In recent years, the generative adversarial network (GAN)-based image translation model has achieved great success in image synthesis, image inpainting, image super-resolution, and other tasks. However, the images generated by these models often have problems such as insufficient details and low quality. Especially for the task of map generation, the generated electronic map cannot achieve effects comparable to industrial production in terms of accuracy and aesthetics. This paper proposes a model called Map Generative Adversarial Networks (MapGAN) for generating multitype electronic maps accurately and quickly based on both remote sensing images and render matrices. MapGAN improves the generator architecture of Pix2pixHD and adds a classifier to enhance the model, enabling it to learn the characteristics and style differences of different types of maps. Using the datasets of Google Maps, Baidu maps, and Map World maps, we compare MapGAN with some recent image translation models in the fields of one-to-one map generation and one-to-many domain map generation. The results show that the quality of the electronic maps generated by MapGAN is optimal in terms of both intuitive vision and classic evaluation indicators.

Globally, natural habitats have suffered tremendous damage from human activities, a phenomenon that is increasingly evident in basin regions. The management of natural habitats in basin regions is dependent on understanding of the various impacts of human activities on these ecosystems. Despite the various studies that have been conducted on the effects of human activities on habitats in basin regions, there is still a lot of doubt regarding the impact of these activities on the quality of basin ecosystems. To fill this gap, this study employs a series of spatial analysis methods and logistic regression modeling to delve into the spatial and temporal patterns of human activities and habitat quality in the Yangtze River Basin (YRB) as well as the differences in the impacts of human activities on habitat quality in the sub-basins of the YRB. The findings indicate a 0.408% decline in the overall environmental quality of the YRB area from 2000 to 2020, accompanied by a 15.396% surge in human activities. Notably, the southeastern Qilian Mountains and the mountainous regions in the northwestern sector of the Sichuan Basin emerge as pivotal areas for habitat quality restoration. Conversely, the southwestern Qilian Mountains and the urban clusters in the Yangtze River Delta (YRD) face significant habitat quality deterioration. Spatial regression analyses reveal a noteworthy trend: the burgeoning human activities in the Yangtze River region pose a substantial threat to habitat recovery efforts. Further differential analyses focusing on the upper, middle, and lower basin segments underscore that human activities exert the most pronounced impact on habitat quality within the lower basin region, while the upper basin experiences the least influence. The implications of this study are manifold. It furnishes valuable policy insights for the comprehensive management and targeted preservation of habitats across the YRB. By delineating areas of habitat restoration and degradation and highlighting the differential impacts of human activities across basin segments, this research lays a solid foundation for informed decision making in habitat conservation and ecosystem management within the YRB.