A good understanding of how meteorological conditions exacerbate or mitigate air pollution is critical for developing robust emission reduction policies. Thus, based on a multiple linear regression (MLR) model in this study, the quantified impacts of six meteorological variables on PM_2.5 (i.e., particle matter with diameter of 2.5 µm or less) and its major components were estimated over the Yangtze River Basin (YRB). The 38-year (1980–2017) daily PM_2.5 and meteorological data were derived from the newly-released Modern-Era Retrospective Analysis and Research and Application, version 2 (MERRA-2) products. The MERRA-2 PM_2.5 was underestimated compared with ground measurements, partly due to the bias in the MERRA-2 Aerosol Optical Depth (AOD) assimilation. An over-increasing trend in each PM_2.5 component occurred for the whole study period; however, this has been curbed since 2007. The MLR model suggested that meteorological variability could explain up to 67% of the PM_2.5 changes. PM_2.5 was robustly anti-correlated with surface wind speed, precipitation and boundary layer height (BLH), but was positively correlated with temperature throughout the YRB. The relationship of relative humidity (RH) and total cloud cover with PM_2.5 showed regional dependencies, with negative correlation in the Yangtze River Delta (YRD) and positive correlation in the other areas. In particular, PM_2.5 was most sensitive to surface wind speed, and the sensitivity was approximately −2.42 µg m⁻³ m⁻¹ s. This study highlighted the impact of meteorological conditions on PM_2.5 growth, although it was much smaller than the anthropogenic emissions impact.

The annotations used during the training process are crucial for the inference results of remote sensing images (RSIs) based on a deep learning framework. Unlabeled RSIs can be obtained relatively easily. However, pixel-level annotation is a process that necessitates a high level of expertise and experience. Consequently, the use of small sample training methods has attracted widespread attention as they help alleviate reliance on large amounts of high-quality labeled data and current deep learning methods. Moreover, research on small sample learning is still in its infancy owing to the unique challenges faced when completing semantic segmentation tasks with RSI. To better understand and stimulate future research that utilizes semantic segmentation tasks with small data, we summarized the supervised learning methods and challenges they face. We also reviewed the supervised approaches with data that are currently popular to help elucidate how to efficiently utilize a limited number of samples to address issues with semantic segmentation in RSI. The main methods discussed are self-supervised learning, semi-supervised learning, weakly supervised learning and few-shot methods. The solution of cross-domain challenges has also been discussed. Furthermore, multi-modal methods, prior knowledge constrained methods, and future research required to help optimize deep learning models for various downstream tasks in relation to RSI have been identified.

Given the increasing frequency and severity of floods caused by climate change, there is a pressing requirement for creative ways to improve public comprehension and control of hydrological phenomena. Contemporary technology provides unparalleled possibilities to transform this domain. This project investigates the possibilities for merging gaming engines and digital twins to enhance flood education, data visualization, and interactive monitoring. This study proposes the utilization of immersive digital twins to enhance the comprehension of hydrological and hydraulic systems. The suggested method utilizes game engines to generate dynamic and interactive models that connect raw data to practical insights, enabling a more profound understanding of flood dynamics. This study underscores the wide-ranging usefulness of digital twins in various watersheds by focusing on the development of advanced monitoring systems, the benefits of improved data visualization, and educational outreach. The incorporation of real-time data via IoT technology considerably improves the significance and precision of these virtual models. This novel approach seeks to refashion flood management approaches by cultivating well-informed stakeholders and advocating for effective environmental education, ultimately leading to more resilient and prepared communities. An immersive digital twin of the real world can assist decision-makers technically, psychologically, and mentally by making complex phenomena easier to understand and visualize, thanks to real-time data and simulations that keep the information up-to-date, consequently leading to a more precise and intuitive decision-making process.

