The advent of Large Language Models (LLMs) holds promise for revolutionizing various fields traditionally dominated by human expertise. Urban planning, a professional discipline that fundamentally shapes our daily surroundings, is one such field heavily relying on multifaceted domain knowledge and experience of human experts. The extent to which LLMs can assist human practitioners in urban planning remains largely unexplored. In this paper, we introduce a comprehensive benchmark, UrbanPlanBench, tailored to evaluate the efficacy of LLMs in urban planning, which encompasses fundamental principles, professional knowledge, and management and regulations, aligning closely with the qualifications expected of human planners. Through extensive evaluation, we reveal a significant imbalance in the acquisition of planning knowledge among LLMs, with even the most proficient models falling short of meeting professional standards. For instance, we observe that 70% of LLMs achieve subpar performance in understanding planning regulations compared to other aspects. Besides the benchmark, we present the largest-ever supervised fine-tuning (SFT) dataset, UrbanPlanText, comprising over 30,000 instruction pairs sourced from urban planning exams and textbooks. Our findings demonstrate that fine-tuned models exhibit enhanced performance in memorization tests and comprehension of urban planning knowledge, while there exists significant room for improvement, particularly in tasks requiring domain-specific terminology and reasoning. By making our benchmark, dataset, and associated evaluation and fine-tuning toolsets publicly available at https://github.com/tsinghua-fib-lab/PlanBench, we aim to catalyze the integration of LLMs into practical urban planning, fostering a symbiotic collaboration between human expertise and machine intelligence.
Urban analytics increasingly relies on AI-driven trajectory analysis, yet current approaches suffer from methodological fragmentation: trajectory learning captures movement patterns but ignores spatial context, while spatial embedding methods encode street networks but miss temporal dynamics. Three gaps persist: (1) lack of joint training that integrates spatial and temporal representations, (2) origin-agnostic treatment that ignores directional asymmetries in navigation ($A \to B \ne B \to A$), and (3) over-reliance on auxiliary data (POIs, imagery) rather than fundamental geometric properties of urban space. We introduce a conditional trajectory encoder that jointly learns spatial and movement representations while preserving origin-dependent asymmetries using geometric features. This framework decomposes urban navigation into shared cognitive patterns and origin-specific spatial narratives, enabling quantitative measurement of cognitive asymmetries across starting locations. Our bidirectional LSTM processes visibility ratio and curvature features conditioned on learnable origin embeddings, decomposing representations into shared urban patterns and origin-specific signatures through contrastive learning. Results from six synthetic cities and real-world validation on Beijing's Xicheng District demonstrate that urban morphology creates systematic cognitive inequalities. This provides urban planners quantitative tools for assessing experiential equity, offers architects insights into layout decisions' cognitive impacts, and enables origin-aware analytics for navigation systems.
The early detection and prediction of health status decline among the elderly at the neighborhood level are of great significance for urban planning and public health policymaking. While existing studies affirm the connection between living environments and health outcomes, most rely on single data modalities or simplistic feature concatenation of multi-modal information, limiting their ability to comprehensively profile the health-oriented urban environments. To fill this gap, we propose CureGraph, a contrastive multi-modal representation learning framework for urban health prediction that employs graph-based techniques to infer the prevalence of common chronic diseases among the elderly within the urban living circles of each neighborhood. CureGraph leverages rich multi-modal information, including photos and textual reviews of residential areas and their surrounding points of interest, to generate urban neighborhood embeddings. By integrating pre-trained visual and textual encoders with graph modeling techniques, CureGraph captures cross-modal spatial dependencies, offering a comprehensive understanding of urban environments tailored to elderly health considerations. Extensive experiments on real-world datasets demonstrate that CureGraph improves the best baseline by $28\%$ on average in terms of $R^2$ across elderly disease risk prediction tasks. Moreover, the model enables the identification of stage-wise chronic disease progression and supports comparative public health analysis across neighborhoods, offering actionable insights for sustainable urban development and enhanced quality of life. The code is publicly available at https://github.com/jinlin2021/CureGraph.
