Paper Info
Title
A data modeling approach to climate change attribution
Abstract
Climate modeling and analysis of climate change have largely been based on forward simulation with physical models. We propose here a data centric approach to climate study based solely on the actual observed data. This novel approach utilizes a variety of relevant statistical modeling and machine learning techniques such as spatial-temporal causal modeling and extreme value modeling, and suggests multiple future research directions. We will describe preliminary results using data for North America from CRU, NOAA, NASA, NCDC, and CDIAC, as well as certain technical challenges encountered. It is hoped that this alternative perspective will help uncover new insights, improve aspects of simulation models with known uncertainties, and provide a useful complementary approach to climate study.
Year
DOI
Venue
2009
10.1145/1601966.1601968
KDD Workshop on Knowledge Discovery from Sensor Data
Keywords
Field
DocType
machine learning,physical model,extreme value,climate model,simulation model,data model,causal models,statistical model,climate change
Data science,Data modeling,Climate model,Climate change,Cru,Computer science,Simulation modeling,Artificial intelligence,Causal model,Database-centric architecture,Simulation,Statistical model,Machine learning
Conference
Citations 
PageRank 
References 
0
0.34
1
Authors
1
Name
Order
Citations
PageRank
Aurelie C. Lozano114520.21