Multiscale Time-Series Modeling

Ask about this topic

Overview

Multiscale time-series modeling studies how to represent and predict signals whose patterns unfold over different time spans, from brief events and local fluctuations to cycles and long-term trends. Common approaches use wavelet or frequency decomposition, hierarchical patches and pooling, multi-branch convolutional or Transformer and state-space encoders, and adaptive gates or expert routing to combine scales; some also handle irregular sampling and cross-variable or spatial structure. These methods support forecasting, classification, anomaly detection, imputation, and generation in settings such as sensors, health, climate, traffic, and finance, where missing a scale can obscure useful dynamics. A central challenge is choosing scales that adapt to changing patterns and sampling rates while preserving detail, generalizing across datasets and horizons, and keeping computation and uncertainty reliable.

Latest papers

CardsList

119 papers18 papers in the last four weeks, up 64% on the four weeks before. 0.1% of all new papers.

  1. SpecLST: Spectral-Enhanced Long-Short Term Spatio-Temporal Multimodal Modeling for Traffic Forecasting

    Oct 26, 2026Kenan Kang, Matthew M. Y. Kuo, Weihua LiSpatiotemporal ForecastingTraffic Forecasting

    Department of Computer Science and Software Engineering, Auckland University of Technology, Auckland 1010, New Zealand · Department of Data Science and Artificial Intelligence, Auckland University of Technology, Auckland 1010, New Zealand

  2. STeP-TS: Shared Temporal Filters with Pruning for Time Series

    Oct 26, 2026Hanne Raum, Jasper Hoffmann, Joschka BoedeckerMultivariate Time Series ForecastingMultiscale Time-Series Modeling

    Department of Computer Science Albert-Ludwigs-Universität Freiburg · Department of Computer Science and BrainLinks-BrainTools Albert-Ludwigs-Universität Freiburg

  3. The Future Is Finer: Multivariate Time Series Super-Resolution Forecasting

    Oct 24, 2026Shuhao Li, Weidong Yang, Yue Cui +2Multivariate Time Series ForecastingMultiscale Time-Series Modeling

    Fudan University, Shanghai, China · Nanyang Technological University, Singapore · Zhuhai Fudan Innovation Research Institute, Zhuhai, China +3

  4. YingLan: A Multimodal Ocean Foundation Model for Unified Representation Learning from Heterogeneous Observations

    Oct 21, 2026Sen Jia, Siqi Wei, Junyu Wang +8Multimodal Foundation ModelsSpatiotemporal Forecasting

    College of Computer Science and Software Engineering, Shenzhen University · College of Life Sciences and Oceanography, Shenzhen University

  5. FracTS: Hierarchical and Autoregressive Time Series Generation

    Oct 18, 2026Jiayu Li, Umair Afzal, Zilong Zhao +3Time Series GenerationAutoregressive Generation

    University of Illinois Urbana-Champaign · Betterdata AI · National University of Singapore

  6. LC-TSRNet: A Land-Cover-Guided Two-Stage Network for Annual MODIS Surface Reflectance Time Series Reconstruction

    Oct 18, 2026Wenjuan Zhang, Xuesong Ma, Zhen Li +5Remote SensingMultiscale Time-Series Modeling

    State Key Laboratory of Remote Sensing and Digital Earth, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, China · Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China · College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, China +3

  7. SuperClip Pyramid for Video Temporal Grounding

    Oct 17, 2026Sanghyeok Lee, Juyeon Ko, Joonmyung Choi +4Temporal Video GroundingVideo Moment Retrieval

    KAIST · TwelveLabs · KT +1

  8. M2NetM^2Net: Unifying Scale-Specific Structures and Prototype Decomposition for Spatial-Temporal Forecasting

    Oct 17, 2026Chengyang Zhou, Zijian Zhang, Hao Miao +5Spatiotemporal ForecastingMultiscale Time-Series Modeling

    College of Computer Science and Technology, Jilin University, Changchun, China · Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China +2

  9. Morpheus-2.0: Multiscale Probabilistic Forecasting with Dual-Axis Attention

    Oct 16, 2026Aakriti, Manoj Cherukumalli, Prathamesh Patil +5Time Series ForecastingProbabilistic Time Series Forecasting

