Understanding how AI will represent and reason about geography should be a key concern for all of us, as the broader public increasingly interacts with spaces and places through these systems. Similarly, in line with the nature of foundation models, our own research often relies on pre-trained models. Hence, understanding what world AI systems construct is as important as evaluating their accuracy, including factual recall. To motivate the need for such studies, we provide three illustrative vignettes, i.e., exploratory probes, in the hope that they will spark lively discussions and follow-up work: (1) Do models form strong defaults, and how brittle are model outputs to minute syntactic variations? (2) Can distributional shifts resurface from the composition of individually benign tasks, e.g., when using AI systems to create personas? (3) Do we overlook deeper questions of understanding when solely focusing on the ability of systems to recall facts such as geographic principles?
Hong Kong' senior geography curriculum has included GIS since the early 2000s. However, GIS in secondary schools does not play a significant role in Hong Kong secondary geography education. Analyzing GIS benefits by literature review, it is believed that GIS should be included in both the senior and junior geography curriculum. Moreover, the literature review indicates that without clear instruction from the Hong Kong Education Bureau (EDB), low preparedness of Hong Kong geography teachers, and unsupportive attitudes from academia and textbook publishers, GIS cannot be implemented in secondary schools of Hong Kong. Therefore, suggestions are made for the EDB, geography teachers, academia and textbook publishers to facilitate GIS involvement in senior and junior geography curriculums. The EDB can develop clear guidelines for teachers, academia and textbook publishers' references, and offer student-centered GIS educational courses for teachers. It is important for teachers to be prepared for advanced GIS technology and to even learn along with students. Academics and textbook publishers can provide free GIS maps targeted at Hong Kong' junior and senior geography curriculums. Although
The undirected edge geography is a two-player combinatorial game on an undirected rooted graph. The players alternatively perform a move consisting of choosing an edge incident to the root vertex, removing the chosen edge, and marking the other endpoint as a new root vertex. The first player who cannot perform a move is the loser. In this paper, we are interested in the undirected edge geography game on the grid graph $P_m\square P_n$. We completely determine whether the root vertex is a winning position (N-position) or a losing position (P-position). Moreover, we give a winning strategy for the winner.
Geography scholarship currently includes interdisciplinary approaches and theories and reflects shifts in research methodologies. Since the spatial turn in geographical thought and the emergence of geo-web technologies, geography scholarship has leaned more toward interdisciplinarity. In recent years geographical research methods have relied on various disciplines ranging from data science to arts and design. Literary geography and film geography are two subfields of geography that employ novels and films in exploring spatiality, respectively. In addition to geographical concepts, these courses include many aspects of relations in space, including human-human relations, human-environment relations, et cetera, which were barely addressed in traditional geography courses. However, a review of the employment of geoweb technologies in literary and film geography practices reveals that these practices have mostly remained limited to isolating geographical passages from novels or movies. This paper explores new opportunities for designing film and literary geography-based apps using a cartographical user-centered design framework.
In a recent note F. Lin showed that if a rational homology sphere $Y$ admits a taut foliation then the Heegaard Floer module $HF^-(Y)$ contains a copy of $\mathbf{F}[U]/U$ as a summand (arXiv:2309.01222). This implies that either the $L$-space conjecture is false or that Heegaard Floer homology satisfies a geography restriction. We verify that Lin's geography restriction holds for a wide class of rational homology spheres. Indeed, we show that the Heegaard Floer module $HF^-(Y)$ may satisfy a stronger geography restriction.
We study the behavior of toric Landau-Ginzburg models under extremal contraction and minimal model program. We also establish a relation between the moduli space of toric Landau-Ginzburg models and the geography of central models. We conjecture that there is a correspondence between extremal contractions and minimal model program on Fano varieties, and degenerations of their associated toric Landau-Ginzburg models written explicitly. We prove the conjectures for smooth toric varieties, as well as general smooth Fano varieties in dimensions 2 and 3. As an application, we compute the elementary syzygies for smooth Fano threefolds.
Road network representation learning aims to learn compressed and effective vectorized representations for road segments that are applicable to numerous tasks. In this paper, we identify the limitations of existing methods, particularly their overemphasis on the distance effect as outlined in the First Law of Geography. In response, we propose to endow road network representation with the principles of the recent Third Law of Geography. To this end, we propose a novel graph contrastive learning framework that employs geographic configuration-aware graph augmentation and spectral negative sampling, ensuring that road segments with similar geographic configurations yield similar representations, and vice versa, aligning with the principles stated in the Third Law. The framework further fuses the Third Law with the First Law through a dual contrastive learning objective to effectively balance the implications of both laws. We evaluate our framework on two real-world datasets across three downstream tasks. The results show that the integration of the Third Law significantly improves the performance of road segment representations in downstream tasks.
