Research on geospatial foundation models (GFMs) has become a trending topic in geospatial artificial intelligence (AI) research due to their potential for achieving high generalizability and domain adaptability, reducing model training costs for individual researchers. Unlike large language models, such as ChatGPT, constructing visual foundation models for image analysis, particularly in remote sensing, encountered significant challenges such as formulating diverse vision tasks into a general problem framework. This paper evaluates the recently released NASA-IBM GFM Prithvi for its predictive performance on high-level image analysis tasks across multiple benchmark datasets. Prithvi was selected because it is one of the first open-source GFMs trained on time-series of high-resolution remote sensing imagery. A series of experiments were designed to assess Prithvi’s performance as compared to other pre-trained task-specific AI models in geospatial image analysis. New strategies, including band adaptation, multi-scale feature generation, and fine-tuning techniques, are introduced and integrated into an image analysis pipeline to enhance Prithvi’s domain adaptation capability and improve model performance. In-depth analyses reveal Prithvi’s strengths and weaknesses, offering insights for both improving Prithvi and developing future visual foundation models for geospatial tasks.

Natural-language spatial relations between geographic entities (geoentities) reflect diverse perceptions influenced by factors like location, culture, and linguistic conventions. These relations play a crucial role in supporting geospatial tasks, such as question answering and cognitive reasoning. While prior studies focused on a limited set of human-selected spatial terms and geometric attributes, they often overlooked essential semantic attributes. To overcome this limitation, we developed a Spatial Relation-based Knowledge Graph Embedding framework, SR-KGE, with new KG fusion functions to predict spatial relation terms among distinct geoentities. This method not only considers graph structures and the diversity of natural language expressions in the embedding and learning process, but also incorporates geoentity types as a constraint to capture spatial and semantic relations more accurately. Our experiments on two knowledge graph datasets, one small-scale and one large-scale, have both shown its superior performance in spatial relation inference compared to popular KGE models, including TransE, RotatE, and HAKE. We hope our research will advance the classic study of natural language described spatial relations in a more automated and intelligent way.

KnowWhereGraph is one of the largest fully publicly available geospatial knowledge graphs. It includes data from 30 layers on natural hazards (e.g., hurricanes, wildfires), climate variables (e.g., air temperature, precipitation), soil properties, crop and land-cover types, demographics, and human health, various place and region identifiers, among other themes. These have been leveraged through the graph by a variety of applications to address challenges in food security and agricultural supply chains; sustainability related to soil conservation practices and farm labor; and delivery of emergency humanitarian aid following a disaster. In this paper, we introduce the ontology that acts as the schema for KnowWhereGraph. This broad overview provides insight into the requirements and design specifications for the graph and its schema, including the development methodology (modular ontology modeling) and the resources utilized to implement, materialize, and deploy KnowWhereGraph with its end-user interfaces and public query SPARQL endpoint.

Improving the interpretability of geospatial artificial intelligence (GeoAI) models has become critically important to open the ‘black box’ of complex AI models, such as deep learning. This paper compares popular saliency map generation techniques and their strengths and weaknesses in interpreting GeoAI and deep learning models’ reasoning behaviors, particularly when applied to geospatial analysis and image processing tasks. We surveyed two broad classes of model explanation methods: perturbation-based and gradient-based methods. The former identifies important image areas, which help machines make predictions by modifying a localized area of the input image. The latter evaluates the contribution of every single pixel of the input image to the model’s prediction results through gradient backpropagation. In this study, three algorithms—the occlusion method, the integrated gradients method, and the class activation map method—are examined for a natural feature detection task using deep learning. The algorithms’ strengths and weaknesses are discussed, and the consistency between model-learned and human-understandable concepts for object recognition is also compared. The experiments used two GeoAI-ready datasets to demonstrate the generalizability of the research findings.