Traditional agent-based urban mobility simulations often rely on rigid rulebased systems that struggle to capture the complexity, adaptability, and behavioral diversity inherent in human travel decision making. Inspired by recent advancements in large language models and AI agent technologies, we introduce GATSim, a novel framework that leverages these advancements to simulate urban mobility using generative agents with dedicated cognitive structures. GATSim agents are characterized by diverse socioeconomic profiles, individual lifestyles, and evolving preferences shaped through psychologically informed memory systems and lifelong learning. The main contributions of this work are: 1) a comprehensive architecture that integrates urban mobility foundation model with agent cognitive systems and transport simulation environment; 2) a hierarchical memory designed for efficient retrieval of contextually relevant information, incorporating spatial and temporal associations; 3) planning and reactive mechanisms for modeling adaptive mobility behaviors which integrate a multi-scale reflection process to transform specific travel experiences into generalized behavioral insights. Experiments indicate that generative agents perform competitively with human annotators in role-playing scenarios, while naturally producing realistic macroscopic traffic patterns. The code for the prototype implementation is publicly available at https://github.com/qiliuchn/gatsim.
Urban Air Mobility (UAM) offers a transformative approach to addressing urban congestion, improving accessibility, and advancing environmental sustainability. Rapid progress has emerged in three tightly linked domains since 2020: (1) Communication, where dynamic spectrum allocation and low-altitude channel characterization support reliable air-ground data exchange; (2) UAM management, with novel air-traffic control concepts for dense, largely autonomous urban airspace; and (3) Sustainability, driven by energy-efficient propulsion, integrated charging infrastructure, and holistic environmental assessment. This paper reviews and synthesizes the latest research across these areas, compares the state-of-the-art solutions, and outlines the technological and infrastructural milestones that are critical to realizing a scalable, sustainable UAM ecosystem.
Participation in urban planning is championed for entrenching democracy and development. Malawi passed the Local Government Act (1998) and Decentralization Policy (1998) to facilitate community participation in decision-making processes. Several studies have been conducted on decentralization and local governance on community participation. Little attention has been paid to examining the impact of the language used in planning processes on democracy and inclusivity envisaged in the law and policy. Using communicative action theory, the study examined challenges posed by language used in planning processes on inclusivity in the approval processes of urban plans. Data were collected through semi-structured interviews, focus group discussions, observations and document review and analyzed using thematic and discourse analysis. The findings show that while there is high participation at community planning levels, because planners communicate using local languages, participation is compromised in the service committees at city level where final planning decisions are made due to language barrier. Specifically, lack of sincerity, truthfulness, comprehensibility and therefore legitimacy are apparent. Planners are reluctant to simplify written language and translate planning jargon into local languages for councillors to understand. The study concludes that community participation in the urban planning process in Mzuzu fails to entrench democracy due to lack of inclusiveness owing to the language barrier at city level where final planning decisions are made. The study proposes a framework for inclusive participation in urban planning including the motivation, conditions for effective participation and outcomes of participation.
Temitope Abigail Adeniji, Martin Binde Gasu, Samuel Kayode Julius
Residents' active participation is crucial in influencing the transformation of inner-city slums, especially in fast-growing cities like Ibadan. Recognizing this role is crucial for developing inclusive planning strategies that effectively address the actual needs of the urban poor. This research examined the impact of community involvement on urban changes in Ibadan’s core areas, Oyo State, Nigeria, from 1990 to 2020. A structured survey of 552 residents from selected slum communities measured their participation in city transformation efforts, focusing on social and environmental improvements, resource allocation, the effectiveness of interventions, and challenges to slum redevelopment. Analysis using the Social Sciences Statistical Package (SPSS) showed that residents’ participation had limited influence on revitalizing Ibadan’s inner-city slums. The primary participation methods were consultations (35.7%) and incentives, such as gifts (27.2%). Despite efforts to involve communities in planning, major obstacles persisted, including corruption, bureaucratic delays, political interference, mismanagement of funds, limited capacity, poor coordination, delays, and insufficient funding (30%) of urban renewal funds were reportedly misused. Persistent challenges such as degraded infrastructure, poor socio- environmental conditions, and ineffective transformative initiatives remain prevalent, with a Slum Deprivation Index (SDI) indicating high levels of residential and environmental deprivation (RED) and water, sanitation, and hygiene (WASH) deprivation across the study areas. The study concludes that comprehensive and inclusive participation is essential for sustainable urban development. It contributes to ongoing discourse on the effectiveness of spatially and politically driven participatory approaches in urban settings, advocating for policies that prioritize periodic urban renewal and robust community involvement.
