The potential of urban parks to enhance social welfare and deliver health benefits has been recognized. However, it is still unclear which landscape characteristics in urban green spaces best improve the physical activity levels of users. Little is known about the relationship between the microenvironment of urban green spaces and the physical activity of children, particularly in the context of high levels of childhood obesity. Using the self-report method, we extracted the perceived environmental characteristics of the landscape and combined this with behavior observation to obtain the level of children’s physical activity in green spaces and to explore the influence of the characteristics of green spaces on these activities. Our results show that the highest levels of activity were found in the semiopen spaces of urban parks, which mainly consist of dense vegetation and a diverse range of recreation facilities. Play facilities were most closely related to the level of intensity of children’s activities, and perceived safety was the primary social perception factor affecting their activities. In addition, perceptions of the social environment were found to play a significant intermediary role in the impact of green space on children’s physical activity. The study results are intended to promote green space planning and design updates, improve the public health level of children, and provide a basis for the construction of child-friendly cities.

The hot and humid feeling of the urban environment enhances residents’ discomfort indices. Although the cooling and humidifying effects of plant communities in various urban parks are significant, there is still insufficient evidence for the effects of plant community characteristics on temperature and humidity. In this study, 36 typical plant communities in the Changchun Water Culture and Ecological Park in China were selected in the summer (21–23 August 2020) from 8:00 to 18:00 for three days when it was sunny and windless. We obtained plant community characteristics through field measurements and drone recordings to explore the relationship between plant community characteristics and the mechanism of temperature and humidity. The study observed that (1) the canopy density and three-dimensional green amount were significantly related to the benefits of cooling and humidification. When the canopy density is between 0.7 and 0.8 and the three-dimensional green volume is above 4 m³/m², the greatest benefit is achieved; (2) the discomfort index is between 0.6 and 0.8, and the three-dimensional green volume is 4 m³/m²–6 m³/m² minimum; and (3) the changes in temperature and humidity are different for different types of plant communities, which lead to differences in people’s perceptions of environmental comfort. The tree–grassland and tree–shrub–grass types had the most apparent improvement effects on comfort. The results show that in the design process of urban park plants, emphasis is placed on plant community configuration with apparent cooling and humidification effects, which can improve the comfort of tourists in hot and humid environments. The research results provide theoretical support for sustainable urban green space development.

Creating attractive urban green spaces in severely cold and harsh climates is significant for promoting peoples’ health and perceived restoration. However, there is little evidence regarding the urban green spaces in wintery and cold climates and its restorative benefits. This study utilized a pixel grid approach to quantify winter landscape characteristics and a self-reporting method to assess the restorative benefits of audiovisual interactions. The results show the following: (1) Different types of roads in urban parks have significant differences in their level of restorativeness, and the restorativeness benefits of the primary path in winter parks are the strongest. (2) The presence of snowy elements in winter landscapes can enhance park users’ potential to experience restorative characteristics in relation to “being away”. Moreover, there exists a noteworthy positive correlation between deciduous trees and their restoration benefits. (3) People’s perceptions of the tranquility of the soundscape and the duration of environmental exposure are critical mediators in the impact of the restorative path effect. (4) Compared with women, men have a higher restorative level in both the landscape and soundscape. This elucidates the restorative role of white space landscapes and soundscapes in public psychological perception when proposing appropriate forest-based healthcare strategies. It also provides theoretical guidance and optimization schemes for the overall planning, health planning, and design of white spaces shaped by cold urban green spaces.

In order to address the limited scale and insufficient diversity of research datasets for maize leaf diseases, this study proposes a maize disease image generation algorithm based on the cycle generative adversarial network (CycleGAN). With the disease image transfer method, healthy maize images can be transformed into diseased crop images. To improve the accuracy of the generated data, the category activation mapping attention mechanism is integrated into the original CycleGAN generator and discriminator, and a feature recombination loss function is constructed in the discriminator. In addition, the minimum absolute error is used to calculate the differences between the hidden layer feature representations, and backpropagation is employed to enhance the contour information of the generated images. To demonstrate the effectiveness of this method, the improved CycleGAN algorithm is used to transform healthy maize leaf images. Evaluation metrics, such as peak signal-to-noise ratio (PSNR), structural similarity (SSIM), Fréchet inception distance (FID), and grayscale histogram can prove that the obtained maize leaf disease images perform better in terms of background and detail preservation. Furthermore, using this method, the original CycleGAN method, and the Pix2Pix method, the dataset is expanded, and a recognition network is used to perform classification tasks on different datasets. The dataset generated by this method achieves the best performance in the classification tasks, with an average accuracy rate of over $91\%$. These experiments indicate the feasibility of this model in generating high-quality maize disease leaf images. It not only addresses the limitation of existing maize disease datasets but also improves the accuracy of maize disease recognition in small-sample maize leaf disease classification tasks.

Urban green ecological space is an important measure of sustainable urban development. Among them, landscape connectivity is one of the key factors in maintaining landscape function. Ecological networks can effectively improve regional ecological quality and promote urban landscape connectivity. However, previous studies on ecological networks have mainly focused on biodiversity conservation and lack research on landscape connectivity. This study used morphological spatial pattern analysis methods and utilized connectivity indices to identify ecological sources in the Chaoyang and Nanguan districts of China’s Changchun City and selected environmental and anthropogenic factors to construct an integrated resistance surface. The minimum cumulative resistance model and network structure index were used for urban ecological network construction and node optimization. The results show that the potential ecological network comprises 17 ecological sources and 34 potential corridors, primarily located in forests and water bodies in the east and south regions. However, the northwest has poor habitat quality and uneven distribution of ecological corridors, that warrant prioritization in future planning, construction, and protection efforts. By introducing six supplemental sources and 25 additional corridors, the function and overall connectivity of the regional ecological network can be improved. The study confirmed that the selection of appropriate connectivity thresholds can improve the accuracy of ecological sources identification, and that the influence of anthropogenic factors on ecological resistance cannot be ignored. This study will provide a scientific basis for promoting urban construction and ecological balance.

Increasing soil contamination with nickel (Ni) and copper (Cu) is a growing environmental concern, adversely affecting ecosystems and the survival of both plants and animals. This study investigated the morphological and physiological responses of Euphorbia marginata Pursh seedlings to varying concentrations of Ni and Cu over a 45-day period. The findings revealed that low concentrations of Ni and Cu enhanced morphological indexes, root indexes, biomass, and photosynthetic pigment content of E. marginata, while high concentrations inhibited these parameters. Compared to the control, Ni and Cu stresses induced membrane peroxidation, increased cell membrane permeability, and inhibited the synthesis of soluble proteins and proline in the leaves. The seedlings demonstrated an ability to mitigate Ni and Cu toxicity by increasing soluble sugar content and enhancing the activities of peroxidase (POD), superoxide dismutase (SOD), and catalase (CAT). Notably, E. marginata exhibited a higher capacity for Cu²⁺ enrichment and translocation compared to Ni²⁺. Combined Ni and Cu treatments reduced the maximum enrichment and translocation levels of both metals in E. marginata. This study highlights the superior tolerance of E. marginata to Ni and Cu stresses and elucidates the mechanisms underlying its response, providing a theoretical basis for the use of landscape plants in the remediation of heavy-metal-contaminated soils.