Soil bacterial community composition and diversity can be an important bioindicator for assessing ecosystem stability, and photovoltaic (PV) shading is a key factor influencing soil bacterial communities in rocky desertification areas; however, how the composition and diversity of soil bacterial communities change with PV operation duration remains unclear. Focusing on the experimental demonstration site of Shilin ecological photovoltaic (PV) power plant in Yunnan Province, we compared soil properties under PV arrays and non-PV control areas with different operation durations (7 and 13 years). The results showed that long-term PV operation significantly increased soil TN and TK content compared to CK, while increasing Ure and ALP activities, but inhibiting CAT activity and decreasing soil moisture, pH, SOC, and TP. High-throughput sequencing revealed stable dominant bacterial phyla (e.g., Aspergillus, Acidobacteriota) and beneficial genera (e.g., RB41, Sphingomonas), with an increase in relative abundance of Bacillota-like phyla but a decrease in Acidobacterium. The α-diversity (ACE, Chao1 index) and β-diversity of soil bacteria greatly increased with years of PV operation, reaching a maximum in the 13-year PV operation area. Correlation analyses showed that differences in soil bacterial communities in regions with different years of PV operation were mainly influenced by differences in PH and enzyme activities.

Predictive modelling is very important for water pollution management. In this study, based on an electromagnetic field-enhanced vertical flow artificial wetland and using the actual measured data as inputs to the model, the ammonia nitrogen (NH₄⁺-N) effluent concentration of this wetland system was analyzed by Pearson’s correlation analysis to be related to six key factors, which were the NH⁺-N raw water concentration, the chemical oxygen demand (COD) raw water concentration, the treatment time, the magnetic field strength, the aeration time, and the electric field strength. Then, different artificial neural network models were constructed for comparison and the constructed models were evaluated based on statistical parameters. The results show that the PSO algorithm can improve the prediction effect of the BP neural network, but the prediction accuracy of the CNN model is better compared to the others. The prediction accuracy of the RF model is the highest compared to the others, and the evaluation parameters of R2, RMSE, and MAE of the test set are (0.9446, 2.4328, and 3.0943), respectively. The prediction error of this model is the smallest, and the model can predict the concentration of electric and magnetic fields in a wetland system with high accuracy compared to other models. This model can more accurately predict the NH₄⁺-N effluent concentration of the magnetic field-enhanced wetland system, which can provide a certain basis for the study of the management of water pollution.

The addition of physical field enhancement measures to improve the purification effect of vertical flow artificial wetlands has gradually become popular. In this study, a vertical flow artificial wetland system reinforced by electric and magnetic fields was constructed. These fields were first optimized using finite element 3D simulation software to obtain the optimal electric and magnetic field parameters. Then, the pollutant removal effects and changes in microbial community structure were comparatively analyzed. The optimal electromagnetic field parameters (applied voltage of 15 V and applied magnetic field of 20 mT) resulted in significantly enhanced removal rates of chemical oxygen demand (COD), nitrate nitrogen (NH₄⁺-N), total phosphorus (TP), and orthophosphorus (PO₄³⁻-P) in wastewater, with rates of 74.47%, 45.44%, 89.85%, and 90.04%, respectively. These rates were notably higher than those observed in the vertical flow artificial wetland system. The microbial community structure analysis revealed that the vertical flow constructed wetland with enhanced electric and magnetic fields exhibited (EM-VFCW) a more diverse and complex microbial community structure. Notably, the abundance of bacteria capable of removing NH₄⁺-N and COD, including Aspergillus, Fusarium, and Actinobacteria, was significantly elevated.