Research map / Time series / Long-term forecasting
Time-Series Decomposition as a Standalone Task: A Mechanism-Driven Diagnostic Benchmark
Zipeng Wu, Jiani Wei, Shiqiao Zhou, Jiajun chen, Fabian Spill, J. W. Andrews
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| decompose with STL, CEEMDAN or VMD before symbolic regression | PySR · Mauna Loa CO2 | Seasonal R2: 0.000 -> 0.897 (STL), 0.989 (VMD) | Improved |
| decompose with SSA before ND2 symbolic regression | ND2 · Linear-plus-sine synthetic | Reconstruction R2: near-zero -> R2 about 0.31 | Improved |
| decompose with STL before ND2 on multi-harmonic signal | ND2 · Linear-plus-multi-harmonic synthetic | Trend SR R2: about 0.55 -> about 0.91 | Improved |
| decompose with STL before ND2 on multi-harmonic signal | ND2 · Linear-plus-multi-harmonic synthetic | Seasonal SR R2: seasonal SR remains low (about 0.03) | No clear effect |
| decompose before PySR when M2/S2 frequencies are close | PySR · Tidal dataset | Seasonal R2: seasonal R2 to the 0.46-0.60 range | Mixed |
| use FFT-estimated period instead of true period (ablation) | STL · Period robustness | Seasonal max-lag correlation: 0.889 -> 0.798 | Hurt |
| misspecify the period by +20% (ablation) | STL · Period robustness | Seasonal max-lag correlation: 0.889 -> 0.405 | Hurt |
| misspecify the period by +20% (ablation) | MSTL · Period robustness | Seasonal max-lag correlation: 0.913 -> 0.338 | Hurt |
| use unsupervised peak matching instead of injected-period matching (ablation) | CEEMDAN · Alignment robustness | Aggregate score: 0.727 -> 0.355 | Hurt |
| use truth-guided component matching instead of injected matching (ablation) | VMD · Alignment robustness | Aggregate score: -0.283 -> 0.559 | Improved |
| bounded common-budget tuning of VMD (ablation) | VMD · Robustness subset (5 scenarios) | Aggregate rank order: STL > Wavelet > VMD -> VMD > STL > Wavelet | Improved |
| frequency drift scenario: fixed-period prior (STL) vs SSA | STL vs SSA · Frequency-drift scenario | Seasonal max-lag correlation: 0.967 (SSA) vs 0.790 (STL) | Hurt |
Closest papers by meaning
- Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecasting (NeurIPS 2024 · similarity 0.87)
- TimeBase: The Power of Minimalism in Efficient Long-term Time Series Forecasting (ICML 2025 · similarity 0.86)
- Filtered Conformal Ellipsoids for Graph-Native Time Series (NeurIPS 2026 · similarity 0.86)
- Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection (NeurIPS 2025 · similarity 0.85)
- Explain Temporal Black-Box Models via Functional Decomposition (ICML 2024 · similarity 0.85)
- CausalDynamics: A large‐scale benchmark for structural discovery of dynamical causal models (NeurIPS 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
