Instance-Based Learning Algorithms
Machine Learning
Machine Learning
ECML '95 Proceedings of the 8th European Conference on Machine Learning
Generating Accurate Rule Sets Without Global Optimization
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Onboard classifiers for science event detection on a remote sensing spacecraft
Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining
Selective fusion of heterogeneous classifiers
Intelligent Data Analysis
Collective machine learning: team learning and classification in multi-agent systems
Collective machine learning: team learning and classification in multi-agent systems
Estimating continuous distributions in Bayesian classifiers
UAI'95 Proceedings of the Eleventh conference on Uncertainty in artificial intelligence
Switching between selection and fusion in combining classifiers: anexperiment
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
| Hi-index | 0.00 |
Ground and airborne radar depth-sounding of the Greenland and Antarctic ice sheets have been used for many years to remotely determine characteristics such as ice thickness, subglacial topography, and mass balance of large bodies of ice. Ice coring efforts have supported these radar data to provide ground truth for validation of the state (wet or frozen) of the interface between the bottom of the ice sheet and the underlying bedrock. Subglacial state governs the friction, flow speed, transport of material, and overall change of the ice sheet. In this paper, we utilize machine learning and classifier combination to model water presence from airborne polar radar data acquired on Greenland in 1999 and 2007. The underlying method results in radar independence, allowing model transfer from 1999 to 2007 radar data to produce water presence maps of the Greenland ice sheet with differing radars. We focus on how to construct a successful set of classifiers capable of high classification accuracy. Utilizing multiple machine learning algorithms is shown to be successful for this classification problem, achieving 86% classification accuracy in the best case. Several heuristics are presented for constructing teams of multiple classifiers for predicting subglacial water presence. The presented methodology could also be applied to radar data acquired over the Antarctic ice sheet.