Knowledge graphs are a rapidly growing paradigm and technology stack for integrating large-scale, heterogeneous data in an AI-ready form, i.e., combining data with the formal semantics required to understand it. However, toolchains that support data synthesis and knowledge discovery through information organization, search, filtering, and visualization have been developed at a pace lagging knowledge graph technology. In this paper, we present Knowledge Explorer, an open-source faceted search interface that provides environmentally intelligent services for interactively browsing and navigating KnowWhereGraph. Currently one of the largest open knowledge graphs, KnowWhereGraph contains over 12 billion statements with rich spatial and temporal information from more than 30 data layers. With an extensive collection of facets, Knowledge Explorer enables spatial, temporal, full-text, and expert search with dereferencing functionality to support "follow-your-nose"exploration, and it allows users to narrow their search by selecting facets. Given the size of the underlying graph and dependency on GeoSPARQL, we have improved query performance by implementing Elasticsearch indexing, spatial query generation, and caching. Knowledge Explorer is capable of retrieving information within seconds, answering a wide variety of competency questions posed by researchers, humanitarian relief organizations, and the broader public, thus helping better perform tasks such as cross-gazetteer place retrieval and disaster assessment from global to local geographic scales.

A cornerstone of the scientific method, the ability to reproduce and replicate the results of research has gained widespread attention across the sciences in recent years. A corresponding burst of energy into how to make research more reproducible and replicable has led to numerous innovations. This article outlines some of the opportunities for geospatial researchers to contribute to and learn from the broader reproducibility literature. We review practices developed in related disciplines to improve the reproducibility and replicability of research and outline current efforts to adapt those practices to geospatial analyses. The article then highlights the open questions, opportunities, and potential new directions in geospatial research related to R&R. We stress that the path ahead will likely require a mixture of computational, geospatial, and behavioral research that collectively addresses the many sides of reproducibility and replicability issues.

Evidence suggests that the proportion of the human population living in cities will continue to grow, to the point where over 90% of the world’s population will be living in one form of city or ano...

Terrain feature detection is a fundamental task in terrain analysis and landscape scene interpretation. Discovering where a specific feature (i.e. sand dune, crater, etc.) is located and how it evolves over time is essential for understanding landform processes and their impacts on the environment, ecosystem, and human population. Traditional induction-based approaches are challenged by their inefficiency for generalizing diverse and complex terrain features as well as their performance for scalable processing of the massive geospatial data available. This paper presents a new deep learning (DL) approach to support automatic detection of terrain features from remotely sensed images. The novelty of this work lies in: (1) a terrain feature database containing 12,000 remotely sensed images (1,000 original images and 11,000 derived images from data augmentation) that supports data-driven model training and new discovery; (2) a DL-based object detection network empowered by ensemble learning and deep and deeper convolutional neural networks to achieve high-accuracy object detection; and (3) fine-tuning the model’s characteristics and behaviors to identify the best combination of hyperparameters and other network factors. The introduction of DL into geospatial applications is expected to contribute significantly to intelligent terrain analysis, landscape scene interpretation, and the maturation of spatial data science.

In this paper, we present a data-driven framework to support exploratory spatial, temporal, and statistical analysis of intra-urban human mobility. We leveraged a new mobility data source, the dockless bike-sharing service Mobike, to quantify short-trip transportation patterns in Shanghai, China, the world’s largest bike-share city. A data-driven framework was established to integrate multiple data sources, including transportation network data (roads, bikes, and public transit), road characteristics, and urban land use, to achieve a detailed, accurate analysis of cycling patterns at both the individual and group levels. The results provide a comprehensive view of mobility patterns in the use of shared-ride bicycles, including: (1) the temporal and spatiotemporal distribution of shared-bike usage and how this varies according to different land use; (2) the statistical distribution of Mobike trips, which are primarily short-distance; and (3) the travel behavior and road factors that influence Mobike users’ route choice. The findings offer valuable insights for city planners regarding infrastructure development, for shared-ride bike companies to offer better bike rebalancing strategies to meet user demand, and for the promotion of this new green transportation mode to alleviate traffic congestion and enhance public health.

