Time-Varying Causal Treatment for Quantifying the Causal Effect of Short-Term Variations on Arctic Sea Ice Dynamics

2026-01-25

AI Summary

This study addresses the challenge of reliably estimating the causal effect between sea ice thickness and sea surface height (SSH) in spatiotemporal settings, where conventional deep learning models are hindered by unobserved confounders and the absence of physical constraints. To overcome these limitations, the authors propose KGCM-VAE, a knowledge-guided causal variational autoencoder that innovatively integrates physical priors with causal inference. The model generates physically consistent interventions by dynamically modulating velocity signals using SSH, while enforcing covariate balance in the latent space via Maximum Mean Discrepancy (MMD) and incorporating a causally constrained adjacency-aware decoder. Evaluated on both synthetic and real Arctic datasets, KGCM-VAE achieves state-of-the-art performance in causal effect estimation (lowest PEHE), with ablation studies demonstrating that the joint use of MMD balancing and causal adjacency constraints reduces estimation error by 1.88%.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Intelligent Robots: State Estimation

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Quantifying the causal relationship between ice melt and freshwater distribution is critical, as these complex interactions manifest as regional fluctuations in sea surface height (SSH). Leveraging SSH as a proxy for sea ice dynamics enables improved understanding of the feedback mechanisms driving polar climate change and global sea-level rise. However, conventional deep learning models often struggle with reliable treatment effect estimation in spatiotemporal settings due to unobserved confounders and the absence of physical constraints. To address these challenges, we propose the Knowledge-Guided Causal Model Variational Autoencoder (KGCM-VAE) to quantify causal mechanisms between sea ice thickness and SSH. The proposed framework integrates a velocity modulation scheme in which smoothed velocity signals are dynamically amplified via a sigmoid function governed by SSH transitions to generate physically grounded causal treatments. In addition, the model incorporates Maximum Mean Discrepancy (MMD) to balance treated and control covariate distributions in the latent space, along with a causal adjacency-constrained decoder to ensure alignment with established physical structures. Experimental results on both synthetic and real-world Arctic datasets demonstrate that KGCM-VAE achieves superior PEHE compared to state-of-the-art benchmarks. Ablation studies further confirm the effectiveness of the approach, showing that the joint application of MMD and causal adjacency constraints yields a 1.88\% reduction in estimation error.

Problem

• causal effect
• sea ice dynamics
• spatiotemporal confounding
• unobserved confounders
• physical constraints

Innovation

• causal inference
• variational autoencoder
• physical constraints
• spatiotemporal modeling
• Maximum Mean Discrepancy