Generative Adversarial Networks (GANs) possess a significant ability to generate novel images that adhere to specific guidelines across multiple domains. GAN-assisted generative design is a design method that can automatically generate design schemes without the constraints of human conditions. However, more research on complex objects with weak regularity, such as parks, is required. In this study, parks were selected as the research object, and we conducted our experiment as follows: (1) data preparation and collection; (2) pre-train the two neural network, then create the design layout generation system and the design plan generation system; (3) realize the data augmentation and enhanced hundred level dataset to thousand level dataset; (4) optimized training; (5) test the optimized training model. Experimental results show that (1) the machine learning model can acquire specific park layout patterns, quickly generate well-laid-out plan layout plans, and create innovative designs that differ from the human designer’s style within reasonable limits; (2) GAN-driven data augmentation methods can significantly improve the generative ability of algorithms, reduce generative pressure, and achieve better generative results; (3) pix2pix is prone to mode collapse, and CycleGAN has fixed rule errors in expressing certain design elements; and (4) GAN has the ability to mine design rules in the same way as humans.

Due to rapid urban expansion, urban agglomerations face enormous challenges on their way to carbon neutrality. Regarding China’s urban agglomerations, 25% of the land contains 75% of the population, and all types of land are used efficiently and intensively. However, few studies have explored the spatiotemporal link between changes in land use and land cover (LULC) and carbon storage. In this work, the carbon storage changes from 1990 to 2020 were estimated using the InVEST model in China’s Beijing–Tianjin–Hebei (BTH) region. By coupling the Future Land Use Simulation (FLUS) model and InVEST model, the LULC and carbon storage changes in the BTH region in 2035 and 2050 under the natural evolution scenario (NES), economic priority scenario (EPS), ecological conservation scenario (ECS), and coordinated development scenario (CDS). Finally, the spatial autocorrelation analysis of regional carbon storage was developed for future zoning management. The results revealed the following: (1) the carbon storage in the BTH region exhibited a cumulative loss of 3.5 × 10⁷ Mg from 1990 to 2020, and the carbon loss was serious between 2000 and 2010 due to rapid urbanization. (2) Excluding the ECS, the other three scenarios showed continued expansion of construction land. Under the EPS, the carbon storage was found to have the lowest value, which decreased to 16.05 × 10⁸ Mg in 2035 and only 15.38 × 10⁸ Mg in 2050; under the ECS, the carbon storage was predicted to reach the highest value, 18.22 × 10⁸ Mg and 19.00 × 10⁸ Mg, respectively; the CDS exhibited a similar trend as the NES, but the carbon storage was found to increase. (3) The carbon storage under the four scenarios was found to have a certain degree of similarity in terms of its spatial distribution; the high-value areas were found to be clustered in the northwestern part of Beijing and the northern and western parts of Hebei. As for the number of areas with high carbon storage, the ECS was found to be the most abundant, followed by the CDS, and the EPS was found to be the least. The findings of this study can help the BTH region implement the “dual carbon” target and provide a leading example for other urban agglomerations.

Abandoned mines are typical areas of soil erosion. Landscape transformation of abandoned mines is an important means to balance the dual objectives of regional ecological restoration and industrial heritage protection, but the secondary development and construction process of mining relics require long-term monitoring with objective scientific indicators and effective assessment of their management effectiveness. This paper takes Tongluo Mountain Mining Park in Chongqing as an example and uses a remote sensing ecological index (RSEI) based on Landsat-8 image data to assess the spatial and temporal differences in the dynamic changes in the ecological and environmental quality of tertiary relic reserves with different degrees of development and protection in the park. Results showed that: ① The effect of vegetation cover, which can significantly improve soil and water conservation capacity. ② The RSEI is applicable to the evaluation of the effectiveness of ecological management of mines with a large amount of bare soil areas. ③ The mean value of the RSEI in the region as a whole increased by 0.090, and the mean values of the RSEI in the primary, secondary and tertiary relic reserves increased by 0.121, 0.112 and 0.006, respectively. ④ The increase in the RSEI in the study area is mainly related to the significant decrease in the dryness index (NDBSI) and the increase in the humidity index (WET). The remote sensing ecological index can objectively reflect the difference in the spatial and temporal dynamics of the ecological environment in tertiary relic protection, and this study provides a theoretical reference for the ecological assessment of secondary development-based management under difficult site conditions.

