
The increasing availability of pretrained Geospatial Artificial Intelligence (GeoAI) models has accelerated the operational adoption of deep learning within geographic information systems. However, models developed in one geographic region frequently experience performance degradation when deployed elsewhere because of geographic domain shift. Although transfer learning is widely used to improve cross-regional model performance, it remains unclear whether improved predictive accuracy alone provides sufficient evidence for trustworthy deployment. This study investigates this question using rooftop solar photovoltaic mapping in Brisbane, Australia, as an operational case study. Esri’s pretrained US Solar Panel Detection model was locally calibrated through transfer learning and evaluated using both development and independent local test datasets within Brisbane. Local calibration substantially improved detection performance, increasing recall from 38.5
Urban compactness and functional mixing are widely recognized as important carbon mitigation strategies. However, determining appropriate levels of compactness and functional mixing, and their potential carbon reductions, remains challenging due to nonlinear morphology–emission relationships and strong spatial dependence. This study develops a spatially explicit Bayesian optimization (SEBO) framework integrating spatial relationship analysis, nonlinear response-interval identification, and constrained configuration optimization. Using 4,347 grid cells in the Nanjing metropolitan region, spatial econometric models identify sector-specific morphology–emission associations and green-blue moderation effects. Tree-based machine learning then identifies responsive ranges for morphological adjustment, which constrain Bayesian optimization to explore lower-emission configurations and assess mitigation potential. Results reveal substantial sectoral differences in morphology–emission relationships and response intervals. Vertical intensity and functional mix are associated with transportation, residential, and power-related emissions, while horizontal density primarily relates to residential emissions. Optimizing vertical intensity yields average simulated reductions of 14.09
This study investigates the evolution of cognitive load in map navigation scenarios, a topic that carries key theoretical and practical value for optimizing map interface layouts and improving navigation visualization. This study adopts a map target search task as the experimental context and employs a 3 × 4 within-subjects design. Task performance, questionnaire scores, and multimodal physiological data (eye-tracking, photoplethysmography, and electrodermal activity) are simultaneously collected. This study applies two-factor repeated-measures ANOVA and linear mixed-effects model to systematically examine the effects of spatial complexity and target location distribution on extraneous map cognitive load. The results demonstrate that high spatial complexity significantly raises extraneous map cognitive load, while target locations in the upper-right quadrant produce the highest extraneous map cognitive load. All eye-tracking indicators, mean heart rate, interbeat interval, low-frequency power, and numbers of skin conductance responses exhibit statistical sensitivity to extraneous map cognitive load manipulations in the map target search task. Fixation duration, low‑frequency power, and numbers of skin conductance responses can genuinely reflect variations in extraneous map cognitive load. This study enriches the theoretical framework of map cognitive load, extends the application of multimodal physiological measurements within cartography, and provides empirical evidence that supports optimized map interface design and cognitive assistance strategies for navigation tasks.
Safety perception plays a crucial role in promoting sustainable urban development, as it influences residents’ spatial use behaviors, social interaction patterns, and neighborhood cohesion. However, existing studies have largely focused on single temporal contexts or relied on perception data derived from Western urban environments, leaving day–night differences in the relationship between safety perception and crime risk insufficiently understood. This study integrates generative artificial intelligence with questionnaire-based perception ratings to examine differences in safety perception between daytime and nighttime and their associations with crime risk. Focusing on central Shanghai, we analyzed adjudicated and publicly disclosed criminal cases from 2017 to 2019, generated corresponding nighttime street-view images (SVI) using a CycleGAN-based Day-to-Night (D2N) model, and obtained safety perception ratings for 1,751 valid SVI samples through a survey of 65 Shanghai residents. We then employed graph convolutional neural network weighted regression (GCNNWR) and bootstrap-based mediation analysis to examine the relationships between daytime and nighttime crime rates and related factors. The results show that the mean safety perception score decreased from 6.29 during daytime to 6.02 at nighttime, with low nighttime safety perception exhibiting more pronounced spatial clustering. Activity density was positively associated with crime rates, whereas the negative association between police facilities and crime rates weakened at night. In addition, TCI and LSU exhibited indirect pathways associated with nighttime crime rates through safety perception. These findings provide empirical support for incorporating nighttime safety experiences into urban safety governance and for implementing more temporally and spatially targeted governance strategies.
The integration of LiDAR sensors into consumer smartphones has opened new possibilities for low-cost 3D documentation, yet the metric accuracy of free iPhone LiDAR applications across different spatial scales and environmental conditions has not been rigorously characterized. This study benchmarks three freely available applications (Modelar, 3D Scanner, and SiteScape) against a high-precision Trimble X7 Terrestrial Laser Scanner (TLS) reference across three case studies at the University of Debrecen: an outdoor building façade (46.5 m), a GNSS-denied indoor corridor, and a small-scale bronze statue. The façade and corridor datasets were georeferenced using a total-station control network, whereas the statue used an independent local reference frame. Point clouds were aligned to reference data using control-point registration followed by iterative closest point (ICP) fine registration, and surface deviations were quantified using multiscale model-to-model cloud comparison (M3C2). Geodetic accuracy follows standard smartphone-LiDAR evaluation protocols, with pre-ICP alignment quantifying fine registration contribution as a 32–57