  10. Hyperbolic Time Series Forecasting with Learnable Decomposition and Manifold Dynamics

    Oct 11, 2026Sarang Rajendra Patil, Vishal Fenn, Mengjia XuLong-Term Time Series ForecastingTime Series Forecasting

    Department of Data Science New Jersey Institute of Technology Newark, NJ 07102, USA

  11. Revisiting Identity and Spectra Dispersion in Media-Bridged Time Series Forecasting: Linking Multivariate Signals and Narrative Flows

    Oct 8, 2026Jierui Lei, Wenjian Zhang, Qingyi Yang +5Time Series ForecastingSpatiotemporal Forecasting

    School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences, Beijing 100049, China · State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China · School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, Guangdong 518107, China +3

  12. Reconstruction of Multiscale Plasma Dynamics Across Operating Regimes

    Oct 7, 2026Maryam Reza, Farbod FarajiRecurrent Neural NetworksMultiscale Time-Series Modeling

    Independent Researcher · Department of Computing, Huxley Building, Imperial College London, London SW7 2RH, United Kingdom

  13. Robust Prediction of Internal Wave-Affected Multi-Scale Sound Speed Distribution Using Lightweight Kolmogorov-Arnold Networks with Hybrid Basis Functions

    Oct 7, 2026Wei Huang, Junpeng Lu, Tianhe Xu +2Underwater AcousticsKolmogorov-Arnold Networks

    Faculty of Information Science and Engineering, Ocean University of China, Qingdao, Shandong 266404, China · School of Space Science and Technology, Shandong University at Weihai, Weihai, Shandong 264200, China · School of Artificial Intelligence, The Chinese University of Hong Kong (Shenzhen), Shenzhen, Guangdong 518172, China

  14. HAN-Mamba: Hierarchical Selective State Space Networks for Multi-Scale Financial Volatility Forecasting

    Oct 7, 2026Mihai Bogdan Deaconu, Ioan Daniel PopTime Series ForecastingFinancial Time Series

    Faculty of Mathematics and Computer Science, Babeş-Bolyai University, Cluj-Napoca, Romania

  15. Matching of signal, noise and hardware timescales for filtering and forecasting of correlated noise signals

    Oct 7, 2026Joshua Donald, Alex Gabbitas, Arthur G. T. Coveney +2Reservoir ComputingTime Series Forecasting

    Department of Physics, Loughborough University, Loughborough, LE11 3TU, United Kingdom

  16. LogSig-SSM: Time-Series Modelling with Multi-Scale Log-Signature Compression for State-Space Models

    Oct 4, 2026Felix Oury, Nicolas Calvo Peiro, Reiko J. TanakaIrregular Time-Series ModelingMultivariate Time Series Forecasting

    Department of Computing Imperial College London · Department of Bioengineering Imperial College London

  17. Inferring Multi-Timescale Neural Dynamics with Switching Linear Dynamical Systems

    Oct 1, 2026Lulu Gong, Yongxu Zhang, Shreya SaxenaStochastic Linear Dynamical SystemsLatent Dynamics Modeling

    Center for Neurocomputation and Machine Intelligence, Wu Tsai Institute, Department of Biomedical Engineering, Yale University, New Haven, CT 06510, USA

  18. NeurDuo-EEG: A Long-Sequence EEG Foundation Model with Persistent State and Explicit Memory

    Sep 29, 2026Yifan Wang, Haiping Liu, Yang Cui +13Memory-Augmented Neural NetworksElectroencephalography

    University of Manchester · ETH Zürich · Shanghai Jiao Tong University +5

  19. No Scale Left Behind: Multi-Scale Autoencoder with Bi-directional Attention for Time Series Anomaly Detection

    Sep 29, 2026Jiaheng Guo, Haochen Zhang, Yu-Chao Huang +3Reconstruction-Based Anomaly DetectionAttention Mechanisms

    UNITES Lab, University of North Carolina at Chapel Hill

  20. Context-dependent time-series prediction via HyperReservoirs

    Sep 28, 2026Kohei Tsuchiyama, Takatomo Mihana, Ryoichi Horisaki +1Time Series ForecastingReservoir Computing

