The progression of the COVID-19 pandemic has demonstrated significant oscillatory characteristics, underscoring the importance of investigating the impact of driving factors on its evolution. This study included an in-depth analysis of the influence of various driving factors on the pandemic’s fluctuations, identifying key elements, to enhance the comprehension of transmission mechanisms and improve scientific precision in formulating mitigation strategies. The experimental outcomes indicate that the Geographically and Temporally Neural Network Weighted Regression (GTNNWR) model achieved commendable accuracy with minimal error in forecasting the number of infected individuals. Leveraging the results from the GTNNWR model, the research meticulously examines the temporal and spatial correlations between the driving factors and the pandemic, delineated the spatiotemporal distribution patterns of each factor’s influence, and quantified their significance. This study reveals the substantial impact of vaccines, masks, and social distancing measures across different regions and periods, with their effects on the number of affected individuals being 2 to 10 times more pronounced than other driving factors. These findings contribute to a deeper understanding of the spatiotemporal transmission dynamics and the influence of driving factors in the COVID-19 pandemic, offering critical decision-making support for control and prevention efforts.

Duckweed/algal bloom-type black–odorous waters (DAWs) exhibit composite optical properties of vegetation and pollution, posing intractable remote sensing identification challenges in complex environments. Current methods suffer from three critical limitations: a misclassification rate exceeding 25% due to spectral confusion with artificial green covers, an 18.7% false-negative rate for small patches (stemming from the imbalance between CNNs and Transformers), and insufficient feature dimensionality to characterize the dual properties of DAWs. To address these gaps, this study proposes a novel method that integrates the ASGICTVS feature set with a customized SwinTf-Unet model. The ASGICTVS feature set combines vegetation-sensitive metrics, optical water quality indicators, and visual features. The SwinTf-Unet model utilizes an optimized 4 × 4 window, an embedded feature fusion module, and an adaptive shifted window stride to balance global context capture and local detail reconstruction. Experiments on 21,104 GF-2 satellite samples demonstrate that the method achieves 87.50% precision, 88.41% recall, an 85.32% F1-score, and an 83.46% Intersection over Union (IoU), outperforming DeepLabV3+ by 14.56 percentage points in the IoU. With an inference time of 0.87 s per 512 × 512-pixel image and a stable performance across cross-regional datasets (IoU: 82.1–85.3%), it exhibits strong efficiency and generalization. This study resolves DAW spectral confusion, enables high-precision segmentation, and establishes a standardized feature threshold system, providing reliable technical support for large-scale automated DAW monitoring and regional water environment management.