با توجه به اهمیت و ضرورت مشارکت عمومی در نظام سلامت بهمنظور افزایش مطلوبیت دسترسی، اثربخشی و عادلانهبودن سیاستهای آن، مطالعۀ حاضر به تحلیل عملکرد کانونهای مردمی سلامت در نظام سلامت شهر تهران میپردازد.این تحقیق به روش کیفی و مصاحبه با 35 نفر از متولیان امر سلامت و کانونهای مردمی سلامت در شهرداری تهران انجام شده است.یافتهها نشان داد کانونها گرچه بنا به دو الزام مشارکت مردمی در سیاستگذاری نظام سلامت و تقویت سرمایۀ اجتماعی در محلهها شکل گرفتند، اما همچنان بخشی از دستگاه بوروکراتیک شهرداری تهران هستند و مختصات مردمی و محلیبودن درمورد آنها کمتر مشاهده میشود. از حیث عملکردی، روایت عملکرد کانونها، روایتی بر ناکامی آنها در برآوردن انتظارات و رسالت تعیینشده است. گرچه عملکرد آنها در ابتدای شکلگیری در دورۀ مدیریت وقت شهرداری که ایدۀ آن با هدف تبدیل شهرداری به یک نهاد اجتماعی مطرح شد بهتر بود، اما در دورههای بعدی این عملکرد رو به ضعف گذاشت. درنهایت اینکه کانونها از زمان آغاز فعالیت تاکنون با پنج دسته مشکل اقتصادی و مالی، اجتماعی و فرهنگی، مدیریتی و اجرایی، فیزیکی و تجهیزاتی، و حقوقی و قانونی مواجه بودند.با استناد به خوانشهای نظری و پیشینۀ تجربی، یافتههای تحقیق حکایت از نامردمیبودن، ریسک ناپایداری، ناکارآمدی و مشارکت حداقلی در رابطه با وضعیت و عملکرد کانونهای سلامت دارد که این وضعیت مانع تحقق ایدۀ کانونهای سلامت بهعنوان یکی از ابزارهای اجتماعیشدن نظام سلامت در محلهها شده است.
Urban areas in semi-arid regions face rising thermal stress and carbon emissions due to rapid densification and scarce vegetation. This study evaluates the effectiveness of green infrastructure (GI) in mitigating these challenges in District one of Karaj, Iran, within a zero-carbon city framework. To address limited evidence on microscale modeling in arid contexts, satellite-based time series analysis was combined with ENVI-met simulations. Environmental indicators including CO (Sentinel-5P) as a proxy for CO₂, Land Surface Temperature (LST, Landsat-8), and vegetation cover (NDVI, MODIS) were extracted via Google Earth Engine for October 2024 to March 2025. Two scenarios were examined: Scenario A as current conditions, and Scenario B with green roofs, vegetated walls, moss, and microalgae panels. Scenario B achieved a 4.6% reduction in CO₂, from 441.8 to 421.4 ppm, an NDVI increase of 0.17 (0.21 to 0.38), and a district-wide temperature decrease of 4.1 °C. Calibration yielded a root mean square error of 1.7 °C for temperature and ±6.3 ppm for CO₂. These interventions improve environmental performance and socio-economic resilience through public health gains, lower energy costs, and equitable green access. Findings highlight hybrid greening strategies as effective for advancing climate resilience and provide a replicable model for zero-carbon interventions in semi-arid cities.