    Department of Information Physics and Computing, Graduate School of Information Science and Technology, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan

  21. Fracast-0: Fractal Weight Sharing for a Time Series Foundation Model with Only 85K Parameters

    Sep 26, 2026Tianxiang Zhan, Huanyao Zhang, Yuanpeng HeTime-Series Foundation ModelsProbabilistic Time Series Forecasting

    University of Electronic Science and Technology of China · Peking University

  22. Neuralized Multi-Wavelet Decomposition for Time Series Classification and Forecasting

    Sep 24, 2026Xiaohan Jiang, Jingyuan Wang, Jiahao Ji +3Time Series ClassificationFrequency-Domain Feature Learning

    School of Computer Science and Engineering, Beihang University, Beijing, China · School of Computer Science and Engineering and the School of Economics and Management, Beihang University, Beijing, China · School of Computer Science and Engineering, Beihang University, Beijing, China, and are also with the MOE Engineering Research Center of Advanced Computer Application Technology, Beihang University, China +1

  23. Multi-Term Fourier Graph Neural Network with Sample Relationship Learning for Enhanced Remaining Useful Life Prediction

    Sep 21, 2026Ya Song, Laurens Bliek, Yaoxin Wu +1Graph Neural NetworksRUL Estimation

    Information Systems, Department of Industrial Engineering & Innovation Sciences, Eindhoven University of Technology, Eindhoven, The Netherlands

  24. Brain-Token Learning: Microstate-Based Tokenization and Multi-Scale Interaction for Long-Horizon EEG Sequence Modeling

    Sep 21, 2026Weishan Ye, Yue Pan, Li Zhang +2ElectroencephalographySequence Modeling

    School of Biomedical Engineering, Medical School, Shenzhen University, Shenzhen 518060, China, also with the Guangdong Provincial Key Laboratory of Biomedical Measurements and Ultrasound Imaging, Shenzhen 518060, China

  25. Recovering Lost Details: Multi-Scale Frequency Compensation for Long-Term Time Series Forecasting

    Sep 21, 2026Runmin Zou, Siyi Xie, Yaohui Huang +1Long-Term Time Series ForecastingTime Series Forecasting

    Central South University Changsha, Hunan, China

  26. HARN: Hierarchical Associative Resonance Network for Event-Driven Multi-Timeframe Forecasting

    Sep 20, 2026Nabeel Ahmad SaiddTime Series ForecastingFinancial Time Series

    Dr. APJ Abdul Kalam Technical University

  27. TWIG: A Time-Causal Wavelet Operator for Autoregressive Forecasting on Irregular Graphs

    Sep 18, 2026Subashree Venkatasubramanian, David A. Barajas-Solano, Chuyang Liu +2Neural Surrogate ModelingSpatiotemporal GNNs

    Lawrence Berkeley National Laboratory, Berkeley, CA, USA · Stanford University, Stanford, CA, USA · Pacific Northwest National Laboratory, Richland, WA, USA

  28. A Multi-Resolution Multi-Domain Pre-Training Framework for Universal Traffic Forecasting

    Sep 12, 2026Zhouyang Liu, Jindong Han, Hao Wang +4Traffic ForecastingSpatiotemporal Forecasting

    PDL Lab, National University of Defense Technology, Hunan, China · Shandong University, Shandong, China · HKUST (GZ) +2

  29. PPDL: A Real-world Industrial User Retention Ratio Forecasting Framework Integrating Physical Priors with Deep Learning

    Sep 12, 2026Zibo Zhao, Zhengxiong Guan, Chaoli Zhang +4Time Series ForecastingHuman Behavior Prediction

    Zhejiang Normal University · Douyin Group · Shanghai Jiao Tong University

  30. HypLTSF: A Hyperbolic Geometric View of Multi-Scale Hierarchies for Long-Term Time Series Forecasting

    Sep 8, 2026Namwoo Kim, Hyungryul Baik, Yoonjin YoonLong-Term Time Series ForecastingHierarchical Representation Learning

    Urban AI Institute, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea · Department of Mathematical Science, KAIST, Daejeon, Republic of Korea · Department of Civil and Environmental Engineering, KAIST, Daejeon, Republic of Korea