eCite Digital Repository

Spatial-contextual supervised classifiers explored: a challenging example of lithostratigraphy classification

Citation

Cracknell, MJ and Reading, AM, Spatial-contextual supervised classifiers explored: a challenging example of lithostratigraphy classification, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8, (3) pp. 1371-1384. ISSN 1939-1404 (2015) [Refereed Article]

Copyright Statement

Copyright 2015 IEEE

DOI: doi:10.1109/JSTARS.2014.2382760

Abstract

Spatial-contextual classifiers exploit characteristics of spatially referenced data and account for random noise that contributes to spatially inconsistent classifications. In contrast, standard global classifiers treat inputs as statistically independent and identically distributed. Spatial-contextual classifiers have the potential to improve visualization, analysis, and interpretation: fundamental requirements for the subsequent use of classifications representing spatially varying phenomena. We evaluate random forests (RF) and support vector machine (SVM) spatial-contextual classifiers with respect to a challenging lithostratigraphy classification problem. Spatial-contextual classifiers are divided into three categories aligned with the supervised classification work flow: 1) data preprocessing-transformation of input variables using focal operators; 2) classifier training-using proximal training samples to train multiple localized classifiers; and 3) postregularization (PR)-reclassification of outputs. We introduce new variants of spatial-contextual classifier that employ self-organizing maps to segment the spatial domain. Segments are used to train multiple localized classifiers from k neighboring training instances and to represent spatial structures that assist PR. Our experimental results, reported as mean (n = 10) overall accuracy 95% confidence intervals, indicate that focal operators (RF 0.754 0.010, SVM 0.683 0.010) and PR majority filters (RF 0.705 0.010, SVM 0.607 0.010 for 11 11 neighborhoods) generate significantly more accurate classifications than standard global classifiers (RF 0.625 0.011, SVM 0.581 0.011). Thin and discontinuous lithostratigraphic units were best resolved using non-preprocessed variables, and segmentation coupled with postregularized RF classifications (0.652 0.011). These methods may be used to improve the accuracy of classifications across a wid- variety of spatial modeling applications.

Item Details

Item Type:Refereed Article
Keywords:decision trees, geology, geophysics, spatial filters, supervised learning, support vector machines (SVMs)
Research Division:Earth Sciences
Research Group:Geophysics
Research Field:Geophysics not elsewhere classified
Objective Division:Expanding Knowledge
Objective Group:Expanding Knowledge
Objective Field:Expanding Knowledge in the Earth Sciences
Author:Cracknell, MJ (Dr Matthew Cracknell)
Author:Reading, AM (Professor Anya Reading)
ID Code:100286
Year Published:2015
Deposited By:Earth Sciences
Deposited On:2015-05-08
Last Modified:2016-05-25
Downloads:0

Repository Staff Only: item control page