We propose CLIFT ( C ross-City Lif estyle Pattern T ransfer for Human Mobility Prediction), a novel framework that enhances human mobility prediction by integrating general lifestyle patterns shared across cities with city-specific mobility patterns. Accurate human mobility prediction in urban environments is critical for transportation planning, marketing strategies, and disaster response. However, most existing deep learning approaches use only single-city data and exhibit significant performance degradation in small cities with limited training data. These limitations motivate methods that jointly leverage cross-city behavioral patterns and city-specific mobility characteristics. CLIFT addresses this challenge through dual complementary encoders: one captures general lifestyle patterns shared across cities, and the other captures city-specific mobility patterns; their outputs are integrated with a Transformer-based mobility predictor (LP-BERT). This architecture enables the model to jointly capture cross-city transferable behavioral patterns and city-specific mobility characteristics. We evaluated the effectiveness of CLIFT through experiments on the multi-city human mobility dataset LYMob-4Cities, comparing its performance with both single-city and multi-city deep learning-based methods. On average, CLIFT improved GEOBLEU and Top-1 accuracy by 11.1% and 10.6% over the single-city baseline, and by 5.0% and 7.9% over the multi-city baseline, respectively. Furthermore, CLIFT outperformed the top-ranked teams in the international competition, Human Mobility Prediction Challenge 2024 , demonstrating superior predictive performance under the same dataset and task setting.

The rapid growth of urban mobility and logistics demands innovative solutions to address congestion, inefficiencies, and sustainability challenges. Unmanned Aerial Systems (UAS) offer a promising alternative for urban transportation, particularly in last-mile deliveries and emergency response. To accommodate the anticipated scale of UAS operations, potentially involving millions of daily flights, the UAS Traffic Management (UTM) ecosystem must support safe, efficient, and fair airspace access while minimizing disruption. UAS operations in dense urban areas must be supported by efficient and scalable path planning and deconflicting mechanisms which compute collision-free trajectories. A dynamic rerouting mechanism allows UAS trajectories to dynamically adapt to real-time deviations caused by environmental factors, communication errors, or dynamic airspace constraints. In this paper, we introduce a UAS Path Planning with Dynamic Rerouting framework that leverages a space-time graph model to ensure safe and efficient variable speed UAS navigation in urban environments. Our approach provides collision-free trajectories by construction and enables real-time path adjustments by dynamically rerouting UAS in case of slowdown events. By incorporating real-time request management and collision-free trajectories, our model enhances the feasibility of integrating UAS into multimodal urban transportation networks. We analyze the computational efficiency of our approach and demonstrate its scalability through simulation experiments using a real-world urban map in very dense scenarios with up to 14000 UAS vehicles. Our results indicate that dynamic rerouting with collision-free trajectory computation improves UAS route availability while maintaining airspace safety and operational efficiency.

Smart cities leverage advancements in big data and artificial intelligence to deliver a multitude of services and information to urban people. Among these services, predicting on-street parking availability is an important application with the potential to enhance parking efficiency, alleviate city congestion, and minimize pollution. Existing methods for forecasting parking occupancy rates mostly rely on recurrent neural networks (RNNs) to capture temporal dimension information from parking time series data. However, these methods typically overlook the crucial spatial dependency among parking areas, resulting in suboptimal prediction accuracy. Furthermore, the computationally intensive nature of RNN-based methods leads to slow prediction speeds. To address these limitations, we propose Multi-view Spatial-temporal Graph Convolutional Networks (MV-STGCN) to predict parking occupancy rates. By integrating spatial and temporal features, MV-STGCN is able to capture complex spatial-temporal correlations and improve prediction accuracy while optimizing prediction speed. The proposed MV-STGCN incorporates a multi-view contrastive Graph Convolution module (mvc-GConv), which employs a multi-view contrast method to extract features from topology and feature spaces with commonalities and differences in a multi-view way. Experimental results based on real-world datasets demonstrate that MV-STGCN outperforms baselines in predicting long-term parking occupancy rates while achieving superior prediction speed.

High-quality, typically administrative, geospatial data should adhere to established measurement and representation practices and be protected from malicious attacks. However, this kind of geospatial data may only be infrequently updated due to its often prolonged production process compared to a data source of volunteered geographic information such as OpenStreetMap. Existing approaches typically try to quality-assure geospatial data by comparing it to another reference dataset of perceived higher quality - often another administrative dataset facing a similar update cycle. In contrast, this article tries to determine whether actual changes present in volunteered geographic information data such as OpenStreetMap, which also need to be applied in an administrative dataset (i.e., consists of actual changes in the real world), can be identified automatically. To that end, we present QPredict, a machine learning approach observing changes in volunteered geospatial data such as OpenStreetMap to predict issues with a target (administrative) dataset. The algorithm is trained by exploiting geospatial object characteristics, intrinsic and extrinsic quality metrics and their respective changes over time. We evaluate the effectiveness of our approach on two datasets representing two mid-size cities in Germany and discuss our findings in terms of their applicability in use cases.

