As a well-known photocatalyst, TiO₂ still suffers from rapid electron–hole recombination and limited visible light absorption. To overcome these challenges, the combination of graphene and TiO₂ has been proposed. However, traditional methods such as ball milling and hydrothermal synthesis face limitations, including high energy consumption and complex procedures. Here, we develop a simple and industrially feasible method to prepare reduced graphene oxide (rGO)-coated TiO₂ nanoparticles, referred to as rGO-TiO₂ composites. The optimized rGO-TiO₂ composites exhibit an enhanced photocatalytic degradation of rhodamine B (RhB) under simulated sunlight conditions, about 99.95% for 4% rGO-TiO₂ within 80 min. The first-order reaction rate constant (k) of 4% rGO-TiO₂ (0.0867 min⁻¹) is 5.42 times higher than that of nano TiO₂ (0.0135 min⁻¹). The key reactive species involved in the degradation process are identified. Additionally, the effects of pH and NaCl concentration on the degradation efficiency of rGO-TiO₂ are also investigated. The 4% rGO-TiO₂ composite exhibits an excellent photocatalytic activity within the pH range of 3.87–11.89, and the NaCl concentration does not affect its photocatalytic efficiency. After characterization, the enhanced photocatalytic activity is ascribed to the introduction of rGO and the generation of surface oxygen vacancies (O_V) and Ti³⁺ in TiO₂ crystals.

The time-scale mismatch between rapid influent fluctuations and slow biochemical responses hinders the stability of wastewater treatment plants (WWTPs). Existing models often fail to capture shock signals due to noise interference (“signal pollution”). To address this, we propose the HD-MAED-LSTM model, which employs a “decompose-and-conquer” strategy. Targeting the dynamic characteristics of different components, this study innovatively designs heterogeneous attention mechanisms: utilizing Long-term Dependency Attention to capture the global evolution of the trend component, employing Multi-scale Periodic Attention to reinforce the cyclic patterns of the seasonal component, and using Gated Anomaly Attention to keenly capture sudden shocks in the residual component. In a case study, the effectiveness of the proposed model was validated based on one year of operational data from a large-scale industrial WWTP. HD-MAED-LSTM outperformed baseline models such as Transformer and LSTM in the medium-to-long-term (10-h) prediction of COD, TN, and TP, clearly demonstrating the positive role of differentiated modeling. Notably, in the core task of shock load early warning, the model achieved an F1-Score of 0.83 (superior to Transformer’s 0.77 and LSTM’s 0.67), and a Mean Directional Accuracy (MDA) as high as 0.93. Ablation studies confirm that the specialized attention mechanism is the key performance driver, reducing the Mean Absolute Error (MAE) by 56.7%. This framework provides precise support for shifting WWTPs from passive response to proactive control.

As a well-known photocatalyst, TiO₂, still suffers from rapid electron-hole recombination and limited visible light absorption. To overcome these challenges, the combination of graphene and TiO₂ has been proposed. However, traditional methods such as ball milling and hydrothermal synthesis face limitations, including high energy consumption and complex procedures. Here, we developed a simple and industrially feasible method to prepare reduced graphene oxide (rGO) coated TiO₂ nanoparticles, referred to as rGO-TiO₂ composites. The optimized rGO-TiO₂ composites exhibited enhanced photocatalytic degradation of of Rhodamine B (RhB) under simulated sunlight condition. The effects of pH and NaCl concentration on the degradation efficiency of rGO-TiO₂ were also investigated. Additionally, the key reactive species involved in the degradation process were identified. After characterization, the enhanced photocatalytic activity is ascribed to the introduction of rGO and the generation of surface oxygen vacancies (OV) and Ti³⁺ in TiO₂ crystals.