Yawei Qu

High-precision and efficient atmospheric environmental forecasting is essential for protecting public health and supporting environmental management. However, traditional physics-based numerical models, while mechanistically interpretable, struggle to balance computational cost and forecast accuracy. Although artificial intelligence(AI) has advanced rapidly in meteorological forecasting, most existing AI models are not optimized for atmospheric environmental prediction and rely heavily on gridded inputs, limiting their ability to integrate site observations and their operational applicability. To overcome these limitations, we develop BiXiao, a new-generation AI-based atmospheric environmental forecasting model. BiXiao features a heterogeneous architecture with non-continuous grids, coupling independent meteorological and environmental modules for synergistic use of multi-source data. The meteorological module employs a 3D Swin Transformer(Swin3D) to process structured meteorological fields, while the environmental module directly assimilates discrete station data, enabling operational urban-scale forecasts. Testing in the Beijing-Tianjin-Hebei region shows that BiXiao completes 72-hour forecasts for six major pollutants across all key cities within 30 seconds. Compared with mainstream numerical models(CAMS and WRF-Chem), BiXiao achieves substantially higher computational efficiency and forecast accuracy, particularly during heavy pollution events.

High-precision and efficient atmospheric environmental forecasting is essential for protecting public health and supporting environmental management. However, traditional physics-based numerical models, while mechanistically interpretable, struggle to balance computational cost and forecast accuracy. Although artificial intelligence(AI) has advanced rapidly in meteorological forecasting, most existing AI models are not optimized for atmospheric environmental prediction and rely heavily on gridded inputs, limiting their ability to integrate site observations and their operational applicability. To overcome these limitations, we develop BiXiao, a new-generation AI-based atmospheric environmental forecasting model. BiXiao features a heterogeneous architecture with non-continuous grids, coupling independent meteorological and environmental modules for synergistic use of multi-source data. The meteorological module employs a 3D Swin Transformer(Swin3D) to process structured meteorological fields, while the environmental module directly assimilates discrete station data, enabling operational urban-scale forecasts. Testing in the Beijing-Tianjin-Hebei region shows that BiXiao completes 72-hour forecasts for six major pollutants across all key cities within 30 seconds. Compared with mainstream numerical models(CAMS and WRF-Chem), BiXiao achieves substantially higher computational efficiency and forecast accuracy, particularly during heavy pollution events.

Despite substantial reductions in PM2.5 and other pollutants, ozone (O3) in eastern China has increased over the past decade, yet the influence of aerosol processes – including aerosol–radiation interactions (ARI) and heterogeneous chemistry (HET) – on these trends remains insufficiently explored, particularly during Clean Air Action Plan (CAAP, Phase I: 2013–2017; Phase II: 2018–2020) and under carbon neutrality pathways. We applied a phase- and season-resolved WRF-Chem framework with explicit ARI and HET to quantify historical and projected O3 changes in the Yangtze River Delta (YRD), linking aerosol effects with CAAP and carbon-neutrality pathways. We separate O3 changes into those driven directly by anthropogenic emissions and meteorological variability, and those mediated by aerosol processes through ARI and HET. The results revealed that anthropogenic emissions and meteorological variability respectively dominated winter and summer O3 increases. Winter O3 increases were dominated by ARI: large aerosol reductions enhanced solar radiation, temperature, and photolysis, resulting in a photochemical O3 rise (+1.14 (+0.74) ppb in Phase I (II)). Summer O3 was more sensitive to HET. In Phase I, aerosol decreases weakened heterogeneous radical uptake, enhancing O3 formation (+1.62 ppb). In Phase II, however, the net HET effect reversed sign (−2.86 ppb), driven by shifts in multiple heterogeneous pathways – including changes in radical uptake, HONO and N2O5 chemistry, and aerosol liquid water – rather than radical scavenging alone. Accounting for aerosol effects (AEs = ARI + HET), reductions in PM2.5 and NOx increased O3, while VOCs reductions consistently lowered O3 in both seasons. Under carbon peaking and neutrality scenarios with AEs, winter O3 increased by 6.7 % and 10.7 %, whereas summer O3 decreased by 2.9 % and 6.7 %, highlighting seasonally contrasting responses. These results underscore the necessity of explicitly accounting for multi-path aerosol–O3 interactions in both near-term air quality management and long-term climate mitigation to prevent unintended trade-offs and maximize co-benefits.

