Quantifying uncertainty for estimates derived from error matrices in land cover mapping applications: the case for a Bayesian approach

Phillipson, Jordan; Blair, Gordon; Henrys, Peter. 2020 Quantifying uncertainty for estimates derived from error matrices in land cover mapping applications: the case for a Bayesian approach. In: Athanasiadis, Ioannis N.; Frysinger, Steven P.; Schimak, Gerald; Knibbe, Willem Jan, (eds.) Environmental software systems: data science in action. 13th IFIP WG 5.11 International Symposium, ISESS 2020, Wageningen, The Netherlands, February 5–7, 2020, Proceedings. Cham, Switzerland, Springer, 151-164. (IFIP Advances in Information and Communication Technology, v. 554).

Full text not available from this repository.

Abstract/Summary

The use of land cover mappings built using remotely sensed imagery data has become increasingly popular in recent years. However, these mappings are ultimately only models. Consequently, it is vital for one to be able to assess and verify the quality of a mapping and quantify uncertainty for any estimates that are derived from them in a reliable manner. For this, the use of validation sets and error matrices is a long standard practice in land cover mapping applications. In this paper, we review current state of the art methods for quantifying uncertainty for estimates obtained from error matrices in a land cover mapping context. Specifically, we review methods based on their transparency, generalisability, suitability when stratified sampling and suitability in low count situations. This is done with the use of a third-party case study to act as a motivating and demonstrative example throughout the paper. The main finding of this paper is there is a major issue of transparency for methods that quantify uncertainty in terms of confidence intervals (frequentist methods). This is primarily because of the difficulty of analysing nominal coverages in common situations. Effectively, this leaves one without the necessary tools to know when a frequentist method is reliable in all but a few niche situations. The paper then discusses how a Bayesian approach may be better suited as a default method for uncertainty quantification when judged by our criteria.

Item Type:	Publication - Book Section
Digital Object Identifier (DOI):	https://doi.org/10.1007/978-3-030-39815-6_15
UKCEH and CEH Sections/Science Areas:	Soils and Land Use (Science Area 2017-)
ISBN:	9783030398149
Additional Keywords:	uncertainty quantification, map assessment, Bayesian, land cover maps
NORA Subject Terms:	Ecology and Environment Mathematics Computer Science Data and Information
Date made live:	14 Feb 2020 12:46 +0 (UTC)
URI:	https://nora.nerc.ac.uk/id/eprint/526884

Actions (login required)

View Item

Document Downloads

More statistics for this item...