With the rapid advancement of the global economy, there has been a noticeable escalation in the level of inhalable particulate matter (PM) pollution in the atmosphere. The utilization of plants has been recognized as an effective means to mitigate the escalation in the atmospheric PM concentration through the capture and retention of this particulate matter on their leaves. This research focuses on investigating the PM retention capacity of nine commonly found greening plant species in Changsha, China, located in the country’s mid-subtropical region. In this study, we employed an air aerosol generator (QRJZFSQ-II) and a portable leaf area meter (LI-3000C) to systematically evaluate the PM retention in unit leaf area for different PM values. In addition, the leaf surface structure was observed via scanning electron microscopy, and the relationship between the leaf microstructure and the retained particles was quantitatively analyzed. The results showed that (1) there were significant differences in the retention of TSP, PM₁₀, and PM_2.5 per unit leaf area among the nine greening tree species analyzed. Rosa saturata was found to have the best retention effect regarding TSP and PM_2.5, and Rhododendron simsii was found to have the best retention effect regarding PM₁₀. (2) There were significant differences in the contents of TSP and PM_2.5 per leaf area among the different tree species with different life forms (p < 0.05), with the order of retention being shrub > arbor (needle leaves) > arbor (broad leaves). (3) Coniferous plants have a deep leaf surface texture, which is conducive to capturing more particles on their leaf surface, and (4) the long stomata diameter was significantly negatively correlated with PM retention, and the stomata density was significantly positively correlated with PM retention. However, the short diameter and small area of stomata demonstrated no significant correlation with PM retention (p < 0.05). Considering the selection of suitable tree species for greening in urban air pollution control, we suggest that Osmanthus fragrans, Pseudolarix amabilis, Rosa saturata, and Rhododendron simsii be used more frequently in urban areas affected by severe air pollution.

Destructive wildfires pose a serious threat to ecosystems, economic development, and human life and property safety. If wildfires can be extinguished in a relatively short period of time after they occur, the losses caused by wildfires will be greatly reduced. Although deep learning methods have been shown to have powerful feature extraction capabilities, many current models still have poor generalization performance when faced with complex tasks. To this end, in this study, we considered introducing attention modules both inside and outside the nested U-shaped structure and trained a neural network model based on the U2-Net architecture to enable the model to suppress the activation of irrelevant areas. Compared with baseline models such as U-Net, our model has made great progress on the test set, with an F1 score improvement of at least 2.8%. The experimental results indicate that the model we proposed has certain practicality and can provide a significant scientific basis for forest fire management and emergency decision-making.

Ormosia microphylla is a nationally prioritized wild plant in China but effects of likely future climate change have been poorly studied. Here distribution data of O. microphylla and environmental data with an optimized MaxEnt maximum entropy model were used to predict potentially suitable areas under current and future climate scenarios. The results showed that with future climate warming, the total area suitable for O. microphylla might gradually increase. In the three future periods (2030s (2021–2040), 2050s (2041–2060) and 2090s (2081–2100)), the medium and high suitable areas under different climate scenarios generally showed an expanding trend, while the low suitable areas mostly showed a decreasing trend. At the same time, the potential suitable areas for O. microphylla in China have shown a certain degree of migration trend towards higher latitudes in the north and northwest, as well as a trend towards higher altitudes. The research results will provide data support for the protection of germplasm resources and the development of artificial cultivation techniques for O. microphylla, and provide a theoretical basis for the protection of other rare and endangered plants.

In order to analyze the primary sources of air pollutants in Chang-Zhu-Tan region, this article selected the environmental monitoring data and meteorological data in the winter of 2019 to calculate the backward airflow trajectories with the Chang-Zhu-Tan region as the starting point by using the backward trajectory model. Combined with the ground concentration monitoring data, cluster analysis, potential source contribution factor (PSCF) analysis, and concentration weighted trajectory (CWT) analysis were carried out to determine the pollutant transportation paths and sources of the potential source area. The results show that air mass transportation mainly comes from three directions: northwest, northeast, and southwest China. The airflow in northwest China moves faster and cleaner, while the airflow from the northeast and southwest moves slowly and carries a high concentration of pollutants. PSCF and CWT analyses show that the critical potential sources are mainly located in this area and some cities next to the study area. This study has important practical significance for the environmental research of Chang-Zhu-Tan region and can provide theoretical reference for regional joint prevention and control of air pollution.

Accurate prediction of PM2.5 concentrations is crucial for public health and environmental management. However, effectively capturing complex spatiotemporal dependencies across multiple time scales remains a persistent challenge for existing methods, particularly in regions with sparse monitoring stations. This study proposes a Multi-Scale Dynamic Graph Neural Network (MSDGNN) for PM2.5 forecasting in station clusters. The model incorporates multi-scale temporal modeling (hourly, daily, weekly) to capture both short- and long-term dependencies. A learnable mapping matrix dynamically groups stations to strengthen spatial correlation learning. Furthermore, MSDGNN employs multi-head attention and spatiotemporal graph attention mechanisms to construct dynamic graphs, utilizing adaptive adjacency matrices and Chebyshev graph convolutions for effective feature propagation. We evaluated MSDGNN on 22 air quality monitoring stations in the Chang-Zhu-Tan region. Results demonstrated that our model reduces MAE by 6.77% and RMSE by 8.67% compared to the best baseline, validating its capability to learn complex dependencies and deliver accurate predictions under diverse spatiotemporal conditions.

Air contamination stands as a formidable obstacle to China’s social-economic progress, significantly impacting citizen well-being and living conditions. The endeavor to forecast air quality accurately, which carries substantial societal implications, has become increasingly crucial particularly within Chinese urban agglomeration. Recent deep learning approaches have significantly enhanced the modeling of complex spatial-temporal correlations within air quality data, primarily by treating the data as a dispersion process. Unfortunately, a substantial portion of previous research has neglected the impact of heterogeneity in air quality data within urban agglomeration on the predictions. Moreover, these studies haven’t adequately modeled and disentangled air quality data specific to individual cities and that originating from other cities within the urban agglomeration. To improve forecasting performance, we propose a novel forecasting model predicated on the Gaussian Decoupled Representation Extractor, engineered to forecast air quality within urban agglomeration. The model, using a data-driven approach, segregates the air-quality time series by quantifying and decoding the heterogeneous constituents of time, location, and origin variables embedded in air-quality data. It incorporates a dual attention mechanism to apprehend the spatial-temporal dependencies to air-quality. The efficacy of the model is corroborated using a data set from urban agglomeration in Hunan Province. Through extensive experiments, it is demonstrated that compared with the baselines, our model has shown an improvement, with a reduction of 11.2% in MAE and 8.97% in RMSE respectively.