Abstract Reading urban form is essential for establishing a cultural relationship with the site’s history, memory and future writings. As Chinese historic sites are generally considered the loci of a despatialised textual memory lacking physical substance, the condition of latency and disappearance together with an overestimation of intangible values too often open the path to unjustified erasures, substitutions and re-historicisation through replicas. Yet, by understanding the place not only through what is today detectable by the eye but rather as a historically layered and culturally defined context, we can inaugurate a methodology to decode the site as an “already-written” text that requires interpretation and guides future writing. The Nanshijie site in Ganzhou Historic City is a paradigmatic urban text that has become unreadable. Through the reading of morphology and building types combined with the hermeneutic work of decoding traces and absences, the research revealed the latent urban form in three structuring components and “Latent Structures” that still inform the site’s readability and potential rewritability. The cognition and interaction between these essential components should be the starting point for defining the “city part” and its conservation boundaries, that is, integrating preservation, regeneration and design approaches into one co-evolutionary rewriting of urban form.
Urban flow prediction is a spatio-temporal modeling task that estimates the throughput of transportation services like buses, taxis, and ride-sharing, where data-driven models have become the most popular solution in the past decade. Meanwhile, the implicitly learned mapping between historical observations to the prediction targets tend to over-simplify the dynamics of real-world urban flows, leading to suboptimal predictions. Some recent spatio-temporal prediction solutions bring remedies with the notion of physics-guided machine learning (PGML), which describes spatio-temporal data with nuanced and principled physics laws, thus enhancing both the prediction accuracy and interpretability. However, these spatio-temporal PGML methods are built upon a strong assumption that the observed data fully conforms to the differential equations that define the physical system, which can quickly become ill-posed in urban flow prediction tasks. The observed urban flow data, especially when sliced into time-dependent snapshots to facilitate predictions, is typically incomplete and sparse, and prone to inherent noise incurred in the collection process. As a result, such physical inconsistency between the data and PGML model significantly limits the predictive power and robustness of the solution. Moreover, due to the interval-based predictions and intermittent nature of data filing in many transportation services, the instantaneous dynamics of urban flows can hardly be captured, rendering differential equation-based continuous modeling a loose fit for this setting. To overcome the challenges, we develop a discretized physics-guided network (PN), and propose a data-aware framework Physics-guided Active Sample Reweighting (P-GASR) to enhance PN. Experimental results in four real-world datasets demonstrate that our method achieves state-of-the-art performance with a demonstrable improvement in robustness.
Abstract This research examines the evolution and renewal of Shanghai’s Huangpu River industrial zone after the 2010 Shanghai Expo, with a temporal focus on the profound changes and development philosophies driven by this mega-event. By investigating emblematic case studies along the Huangpu River, such as the transformative 80,000-ton silo, the Shanghai Museum of Contemporary Art, and the Long Museum, this research articulates how mega-events serve as pivotal moments for reimagining and repurposing industrial heritage. In the wake of the 2010 Shanghai Expo, these industrial relics emerged as focal points of urban regeneration, embodying the tensions and synergies between historical preservation and contemporary urban development. This study explores the temporal layers—from the event’s catalytic role to enduring legacies—and reveals how time influences the trajectory of urban spaces and the community’s connection to them. Through this temporal lens, the paper analyses the redevelopment process, assessing how these initiatives have reconfigured the industrial waterfront into a dynamic cultural landscape. The findings offer a dynamic perspective on the temporal dimensions that underpin the redevelopment of industrial heritage sites, providing insights into how such spaces can be continuously activated and symbiotically integrated into the fabric of the city. This paper aims to contribute to a broader understanding of the complexities involved in harnessing industrial heritage for mega-events, with implications for future urban planning and heritage conservation strategies.
رقیه قنبری قادیکلایی, محمود ضیائی, وجه الله قربانی زاده
et al.
