This paper presents a comprehensive cross-task analysis of time series methodologies, revealing fundamental connections that are often obscured by task-specific perspectives. Our contributions are fivefold. First, we introduce seven priority properties, along with exogenous integration, that characterize methodologies independent of application domain, enabling systematic comparison across traditional and modern approaches. Second, we classify neural architectures by transparency levels determined by two characteristics: parameter time-invariance and the explicitness of mathematical formulations. Locally time-invariant operations enable mechanistic understanding, but globally time-varying operations pose fundamental challenges to achieving it. Third, our hierarchical taxonomy guides the selection of methodologies. Fourth, we comparatively evaluate explanation methods by quantifying how closely they recover transparency, measuring explanation richness via breadth (granularity) and depth (mechanistic understanding): pointwise methods offer lower richness, component-level methods achieve medium richness, and concept-based methods achieve higher richness, sometimes at the cost of generalization. Finally, we identify an ongoing challenge from the absence of ground truth for temporal components and outline future research directions for time-varying modeling explanations. This survey provides methodological insights and practical frameworks in time series analysis.
Park et al. (Thu,) studied this question.