Spatial Ensemble Learning for Heterogeneous Geographic Data with Class Ambiguity: A Summary of Results

Zhe Jiang, Yan Li, Shashi Shekhar, Lian P Rampi, Joe Knight

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Scopus citations

Abstract

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 languageEnglish (US)
Title of host publicationGIS
Subtitle of host publicationProceedings of the ACM International Symposium on Advances in Geographic Information Systems
EditorsSiva Ravada, Erik Hoel, Roberto Tamassia, Shawn Newsam, Goce Trajcevski, Goce Trajcevski
PublisherAssociation for Computing Machinery
ISBN (Print)9781450354905
DOIs
StatePublished - Nov 7 2017
Event25th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2017 - Redondo Beach, United States
Duration: Nov 7 2017Nov 10 2017

Publication series

NameGIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems
Volume2017-November

Other

Other25th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2017
CountryUnited States
CityRedondo Beach
Period11/7/1711/10/17

Keywords

  • Class ambiguity
  • Local models
  • Spatial classification
  • Spatial ensemble
  • Spatial heterogeneity

Fingerprint Dive into the research topics of 'Spatial Ensemble Learning for Heterogeneous Geographic Data with Class Ambiguity: A Summary of Results'. Together they form a unique fingerprint.

  • Cite this

    Jiang, Z., Li, Y., Shekhar, S., Rampi, L. P., & Knight, J. (2017). Spatial Ensemble Learning for Heterogeneous Geographic Data with Class Ambiguity: A Summary of Results. In S. Ravada, E. Hoel, R. Tamassia, S. Newsam, G. Trajcevski, & G. Trajcevski (Eds.), GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems [23] (GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems; Vol. 2017-November). Association for Computing Machinery. https://doi.org/10.1145/3139958.3140044