تعارض مسئله مبتلابه مناطق حفاظتشده در ایران است و فائق آمدن بر آن چالشی بزرگ برای برنامه ریزان است. توسعه گردشگری میتواند یکی از عوامل اصلی تشدید این تعارضات باشد. ازاینرو هدف این مقاله شناسایی ویژگیها و دلایل بروز تعارضات ناشی از توسعه گردشگری در مناطق حفاظتشده بهخصوص تالاب میانکاله در ایران و همچنین شناسایی شیوههای فائق آمدن بر آنها است. بدین منظور یافتههای کیفی مطالعات پیشین با استفاده از روش فراترکیب مورد تجزیهوتحلیل قرار گرفتند. مقالات، کتب و رسالههای منتشرشده در پایگاههای مطالعاتی در بازه زمانی 2000 تا 2024 بر اساس روش نمونهگیری هدفمند انتخاب شدند. پس از تجزیهوتحلیل یافتهها، شبکه مضامین در سه بعد چیستی، چرایی و چگونگی مدیریت تعارض ارائه شد. بر اساس یافتهها، تعارض در مناطق حفاظتشده اغلب در سطح بین گروهی و بین سازمانی است. مهمترین دلایل بروز تعارض ارتباطات ضعیف و فقدان همکاری، بیعدالتی و سلطه قدرت، ساختار حکمرانی معیوب است. همچنین برای مدیریت تعارض نیاز به طی شش مرحله افزایش سرمایه اجتماعی، مصالحه و اجماع، کنش جمعی، هم تکاملی تدریجی و بهبود تعارض است. نتایج پژوهش حاضر علاوه بر اینکه به گسترش دایره شناختی شیوههای کاهش تعارض در گردشگری کمک خواهد کرد، میتواند مبنایی برای پژوهشهای آتی در این حوزه مطالعاتی باشد.
بستر قانونی مداخله در فرآیند تأمین مسکن مناسب در شهرهای کشور، طرحهای توسعه است که در مقیاسهای مختلف ( از سطح ملی تا محلی) باید بهطور سیستماتیک و یکپارچه سیاستهای تأمین مسکن مناسب را در خود جای دهند و از طریق حاکمیت قانون ، ضمانت اجرایی آن را تضمین نمایند. در این پژوهش سعی شده تا با استفاده از مرور روایی، چیستی و چگونگی ارتباط میان برنامهریزی و سیاستگذاری مسکن و طرحهای توسعه در پژوهشهای انجام شده در شهرهای ایران، مورد نقد و بررسی قرار گیرد. نتایج پس از بررسی 27 مقاله علمی- پژوهشی منتخب بیانگر آن است که در پژوهشهای انجام شده به ندرت درک درستی از مفهوم مسکن مناسب لحاظ شده است؛ روششناسی و شیوه سنجش صرفاً کمی و مبتنی بر نگاه تکنوکرات است و نمیتواند بیانگر وضعیت واقعی مسکن باشد؛ توجه به حیطه فضایی کلانشهرها به خصوص شهر تهران است و صرف توجه به ارتباط مسکن و طرحهای توسعه در یک دهه اخیر نشان از بی توجهی به سایر ابعاد فضایی و زمانی کشور است؛ و در نهایت عدم توجه به ساختارهای کلان تأثیرگذار بر امر مسکن از نگاه اقتصاد- سیاسی فضا در پژوهشها مشهود است.
This paper explores the meaning of home from multiple regions and the factors that influence the definition of home from multi-ethnic perspectives. A hypothesis derived that each ethnicity of a household practises cultural values and that reconfiguring physical spaces provides greater knowledge of their definition of home. This study employed a systematic review to gather the most relevant papers in the existing literature from the year 2000 to 2023, to address the gaps in knowledge in conceptualising the meaning of home in multi-ethnic settings. The findings respond to the hypothesis of this paper, that each household practises privacy and social boundaries in line with their belief systems and that reconfiguring physical space is part of homemaking tactics. This study outcome contributes to the development of a new conceptual framework that clarifies a comprehensive cause-effect relationship between key variables, ethnicity as the social aspect, built space as the physical aspect and practice as the personal or psychological aspect, resulting in a greater understanding of the meaning of home in multi-ethnic settings from three scenarios; the home as socio-spatial, psycho-spatial and emotive space entity.
