Contributions of various driving factors to air pollution events: Interpretability analysis from Machine learning perspective.

The air quality in China has been improved substantially, however fine particulate matter (PM2.5) still remain at a high level in many areas. PM2.5 pollution is a complex process that is attributed to gaseous precursors, chemical, and meteorological factors. Quantifying the contribution of each variable to air pollution can facilitate the formulation of effective policies to precisely eliminate air pollution. In this study, we first used decision plot to map out the decision process of the Random Forest (RF) model for a single hourly data set and constructed a framework for analyzing the causes of air pollution using multiple interpretable methods. Permutation importance was used to qualitatively analyze the effect of each variable on PM2.5 concentrations. The sensitivity of secondary inorganic aerosols (SIA): SO42-, NO3- and NH4+ to PM2.5 was verified by Partial dependence plot (PDP). Shapley Additive Explanation (Shapley) was used to quantify the contribution of drivers behind the ten air pollution events. The RF model can accurately predict PM2.5 concentrations, with determination coefficient (R2) of 0.94, root mean square error (RMSE) and mean absolute error (MAE) of 9.4 µg/m3 and 5.7 µg/m3, respectively. This study revealed that the order of sensitivity of SIA to PM2.5 was NH4+＞NO3-＞SO42-. Fossil fuel and biomass combustion may be contributing factors to air pollution events in Zibo in 2021 autumn-winter. NH4+ contributed 19.9-65.4 µg/m3 among ten air pollution events (APs). K, NO3-, EC and OC were the other main drivers, contributing 8.7 ± 2.7 µg/m3, 6.8 ± 7.5 µg/m3, 3.6 ± 5.8 µg/m3 and 2.5 ± 2.0 µg/m3, respectively. Lower temperature and higher humidity were vital factors that promoted the formation of NO3-. Our study may provide a methodological framework for precise air pollution management.

Effects of forest age on soil erosion and nutrient loss in Dianchi watershed, China.

Soil erosion and nutrient loss are important environmental and ecological problems in the Dianchi watershed in southwestern China. Woodlands-the primary land type in the Dianchi watershed-play an important ecological role in controlling soil and water loss. In this study, we compared soil erosion and loss of total organic carbon (TOC), total nitrogen (TN), and total phosphorus (TP) in woodlands of different ages, i.e., young forest, medium forest, and near-mature forest, at the Dongda River catchment in south-western Dianchi watershed. Furthermore, changes in stoichiometries in soil were analyzed. The average degree of erosion of each forest age stage was below moderate. Based on the non-arable soil erosion modulus models of 137Cs and 210Pbex, the soil erosion rates decreased gradually with the increasing forest age. The forest age affected soil nutrient distribution and loss. The losses of TOC and TP gradually decreased, while the losses of TN first increased and then decreased with the growth of forest age. TOC, TN, and TP were enriched in the topsoil. Forest age affected soil stoichiometry and soil nutrient supply level. In general, the forest can effectively reduce soil erosion and nutrient loss in the red soil area with the forest age increasing.

Historical evolution of polycyclic aromatic hydrocarbon pollution in Chaihe Reservoir from 1863 to 2018.

Pollution from polycyclic aromatic hydrocarbons (PAHs) spreads and changes worldwide. The pollution evolution in the regional water environment evolves in response to multiple factors, requiring considerable attention. PAH heterogeneity in the sediment core from Chaihe Reservoir was investigated to indicate dynamic changes in PAH pollution levels and sources and propose recommendations for controlling PAHs. Dynamic PAH patterns showed that the overall decline in PAH pollution was in association with local anthropogenic activities, temperature, and precipitation over the period 1863-2018. Nevertheless, coal, oil, and natural gas consumptions still played significant roles in transferring PAHs to the reservoir. Meanwhile, there were dominant local origins, including grass, wood, and coal combustion. The results highlight that the joint action of natural and anthropogenic interventions mitigated PAH pollution in the reservoir. Promoting improved fuels, new energy vehicles, and cleaner energy may further lower PAH pollution.

Response of sedimentation rate to environmental evolution in Da River Reservoir in Southwest China.

Lake sediment records the evolution process of the interaction between human and nature. It is important to master the lacustrine sedimentation rate for the ecological environment assessment of catchment. A 60-cm sediment core was collected in the Da River Reservoir during 2019 to analyze radionuclides (210Pb and 137Cs) massic activities, grain size, total organic carbon (TOC), total nitrogen (TN), total phosphorus (TP), and metals (Mn, Cu, Al, and Pb) mass fractions to reconstruct the response of sedimentation rate to environmental evolution. The environmental changes in the small catchment were classified into the following three stages through cluster analysis (CA) for geochemical parameters in the sediment core: phase I (1881-1985), phase II (1987-1999), and phase III (2000-2018). The average depth sedimentation rates (ADSRs) of the three stages were 0.33, 0.90, and 1.50 cm/year, respectively. The sedimentation rates increased from the bottom to the surface layer, indicating that the exogenous inputs into the reservoir have been occurring. The sediment deposition in phase III was strongly disturbed by the environmental changes (such as warmer climate and intensified land use). Therefore, sedimentation rates showed a rapid increase. Both Pearson correlation analysis and redundancy analysis (RDA) showed that sedimentation rates were positively correlated with climatic factors, particle size, nutrients and metals mass fractions, elemental ratios, and socioeconomic parameters. Sedimentation rates show high sensitivity to anthropogenic activities and climatic change, which can be used to reconstruct the environmental evolution process at a small catchment scale.