Despite substantial reductions in PM_2.5 and other pollutants, ozone (O₃) in eastern China has increased over the past decade, yet the influence of aerosol processes – including aerosol–radiation interactions (ARI) and heterogeneous chemistry (HET) – on these trends remains poorly understood, particularly during Clean Air Action (Phase I: 2013–2017; Phase II: 2018–2020) and under carbon neutrality pathways. We applied a phase- and season-resolved WRF-Chem framework with explicit ARI and HET to quantify historical and projected O₃ changes in the Yangtze River Delta (YRD), linking aerosol effects with clean air actions and carbon-neutrality pathways. Winter O₃ increases were dominated by ARI: large aerosol reductions enhanced solar radiation, temperature, and photolysis, resulting in a photochemical O₃ rise (+1.14 (+0.74) ppb in Phase I (II)). Summer O₃ was more sensitive to HET: initial aerosol decreases weakened radical scavenging, promoting O₃ formation (+1.62 ppb), whereas the weakening of this effect during Phase II reduced O₃ (-2.86 ppb). Accounting for aerosol effects (ARI+HET), reductions in PM_2.5 and NOx increased O₃, while VOCs reductions consistently lowered O₃ in both seasons. Under carbon peaking and neutrality scenarios with AEs, winter O₃ increased by 6.7 % and 10.7 %, whereas summer O₃ decreased by 2.9 % and 6.7 %, highlighting seasonally contrasting responses. These results underscore the necessity of explicitly accounting for multi-path aerosol–O₃ interactions in both near-term air quality management and long-term climate mitigation to prevent unintended trade-offs and maximize co-benefits.

Despite substantial reductions in PM_2.5 and other pollutants, ozone (O₃) in eastern China has increased over the past decade, yet the influence of aerosol processes – including aerosol–radiation interactions (ARI) and heterogeneous chemistry (HET) – on these trends remains poorly understood, particularly during Clean Air Action (Phase I: 2013–2017; Phase II: 2018–2020) and under carbon neutrality pathways. We applied a phase- and season-resolved WRF-Chem framework with explicit ARI and HET to quantify historical and projected O₃ changes in the Yangtze River Delta (YRD), linking aerosol effects with clean air actions and carbon-neutrality pathways. Winter O₃ increases were dominated by ARI: large aerosol reductions enhanced solar radiation, temperature, and photolysis, resulting in a photochemical O₃ rise (+1.14 (+0.74) ppb in Phase I (II)). Summer O₃ was more sensitive to HET: initial aerosol decreases weakened radical scavenging, promoting O₃ formation (+1.62 ppb), whereas the weakening of this effect during Phase II reduced O₃ (-2.86 ppb). Accounting for aerosol effects (ARI+HET), reductions in PM_2.5 and NOx increased O₃, while VOCs reductions consistently lowered O₃ in both seasons. Under carbon peaking and neutrality scenarios with AEs, winter O₃ increased by 6.7 % and 10.7 %, whereas summer O₃ decreased by 2.9 % and 6.7 %, highlighting seasonally contrasting responses. These results underscore the necessity of explicitly accounting for multi-path aerosol–O₃ interactions in both near-term air quality management and long-term climate mitigation to prevent unintended trade-offs and maximize co-benefits.

