Guide to Predicting Plant Traits from Leaf Hyperspectral Data

Resources to guide the suggested application of a powerful emerging technique for prediction of plant traits

Illustration of suggested approach for developing PLSR models (left) and applying these models to new reflectance measurements to rapidly estimate leaf trait data (right).

[Courtesy Brookhaven National Laboratory, from Burnett et al. 2021.]

The Science

The estimation of leaf traits, such as leaf nitrogen, from hyperspectral reflectance data enables rapid, high-throughput, non-destructive characterization of leaf function and plant phenotyping with applications in ecosystem characterization and monitoring. However, lack of a standard approach for developing and reporting this information has limited the wider application of the technique. To address these challenges, scientists developed a detailed description of the use of partial least squares regression (PLSR) to predict leaf traits with spectra and offer recommendations for best practices across all steps of the process: from experimental design and data collection, to PLSR model building, model application, and reporting of results. Hands-on tutorials are also provided to assist users to in understanding these best practices for PLSR modeling and application with their own data.

The Impact

Plant scientists require detailed and extensive information on the concentration and distribution of physiological and structural leaf properties to study vegetation responses to environmental change, monitor plant health, and facilitate the rapid screening of different plant phenotypes. Traditional approaches to measure these traits directly are expensive and logistically challenging. Therefore, scientists developed an alternative spectroscopic approach for the rapid, accurate and non-destructive estimation of traits using remote sensing data, along with tools for broadening its use and standardizing its application.


Plant physiologists and ecologists regularly measure leaf functional traits, including leaf nitrogen or photosynthetic rate, across a range of leaves, plants, species, or environments. These direct measurements, while very accurate for characterizing leaf structure and function, are typically slow, expensive, and can be logistically challenging. In addition, many ecological or phenotyping studies require many samples, which can be impractical with traditional methods. On the other hand, remote sensing methods have been shown to be effective for the rapid estimation of many of key leaf traits; however, inconsistent usage of the methods have led to challenges in the wider application across the plant sciences. To address this challenge and to help standardize the approach across studies to facilitate wider adoption, scientists provide a detailed summary of the spectral method of leaf trait estimation. Clear examples and tutorials as well as a range of suggested best practices are also provided to illustrate how to use the approach. Importantly, scientists also highlight how the same approach can be scaled up to estimate vegetation traits across landscapes using non-contact remote sensing data.

Principal Investigator

Angela Burnett
Brookhaven National Laboratory

Program Manager

Brian Benscoter
U.S. Department of Energy, Biological and Environmental Research (SC-33)
Environmental System Science


This work was supported by the Next-Generation Ecosystem Experiments (NGEE-Arctic and NGEE-Tropics) projects, which are funded by the Office of Biological and Environmental Research (BER) in the Department of Energy’s (DOE) Office of Science. Project support also came from DOE contract No. DE-SC0012704 to Brookhaven National Laboratory.


Burnett, A.C., et al. "A Best-Practice Guide to Predicting Plant Traits from Leaf-Level Hyperspectral Data using Partial Least Squares Regression." Journal of Experimental Botany 72 (18), 6175–6189  (2021).