Branden Lopez

Publication Date

Spring 2024

Degree Type

Master's Project

Degree Name

Master of Science in Computer Science (MSCS)

Department

Computer Science

First Advisor

Genya Ishigaki

Second Advisor

Behin Elahi

Third Advisor

Faranak Abri

Keywords

Sea Level Rise, Vertical Land Motion, Deep Learning.

Abstract

Earth system data is vast in volume and variety, and is used to forecast weather,

hurricanes, floods, and sea level. Sea Level Rise (SLR) impacts various sectors, espe- cially ecosystems, food production, industry, population, health, and the availability of

clean water. Because of its broad impact, describing the behavior and forecasting SLR is an important topic. Traditional Machine Learning (ML) models vary in use, but many are not capable of capturing all the non-linear spatial and temporal properties of SLR factors. Deep learning models efficaciously handle complex time series data, noise, and high dimensional spaces, making them a focus of recent SLR research. Long Short-Term Memory (LSTM) historically performs well for SLR predictions but has underperformed when forecasting regional SLR using altimetry data such as Mean

Temperature Anomaly (MTA) and Oceanic Heat Content (OHC) time-scaled to quar- ters. This project proposes the inclusion of Vertical Land Motion (VLM) data, which

are often disregarded by existing literature due to the lack of cohesive datasets, in the dataset along with oceanic and atmospheric variables. Our experiments focusing on Monterey Bay, California demonstrates that VLM data can improve the performance of LSTMs for regional SLR prediction. We also identify key LSTM features by feature importance computation. Furthermore, we assess the viability of using VLM in the presence of missing data points and its effects on the prediction.

Download

Share

COinS