Roughly speaking, the problem of geography asks for the existence of varieties of general type after we fix some invariants. In dimension $1$, where we fix the genus, the geography question is trivial, but already in dimension $2$, it becomes a hard problem in general. In higher dimensions, this problem is essentially wide open. In this paper, we focus on geography in dimension $3$. We generalize the techniques which compare the geography of surfaces with the geography of arrangements of curves via asymptotic constructions. In dimension $2$ this involves resolutions of cyclic quotient singularities and a certain asymptotic behavior of the associated Dedekind sums and continued fractions. We discuss the general situation with emphasis on dimension $3$, analyzing the singularities and various resolutions that show up, and proving results about the asymptotic behavior of the invariants we fix.
This paper examines the recent advances and applications of AI in human geography especially the use of machine (deep) learning, including place representation and modeling, spatial analysis and predictive mapping, and urban planning and design. AI technologies have enabled deeper insights into complex human-environment interactions, contributing to more effective scientific exploration, understanding of social dynamics, and spatial decision-making. Furthermore, human geography offers crucial contributions to AI, particularly in context-aware model development, human-centered design, biases and ethical considerations, and data privacy. The synergy beween AI and human geography is essential for addressing global challenges like disaster resilience, poverty, and equitable resource access. This interdisciplinary collaboration between AI and geography will help advance the development of GeoAI and promise a better and sustainable world for all.
Earth observation (EO) data such as satellite imagery can have far-reaching impacts on our understanding of the geography of poverty, especially when coupled with machine learning (ML) and computer vision. Early research used computer vision to predict living conditions in areas with limited data, but recent studies increasingly focus on causal analysis. Despite this shift, the use of EO-ML methods for causal inference lacks thorough documentation, and best practices are still developing. Through a comprehensive scoping review, we catalog the current literature on EO-ML methods in causal analysis. We synthesize five principal approaches to incorporating EO data in causal workflows: (1) outcome imputation for downstream causal analysis, (2) EO image deconfounding, (3) EO-based treatment effect heterogeneity, (4) EO-based transportability analysis, and (5) image-informed causal discovery. Building on these findings, we provide a detailed protocol guiding researchers in integrating EO data into causal analysis -- covering data requirements, computer vision model selection, and evaluation metrics. While our focus centers on health and living conditions outcomes, our protocol is adaptab
In this article, we describe the geography of the Teichmüller stack of \cite{LMStacks} and of one of its variants we introduce here, giving some answers to questions as: which points are orbifold points? What are the different local models of special points?... We give a rough description in the general case, and we use the compacity of the cycle spaces to get a much more detailed picture in the Kähler setting.
Cities and metropolitan areas are major drivers of creativity and innovation in all possible sectors: scientific, technological, social, artistic, etc. The critical concentration and proximity of diverse mindsets and opportunities, supported by efficient infrastructures, enable new technologies and ideas to emerge, thrive, and trigger further innovation. Though this pattern seems well established, geography's role in the emergence and diffusion of new technologies still needs to be clarified. An additional important question concerns the identification of the innovation pathways of metropolitan areas. Here, we explore the factors that influence the spread of technology among metropolitan areas worldwide and how geography and political borders impact this process. Our evidence suggests that political geography has been highly important for the diffusion of innovation till around two decades ago, slowly declining afterwards in favour of a more global innovation ecosystem. Further, the visualisation of the evolution of countries and metropolitan areas in a 2d space of competitiveness and diversification reveals the existence of two main innovation pathways, discriminating between diff
Complex systems are made up of many interacting components. Network science provides the tools to analyze and understand these interactions. Community detection is a key technique in network science for uncovering the structures that shape the behavior of these networks. This thesis introduces the Adaptive Cut, a novel method that improves clustering methods by employing multi-level cuts in hierarchical dendrograms. Overcoming the limitations of traditional single-level cuts-especially in unbalanced dendrograms-the Adaptive Cut provides a multi-level cut by optimizing a Markov chain Monte Carlo with simulated annealing. In addition, we propose the Balanceness score, an information-theoretic metric that quantifies dendrogram balance and predicts the benefits of multilevel cuts. Evaluations on over 200 real and synthetic networks show significant improvements in partition density and modularity. In the second part, our analysis shows that incorporating network geometry allows redefining administrative boundaries into non-contiguous regions that better reflect social and spatial dynamics. We also discuss the representation of hierarchical data in hyperbolic space through Poincare maps
First-nature geography shapes the location of prosperity. I provide evidence by investigating the effects when it suddenly changes. In 1825 a storm breached the Agger Isthmus. This connected Denmark's west Limfjord Region to the North Sea. I demonstrate that trade followed. Prosperity relocated with it: population rose 27.0 percent within a generation - an elasticity of 1.6 relative to market access - with occupational shifts toward fishing and manufacturing. Fertility, not migration, drove the expansion. A mirror experiment, the waterway's closure circa 1086-1208, caused symmetric declines in medieval coin and building finds.
