Urban green space (UGS) constitutes critical ecological infrastructure for climate adaptation and sustainable urban transitions. This review synthesizes the conceptual evolution of UGS, elucidating the coupled dynamics driven by anthropogenic interventions and climatic forces. We highlight that UGS has evolved from spontaneous vegetation to systematically planned infrastructure, serving dual cultural and ecological functions. While human drivers—spanning policy frameworks, species selection, and maintenance regimes—dictate the spatial morphology of UGS, climatic conditions and extreme weather events modulate vegetation resilience and performance, creating distinct bioclimatic patterns, particularly within Chinese cities. Collectively, these forces govern the structural integrity and ecosystem performance of UGS. Methodologically, this study combines a bibliometric analysis of Web of Science publications from 2000 to 2025 with a PRISMA-based systematic literature review and a semi-quantitative synthesis of recent empirical studies. The bibliometric analysis provides a global overview of research hotspots and thematic evolution in UGS research, while the in-depth synthesis and factor prioritization primarily focus on China-based studies published between 2021 and 2025. By integrating evidence on both human activities and climatic factors, this review clarifies the dominant driving mechanisms shaping UGS under rapid urbanization and climate change, while situating China-specific findings within the broader international literature. Although UGS delivers well-documented benefits for microclimate regulation and social well-being, accelerating urbanization and increasing climate complexity pressures indicate that existing management approaches could be further enhanced to meet emerging demands. Consequently, future UGS development should shift from quantitative expansion to qualitative optimization and spatial equity. We propose a research agenda prioritizing cross-climate comparative frameworks, smart maintenance technologies, and inclusive governance to bolster UGS resilience, thereby advancing long-term sustainable development goals.
Accurate forecasting of urban water demand is essential for scientific regulation and sustainable management of water resources, particularly in complex DMA (District Metered Area) environments. This study proposes an integrated regional water demand prediction framework that combines CEEMDAN decomposition with deep learning techniques. CEEMDAN is first applied to decompose the original water demand time series into multiple Intrinsic Mode Functions (IMFs), effectively extracting multi-scale features and mitigating non-stationarity and complexity. A hybrid Transformer-BiLSTM model is then constructed to capture global dependencies, nonlinear dynamics, and bidirectional temporal features. Experimental results demonstrate that the proposed CEEMDAN-Transformer-BiLSTM model significantly outperforms various benchmark models in terms of prediction accuracy, robustness, and generalization across different DMAs. This research provides a new perspective for modeling complex water resource time series and offers theoretical and practical support for optimizing urban water allocation and achieving sustainable management, while laying a foundation for future work involving external driving factors, enhanced model interpretability, and dynamic regulation mechanisms.