The Total Operating Characteristic from Stratified Random Sampling with an Application to Flood Mapping

Keywords: flood, remote sensing, stratified random sampling, Total Operating Characteristic (TOC), water index
Session Type: Virtual Paper Abstract
Day: Monday
Session Start / End Time: 2/28/2022 03:40 PM (Eastern Time (US & Canada)) - 2/28/2022 05:00 PM (Eastern Time (US & Canada))
Room: Virtual 46

Abstract

The Total Operating Characteristic (TOC) measures how the ranks of an index variable distinguish between presence and absence in a binary reference variable. Previous methods to generate the TOC required the reference data to derive from a census or a simple random sample. However, many researchers apply stratified random sampling to collect reference data because stratified random sampling is more efficient than simple random sampling for many applications. Our manuscript derives a new methodology that uses stratified random sampling to generate the TOC. An application to flood mapping illustrates how the TOC compares the abilities of three indices to diagnose water. The TOC shows visually and quantitatively each index’s diagnostic ability relative to baselines. Results show that the Modified Normalized Difference Water Index has the greatest diagnostic ability, while the Normalized Difference Vegetation Index has diagnostic ability greater than the Normalized Difference Water Index at the threshold where the Diagnosed Presence equals the Abundance of water. Some researchers consider only one accuracy metric at only one threshold, whereas the TOC allows visualization of several metrics at all thresholds. The TOC gives more information and clearer interpretation compared to the popular Relative Operating Characteristic. Our software generates the TOC from a census, simple random sample, or stratified random sample. The TOC Curve Generator is free as an executable file at https://lazygis.github.io/projects/TOCCurveGenerator
The manuscript is free at https://www.mdpi.com/2072-4292/13/19/3922