Globally, cities have become hubs for economic activity, productivity, and important platforms for achieving sustainable development goals. The potential of urban agriculture (UA) in improving urban local economies and urban micro-climate has been acknowledged in the literature. The study looked at how the concepts of UA, local economic development (LED), and climate change can be treated in unison. Based on the review of credible published papers on the various concepts of UA, LED, climate change and nature-based solutions (NBS), a proposed conceptual framework was developed in this paper showing the linkages. The paper established that UA could boost LED, build resilient urban settlements, and promote social inclusiveness, but with social challenges. It is therefore recommended that policymakers make UA a crucial aspect of their agenda in the coming years to address the local economic and climate challenges now and in the future.
Giuliano Cornacchia, Matteo Böhm, Giovanni Mauro
et al.
Navigation apps use routing algorithms to suggest the best path to reach a user's desired destination. Although undoubtedly useful, navigation apps' impact on the urban environment (e.g., carbon dioxide emissions and population exposure to pollution) is still largely unclear. In this work, we design a simulation framework to assess the impact of routing algorithms on carbon dioxide emissions within an urban environment. Using APIs from TomTom and OpenStreetMap, we find that settings in which either all vehicles or none of them follow a navigation app's suggestion lead to the worst impact in terms of CO2 emissions. In contrast, when just a portion (around half) of vehicles follow these suggestions, and some degree of randomness is added to the remaining vehicles' paths, we observe a reduction in the overall CO2 emissions over the road network. Our work is a first step towards designing next-generation routing principles that may increase urban well-being while satisfying individual needs.
This paper explores the extension of the idea of allometric urban scaling law to study the scaling behaviour of Indian districts, with both the urban and rural population. To proceed, we have chosen districts (both rural and urban) of India, a relatively larger local administrative units, which are more or less independently functional within a country. This interdisciplinary work focus on the scaling analysis of various socio-economic indicators (SEIs) corresponding to the size (population) of four distinct urbanization classes, namely rural, semi-rural, semi-urban and urban districts. The scaling exponents were estimated for each classes for the years 2001 and 2011 along with their goodness-of-fit measured by the $R^2$ values. Our rigorous statistical analysis indicates that the scaling laws indeed exist even at the district level for most of the SEIs considered, related to education, employment, housing, health, etc.; the $R^2$ values obtained for these SEIs are very high (often greater than 0.8 or 0.9) in both the the years. Moreover, linearity of the scaling factors have been statistically tested and it has been found, at 95% level of confidence, that not all the SEIs behave linearly; some of them are characterized by super-linear behaviour and some behave sub-linearly. Statistical hypothesis tests have also been performed to test the equality of two scaling factors corresponding to two distinct classes and two different years to understand the differences in scaling relationships among increasing urbanisation classes and their changes over time.
Álvaro Martínez-Sánchez, Eneko Lazpita, Adrián Corrochano
et al.
Understanding flow structures in urban areas is widely recognized as a challenging concern due to its effect on urban development, air quality, and pollutant dispersion. In this study, state-of-the-art data-driven methods for modal analysis of simplified urban flows are used to study the dominant flow processes in these environments. Higher order dynamic mode decomposition (HODMD), a highly-efficient method to analyze turbulent flows, is used together with traditional techniques such as proper-orthogonal decomposition (POD) to analyze high-fidelity simulation data of a simplified urban environment. Furthermore, the spatio-temporal Koopman decomposition (STKD) will be applied to the temporal modes obtained with HODMD to perform spatial analysis. The flow interaction within the canopy influences the flow structures, particularly the arch vortex. The latter is a vortical structure generally found downstream of wall-mounted obstacles, which is generated as a consequence of flow separation. Therefore, the main objective of the present study is to characterize the mechanisms that promote these phenomena in urban areas with different geometries. Remarkably, among all the vortical structures identified by the HODMD algorithm, low- and high-frequency modes are classified according to their relation with the arch vortex. They are referred to as vortex-generator and vortex-breaker modes, respectively. This classification implies that one of the processes driving the formation and destruction of major vortical structures in between the buildings is the interaction between low- and high-frequency structures. The high energy revealed by the POD for the vortex-breaker modes points to this destruction process as the mechanism driving the flow dynamics.