Xinjiang, Sophora alopecuroides has emerged as the dominant toxic species; yet, its expansion mechanisms and sensitivity to management interventions remain poorly understood. This study utilized a three-year (2023–2025) field experiment to evaluate the impacts of nitrogen addition (N), mowing (M), and their combination (NM) on the stoichiometric characteristics and homeostasis of the plant–soil system. The results demonstrated that while M suppressed aboveground biomass, it facilitated the accumulation of root carbon (RC) and phosphorus (RP). Nitrogen enrichment significantly lowered soil C:N and C:P ratios, thereby alleviating phosphorus limitation. Crucially, the NM treatment effectively counteracted N-induced weed proliferation and mitigated M-induced biomass reductions. Analysis of stoichiometric homeostasis revealed that NM optimized plant adaptive strategies, maintaining strict homeostasis for RC and RP (H > 4) while preserving the sensitivity of the root N:P ratio of S. alopecuroides (RN:P). Structural equation modeling further indicated that soil C:P and N:P indirectly regulated total biomass by modulating the root C:P ratio of S. alopecuroides (RC:P). Consequently, stoichiometric coupling within the plant–soil system is essential for maintaining ecosystem functions. Integrated management (NM) optimizes soil nutrient balance and harnesses compensatory growth to suppress weed expansion, providing a robust scientific framework for the restoration of S. alopecuroides-invaded grasslands.