The emergence and rapid advancement of large language models (LLMs), represented by OpenAI’s Generative Pre-trained Transformer (GPT), has brought up new opportunities across various industries and disciplines. These cutting-edge technologies are transforming the way we interact with information, communicate, and solve complex problems. We conducted a pilot study exploring making maps with ChatGPT, a popular artificial intelligence (AI) chatbot. Specifically, we tested designing thematic maps using given or public geospatial data, as well as creating mental maps purely using textual descriptions of geographic space. We conclude that ChatGPT provides a useful alternative solution for mapping given its unique advantages, such as lowering the barrier to producing maps, boosting the efficiency of massive map production, and understanding geographical space with its spatial thinking capability. However, mapping with ChatGPT still has limitations at the current stage, such as its unequal benefits for different users and dependence on user intervention for quality control.

Climate change and natural hazards pose great threats to road transport systems which are ‘lifelines’ of human society. However, there is generally a lack of empirical data and approaches for assessing resilience of road networks in real hazard events. This study introduces an empirical approach to evaluate road network resilience using crowdsourced traffic data in Google Maps. Based on the conceptualization of resilience and the Hansen accessibility index, resilience of road network is measured from accumulated accessibility reduction over time during a hazard. The utility of this approach is demonstrated in a case study of the Cleveland metropolitan area (Ohio) in Winter Storm Harper. The results reveal strong spatial variations of the disturbance and recovery rate of road network performance during the hazard. The major findings of the case study are: (1) longer distance travels have higher increasing ratios of travel time during the hazard; (2) communities with low accessibility at the normal condition have lower road network resilience; (3) spatial clusters of low resilience are identified, including communities with low socio-economic capacities. The introduced approach provides ground-truth validation for existing quantitative models and supports disaster management and transportation planning to reduce hazard impacts on road network.

In late 2023, the image-reading capability added to a Generative Pre-trained Transformer (GPT) framework provided the opportunity to potentially revolutionize the way we view and understand geographic maps, the core component of cartography, geography, and spatial data science. In this study, we explore reading and analyzing maps with the latest version of GPT-4-vision-preview (GPT-4V), to fully evaluate its advantages and disadvantages in comparison with human eye-based visual inspections. We found that GPT-4V is able to properly retrieve information from various types of maps in different scales and spatiotemporal resolutions. GPT-4V can also perform basic map analysis, such as identifying visual changes before and after a natural disaster. It has the potential to replace human efforts by examining batches of maps, accurately extracting information from maps, and linking observed patterns with its pre-trained large dataset. However, it is encumbered by limitations such as diminished accuracy in visual content extraction and a lack of validation. This paper sets an example of effectively using GPT-4V for map reading and analytical tasks, which is a promising application for large multimodal models, large language models, and artificial intelligence.

The declining pattern of population density from city centres to the outskirts has been widely observed in American cities. Such a pattern reflects a trade-off between housing price/commuting cost and employment. However, most previous studies in urban population density functions are based on the Euclidean distance, and do not consider commuting cost in cities. This study provides an empirical evaluation of the classic population density functions in 382 metropolitan statistical areas (MSA) in the USA using travel times to city centres as the independent variable. The major findings of the study are: (1) the negative exponential function has the overall best fit for population density in the MSAs; (2) the Gaussian and exponential functions tend to fit larger MSAs, while the power function has better performance for small MSAs; (3) most of the MSAs appear to show a decentralisation trend during 1990–2016, and larger MSAs tend to have a higher rate of decentralisation. This study leverages crowdsourced geospatial data to provide empirical evidence of the classic urban economic models. The findings will increase our understanding about urban morphology, population–job displacement and urban decentralisation. The findings also provide baseline information to monitor and predict the changing trend of urban population distribution that could be driven by future environmental and technological changes.

Quantitative assessment of community resilience is a challenge due to the lack of empirical data about human dynamics in disasters. To fill the data gap, this study explores the utility of nighttime lights (NTL) remote sensing images in assessing community recovery and resilience in natural disasters. Specifically, this study utilized the newly-released NASA moonlight-adjusted SNPP-VIIRS daily images to analyze spatiotemporal changes of NTL radiance in Hurricane Sandy (2012). Based on the conceptual framework of recovery trajectory, NTL disturbance and recovery during the hurricane were calculated at different spatial units and analyzed using spatial analysis tools. Regression analysis was applied to explore relations between the observed NTL changes and explanatory variables, such as wind speed, housing damage, land cover, and Twitter keywords. The result indicates potential factors of NTL changes and urban-rural disparities of disaster impacts and recovery. This study shows that NTL remote sensing images are a low-cost instrument to collect near-real-time, large-scale, and high-resolution human dynamics data in disasters, which provide a novel insight into community recovery and resilience. The uncovered spatial disparities of community recovery help improve disaster awareness and preparation of local communities and promote resilience against future disasters. The systematical documentation of the analysis workflow provides a reference for future research in the application of SNPP-VIIRS daily images.