Urban flooding presents acute challenges in heritage cities, where dense populations and valuable cultural assets coexist. While Nature-Based Solutions (NbSs) have been widely studied, their implementation in heritage cities remains underexplored due to spatial constraints and cultural sensitivities. This study develops a quantitative evaluative framework integrating the Spatial Multi-Criteria Evaluation (SMCE) and NbSs to address urban flooding in Quanzhou, a UNESCO World Heritage site. In GIS-based spatial analysis, the framework prioritizes high-risk zones by synthesizing hydrological and socio-economic factors. The analysis reveals that the Surface Runoff Coefficient (SRC) contributes 30% to urban flooding exposure, with high building congestion and elevated PM2.5 levels exacerbating risks by 17% and 16.8%, respectively. Vulnerability mapping underscores the critical role of cultural heritage, accounting for 71.1% of the vulnerability index, and highlights priority townships such as Linjiang, Kaiyuan, and Lizhong, with integrated exposure and vulnerability rates of 11.8%, 10.3%, and 9.5%, respectively. This study proposes four NbS models tailored to heritage urban landscapes, with Solution I—direct surface infiltration—identified as the most applicable, covering 170.9 ha, followed by Solution II—subterranean stormwater infiltration—at 52.3 ha. Despite limited spatial feasibility (1.3–33.5% of township areas), the framework demonstrates significant potential for integrating NbSs with existing grey infrastructure, contributing to flood risk mitigation and broader sustainability goals. The findings provide actionable insights for urban planners and policymakers, offering a replicable methodology for the deployment of NbSs in heritage-rich urban contexts worldwide. By bridging flood risk management with cultural preservation, this work advances the discourse on resilient and sustainable urban planning.

This paper explores the integration of ecological sustainability, human-centered design, and advanced computational techniques, with a particular focus on the use of Long Short-Term Memory (LSTM), Recurrent Neural Networks (RNNs), and Deep Recurrent Neural Networks (DRNNs) in urban landscape planning and rural landscape restoration. DRNNs, an advanced extension of traditional RNNs, are specifically designed to capture complex temporal dependencies in sequential data through deeper network architectures. These models are particularly effective in identifying intricate patterns in time-series data, making them well-suited for dynamic processes in landscape planning and ecological analysis. The study highlights the significance of applying ecological principles to urban design, aiming to create spaces that are not only visually appealing but also environmentally harmonious and socially inclusive. Additionally, the research investigates the role of installation art in public urban spaces, emphasizing its potential to foster community interaction, raise environmental awareness, and promote sustainability. By integrating data-driven approaches, such as LSTM-based lithology identification and DRNN-based ecological forecasting, the paper illustrates how advanced algorithms can optimize landscape features, predict ecological trends, and guide more informed planning decisions. Ultimately, this research underscores the need for a holistic and sustainable approach in urban landscape design that balances environmental, social, and technological dimensions, ensuring a harmonious coexistence between people and their environments.

Whether the leaf economics spectrum (LES) and its trait correlations operate at the intraspecific level, and how light versus soil nutrients are associated with leaf traits, remain unclear in stress-tolerant island plants. We quantified leaf morphological, anatomical, and LES traits of Eurya emarginata across four island populations and evaluated their associations with field-measured light availability (canopy density) and soil conditions; a shading experiment was used to test light-driven plasticity directly. Across field populations, leaf anatomical traits showed greater variability than LES traits (Kruskal–Wallis, p = 0.001). Most leaf trait pairs were correlated at the metapopulation level, whereas within local island populations many of these correlations became non-significant; this pattern may reflect smaller sample sizes and narrower trait ranges within islands as well as possible biological decoupling. Redundancy analysis indicated that canopy density was the main variable associated with leaf morphological and anatomical trait variation, whereas soil nutrients were the main variables associated with LES trait variation. The shading experiment confirmed that reduced light availability altered structural and photosynthetic traits. Our results show that light and soil conditions are associated with different trait groups, and that trait associations are scale-dependent. We conclude that intraspecific leaf trait variation in island populations is context-dependent, with anatomical traits varying more than LES traits, and that trait correlations observed at broad scales are not necessarily maintained within local populations.