mlsanityData to 7 Oct 2026

On the Integration of Spatial-Temporal Knowledge: A Lightweight Approach to Atmospheric Time Series Forecasting

arXiv 2408.09695 ↗First posted 19 Aug 2024cs.LG cs.AI physics.ao-phcited by 7

Not on the map. Why?

Abstract (arXiv)

Transformers have gained attention in atmospheric time series forecasting (ATSF) for their ability to capture global spatial-temporal correlations. However, their complex architectures lead to excessive parameter counts and extended training times, limiting their scalability to large-scale forecasting. In this paper, we revisit ATSF from a theoretical perspective of atmospheric dynamics and uncover a key insight: spatial-temporal position embedding (STPE) can inherently model spatial-temporal correlations even without attention mechanisms. Its effectiveness arises from the integration of geographical coordinates and temporal features, which are intrinsically linked to atmospheric dynamics. Based on this, we propose STELLA, a Spatial-Temporal knowledge Embedded Lightweight modeL for ASTF, utilizing only STPE and an MLP architecture in place of Transformer layers. With 10k parameters and one hour of training, STELLA achieves superior performance on five datasets compared to other advanced methods. The paper emphasizes the effectiveness of spatial-temporal knowledge integration over complex architectures, providing novel insights for ATSF. The code is available at https://github.com/GestaltCogTeam/STELLA.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 27 of its 54 references that are in the map. First posted on arXiv 19 Aug 2024.

Builds on

27 of 54 references.

References · 27

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  3. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  4. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  5. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  6. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 744
  7. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 563
  8. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 525
  9. 2021MetaFormer Is Actually What You Need for Visioncited by 523
  10. 2023FITS: Modeling Time Series with 10k Parameterscited by 185
  11. 2021Discrete Graph Structure Learning for Forecasting Multiple Time Seriescited by 169
  12. 2022Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecastingcited by 149
15 more
  1. 2022Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecastingcited by 117
  2. 2023Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysiscited by 113
  3. 2024SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameterscited by 103
  4. 2024SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusioncited by 75
  5. 2022AirFormer: Predicting Nationwide Air Quality in China with Transformerscited by 73
  6. 2023MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixingcited by 52
  7. 2023DSformer: A Double Sampling Transformer for Multivariate Time Series Long-term Predictioncited by 49
  8. 2023Improving Deep Regression with Ordinal Entropycited by 44
  9. 2021Conditional Local Convolution for Spatio-temporal Meteorological Forecastingcited by 30
  10. 2021Historical Inertia: A Neglected but Powerful Baseline for Long Sequence Time-series Forecastingcited by 26
  11. 2024Hierarchical Classification Auxiliary Network for Time Series Forecastingcited by 26
  12. 2024AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality Predictioncited by 25
  13. 2024Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecastingcited by 18
  14. 2024MLP Can Be A Good Transformer Learnercited by 16
  15. 2021Prototyping Low-Cost Automatic Weather Stations for Natural Disaster Monitoringcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 5.

7 papers.

  1. 2026AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discoverycited by 17
  2. 2025Selective Learning for Deep Time Series Forecastingcited by 8
  3. 2024OMG-HD: A High-Resolution AI Weather Model for End-to-End Forecasts from Observationscited by 5
  4. 2026Zeus: Towards Tuning-Free Foundation Model for Time Series Analysiscited by 2
  5. 2026Learning from Complexity: Exploring Dynamic Sample Pruning of Spatio-Temporal Trainingcited by 0
  6. 2026M2Weather: A Benchmark for Joint Multi-Station and Multi-Variable Weather Forecastingcited by 0
  7. 2026STCFormer: Adaptive Spatio-Temporal Modeling with Dynamic Cluster Transformer for Station-based Weather Forecastingcited by 0