Geographically Weighted Regression (GWR) is a widely used tool for exploring spatial heterogeneity of processes over geographic space. GWR computes location-specific parameter estimates, which makes its calibration process computationally intensive. The maximum number of data points that can be handled by current open-source GWR software is approximately 15,000 observations on a standard desktop. In the era of big data, this places a severe limitation on the use of GWR. To overcome this limitation, we propose a highly scalable, open-source FastGWR implementation based on Python and the Message Passing Interface (MPI) that scales to the order of millions of observations. FastGWR optimizes memory usage along with parallelization to boost performance significantly. To illustrate the performance of FastGWR, a hedonic house price model is calibrated on approximately 1.3 million single-family residential properties from a Zillow dataset for the city of Los Angeles, which is the first effort to apply GWR to a dataset of this size. The results show that FastGWR scales linearly as the number of cores within the High-Performance Computing (HPC) environment increases. It also outperforms currently available open-sourced GWR software packages with drastic speed reductions – up to thousands of times faster – on a standard desktop.

This article introduces our research in developing a probabilistic model to extract linear terrain features from high resolution Digital Elevation Models (DEMs). The proposed model takes full advantage of spatio-contextual information to characterize terrain changes. It first derives a quantifiable measure of spatio-contextual patterns of linear terrain features, such as ridgelines, valley lines and crater boundaries, and then adopts multiple neighborhood analysis and a probability model to address data uncertainty in terrain surface modeling. Different from traditional approaches, the proposed model has the ability to achieve near-automated processing. It also supports effective extraction of terrain features in both smooth and rough surfaces. Through a series of experiments, we demonstrate that the proposed approach outperforms existing techniques, including thresholding, stream/drainage network analysis, visual descriptor detection, object-based image analysis and edge detection. This work contributes to both the geospatial data science and geomorphology communities with a new way of utilizing high-resolution imagery in terrain analysis.

The increasing research interest in global climate change and the rise of the public awareness have generated a significant demand for new tools to support effective visualization of big climate data in a cyber environment such that anyone from any location with an Internet connection and a web browser can easily view and comprehend the data. In response to the demand, this paper introduces a new web-based platform for visualizing multidimensional, time-varying climate data on a virtual globe. The web-based platform is built upon a virtual globe system Cesium, which is open-source, highly extendable and capable of being easily integrated into a web environment. The emerging WebGL technique is adapted to support interactive rendering of 3D graphics with hardware graphics acceleration. To address the challenges of transmitting and visualizing voluminous, complex climate data over the Internet to support real-time visualization, we develop a stream encoding and transmission strategy based on video-compression techniques. This strategy allows dynamic provision of scientific data in different precisions to balance the needs for scientific analysis and visualization cost. Approaches to represent, encode and decode processed data are also introduced in detail to show the operational workflow. Finally, we conduct several experiments to demonstrate the performance of the proposed strategy under different network conditions. A prototype, PolarGlobe, has been developed to visualize climate data in the Arctic regions from multiple angles.

The efficiency of public investments and services has been of interest to geographic researchers for several decades. While in the private sector inefficiency often leads to higher prices, loss of competitiveness, and loss of business, in the public sector inefficiency in service provision does not necessarily lead to immediate changes. In many cases, it is not an entirely easy task to analyze a particular service as appropriate data may be difficult to obtain and hidden in detailed budgets. In this paper, we develop an integrative approach that uses cyber search, Geographic Information System (GIS), and spatial optimization to estimate the spatial efficiency of fire protection services in Los Angeles (LA) County. We develop a cyber-search process to identify current deployment patterns of fire stations across the major urban region of LA County. We compare the results of our search to existing databases. Using spatial optimization, we estimate the level of deployment that is needed to meet desired coverage levels based upon the location of an ideal fire station pattern, and then compare this ideal level of deployment to the existing system as a means of estimating spatial efficiency. GIS is adopted throughout the paper to simulate the demand locations, to conduct location-based spatial analysis, to visualize fire station data, and to map model simulation results. Finally, we show that the existing system in LA County has considerable room for improvement. The methodology presented in this paper is both novel and groundbreaking, and the automated assessments are readily transferable to other counties and jurisdictions.

Spatial optimization deals with a variety of problems involved in arranging, operating, and designing systems of activities across a spatial domain. It is comprised of both models and optimization ...

