Utilising LANDHYPERNET data products over a deciduous broadleaf forest to validate Sentinel-2 and Landsat surface reflectance products

Abstract

This paper demonstrates the use of a novel, autonomous hyperspectral surface reflectance data collected at Wytham Woods, United Kingdom (WWUK) as part of the LANDHYPERNET network for the validation of multispectral data from Sentinel-2, Landsat 8 and Landsat 9. The deployment of the HYPSTAR instrument at the site and the corresponding quality control of the data products is described. In addition, a methodology based upon metrological principles is outlined showing the propagation of uncertainties from the LANDHYPERNET and satellite data products to enable conformity testing of the satellite products using the satellite mission requirements. A total of 9 matchups are found for satellite validation at the site, where there is a cloud-free satellite scene and a corresponding LANDHYPERNET sequence, which has passed all quality checks, within two hours of the overpass. An analysis of the impact of the spatial variability of the site is presented and can account for up to 40% of the uncertainty associated with the in-situ surface reflectance data. There is no systematic bias in the Bottom-Of-Atmosphere reflectance data obtained from the LANDHYPERNET data in comparison to the satellite data. In the best case, differences of less than 2% are found for certain spectral bands. However, in the worst cases, relatively large differences are found which exceed 100%, this is affected by the relatively low reflectance values found in the visible bands. These differences could be caused by the spatial and temporal mismatch between the in-situ and satellite measurement, or due to shadowing caused by the flux tower. Further data quality control and assurance is needed to best choose data sets suitable for satellite validation. Incorporating a Bidirectional Reflectance Distribution Function model into the processing chain for the forest canopy is recommended. Overall, although there are areas to further characterise, the site provides a useful benchmark for which to develop techniques for validation of satellite surface reflectance products over a challenging environment.

HYPERNETS: a network of automated hyperspectral radiometers to validate water and land surface reflectance (380–1680 nm) from all satellite missions

“…So far, PANTHYR (Vanhellemont, 2020;Vanhellemont and Ruddick, 2021;Braga et al, 2022;Vanhellemont, 2023;Ruddick et al, 2024) and HYPSTAR ® (Dogliotti et al, 2024;Doxaran et al, 2024;Gonzalez Vilas et al, 2024;Ruddick et al, 2024) data have been used for validation of water reflectance from Landsat-8&9/OLI, Sentinel-2/MSI, Sentinel-3/OLCI, PRISMA, Aqua/MODIS, SNPP&JPSS1/VIIRS, and the constellation of PlanetScope Dove and Superdove satellite data, generally comparing different atmospheric correction algorithms. HYPSTAR ® data have been used for validation of land surface reflectance from Sentinel-2/MSI and Landsat-8&9/OLI for a deciduous forest site (Morris et al, 2024).…”

“…Measurement uncertainties from the following processes are in preparation for future implementation: a) radiometer thermal sensitivity, straylight and angular response, b) mounting platform optical perturbations (shading/reflection) and, for water, c) airwater interface reflected light. Additional uncertainties relating to space and time differences when using HYPERNETS data for satellite validation are also being addressed (Dogliotti et al, 2024;Doxaran et al, 2024;Morris et al, 2024).…”

“…A key question for each validation site is the spatial heterogeneity. Each validation site should be characterised in terms of spatial variability to give the additional uncertainty involved in a matchup comparison as function of length scale, e.g., Dogliotti et al (2015), Dogliotti et al (2024), Doxaran et al (2024) for water and Morris et al (2024) for land.…”