Zahratu Shabrina

Despite the growing expansion of short-term rentals, the existing literature remains strongly focused on metropolitan areas, with much less attention paid to how these dynamics play out in non-metropolitan regions. Using monthly listing-level data for Cornwall, United Kingdom, from 2016 to 2025, our paper combines time-series analysis, including 12-month moving averages and STL decomposition, with spatial techniques such as Moran's I and Getis-Ord Gi*, to construct temporal and spatial analysis of the Airbnb market in Cornwall region. In addition, we develop an Airbnb Pressure and Professionalisation Index (APPI) as a tool for an evidence-based approach to shortterm rental regulation. The results show that Cornwall's STR market is neither a marginal extension of tourism accommodation nor a dispersed peer-to-peer system. Rather, it is a dynamic platform market that expands and contracts seasonally, survives major shocks, concentrates in coastal hotspots and is increasingly shaped by multi-properties operators. Our argument is that regulatory debates have often been framed as a binary choice between night caps and area-based restrictions. However, the short-term rental phenomenon is far more complex than this opposition implies, and therefore its regulation requires more technically grounded tools capable of capturing its spatial, temporal, and professional dimensions. Overall, our paper advances a more "measured" approach to regulation able to capture the multidimensional nature of short-term rental pressure.

Urban flooding driven by climate change, rapid urbanisation, and land subsidence poses a severe threat to sinking coastal megacities such as Jakarta. Jakarta is exposed to interacting tidal, fluvial, and pluvial processes, but these processes are not experienced as isolated flood types. This paper therefore compares two analytical dimensions of flood exposure: routine cumulative exposure and extreme-event shock exposure. Flood susceptibility is defined as the relative spatial propensity of each grid cell to experience inundation, derived from observed flood frequency, inundation depth, inundated area, and event intensity rather than from monetary loss or social vulnerability alone. Using Sentinel-1 SAR data and ground-based water-level monitoring, we construct a composite Flood Susceptibility Index for 6,623 spatial grids and apply a LightGBM-based machine-learning framework to simulate the marginal effects of land subsidence, nature-based solutions (NBS), drainage enhancement, and urban densification. The results show that routine waterlogging is concentrated in low-lying northern coastal zones, whereas extreme events expand along major river corridors and form dual-exposure hotspots, especially around the Ciliwung basin. Flood burden is highly unequal, with about 20% of high-susceptibility areas accounting for nearly 50% of cumulative flood impacts. Scenario simulations further show that accelerated subsidence and high-density urban expansion increase long-tail susceptibility, while NBS mainly reduces routine and moderate susceptibility and drainage enhancement most directly truncates extreme-event tail risk in dense urban cores. These findings suggest that strengthening flood resilience in Jakarta requires spatially differentiated green-blue-grey flood-management strategies rather than a single citywide intervention pathway.

Understanding how large-scale transport infrastructure shapes mobility patterns and the spatial structure is essential for assessing the impacts of urban development and policy. However, it is a challenging task given the dynamic nature of urban processes, and it is even more so in a megacity context. This study proposes a simulation-based framework that combines travel behaviour modelling with functional zone delineation to assess the impacts of infrastructure development. The framework builds on a two-step spatial interaction model in which localised distance-decay parameters are estimated for socioeconomically differentiated area clusters. Predicted flows from the spatial interaction model, incorporating projected population and updated travel time, are fed into a regionalisation algorithm that delineates urban functional zones. We illustrated the framework through a case study of the Shenzhen–Dongguan–Huizhou–Zhongshan region, simulating the opening of the Shenzhen–Zhongshan Bridge in the China Bay Area. Results demonstrated substantial reductions in cross-estuary travel impedance and a reconfiguration of functional boundaries, with parts of Zhongshan becoming functionally integrated into Shenzhen. However, average travel distances increase as greater accessibility enables longer-distance commuting, which is a counterintuitive yet insightful observation. Overall, the proposed framework has been shown to be a scalable instrument for linking behavioural heterogeneity, infrastructure modifications, and the emergent urban spatial structure within rapidly integrating mega-city regions.

