Class ambiguity refers to the phenomenon whereby samples with similar features belong to different classes at different locations. Given heterogeneous geographic data with class ambiguity, the spatial ensemble learning (SEL) problem aims to find a decomposition of the geographic area into disjoint zones such that class ambiguity is minimized and a local classifier can be learned in each zone. SEL problem is important for applications such as land cover mapping from heterogeneous earth observation data with spectral confusion. However, the problem is challenging due to its high computational cost (finding an optimal zone partition is NP-hard). Related work in ensemble learning either assumes an identical sample distribution (e.g., bagging, boosting, random forest) or decomposes multi-modular input data in the feature vector space (e.g., mixture of experts, multimodal ensemble), and thus cannot effectively minimize class ambiguity. In contrast, our spatial ensemble framework explicitly partitions input data in geographic space. Our approach first preprocesses data into homogeneous spatial patches and uses a greedy heuristic to allocate pairs of patches with high class ambiguity into different zones. Both theoretical analysis and experimental evaluations on two real world wetland mapping datasets show the feasibility of the proposed approach.
|Original language||English (US)|
|Title of host publication||GIS|
|Subtitle of host publication||Proceedings of the ACM International Symposium on Advances in Geographic Information Systems|
|Editors||Siva Ravada, Erik Hoel, Roberto Tamassia, Shawn Newsam, Goce Trajcevski, Goce Trajcevski|
|Publisher||Association for Computing Machinery|
|State||Published - Nov 7 2017|
|Event||25th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2017 - Redondo Beach, United States|
Duration: Nov 7 2017 → Nov 10 2017
|Name||GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems|
|Other||25th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2017|
|Period||11/7/17 → 11/10/17|
Bibliographical noteFunding Information:
This project is supported by the NSF under Grant No. 1029711, IIS-1320580, 0940818 and IIS-1218168, the USDOD under Grant No. HM1582-08-1-0017 and HM0210-13-1-0005, the OVPR U-Spatial and MSI at the University of Minnesota.
© 2017 Association for Computing Machinery.
Copyright 2018 Elsevier B.V., All rights reserved.
- Class ambiguity
- Local models
- Spatial classification
- Spatial ensemble
- Spatial heterogeneity