{"id":"doi:10.1016/j.cosrev.2025.100883","kind":"article","title":"A survey of transformer networks for time series forecasting","authors":["Jingyuan Zhao","Fulin Chu","Lili Xie","Yunhong Che","Yuyan Wu","Andrew F. Burke"],"author_count":6,"year":2025,"published":"2025-12-19","venue":"Computer Science Review","cited_by":54,"doi":"10.1016/j.cosrev.2025.100883","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1016/j.cosrev.2025.100883","archive_url":"https://space-kitty.com/papers/doi:10.1016/j.cosrev.2025.100883","updated":null,"pmid":null,"pmcid":null,"openalex_id":"W4417506931","pdf_url":null,"abstract":"• Introduction to Transformers, their framework, hyperparameters, and learning paradigms. • Comprehensive assessment of tailored Transformers for advanced time series forecasting. • In-depth analysis of applications in finance, healthcare, energy, and transportation. • Discussion of challenges such as computational cost, datasets, overfitting, and interpretability. • Insights into integrating knowledge, multimodal, efficiency and AI-driven approaches. Time-series data support critical functions in forecasting, anomaly detection, resource optimization, and real-time decision making across finance, healthcare, energy systems, and networked computing. Classical statistical approaches and early deep-learning architectures (RNNs, LSTMs, CNNs) have achieved notable progress, yet they exhibit structural limitations: recurrent models struggle with long-range dependencies, convolutional models require deep stacking to enlarge receptive fields, and both scale suboptimally to high-dimensional and high-volume data. Transformer architectures—characterized by global attention mechanisms, flexible temporal receptive fields, and growing adoption within foundation-model paradigms—have consequently gained increasing prominence for modern time-series analysis. Drawing on a systematic review of IEEE Xplore, ACM Digital Library, and Scopus (2020–2025), this survey offers a unified, theoretically grounded synthesis of Transformer-based methods for time-series learning. The survey summarizes defining characteristics of time-series data and analyzes core architectural elements, including attention formulations, encoder–decoder structures, hyperparameter design, and domain-specific adaptations. An architecture-centered and task-aware taxonomy is presented to organize recent advances across forecasting, representation learning, anomaly detection, and multimodal fusion. Persistent challenges—spanning computational scalability, data-efficiency constraints, distributional heterogeneity, overfitting risks, hyperparameter instability, interpretability, and reproducibility—are examined in depth. A forward-looking research agenda is outlined, highlighting opportunities in physics-informed architectural design, hybrid neural–mechanistic modeling, resource-efficient real-time inference, multi-resolution spatiotemporal learning, and emerging human–AI collaborative paradigms. By consolidating these methodological developments, this survey aims to provide a structured reference point for ongoing research on Transformer models for time-series machine learning.","abstract_license":"CC-BY (publisher license, via OpenAlex)","license":"cc-by","is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Time Series Analysis and Forecasting"],"details":null,"provenance":"openalex","attribution":"Abstract of \"A survey of transformer networks for time series forecasting\" by Jingyuan Zhao, Fulin Chu, Lili Xie et al., https://doi.org/10.1016/j.cosrev.2025.100883, used under its Creative Commons Attribution license (CC-BY); markup removed, otherwise unmodified.","topics":[{"slug":"interpretability","name":"Mechanistic Interpretability","domain_slug":"ai"}],"cited_in_dossiers":[]}