In this paper, we report efforts to develop a parallel implementation of the p-compact regionalization problem suitable for multi-core desktop and high-performance computing environments. Regionalization for data aggregation is a key component of many spatial analytical workflows that are known to be NP-Hard. We utilize a low communication cost parallel implementation technique that provides a benchmark for more complex implementations of this algorithm. Both the initialization phase, utilizing a Memory-based Randomized Greedy and Edge Reassignment (MERGE) algorithm, and the local search phase, utilizing Simulated Annealing, are distributed over available compute cores. Our results suggest that the proposed parallelization strategy is capable of solving the compactness-driven regionalization problem both efficiently and effectively. We expect this work to advance CyberGIS research by extending its application areas into the regionalization world and to make a contribution to the spatial analysis community by proposing this parallelization strategy to solve large regionalization problems efficiently.

Within a CyberGIS environment, the development of effective mechanisms to encode metadata for spatial analytical methods and to track the provenance of operations is a key requirement. Spatial weights are a fundamental element in a wide range of spatial analysis methods that deal with testing for and estimating models with spatial autocorrelation. They form the link between the data structure in a GIS and the spatial analysis methods. Over time, the number of formats for spatial weights implemented in software has proliferated, without any standard or easy interoperability. In this paper, we propose a flexible format that provides a way to ensure interoperability within a cyberinfrastructure environment. We illustrate the format with an application of a spatial weights web service, which is part of an evolving spatial analytical workbench. We describe an approach to embed provenance in spatial weights structures and illustrate the performance of the web service by means of a number of small experiments.

Cellular automata (CA) modeling is useful to assist in understanding rural–urban land conversion processes. Although CA calibration is essential to ensuring an accurate modeling outcome, it remains a significant challenge. This study aims to address that challenge by developing and evaluating a multi-objective optimization model that considers the objectives of minimizing minus maximum likelihood estimation (MLE) value and minimizing number of errors (NOE) when calibrating CA transition rules. A Pareto front-based heuristic search algorithm, the Non-dominated Sorting Genetic Algorithm-II (NSGA-II), is used to obtain optimal or near-optimal solutions. The proposed calibration approach is validated using a case study from New Castle County, Delaware, United States. A comparison of the NSGA-II-based calibration model, the generic Logit regression calibration approach (MLE-based Generic Genetic Algorithm (GGA) calibration approach), and the NOE-based GGA calibration approach demonstrates that the proposed calibration model can produce stable solutions with better simulation accuracy. Furthermore, it can generate a set of solutions with different preferences regarding the two objectives which can provide CA simulation with robust parameters options.

A measure of shape compactness is a numerical quantity representing the degree to which a shape is compact. Ways to provide an accurate measure have been given great attention due to its application in a broad range of GIS problems, such as detecting clustering patterns from remote-sensing images, understanding urban sprawl, and redrawing electoral districts to avoid gerrymandering. In this article, we propose an effective and efficient approach to computing shape compactness based on the moment of inertia (MI), a well-known concept in physics. The mathematical framework and the computer implementation for both raster and vector models are discussed in detail. In addition to computing compactness for a single shape, we propose a computational method that is capable of calculating the variations in compactness as a shape grows or shrinks, which is a typical application found in regionalization problems. We conducted a number of experiments that demonstrate the superiority of the MI over the popular isoperimetric quotient approach in terms of (1) computational efficiency; (2) tolerance of positional uncertainty and irregular boundaries; (3) ability to handle shapes with holes and multiple parts; and (4) applicability and efficacy in districting/zonation/regionalization problems.

This article presents a new approach to automatically measure semantic similarity between spatial objects. It combines a description logic based knowledge base (an ontology) and a multi-layer neural network to simulate the human process of similarity perception. In the knowledge base, spatial concepts are organized hierarchically and are modelled by a set of features that best represent the spatial, temporal and descriptive attributes of the concepts, such as origin, shape and function. Water body ontology is used as a case study. The neural network was designed and human subjects' rankings on similarity of concept pairs were collected for data training, knowledge mining and result validation. The experiment shows that the proposed method achieves good performance in terms of both correlation and mean standard error analysis in measuring the similarity between neural network prediction and human subject ranking. The application of similarity measurement with respect to improving relevancy ranking of a semantic search engine is introduced at the end.