Airbnb adoption is growing in Indonesian cities, yet little is known about how its spatial dynamics intersect with urban features and tourism economies in cities of the Global South. This study presents a systematic spatial analysis of Airbnb performance in Indonesia, with a focus on Jakarta and Bandung. Using detailed performance data from AirDNA, we employ spatial autocorrelation and spatial regression models, specifically the Spatial Lag Model (SLM) and Spatial Error Model (SEM), to investigate the potential impact of urban amenities on Airbnb revenue. Our findings reveal distinct city-specific dynamics: in Bandung, Airbnb revenue is positively associated with the presence of restaurants and hotels but negatively correlated with concentrated commercial centres such as shopping malls, reflecting the city’s culinary-driven tourism economy. In contrast, in Jakarta, Airbnb revenue is strongly linked to shopping centres and restaurants, while hotels show no significant influence, suggesting Airbnb operates within differentiated market niches. These results underscore the critical role of local context and associated development policies in shaping platform economies, demonstrating that Airbnb’s performance cannot be generalised across cities, even within the same country. By highlighting the association between spatial factors and short-term rental markets in Indonesia, this paper contributes to the broader debate on sustainable tourism and platform urbanism in the Global South.

This paper aims at improving predictive crime models by extending the mathematical framework of Artificial Neural Networks (ANNs) tailored to general spatiotemporal problems and appropriately applying them. Recent advancements in the geospatial-temporal modelling field have focused on the inclusion of geographical weighting in their deep learning models to account for nonspatial stationarity, which is often apparent in spatial data. We formulate a novel semi-analytical approach to solving Geographically and Temporally Weighted Regression (GTWR), and applying it to London crime data. The results produce high-accuracy predictive evaluation scores that affirm the validity of the assumptions and approximations in the approach. This paper presents mathematical advances to the Geographically and Temporally Weighted Neural Network (GTWNN) framework, which offers a novel contribution to the field. Insights from past literature are harmoniously employed with the assumptions and approximations to generate three mathematical extensions to GTWNN's framework. Combinations of these extensions produce five novel ANNs, applied to the London and Detroit datasets. The results suggest that one of the extensions is redundant and is generally surpassed by another extension, which we term the history-dependent module. The remaining extensions form three novel ANN designs that pose potential GTWNN improvements. We evaluated the efficacy of various models in both the London and Detroit crime datasets, highlighting the importance of accounting for specific geographic and temporal characteristics when selecting modelling strategies to improve model suitability. In general, the proposed methods provide the foundations for a more context-aware, accurate, and robust ANN approach in spatio-temporal modelling.

This study employs percolation theory to investigate the hierarchical organisation of Australian urban centres through the connectivity of their road networks. The analysis demonstrates how discrete urban clusters have developed into integrated regional entities, delineating the pivotal distance thresholds that regulate these urban transitions. The study reveals the interconnections between disparate urban clusters, shaped by their functional differentiation and historical development. Furthermore, the study identifies a dichotomy of urban agglomeration forces and a persistent spatial disconnection between Australia’s wider urban landscape. This highlights the interplay between urban densification and peripheral growth. It suggests the need for new thinking on potential integrated governance structures that bridge urban development with broader social and economic policies across regional and national scales. Additionally, the study emphasises the growing importance of national coordination in Australian urban development planning to ensure regional consistency, equity, and productivity.

Caitlin and Michele walk the city in an experimental six-legged stroll with both Zara Shabrina and Mike Batty, debating the challenges of platforms in cities and the limits of urban prediction, along with the story of AirBnB.

This study employs percolation theory to investigate the hierarchical organisation of Australian urban centres through the connectivity of their road networks. The analysis demonstrates how discrete urban clusters have developed into integrated regional entities, delineating the pivotal distance thresholds that regulate these urban transitions. The study reveals the interconnections between disparate urban clusters, shaped by their functional differentiation and historical development. Furthermore, the study identifies a dichotomy of urban agglomeration forces and a persistent spatial disconnection between Australia's wider urban landscape. This highlights the interplay between urban densification and peripheral growth. It suggests the need for new thinking on potential integrated governance structures that bridge urban development with broader social and economic policies across regional and national scales. Additionally, the study emphasises the growing importance of national coordination in Australian urban development planning to ensure regional consistency, equity, and productivity.