Machine learning (ML) and deep learning (DL) techniques are increasingly applied to produce efficient query optimizers, in particular in regards to big data systems. The optimization of spatial operations is even more challenging due to the inherent complexity of such kind of operations, like spatial join or range query, and the peculiarities of spatial data. Although a few ML-based spatial query optimizers have been proposed in literature, their design limits their use, since each one is tailored for a specific collection of datasets, a specific operation, or a specific hardware setting. Changes to any of these will require building and training a completely new model which entails collecting a new very large training dataset to obtain a good model. This article proposes a different approach which exploits the use of the novel notion of spatial embedding to overcome these limitations. In particular, a preliminary model is defined which captures the relevant features of spatial datasets, independently from the operation to be optimized and in an unsupervised manner. This model is trained with a large amount of both synthetic and real-world data, with the aim to produce meaningful spatial embeddings. The construction of an embedding model could be intended as a preliminary step for the optimization of many different spatial operations, so the cost of its building can be compensated during the subsequent construction of specific models. Indeed, for each considered spatial operation, a specific tailored model will be trained but by using spatial embeddings as input, so a very little amount of training data points is required for them. Three peculiar operations are considered as proof of concept in this article: range query, self-join, and binary spatial join. Finally, a comparison with an alternative technique, known as transfer learning, is provided and the advantages of the proposed technique over it are highlighted.

Travel time estimation is one of the core tasks for the development of intelligent transportation systems. Most previous works model the road segments or intersections separately by learning their spatio-temporal characteristics to estimate travel time. However, due to the continuous alternations of the road segments and intersections in a path, the dynamic features are supposed to be coupled and interactive. Therefore, modeling one of them limits further improvement in accuracy of estimating travel time. To address the above problems, a novel graph-based deep learning framework for travel time estimation is proposed in this article, namely, Spatio-temporal Dual Graph Neural Networks (STDGNN). Specifically, we first establish the node-wise and edge-wise graphs to, respectively, characterize the adjacency relations of intersections and that of road segments. To extract the joint spatio-temporal correlations of the intersections and road segments, we adopt the spatio-temporal dual graph learning approach that incorporates multiple spatial-temporal dual graph learning modules with multi-scale network architectures for capturing multi-level spatial-temporal information from the dual graph. Finally, we employ the multi-task learning approach to estimate the travel time of a given whole route, each road segment and intersection simultaneously. We conduct extensive experiments to evaluate our proposed model on three real-world trajectory datasets, and the experimental results show that STDGNN significantly outperforms several state-of-art baselines.

We consider the problem of reducing the time that healthcare professionals need to understand the patient’s medical history through the next generation of biomedical decision support. This problem is societally important because it has the potential to improve healthcare quality and patient outcomes. However, navigating electronic health records (EHR) is challenging due to high patient-doctor ratios, potentially long medical histories, urgency of treatment for some medical conditions, and patient variability. The current EHR systems provide only a longitudinal view of patient medical history, which is time-consuming to browse, and doctors often need to engage nurses, residents, and others for initial analysis. To overcome this limitation, we envision an alternative spatial representation of patient histories (e.g., electronic health records) and other biomedical data in the form of Atlas-EHR. Just like Google Maps, which allows a global, national, regional, and local view, Atlas-EHR can start with an overview of the patient’s anatomy and history before drilling down to spatially anatomical subsystems, their individual components, or subcomponents. Atlas-EHR presents a compelling opportunity for spatial computing since healthcare is almost a fifth of the US economy. However, traditional spatial computing designed for geographic use cases (e.g., navigation, land survey, and mapping) faces many hurdles in the biomedical domain. This article presents several open research questions under this theme in five broad areas of spatial computing.

In this introductory paper, I discuss the goals and motivations for the special issue New Perspectives in Organization Science, which coincides with the 20th anniversary of the journal Organization Science. Senior editors of Organization Science provide ...

Human mobility is the foundation of urban dynamics and its prediction significantly benefits various downstream location-based services. Nowadays, while deep learning approaches are dominating the mobility prediction field where various model architectures/designs are continuously updating to push up the prediction accuracy, there naturally arises a question: whether these models are sufficiently good to reach the best possible prediction accuracy? To answer this question, predictability study is a method that quantifies the inherent regularities of the human mobility data and links the result to that limit. Mainstream predictability studies achieve this by analyzing the individual trajectories and merging all individual results to obtain an upper bound. However, the multiple individuals composing the city are not totally independent and the individual behavior is heavily influenced by its implicit or explicit surroundings. Therefore, the collective factor should be considered in the mobility predictability measurement, which has not been addressed before. This vision paper points out this concern and envisions a few potential research problems along such an individual-to-collective transition from both data and methodology aspects. We hope the discussion in this paper sheds some light on the human mobility predictability community.

Point feature labeling is a classical problem in cartography and GIS that has been extensively studied for geospatial point data. At the same time, word clouds are a popular visualization tool to show the most important words in text data which has also been extended to visualize geospatial data (Buchin et al. PacificVis 2016). In this article, we study a hybrid visualization, which combines aspects of word clouds and point labeling. In the considered setting, the input data consist of a set of points grouped into categories and our aim is to place multiple disjoint and axis-aligned rectangles, each representing a category, such that they cover points of (mostly) the same category under some natural quality constraints. In our visualization, we then place category names inside the computed rectangles to produce a labeling of the covered points which summarizes the predominant categories globally (in a word-cloud-like fashion) while locally avoiding excessive misrepresentation of points (i.e., retaining the precision of point labeling). We show that computing a minimum set of such rectangles is NP -hard. Hence, we turn our attention to developing a heuristic with (optional) exact components using SAT models to compute our visualizations. We evaluate our algorithms quantitatively, measuring running time and quality of the produced solutions, on several synthetic and real-world data sets. Our experiments show that the fully heuristic approach produces solutions of comparable quality to heuristics combined with exact SAT models, while running much faster.