The recent publications in the field of urban and environmental planning highlight a significant shift towards integrating advanced computational methods with traditional planning practices to address complex urban challenges. A notable trend is the application of graph neural networks (GNNs) and machine learning techniques to enhance the accuracy and equity of environmental predictions, such as water temperature and heavy rainfall, which are crucial for sustainable urban development and disaster preparedness. Additionally, there is a growing emphasis on developing hybrid frameworks that combine top-down and bottom-up approaches for more nuanced urban planning, ensuring that both city-wide infrastructure needs and localized demographic preferences are met. Another innovative direction is the use of graph structure learning and motif-enhanced graph prototype learning to better understand and mitigate urban social segregation, offering new insights into the complex interplay between urban spaces and resident interactions. These advancements underscore the field's move towards more adaptive, equitable, and sustainable urban planning solutions.

Noteworthy Papers

• Adaptive Urban Planning: A Hybrid Framework for Balanced City Development: Introduces a two-tier approach combining deterministic optimization with demographic-specific modifications for cohesive urban development.
• Bi-directional Mapping of Morphology Metrics and 3D City Blocks for Enhanced Characterization and Generation of Urban Form: Proposes a methodology for bi-directional mapping between morphology metrics and urban forms, facilitating sustainable urban design.
• Physics-Guided Fair Graph Sampling for Water Temperature Prediction in River Networks: Develops a GNN-based method that leverages physical knowledge to reduce model bias in water temperature predictions.
• Graph Learning-based Regional Heavy Rainfall Prediction Using Low-Cost Rain Gauges: Presents a low-cost IoT system and GNN approach for effective heavy rainfall prediction in resource-limited regions.
• Active Geospatial Search for Efficient Tenant Eviction Outreach: Introduces a hierarchical reinforcement learning approach for identifying at-risk tenants in large urban areas.
• MotifGPL: Motif-Enhanced Graph Prototype Learning for Deciphering Urban Social Segregation: Offers a framework for analyzing urban social segregation through motif-enhanced graph prototype learning.
• Graph Structure Learning for Spatial-Temporal Imputation: Adapting to Node and Feature Scales: Introduces a multi-scale graph structure learning framework for improved spatial-temporal data imputation.