Tanya Mason

Dr Tanya Mason

Publications

Author Date Title Link PDF
Lyons et al. 2018 A comparison of resampling methods for remote sensing classification and accuracy assessment

Abstract: Maps that categorise the landscape into discrete units are a cornerstone of many scientific, management and conservation activities. The accuracy of these maps is often the primary piece of information used to make decisions about the mapping process or judge the quality of the final map. Variance is critical information when considering map accuracy, yet commonly reported accuracy metrics often do not provide that information. Various resampling frameworks have been proposed and shown to reconcile this issue, but have had limited uptake. In this paper, we compare the traditional approach of a single split of data into a training set (for classification) and test set (for accuracy assessment), to a resampling framework where the classification and accuracy assessment are repeated many times. Using a relatively simple vegetation mapping example and two common classifiers (maximum likelihood and random forest), we compare variance in mapped area estimates and accuracy assessment metrics (overall accuracy, kappa, user, producer, entropy, purity, quantity/allocation disagreement). Input field data points were repeatedly split into training and test sets via bootstrapping, Monte Carlo cross-validation (67:33 and 80:20 split ratios) and k-fold (5-fold) cross-validation. Additionally, within the cross-validation, we tested four designs: simple random, block hold-out, stratification by class, and stratification by both class and space. A classification was performed for every split of every methodological combination (100’s iterations each), creating sampling distributions for the mapped area of each class and the accuracy metrics. We found that regardless of resampling design, a single split of data into training and test sets results in a large variance in estimates of accuracy and mapped area. In the worst case, overall accuracy varied between ~40–80% in one resampling design, due only to random variation in partitioning into training and test sets. On the other hand, we found that all resampling procedures provided accurate estimates of error, and that they can also provide confidence intervals that are informative about the performance and uncertainty of the classifier. Importantly, we show that these confidence intervals commonly encompassed the magnitudes of increase or decrease in accuracy that are often cited in literature as justification for methodological or sampling design choices. We also show how a resampling approach enables generation of spatially continuous maps of classification uncertainty. Based on our results, we make recommendations about which resampling design to use and how it could be implemented. We also provide a fully worked mapping example, which includes traditional inference of uncertainty from the error matrix and provides examples for presenting the final map and its accuracy.

View PDF
French et al. 2013 Invasion of woody shrubs and trees
Mason et al. 2013 Arrival order among native plant functional groups does not affect invasibility of constructed dune communities
Mason et al. 2012 Are competitive effects of native species on an invader mediated by water availability?

Go to article

French et al. 2011 Recruitment limitation of native species in invaded coastal dune communities
Mason et al. 2009 Do graminoid and woody invaders have different effects on species richness within plant functional groups in native communities?
Mason and French 2008 Impacts of a woody invader vary in different vegetation communities
French et al. 2008 Management implications of recent research into the effect of bitou bush invasion
Mason and French 2007 Management regimes for plant invaders differentially impact resident communities
Mason et al. 2007 Moderate impacts of plant invasion and management regimes in coastal hind dune seed banks
Mason et al. 2005 Environmental weed control policy in Australia: current approaches, policy limitations and future directions
Go to top