The road networks provide key information for a broad range of applications such as urban planning, urban management, and navigation. The fast-developing technology of remote sensing that acquires high-resolution observational data of the land surface offers opportunities for automatic extraction of road networks. However, the road networks extracted from remote sensing images are likely affected by shadows and trees, making the road map irregular and inaccurate. This research aims to improve the extraction of road centerlines using both very-high-resolution (VHR) aerial images and light detection and ranging (LiDAR) by accounting for road connectivity. The proposed method first applies the fractal net evolution approach (FNEA) to segment remote sensing images into image objects and then classifies image objects using the machine learning classifier, random forest. A post-processing approach based on the minimum area bounding rectangle (MABR) is proposed and a structure feature index is adopted to obtain the complete road networks. Finally, a multistep approach, that is, morphology thinning, Harris corner detection, and least square fitting (MHL) approach, is designed to accurately extract the road centerlines from the complex road networks. The proposed method is applied to three datasets, including the New York dataset obtained from the object identification dataset, the Vaihingen dataset obtained from the International Society for Photogrammetry and Remote Sensing (ISPRS) 2D semantic labelling benchmark and Guangzhou dataset. Compared with two state-of-the-art methods, the proposed method can obtain the highest completeness, correctness, and quality for the three datasets. The experiment results show that the proposed method is an efficient solution for extracting road centerlines in complex scenes from VHR aerial images and light detection and ranging (LiDAR) data.

The COVID-19 outbreak is a manifestation of the contradiction between man and land. Geography plays an important role in epidemic prevention and control with its cross-sectional characteristics and spatial perspective. Based on a systematic review of previous studies, this paper summarizes the research progress on factors influencing the spatial spread of COVID-19 from the research content and method and proposes the main development direction of geography in epidemic prevention and control research in the future. Overall, current studies have explored the factors influencing the epidemic spread on different scales, including global, national, regional and urban. Research methods are mainly composed of quantitative analysis. In addition to the traditional regression analysis and correlation analysis, the spatial lag model, the spatial error model, the geographically weighted regression model and the geographic detector have been widely used. The impact of natural environment and economic and social factors on the epidemic spread is mainly reflected in temperature, humidity, wind speed, air pollutants, population movement, economic development level and medical and health facilities. In the future, new technologies, new methods and new means should be used to reveal the driving mechanism of the epidemic spread in a specific geographical space, which is refined, multi-scale and systematic, with emphasis on exploring the factors influencing the epidemic spread from the perspective of spatial and behavioral interaction, and establish a spatial database platform that combines the information of residents’ cases, the natural environment and economic society. This is of great significance to further play the role of geography in epidemic prevention and control.

Under the continuous impact of global warming, the water cycle has undergone significant changes, causing a series of problems such as water shortage, frequent climate disasters and ecological environment deterioration. Therefore, understanding the evolution of regional historical and future drought and wet conditions is crucial for adapting and mitigating disasters. This paper discusses the evolution of drought and pluvial events in the Henan section of the Yellow River from 1970 to 2014, projects the future evolution of drought and wet conditions, and assesses the performance of various climate models from Coupled Model Intercomparison Project Phase 6 in simulating precipitation and temperature. Subsequently, future drought and wet conditions in the Henan section were projected for the 2015–2100 period across four SSP-RCP scenarios using Standardized Precipitation and Evapotranspiration Index (SPEI) and run theory. The results indicate that the Henan section of the Yellow River exhibited a significant drying trend during the historical period, with a rate of 0.15 per decade. Looking ahead, a wetting tendency is projected under the SSP1-2.6 scenario, with an increasing rate of 0.02 per decade, whereas the other three scenarios consistently show drying trends, with rates of −0.11, −0.15, and −0.23 per decade, respectively. Across all scenarios, drought and wetness variations exhibit pronounced periodicity, particularly at timescales of approximately 20–30 years, suggesting the persistence of multi-decadal hydroclimatic oscillations. Furthermore, drought and wetness events are projected to become more persistent and severe during the mid-to-late 21st century. Compared with the historical baseline, increasing radiative forcing is associated with an expansion in drought-affected areas, accompanied by reduced event frequency but longer duration and greater severity. In terms of risk, the SSP3-7.0 scenario presents the highest overall drought and wetness risk with the widest spatial extent, whereas the SSP2-4.5 scenario shows relatively lower risk levels and a more balanced spatial distribution.