# Learning What Matters: Causal Time Series Modeling for Arctic Sea Ice Prediction

arXiv: https://arxiv.org/abs/2509.09128 · HTML: https://mlsanity.com/paper/2509.09128/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 28 references that are in the map.
- First posted on arXiv 11 Sep 2025.

## Builds on (most cited first, 9 of 9)

- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Discovering contemporaneous and lagged causal relations in autocorrelated nonlinear time series datasets](https://mlsanity.com/paper/2003.03685/) (2020)
- [A Survey on Causal Discovery Methods for I.I.D. and Time Series Data](https://mlsanity.com/paper/2303.15027/) (2023)
- [TimeGraph: Synthetic Benchmark Datasets for Robust Time-Series Causal Discovery](https://mlsanity.com/paper/2506.01361/) (2025)
- [Sea Ice Forecasting using Attention-based Ensemble LSTM](https://mlsanity.com/paper/2108.00853/) (2021)
- [Hierarchical Information-sharing Convolutional Neural Network for the Prediction of Arctic Sea Ice Concentration and Velocity](https://mlsanity.com/paper/2311.00167/) (2023)
- [Correlation to Causation: A Causal Deep Learning Framework for Arctic Sea Ice Prediction](https://mlsanity.com/paper/2503.02093/) (2025)
- [Time Series Classification of Supraglacial Lakes Evolution over Greenland Ice Sheet](https://mlsanity.com/paper/2410.05638/) (2024)
- [SIFM: A Foundation Model for Multi-granularity Arctic Sea Ice Forecasting](https://mlsanity.com/paper/2410.14732/) (2024)

## Built on by (most cited first, 1 of 1)

- [Causal Time Series Modeling of Supraglacial Lake Evolution in Greenland under Distribution Shift](https://mlsanity.com/paper/2510.15265/) (2025)

## Abstract (arXiv)

Conventional machine learning and deep learning models typically rely on correlation-based learning, which often fails to distinguish genuine causal relationships from spurious associations, limiting their robustness, interpretability, and ability to generalize. To overcome these limitations, we introduce a causality-aware deep learning framework that integrates Multivariate Granger Causality (MVGC) and PCMCI+ for causal feature selection within a hybrid neural architecture. Leveraging 43 years (1979-2021) of Arctic Sea Ice Extent (SIE) data and associated ocean-atmospheric variables at daily and monthly resolutions, the proposed method identifies causally influential predictors, prioritizes direct causes of SIE dynamics, reduces unnecessary features, and enhances computational efficiency. Experimental results show that incorporating causal inputs leads to improved prediction accuracy and interpretability across varying lead times. While demonstrated on Arctic SIE forecasting, the framework is broadly applicable to other dynamic, high-dimensional domains, offering a scalable approach that advances both the theoretical foundations and practical performance of causality-informed predictive modeling.