Grass Evolutionary Lineages Can Be Identified Using Hyperspectral Leaf Reflectance.

Hyperspectral remote sensing has the potential to map numerous attributes of the Earth's surface, including spatial patterns of biological diversity. Grasslands are one of the largest biomes on Earth. Accurate mapping of grassland biodiversity relies on spectral discrimination of endmembers of species or plant functional types. We focused on spectral separation of grass lineages that dominate global grassy biomes: Andropogoneae (C4), Chloridoideae (C4), and Pooideae (C3). We examined leaf reflectance spectra (350–2,500 nm) from 43 grass species representing these grass lineages from four representative grassland sites in the Great Plains region of North America. We assessed the utility of leaf reflectance data for classification of grass species into three major lineages and by collection site. Classifications had very high accuracy (94%) that were robust to site differences in species and environment. We also show an information loss using multispectral sensors, that is, classification accuracy of grass lineages using spectral bands provided by current multispectral satellites is much lower (accuracy of 85.2% and 61.3% using Sentinel 2 and Landsat 8 bands, respectively). Our results suggest that hyperspectral data have an exciting potential for mapping grass functional types as informed by phylogeny. Leaf‐level hyperspectral separability of grass lineages is consistent with the potential increase in biodiversity and functional information content from the next generation of satellite‐based spectrometers. Plain Language Summary: Understanding and identifying changes in plant diversity along broad environmental gradients requires scalable and reliable data. Spectroscopy has been shown to provide data across scales with the ability to measure plant reflectance at various extents (e.g., leaf, plot, and landscapes) with high spectral resolution and broad coverage of the electromagnetic spectrum (350–2,500 nm). In grasses, evolutionary lineage captures major axes in plant biodiversity and functional variation. We show that identifying grass evolutionary lineages from spectroscopy is possible based on common characteristics in their leaf‐level spectra. We classified 43 grass species from four sites in North America into their respective evolutionary lineages with very high accuracy (>90%) based on similarities in their leaf spectra. Classifying grass species into lineages using coarser spectral resolution data, similar to existing multispectral satellites, Sentinel 2 and Landsat 8, resulted in lower accuracy due to a loss of information from decreasing the spectral resolution. Grass lineages likely have similar spectra because of common leaf traits that evolved under similar ecological contexts. The importance of these distinctions found in the spectral reflectance of dominant grass lineages, should help our efforts in mapping and understanding grassland ecosystem function and patterns of biodiversity. Key Points: Globally dominant grass lineages are identifiable using hyperspectral leaf signaturesKey wavelengths for separating grass lineages were visible, red‐edge and shortwave infrared regions, rarely measured by multispectral sensorsHyperspectral sensors have the potential to improve remote sensing identification of grass functional types over multispectral sensors [ABSTRACT FROM AUTHOR]