Despite substantial reductions in PM_2.5 and other pollutants, ozone (O₃) in eastern China has increased over the past decade, yet the influence of aerosol processes – including aerosol–radiation interactions (ARI) and heterogeneous chemistry (HET) – on these trends remains poorly understood, particularly during Clean Air Action (Phase I: 2013–2017; Phase II: 2018–2020) and under carbon neutrality pathways. We applied a phase- and season-resolved WRF-Chem framework with explicit ARI and HET to quantify historical and projected O₃ changes in the Yangtze River Delta (YRD), linking aerosol effects with clean air actions and carbon-neutrality pathways. Winter O₃ increases were dominated by ARI: large aerosol reductions enhanced solar radiation, temperature, and photolysis, resulting in a photochemical O₃ rise (+1.14 (+0.74) ppb in Phase I (II)). Summer O₃ was more sensitive to HET: initial aerosol decreases weakened radical scavenging, promoting O₃ formation (+1.62 ppb), whereas the weakening of this effect during Phase II reduced O₃ (-2.86 ppb). Accounting for aerosol effects (ARI+HET), reductions in PM_2.5 and NOx increased O₃, while VOCs reductions consistently lowered O₃ in both seasons. Under carbon peaking and neutrality scenarios with AEs, winter O₃ increased by 6.7 % and 10.7 %, whereas summer O₃ decreased by 2.9 % and 6.7 %, highlighting seasonally contrasting responses. These results underscore the necessity of explicitly accounting for multi-path aerosol–O₃ interactions in both near-term air quality management and long-term climate mitigation to prevent unintended trade-offs and maximize co-benefits.

Despite substantial reductions in PM_2.5 and other pollutants, ozone (O₃) in eastern China has increased over the past decade, yet the influence of aerosol processes – including aerosol–radiation interactions (ARI) and heterogeneous chemistry (HET) – on these trends remains poorly understood, particularly during Clean Air Action (Phase I: 2013–2017; Phase II: 2018–2020) and under carbon neutrality pathways. We applied a phase- and season-resolved WRF-Chem framework with explicit ARI and HET to quantify historical and projected O₃ changes in the Yangtze River Delta (YRD), linking aerosol effects with clean air actions and carbon-neutrality pathways. Winter O₃ increases were dominated by ARI: large aerosol reductions enhanced solar radiation, temperature, and photolysis, resulting in a photochemical O₃ rise (+1.14 (+0.74) ppb in Phase I (II)). Summer O₃ was more sensitive to HET: initial aerosol decreases weakened radical scavenging, promoting O₃ formation (+1.62 ppb), whereas the weakening of this effect during Phase II reduced O₃ (-2.86 ppb). Accounting for aerosol effects (ARI+HET), reductions in PM_2.5 and NOx increased O₃, while VOCs reductions consistently lowered O₃ in both seasons. Under carbon peaking and neutrality scenarios with AEs, winter O₃ increased by 6.7 % and 10.7 %, whereas summer O₃ decreased by 2.9 % and 6.7 %, highlighting seasonally contrasting responses. These results underscore the necessity of explicitly accounting for multi-path aerosol–O₃ interactions in both near-term air quality management and long-term climate mitigation to prevent unintended trade-offs and maximize co-benefits.

Despite substantial reductions in PM_2.5 and other pollutants, ozone (O₃) in eastern China has increased over the past decade, yet the influence of aerosol processes – including aerosol–radiation interactions (ARI) and heterogeneous chemistry (HET) – on these trends remains poorly understood, particularly during Clean Air Action (Phase I: 2013–2017; Phase II: 2018–2020) and under carbon neutrality pathways. We applied a phase- and season-resolved WRF-Chem framework with explicit ARI and HET to quantify historical and projected O₃ changes in the Yangtze River Delta (YRD), linking aerosol effects with clean air actions and carbon-neutrality pathways. Winter O₃ increases were dominated by ARI: large aerosol reductions enhanced solar radiation, temperature, and photolysis, resulting in a photochemical O₃ rise (+1.14 (+0.74) ppb in Phase I (II)). Summer O₃ was more sensitive to HET: initial aerosol decreases weakened radical scavenging, promoting O₃ formation (+1.62 ppb), whereas the weakening of this effect during Phase II reduced O₃ (-2.86 ppb). Accounting for aerosol effects (ARI+HET), reductions in PM_2.5 and NOx increased O₃, while VOCs reductions consistently lowered O₃ in both seasons. Under carbon peaking and neutrality scenarios with AEs, winter O₃ increased by 6.7 % and 10.7 %, whereas summer O₃ decreased by 2.9 % and 6.7 %, highlighting seasonally contrasting responses. These results underscore the necessity of explicitly accounting for multi-path aerosol–O₃ interactions in both near-term air quality management and long-term climate mitigation to prevent unintended trade-offs and maximize co-benefits.