In the domain of Mobility Data Science, the intricate task of interpreting models trained on trajectory data, and elucidating the spatio-temporal movement of entities, has persistently posed significant challenges. Conventional XAI techniques, although brimming with potential, frequently overlook the distinct structure and nuances inherent within trajectory data. Observing this deficiency, we introduced a comprehensive framework that harmonizes pivotal XAI techniques: LIME (Local Interpretable Model-agnostic Explanations), SHAP (SHapley Additive exPlanations), Saliency maps, attention mechanisms, direct trajectory visualization, and Permutation Feature Importance (PFI). Unlike conventional strategies that deploy these methods singularly, our unified approach capitalizes on the collective efficacy of these techniques, yielding deeper and more granular insights for models reliant on trajectory data. In crafting this synthesis, we effectively address the multifaceted essence of trajectories, achieving not only amplified interpretability but also a nuanced, contextually rich comprehension of model decisions. To validate and enhance our framework, we undertook a survey to gauge preferences and reception among various user demographics. Our findings underscored a dichotomy: professionals with academic orientations, particularly those in roles like Data Scientist, IT Expert, and ML Engineer, showcased a profound, technical understanding and often exhibited a predilection for amalgamated methods for interpretability. Conversely, end-users or individuals less acquainted with AI and Data Science showcased simpler inclinations, such as bar plots indicating timestep significance or visual depictions pinpointing pivotal segments of a vessel's trajectory.

XAI, or Explainable AI, develops Artificial Intelligence (AI) systems that can explain their decisions and actions. XAI thus promotes transparency and aims to enable trust in AI technologies [18]. While traditional interpretable machine learning (ML) approaches (such as Gaussian Mixture Models [10], K-Nearest Neighbors [3], and decision trees [23]) have been widely used to model geospatial (and spatiotemporal) phenomena and corresponding data, the increasing size and complexity of spatiotemporal data have raised the need for complex methods to model such data. Therefore, recent studies focused on using black-box models, often in the form of deep learning models [9, 11, 7, 8, 13, 2]. With this rise of Geospatial AI (GeoAI), there is a growing need for explainability, particularly for GeoAI applications where decisions can have significant social and environmental implications [5, 25, 4]. However, XAI research and development tends towards computer vision, natural language processing, and applications involving tabular data (such as healthcare and finance) [20] and few studies have deployed XAI approaches for GeoAI (GeoXAI) [11, 25].