Sahara Ali Successfully Defends her Dissertation

PhD Candidate: Sahara Ali
Dissertation Title: Spatiotemporal Forecasting and Causality Methods for the Arctic Amplification

Committee:

- Dr Jianwu Wang (Committee Chair, UMBC)

- Dr Vandana Janeja (UMBC)

- Dr Sanjay Purushotham (UMBC)

- Dr Md. Osman Gani (UMBC)

- Dr Aneesh Subramanian (UC Boulder)

The Arctic is a region with unique climate features where warming has been almost twice as fast as the rest of the world. The warming of the Arctic, also known as Arctic amplification, is led by several atmospheric and oceanic drivers. The essential part of Arctic amplification is the unprecedented sea ice loss as demonstrated by satellite observations. However, understanding the causes of sea-ice variations and its feedback on the atmospheric processes is a complex task. Therefore, accurately forecasting Arctic sea ice from sub-seasonal to seasonal scales has been a major scientific challenge and has gained interest of Data Scientists to develop novel statistical and machine learning approaches for this task. This brings us to three key research areas studied in this dissertation: (i) accurate forecasting of climate data in the Arctic on sub-seasonal to seasonal scales, (ii) estimating the influence of atmospheric processes and their time-varying effects on the sea-ice and ice-sheet variations. (iii) estimating the spatial interference of atmospheric processes and their time-varying effects on the sub-regional sea-ice variations.

For the first topic, this research explores the potential of data-driven approaches to study sea ice variations by proposing custom deep learning modeling techniques to learn spatiotemporal variations in the sea ice. By combining the spatial skills of convolutional neural networks (CNNs), predictive power of recurrent neural networks (RNNs) and other hybrid modeling techniques (ConvLSTM), the proposed models reduce the prediction error by 60% as compared to the state-of-the-art approaches. The work further contributes to accurate long-term forecasting beyond the seasonal barrier.

For the second topic, the research utilizes potential outcome framework to infer causation in climate data on daily and monthly temporal scales using custom deep learning based forecasting models. In comparison with related work, the framework proposes a deep learning based causal inference model to infer causation under continuous treatment using recurrent neural networks, and a novel probabilistic balancing technique to reduce the confounding bias.
For the third topic, this work formalizes the concept of spatial interference in case of time-varying treatment assignments by extending the potential outcome framework under the assumption of no unmeasured confounding. The extended framework utilizes latent factor modeling to reduce the bias due to time-varying confounding while leveraging the power of U-Net architecture to capture global and local spatial interference in data over time. The proposed causal estimators are an extension of average treatment effect (ATE) for estimating direct (DATE) and indirect effects (IATE) of spatial interference on treated and untreated data. Being the first of its kind deep learning based spatiotemporal causal inference technique, the proposed approach shows advantages over several baseline methods based on the experiment results on synthetic datasets, with and without spatial interference. The empirical results on the Arctic dataset not only align with domain knowledge, but also pave paths in quantifying the impact of causal drivers of climate change in the Arctic.

Overall, these predictive and inferential models have the potential to generalize for multiple downstream tasks and can be extended to other domains beyond Earth Science.