This survey focuses on the geometric problem of log-surfaces, which are pairs consisting of a smooth projective surface and a reduced non-empty boundary divisor. In the first part, we focus on the geography problem for complex log-surfaces associated with pairs of the form $(\mathbb{P}^{2}, C)$, where $C$ is an arrangement of smooth plane curves admitting ordinary singularities. Specifically, we focus on the case in which $C$ is an arrangement consisting of smooth rational curves as its irreducible components. In the second part, containing original new results, we study log-surfaces constructed as pairs consisting of a complex projective $K3$ surface and a rational curve arrangement. In particular, we provide some combinatorial conditions for such pairs to have the log-Chern slope equal to $3$. Our survey is illustrated with many explicit examples of log-surfaces.
The recent success of large language models and AI chatbots such as ChatGPT in various knowledge domains has a severe impact on teaching and learning Geography and GIScience. The underlying revolution is often compared to the introduction of pocket calculators, suggesting analogous adaptations that prioritize higher-level skills over other learning content. However, using ChatGPT can be fraudulent because it threatens the validity of assessments. The success of such a strategy therefore rests on the assumption that lower-level learning goals are substitutable by AI, and supervision and assessments can be refocused on higher-level goals. Based on a preliminary survey on ChatGPT's quality in answering questions in Geography and GIScience, we demonstrate that this assumption might be fairly naive, and effective control in assessments and supervision is required.
The spatial metaphor of the network along with its accompanying abstractions, such as flow, movement, and connectivity, have been central themes throughout the relational turn in human geography. However, to date networks in geography have been primarily explored either through actor-network theory or assemblage thinking, both of which embrace the network metaphor without specifically and formally interrogating networks themselves. We seek to problematize the treatment of networks in geography by exploring the largely underutilized literature on social networks as an alternative to the now dominant actor-network and assemblage frameworks. Our paper discusses the conceptual connections between key concepts in geography, such as place, distance, scale, and power, and those in network theory, such as centrality, density, and homophily. Voluntarily written from the periphery of human geography, our paper opens new directions for geographers that are interested in more than the metaphor of the network.
Using trajectories from acoustically tracked (RAFOS) floats in the Gulf of Mexico, we construct a geography of its Lagrangian circulation within the 1500--2500-m layer. This is done by building a Markov-chain representation of the Lagrangian dynamics. The geography is composed of weakly interacting provinces that constrain the connectivity at depth. The main geography includes two provinces of near equal areas and separated by a roughly meridional boundary. The residence time is about 4.5 (3.5) years in the western (eastern) province. The exchange between these provinces is effected through a slow cyclonic circulation, which is well constrained in the western basin by preservation of $f/H$, where $f$ is the Coriolis parameter and $H$ is depth. Secondary provinces of varied shapes covering smaller areas are identified with residence times ranging from about 0.4 to 1.2 years or so. Except for the main provinces, the deep Lagrangian geography does not resemble the surface Lagrangian geography recently inferred from satellite-tracked drifter trajectories. This implies disparate connectivity characteristics with potential implications for pollutant (e.g., oil) dispersal at the surface a
We settle two long-standing complexity-theoretical questions-open since 1981 and 1993-in combinatorial game theory (CGT). We prove that the Grundy value (a.k.a. nim-value, or nimber) of Undirected Geography is PSPACE-complete to compute. This exhibits a stark contrast with a result from 1993 that Undirected Geography is polynomial-time solvable. By distilling to a simple reduction, our proof further establishes a dichotomy theorem, providing a "phase transition to intractability" in Grundy-value computation, sharply characterized by a maximum degree of four: The Grundy value of Undirected Geography over any degree-three graph is polynomial-time computable, but over degree-four graphs-even when planar and bipartite-is PSPACE-hard. Additionally, we show, for the first time, how to construct Undirected Geography instances with Grundy value $\ast n$ and size polynomial in n. We strengthen a result from 1981 showing that sums of tractable partisan games are PSPACE-complete in two fundamental ways. First, since Undirected Geography is an impartial ruleset, we extend the hardness of sums to impartial games, a strict subset of partisan. Second, the 1981 construction is not built from a nat
Many models for spatial and spatio-temporal data assume that "near things are more related than distant things," which is known as the first law of geography. While geography may be important, it may not be all-important, for at least two reasons. First, technology helps bridge distance, so that regions separated by large distances may be more similar than would be expected based on geographical distance. Second, geographical, political, and social divisions can make neighboring regions dissimilar. We develop a flexible Bayesian approach for learning from spatial data which units are close in an unobserved socio-demographic space and hence which units are similar. As a by-product, the Bayesian approach helps quantify the relative importance of socio-demographic space relative to geographical space. To demonstrate the proposed approach, we present simulations along with an application to county-level data on median household income in the U.S. state of Florida.