Discovering Communicable Models from Earth Science Data

Authors:
Mark Schwabacher;Pat Langley;Christopher Potter;Steven Klooster;Alicia Torregrosa
Affiliations:
Intelligent Systems Division, NASA Ames Research Center, Moffett Field, California, USA;Institute for the Study of Learning and Expertise, Palo Alto, California, USA;Earth Science Division, NASA Ames Research Center, Moffett Field, California, USA;Earth Science Division, NASA Ames Research Center, Moffett Field, California, USA and Earth System Science and Policy, California State University Monterey Bay, Seaside, California, USA;Earth Science Division, NASA Ames Research Center, Moffett Field, California, USA and Earth System Science and Policy, California State University Monterey Bay, Seaside, California, USA
Venue:
Computational Discovery of Scientific Knowledge
Year:
2007

Citing 7
Cited 1

The visual display of quantitative information

The visual display of quantitative information
C4.5: programs for machine learning

C4.5: programs for machine learning
Guest Editors‘ Introduction: On Applied Research in MachineLearning

Machine Learning - Special issue on applications of machine learning and the knowledge discovery process
Visualizing high-dimensional predicitive model quality

Proceedings of the conference on Visualization '00
Visualization Techniques for Mining Large Databases: A Comparison

IEEE Transactions on Knowledge and Data Engineering
Declarative Bias in Equation Discovery

ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
Discovering Communicable Scientific Knowledge from Spatio-Temporal Data

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning

Introduction to data mining for sustainability

Data Mining and Knowledge Discovery

Quantified Score

Hi-index	0.00

Visualization

Abstract

This chapter describes how we used regression rules to improve upon results previously published in the Earth science literature. In such a scientific application of machine learning, it is crucially important for the learned models to be understandableand communicable. We recount how we selected a learning algorithm to maximize communicability, and then describe two visualization techniques that we developed to aid in understanding the model by exploiting the spatial nature of the data. We also report how evaluating the learned models across time let us discover an error in the data.