In order to meet the requirements for comprehensive and multidimensional generalization of ecological management effectiveness evaluation indexes in the context of ecological restoration advocating comprehensive management by multiple means, this paper explores the rationality of using RSEI as an ecological management effectiveness evaluation index to adapt to the systematic transformation of the management goal of abandoned mine restoration from ecological restoration to regional socioeconomic sustainable development. Based on Landsat-8 image data, the remote sensing ecological index (RSEI) was used to evaluate the dynamic changes and spatial and temporal differences of the ecological environment in the study area under the long-term multimeans comprehensive management. The RSEI is suitable for evaluating the effectiveness of comprehensive ecological management in mining areas with a large amount of bare soil. The regional RSEI mean value increased by 0.029 in the early stage and 0.051 in the later stage by fragmentation management, indicating a better effect of multimeans comprehensive management. The remote sensing ecological index can objectively reflect the difference of spatial distribution characteristics of ecological environment in the four “Ecological+” governance regions. It can both objectively reflect the ecological status of the study area and reflect the differentiated spatial distribution characteristics of the ecological environment in different treatment areas, which is of long-term practical significance to the ecological construction of the study area. This study provides a theoretical reference for ecological assessment of complex situation under difficult site conditions.

Since 2013, China has implemented a series of strict Air Pollution Control Strategies (APCS) to mitigate environmental and health risks associated with ambient fine particulate matter (PM_2.5). However, while APCS sets clear targets for PM_2.5 concentration, it lacks quantitative control over O₃ levels. Most existing studies have focused on nation-wide health assessments. Therefore, by conducting a coupled framework using health assessment and decomposition method, the spatiotemporal variation in deaths attributable to PM_2.5 pollution, as well as the role of APCS and the synergies between PM_2.5 and O₃ on PM_2.5 concentration and health impacts in the Beijing-Tianjin-Hebei (BTH) region have been explored. The result showed that: (1) PM_2.5 concentration in the BTH region decreased by 68.2%, with a reduction of 45,833 (95% Confidence Interval [CI]: 33,808, 50,069) deaths over the period. However, both concentrations and mortality remained high, indicating a need for faster reductions. (2) End-of-pipe control contributed the most to reducing PM_2.5 concentrations and deaths, though the gaps between source control and end-of-pipe control is narrowing. (3) The synergistic effects of O₃ and PM_2.5 in reducing concentration and mortality have increased, becoming a significant driver of PM_2.5-related health impacts. Our study emphasizes the future importance of implementing refined, diverse emission reduction measures and coordinating efforts to reduce both O₃ and PM_2.5 emissions, which are crucial for achieving the Sustainable Development Goals (SDGs) and advancing the "Beautiful China" and "Healthy China" initiatives.

In urban ecological development, the effective planning and design of living spaces are crucial. Traditional color plan rendering methods, mainly using generative adversarial networks (GANs), rely heavily on edge extraction. This often leads to the loss of important details from hand-drawn drafts, significantly affecting the portrayal of the designer’s key concepts. This issue is especially critical in complex park planning. To address this, our study introduces a system based on conditional GANs. This system rapidly converts black-and-white park sketches into comprehensive color designs. We also employ a data augmentation strategy to enhance the quality of the output. The research reveals: (1) Our model efficiently produces designs suitable for industrial applications. (2) The GAN-based data augmentation improves the data volume, leading to enhanced rendering effects. (3) Our unique approach of direct rendering from sketches offers a novel method in urban planning and design. This study aims to enhance the rendering aspect of an intelligent workflow for landscape design. More efficient rendering techniques will reduce the iteration time of early design solutions and promote the iterative speed of designers’ thinking, thus improving the speed and efficiency of the whole design process.