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 methods 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 Network to infer causation under continuous treatment using recurrent neural networks and a novel probabilistic balancing technique. More specifically, we propose a neural network based potential outcome model using the long-short-term-memory (LSTM) layers for time-delayed factual and counterfactual predictions with a custom weighted loss. To tackle the confounding bias, we experiment with multiple balancing strategies, namely TCINet with the inverse probability weighting (IPTW), TCINet with stabilized weights using Gaussian Mixture Model (GMMs) and TCINet without any 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.

Arctic sea ice plays integral roles in both polar and global environmental systems, notably ecosystems, commu-nities, and economies. As sea ice continues to decline due to climate change, it has become imperative to accurately predict the future of sea ice extent (SIE). Using datasets of Arctic meteorological and SIE variables spanning 1979 to 2021, we propose architectures capable of processing multivariate time series and spatiotemporal data. Our proposed framework consists of ensembled stacked Fourier Transform signals (FFTstack) and Gradient Boosting models. In FFTstack, grid search iteratively detects the optimal combination of representative FFT signals, a process that improves upon current FFT implementations and deseasonalizers. An optimized Gradient Boosting Regressor is then trained on the residual of the FFTstack output. Through ex-periment, we found that the models trained on both multivariate and spatiotemporal time series data performed either similar to or better than models in existing research. In addition, we found that integration of FFTstack improves the performance of current multivariate time series deep learning models. We conclude that the high flexibility and performance of this methodology have promising applications in guiding future adaptation, resilience, and mitigation efforts in response to Arctic sea ice retreat.

Arctic amplification has altered the climate patterns both regionally and globally, resulting in more frequent and more intense extreme weather events in the past few decades. The essential part of Arctic amplification is the unprecedented sea ice loss as demonstrated by satellite observations. Accurately forecasting Arctic sea ice from sub-seasonal to seasonal scales has been a major research question with fundamental challenges at play. In addition to physics-based Earth system models, researchers have been applying multiple statistical and machine learning models for sea ice forecasting. Looking at the potential of data-driven approaches to study sea ice variations, we propose MT-IceNet – a UNet-based spatial and multi-temporal (MT) deep learning model for forecasting Arctic sea ice concentration (SIC). The model uses an encoder-decoder architecture with skip connections and processes multi-temporal input streams to regenerate spatial maps at future timesteps. Using bi-monthly and monthly satellite retrieved sea ice data from NSIDC as well as atmospheric and oceanic variables from ERA5 reanalysis product during 1979-2021, we show that our proposed model provides promising predictive performance for per-pixel SIC forecasting with up to 60% decrease in prediction error for a lead time of 6 months as compared to its state-of-the-art counterparts.

The Arctic is a region with unique climate features, motivating new AI methodologies to study it. Unfortunately, Arctic sea ice has seen a continuous decline since 1979. This not only poses a significant threat to Arctic wildlife and surrounding coastal communities but is also adversely affecting the global climate patterns. To study the potential of AI in tackling climate change, we analyze the performance of four probabilistic machine learning methods in forecasting sea-ice extent for lead times of up to 6 months, further comparing them with traditional machine learning methods. Our comparative analysis shows that Gaussian Process Regression is a good fit to predict sea-ice extent for longer lead times with lowest RMSE score.

Critical natural resources and processes in the Arctic depend heavily on sea ice. Thus, accurate and timely predictions of Arctic sea ice changes is important. Arctic sea ice forecasting involves two connected tasks: predicting sea ice concentration (SIC) at each pixel and predicting overall sea ice extent (SIE). Instead of having two separate models for these two forecasting tasks, in this paper we study how to use multi-task learning techniques and leverage the connections between ice concentration and ice extent to improve accuracy for both forecasting tasks. Because of the spatiotemporal nature of the data, we designed two novel multi-task learning models based on the CNN and ConvLSTM, respectively. Further, in conjunction with multi-task models, we developed custom loss functions which train the models to ignore land pixels and optimize for both concentration and extent when making predictions. Our experiments show that multi-task models provide better accuracy for a 1-month lead time than models that predict sea ice extent and concentration separately. Our accuracies are better than or comparable to results in related state-of-the-art studies. Our best model in SIC prediction outperformed the best existing SIC prediction model in the literature with 1.78% less error, and our best model in SIE prediction outperformed the best existing SIE prediction model with 0.283 million km2less error.

Domain adaptation techniques have been developed to handle data from multiple sources or domains. Most existing domain adaptation models assume that source and target domains are homogeneous, i.e., they have the same feature space. Nevertheless, many real world applications often deal with data from heterogeneous domains that come from completely different feature spaces. In our remote sensing application, data in source domain (from an active spaceborne Lidar sensor CALIOP onboard CALIPSO satellite) contain 25 attributes, while data in target domain (from a passive spectroradiometer sensor VIIRS onboard Suomi-NPP satellite) contain 20 different attributes. CALIOP has better representation capability and sensitivity to aerosol types and cloud phase, while VIIRS has wide swaths and better spatial coverage but has inherent weakness in differentiating atmospheric objects on different vertical levels. To address this mismatch of features across the domains/sensors, we propose a novel end-to-end deep domain adaptation with domain mapping and correlation alignment (DAMA) to align the heterogeneous source and target domains in active and passive satellite remote sensing data. It can learn domain invariant representation from source and target domains by transferring knowledge across these domains, and achieve additional performance improvement by incorporating weak label information into the model (DAMA-WL). Our experiments on a collocated CALIOP and VIIRS dataset show that DAMA and DAMA-WL can achieve higher classification accuracy in predicting cloud types.