Spatiotemporally seamless precipitable water vapor (PWV) maps with high accuracy, spatiotemporal resolution, and continuity are of significance for climatical research. The current frameworks for the PWV maps have predominantly concentrated on fusing PWV derived from ERA5 reanalysis (ERA-PWV) and MODIS near-infrared data (MOD-NIR-PWV), falling short in accuracy. In this study, PWV derived from Global Navigation Satellite Systems (GNSS-PWV) is introduced to produce spatiotemporally PWV maps with improved accuracy. The fusion framework involves two main steps: 1) spatial fusion for producing an initial PWV map with spatiotemporal continuity through spherical cap harmonic analysis; 2) temporal fusion for producing a refined PWV map with high accuracy through residual correction. GNSS-PWV over 188 stations, 0.25°×0.25° ERA-PWV, and 0.05°×0.05° MOD-NIR-PWV over China from 2013 to 2018 are used to produce the daily 0.05°×0.05° PWV maps. The performance is evaluated using out-of-sample data, containing 18 GNSS-PWV and 90 ERA-PWV, and independent reference data, containing radiosonde-derived PWV over 72 stations. When compared to the out-of-sample GNSS-PWV and ERA-PWV, the PWV maps exhibit mean biases of -1.04 and -0.55 mm and RMS of 1.75 and 0.97 mm, respectively. These are equivalent to 8.7% and 32.1% reductions in bias and 25.5% and 49.5% reductions in RMSE relative to MOD-NIR-PWV. When radiosonde-derived PWV is used as the reference, the PWV maps have the mean bias and RMSE of -0.53 and 2.21 mm, respectively, which outperforms ERA-PWV (-0.75 and 2.69 mm). These results indicate the effectiveness of the novel fusion framework in producing seamless PWV maps.

Urban forms, such as size, shape, density, compactness, and fragmentation, are associated with local air pollution concentrations. However, empirical analyses on how urban form improves or degrades urban air quality are still limited and inconclusive, especially for those rapidly expanding cities in developing countries. In this study, by using the improved STIRPAT (stochastic impacts by regression on population, affluence, and technology) model, the quantitative impact of urban form on near-surface PM_2.5 and NO₂ concentrations was identified in the 10 prefecture-level cities of the Yangtze River Basin (YRB) from 2000 to 2013. Trend analyses showed a significant increasing trend in both PM_2.5 (9.69 × 10⁻⁴ µg·m⁻³·year⁻¹) and NO₂ (1.73 × 10⁻⁴ ppb·year⁻¹) for the whole study period. Notably, a turning point of PM_2.5 from increasing to decreasing trends occurred around 2007. In addition, both pollutants showed a spatial agglomeration. The STIRPAT model demonstrated that socioeconomic, transportation and urban form factors played an important role in alleviating the increase of PM_2.5 and NO₂. In particular, a 1% decrease in urban extent density (UED) significantly increased NO₂ by 0.203%, but reduced PM_2.5 by 0.033%. The proximity index (PI) measured as a city’s compactness was significantly negatively correlated with PM_2.5 and NO₂. Conversely, a significant positive relationship of PM_2.5 and NO₂ concentrations against the openness index (OI) was observed, an important variable for measuring a city’s fragmentation. In addition, the environmental Kuznets curve (EKC) hypothesis between per capita GDP and PM_2.5 concentration was confirmed but failed in NO₂. Overall, this study encouraged a less fragmented and more compact urban form, which helped alleviate local air pollution concentrations by enhancing urban connectivity, reducing vehicle dependence, and facilitating the use of bicycles and walking.

The deep learning method has achieved great success in hyperspectral image classification, but the lack of labeled training samples still restricts the development and application of deep learning methods. In order to deal with the problem of small samples in hyperspectral image classification, a novel small sample classification method based on rotation-invariant uniform local binary pattern (RULBP) features and a graph-based masked autoencoder is proposed in this paper. Firstly, the RULBP features of hyperspectral images are extracted, and then the k-nearest neighbor method is utilized to construct the graph. Furthermore, self-supervised learning is conducted on the constructed graph so that the model can learn to extract features more suitable for small sample classification. Since the self-supervised training mainly adopts the masked autoencoder method, only unlabeled samples are needed to complete the training. After training, only a small number of samples are used to fine-tune the graph convolutional network, so as to complete the classification of all nodes in the graph. A large number of classification experiments on three commonly used hyperspectral image datasets show that the proposed method could achieve higher classification accuracy with fewer labeled samples.