Enhancing understanding and improving prediction of severe weather through spatiotemporal relational learning

Authors:
Amy Mcgovern;David J. Gagne, Ii;John K. Williams;Rodger A. Brown;Jeffrey B. Basara
Affiliations:
School of Computer Science, University of Oklahoma, Norman, USA 73019;School of Meteorology, University of Oklahoma, Norman, USA 73072;Research Applications Laboratory, National Center for Atmospheric Research, Boulder, USA 80301;NOAA/National Severe Storms Laboratory, Norman, USA 73072;School of Meteorology, University of Oklahoma, Norman, USA 73072
Venue:
Machine Learning
Year:
2014

Citing 26
Cited 2

C4.5: programs for machine learning

C4.5: programs for machine learning
Random Forests

Machine Learning
Shape distributions

ACM Transactions on Graphics (TOG)
Induction of Decision Trees

Machine Learning
Learning a Go Heuristic with TILDE

CG '00 Revised Papers from the Second International Conference on Computers and Games
Transforming classifier scores into accurate multiclass probability estimates

Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
Tree Induction for Probability-Based Ranking

Machine Learning
Learning relational probability trees

Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining
Using relational knowledge discovery to prevent securities fraud

Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining
LB_Keogh supports exact indexing of shapes under rotation invariance with arbitrary representations and distance measures

VLDB '06 Proceedings of the 32nd international conference on Very large data bases
Relational Dependency Networks

The Journal of Machine Learning Research
Relational data pre-processing techniques for improved securities fraud detection

Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining
Introduction to Statistical Relational Learning (Adaptive Computation and Machine Learning)

Introduction to Statistical Relational Learning (Adaptive Computation and Machine Learning)
A time-split nonhydrostatic atmospheric model for weather research and forecasting applications

Journal of Computational Physics
Exploiting time-varying relationships in statistical relational models

Proceedings of the 9th WebKDD and 1st SNA-KDD 2007 workshop on Web mining and social network analysis
Towards a general theory of geographic representation in GIS

International Journal of Geographical Information Science
Spatiotemporal Relational Probability Trees: An Introduction

ICDM '08 Proceedings of the 2008 Eighth IEEE International Conference on Data Mining
Temporal-Relational Classifiers for Prediction in Evolving Domains

ICDM '08 Proceedings of the 2008 Eighth IEEE International Conference on Data Mining
Time series shapelets: a new primitive for data mining

Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining
Learning when training data are costly: the effect of class distribution on tree induction

Journal of Artificial Intelligence Research
Top-down induction of first-order logical decision trees

Artificial Intelligence
Logical-shapelets: an expressive primitive for time series classification

Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining
Using spatiotemporal relational random forests to improve our understanding of severe weather processes

Statistical Analysis and Data Mining
Learning to "read between the lines" using Bayesian logic programs

ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1
Enhanced spatiotemporal relational probability trees and forests

Data Mining and Knowledge Discovery
Using random forests to diagnose aviation turbulence

Machine Learning

Using random forests to diagnose aviation turbulence

Machine Learning
Machine learning for science and society

Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

Severe weather, including tornadoes, thunderstorms, wind, and hail annually cause significant loss of life and property. We are developing spatiotemporal machine learning techniques that will enable meteorologists to improve the prediction of these events by improving their understanding of the fundamental causes of the phenomena and by building skillful empirical predictive models. In this paper, we present significant enhancements of our Spatiotemporal Relational Probability Trees that enable autonomous discovery of spatiotemporal relationships as well as learning with arbitrary shapes. We focus our evaluation on two real-world case studies using our technique: predicting tornadoes in Oklahoma and predicting aircraft turbulence in the United States. We also discuss how to evaluate success for a machine learning algorithm in the severe weather domain, which will enable new methods such as ours to transfer from research to operations, provide a set of lessons learned for embedded machine learning applications, and discuss how to field our technique.