Analysis of Dynamic Thresholds for the Normalized Difference Water Index

TLDR

NDWI is widely used to delineate surface water, but differing band combinations and subpixel water proportions cause inconsistent thresholds. The study aims to evaluate all NDWI variants and establish optimal thresholds for accurate water feature identification. Spectral data from a library were used to simulate Landsat ETM, SPOT‑5, ASTER, and MODIS sensors, generating NDWI values in various forms. The NDWI computed as (green – SWIR)/(green + SWIR) with SWIR 1.2–1.8 µm produced the most stable threshold and is recommended for water mapping with situational threshold adjustments.

Abstract

The normalized difference water index (NDWI) has been successfully used to delineate surface water features. However, two major problems have been often encountered: (a) NDWIs calculated from different band combinations [visible, nearinfrared, or shortwave-infrared (SWIR)] can generate different results, and (b) NDWI thresholds vary depending on the proportions of subpixel water/non-water components. We need to evaluate all the NDWIs for determining the best performing index and to establish appropriate thresholds for clearly identifying water features. We used the spectral data obtained from a spectral library to simulate the satellite sensors Landsat ETM, SPOT-5, ASTER, and MODIS, and calculated the simulated NDWI in different forms. We found that the NDWI calculated from (green ‐ SWIR)/(green SWIR), where SWIR is the shorter wavelength region (1.2 to 1.8 mm), has the most stable threshold. We recommend this NDWI be employed for mapping water, but adjustment of the threshold based on actual situations is necessary.