Reducing Uncertainty in Sea-level Rise Prediction: A Spatial-Variability-Aware Approach

• Main Authors: Ghosh, Subhankar, An, Shuai, Sharma, Arun, Gupta, Jayant, Shekhar, Shashi, Subramanian, Aneesh
• Format: Text
• Language: unknown
• Published: Purdue University 2023
• Subjects: Applied Statistics; Artificial Intelligence and Robotics; Atmospheric Sciences; Climate; Databases and Information Systems; Data Science; Dynamical Systems; Geographic Information Sciences; Geological Engineering; Geology; Geophysics and Seismology; Glaciology; Human Geography; Hydrology; Numerical Analysis and Scientific Computing; Ocean Engineering; Oceanography; Operations Research; Systems Engineering and Industrial Engineering; Other Computer Sciences; Other Earth Sciences; Other Environmental Sciences; Other Geography; Other Mathematics; Other Physical Sciences and Mathematics; Physical and Environmental Geography; Remote Sensing; Spatial Science; Urban Studies and Planning; Water Resource Management; Antarctic; Greenland; Antarc*; Ice; Ice Shelf; permafrost
• Online Access: https://docs.lib.purdue.edu/iguide/2023/presentations/3; https://docs.lib.purdue.edu/context/iguide/article/1022/viewcontent/Reducing_Uncertainty_in_Sea_level_Rise_Prediction__A_Spatial_variability_aware_Approach.pdf

Given multi-model ensemble climate projections, the goal is to accurately and reliably predict future sea-level rise while lowering the uncertainty. This problem is important because sea-level rise affects millions of people in coastal communities and beyond due to climate change's impacts on polar ice sheets and the ocean. This problem is challenging due to spatial variability and unknowns such as possible tipping points (e.g., collapse of Greenland or West Antarctic ice-shelf), climate feedback loops (e.g., clouds, permafrost thawing), future policy decisions, and human actions. Most existing climate modeling approaches use the same set of weights globally, during either regression or deep learning to combine different climate projections. Such approaches are inadequate when different regions require different weighting schemes for accurate and reliable sea-level rise predictions. This paper proposes a zonal regression model which addresses spatial variability and model inter-dependency. Experimental results show more reliable predictions using the weights learned via this approach on a regional scale.