Quantifying Causes of Arctic Amplification via Deep Learning based Time-series Causal Inference
This work addresses the challenge of causal inference in observational Earth science, specifically for understanding Arctic amplification, but it appears incremental as it builds on existing methods with a novel technique for known bottlenecks.
The paper tackled the problem of quantifying causal effects of atmospheric processes on Arctic sea ice melt, which is hindered by time-varying confoundedness and non-linearity in Earth science data, and proposed TCINet, a time-series causal inference model using recurrent neural networks and probabilistic balancing, showing it can substantially improve quantification of leading causes.
The warming of the Arctic, also known as Arctic amplification, is led by several atmospheric and oceanic drivers. However, the details of its underlying thermodynamic causes are still unknown. Inferring the causal effects of atmospheric processes on sea ice melt using fixed treatment effect strategies leads to unrealistic counterfactual estimations. Such models are also prone to bias due to time-varying confoundedness. Further, the complex non-linearity in Earth science data makes it infeasible to perform causal inference using existing marginal structural techniques. In order to tackle these challenges, we propose TCINet - time-series causal inference model to infer causation under continuous treatment using recurrent neural networks and a novel probabilistic balancing technique. Through experiments on synthetic and observational data, we show how our research can substantially improve the ability to quantify leading causes of Arctic sea ice melt, further paving paths for causal inference in observational Earth science.