GeoEvent Detection and Spatiotemporal Analytics - using Tropical Cyclone Hot Tower as an example

Authors: Manzhu Yu*, George Mason University, Chaowei Yang, George Mason University, Dan Duffy, NASA Center for Climate Simulation
Topics: Spatial Analysis & Modeling, Geographic Information Science and Systems
Keywords: Tropical Cyclones, Hot Tower, Random Forests
Session Type: Paper
Day: 4/5/2019
Start / End Time: 9:55 AM / 11:35 AM
Room: Forum Room, Omni, West
Presentation File: No File Uploaded

Climate simulations provide valuable information to represent the situations of the atmosphere, ocean, and land. Increasingly advanced computational technologies and Earth observation capabilities have enabled the climate models to have higher spatial and temporal resolution, providing an ever realistic coverage of the Earth. The high spatiotemporal resolution provides us the opportunity to more precisely pinpoint and identify the occurrence of extreme weather events, e.g., cyclones, dust storms, and ocean eddies. The precise identification, along with the temporal movement tracking, enables the scientists a better understanding of the spatiotemporal dynamics of these events, e.g., their common origins, their temporal (diurnal, monthly, seasonal, or inter-annual) trends in a regional or global scale, or their impacting spatial scales. This research illustrates the understanding of spatiotemporal dynamics of tropical cyclone hot towers and the discovery of the relationship between hot towers and climate variables in high dimension using Random Forests. Experiment results showed a high detection accuracy of ~98% on predicting the occurrence and height of hot towers.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login