Dissertation Defense, PhD Geography & Geoinformation Science

Candidate: Bradley A. Gay 

PhD of Science, Earth Systems and Geoinformation Sciences 

Department of Geography and Geoinformation Science 

Date: Monday, May 1, 2023 

Time: 1:00 PM 

Location: GGS Conference Room | Exploratory Hall 2304 

Virtual Location:  Microsoft Teams 

Meeting ID: 271 178 648 638 

Passcode: C48uqZ 

Committee: 

Dr. John J. Qu, Dissertation Director 

Dr. Amanda H. Armstrong, Committee Member 

Dr. Paul A. Dirmeyer, Committee Member 

Dr. Konrad J. Wessels, Committee Member 

Dr. Andreas E. Züfle, Committee Member 

Title:  INVESTIGATING HIGH-LATITUDE PERMAFROST CARBON DYNAMICS WITH ARTIFICIAL INTELLIGENCE AND EARTH SYSTEM DATA ASSIMILATION 

Abstract: 

It is well-established that positive feedbacks between permafrost degradation and the release of soil carbon into the atmosphere impacts land-atmosphere interactions, disrupts the global carbon cycle, and accelerates climate change. The widespread distribution of thawing permafrost is causing a cascade of geophysical and biochemical disturbances with global impact. Currently, few earth system models account for permafrost carbon feedback mechanisms. Therefore, the scope of this research seeks to identify, interpret, and explain the causal links and feedback sensitivities attributed to permafrost degradation and terrestrial carbon cycling asymmetry with in-situ measurements and flux tower observations, remote sensing technology, process-based modeling products, and deep learning architecture. In summary, this dissertation addresses the following objectives: (1) define and formulate high-resolution polymodal datasets with multitemporal extents and hyperspatiospectral fidelity; (2) simulate and quantify the non-linear feedback mechanisms attributed to permafrost degradation and carbon cycle perturbation across Alaska with a process-constrained deep learning architecture composed of cascading stacks of convolutionally layered memory-encoded recurrent neural networks; and (3) quantify and interpret historical and future emulations of freeze-thaw dynamics and the permafrost carbon feedback with a suite of evaluation metrics. These contributions seek to improve our understanding of the arctic system by coupling conventional wisdom and traditional science with state-of-the-art resources to bridge gap-filling multimodalities, disentangle the complex spatiotemporal processes governing abrupt and persistent drivers of change in high-latitude ecosystems, and reconcile disparate estimations and below-ground uncertainty across the Arctic system.