Given a set of historical vehicle trajectories and their descriptive attributes, the goal is to train a generative model that produces synthetic trajectories with high physical fidelity. Here, physical fidelity is defined as fidelity to both geometric and dynamic properties of trajectories. The problem is important since trajectory generation can contribute to data augmentation for many traffic-related applications, such as popular route discovery and traffic light control. The key challenge of this problem lies in achieving high physical fidelity under coarse geospatial attributes (e.g., origin-destination pairs) that lack fine-grained details. Current methods, which mostly focus on geometric properties, have limited utility in domain-specific scenarios due to their neglect of trajectory dynamics. To address these limitations, we propose GCDM, a novel Geo-Lucid Conditional Diffusion Model framework that integrates road map attributes into the generative process through spatially hierarchical generation and map-informed latent variables. Experiments on real-world vehicle trajectory datasets show that GCDM outperforms state-of-the-art methods in geo-distribution similarity and dynamics fidelity.

Given multi-type point maps from different place-types (e.g., tumor regions), our objective is to develop a classifier trained on the source place-type to accurately distinguish between two classes of the target place-type based on their point arrangements. This problem is societally important for many applications, such as generating clinical hypotheses for designing new immunotherapies for cancer treatment. The challenge lies in the spatial variability, the inherent heterogeneity and variation observed in spatial properties or arrangements across different locations (i.e., place-types). Previous techniques focus on self-supervised tasks to learn domain-invariant features and mitigate domain differences; however, they often neglect the underlying spatial arrangements among data points, leading to significant discrepancies across different place-types. We explore a novel multi-task self-learning framework that targets spatial arrangements, such as spatial mix-up masking and spatial contrastive predictive coding, for spatially-delineated domain-adapted AI classification. Experimental results on real-world datasets (e.g., oncology data) show that the proposed framework provides higher prediction accuracy than baseline methods.

Given a collection of Boolean spatial features, Super-Colocation Pattern Discovery identifies subsets of features that are not only frequently located together but also have dense interactions.For example, the presence of multiple immune cells around cancer cells is more interesting to oncologists than a simple colocation between immune and cancer cells.This problem is important due to its societal applications, including oncology, transportation, and economic analysis.The problem is challenging due to the need to model interaction density among a subset of Boolean spatial features.Related work on colocation pattern mining is limited due to a lack of conceptual, logical, and physical models that accurately represent interaction density.Traditional interest measures (e.g., participation index) largely focus on the mere presence of another spatial feature type and overlook the number or density of neighboring instances.We propose a novel interest measure, termed Super-Colocation Density, which utilizes a matrix or tensor along with a utility-based index to quantify the interaction density among subsets of spatial features.We also introduce novel Super-Colocation Mining algorithms and evaluate the proposed methods through both theoretical analysis and experiments with real and synthetic data.

Given multi-category point sets from different place-types, our goal is to develop a spatially-lucid classifier that can distinguish between two classes based on the arrangements of their points. This problem is important for many applications, such as oncology, for analyzing immune-tumor relationships and designing new immunotherapies. It is challenging due to spatial variability and interpretability needs. Previously proposed techniques require dense training data or have limited ability to handle significant spatial variability within a single place-type. Most importantly, these deep neural network (DNN) approaches are not designed to work in non-Euclidean space, particularly point sets. Existing non-Euclidean DNN methods are limited to one-size-fits-all approaches. We explore a spatial ensemble framework that explicitly uses different training strategies, including weighted-distance learning rate and spatial domain adaptation, on various place-types for spatially-lucid classification. Experimental results on real-world datasets (e.g., MxIF oncology data) show that the proposed framework provides higher prediction accuracy than baseline methods.

The eco-toll estimation problem quantifies the expected environmental cost (e.g., energy consumption, exhaust emissions) for a vehicle to travel along a path. This problem is important for societal applications such as eco-routing, which aims to find paths with the lowest exhaust emissions or energy need. The challenges of this problem are threefold: (1) the dependence of a vehicle's eco-toll on its physical parameters; (2) the lack of access to data with eco-toll information; and (3) the influence of contextual information (i.e. the connections of adjacent segments in the path) on the eco-toll of road segments. Prior work on eco-toll estimation has mostly relied on pure data-driven approaches and has high estimation errors given the limited training data. To address these limitations, we propose a novel Eco-toll estimation Physics-informed Neural Network framework (Eco-PiNN) using three novel ideas, namely, (1) a physics-informed decoder that integrates the physical laws governing vehicle dynamics into the network, (2) an attention-based contextual information encoder, and (3) a physics-informed regularization to reduce overfitting. Experiments on real-world heavy-duty truck data show that the proposed method can greatly improve the accuracy of eco-toll estimation compared with state-of-the-art methods. *The full version of the paper can be accessed at https://arxiv.org/abs/2301.05739

The goal of spatially explainable artificial intelligence (AI) classification approach is to build a classifier to distinguish two classes (e.g., responder, non-responder) based on the their spatial arrangements (e.g., spatial interactions between different point categories) given multi-category point data from two classes. This problem is important for generating hypotheses towards discovering new immunotherapies for cancer treatment as well as for other applications in biomedical research and microbial ecology. This problem is challenging due to an exponential number of category subsets which may vary in the strength of their spatial interactions. Most prior efforts on using human selected spatial association measures may not be sufficient for capturing the relevant spatial interactions (e.g., surrounded by) which may be of biological significance. In addition, the related deep neural networks are limited to category pairs and do not explore larger subsets of point categories. To overcome these limitations, we propose a Spatial-interaction Aware Multi-Category deep neural Network (SAMCNet) architecture and contribute novel local reference frame characterization and point pair prioritization layers for spatially explainable classification. Experimental results on multiple cancer datasets (e.g., MxIF) show that the proposed architecture provides higher prediction accuracy over baseline methods. A real-world case study demonstrates that the proposed work discovers patterns that are missed by the existing methods and has the potential to inspire new scientific discoveries.