Mapping foliar functional traits and their uncertainties across three years in a grassland experiment

Zhihui Wang, Philip A. Townsend, Anna K Schweiger, John J. Couture, Aditya Singh, Sarah E Hobbie, Jeannine M Cavender-Bares

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Foliar functional traits refer to a range of biochemical and physiognomic characteristics of vegetation that control photosynthesis, nutrient and water cycling, and can be used to describe the functional diversity of ecosystems. In this study, we utilize NASA AVIRIS - Next Generation imaging spectroscopy data to map 15 foliar functional traits in a grassland experiment at the Cedar Creek Ecosystem Science Reserve, a Long-Term Ecological Research site in Central Minnesota, across three years. To estimate traits, we compared the widely used partial least squares regression (PLSR) with Gaussian processes regression (GPR) to assess differences in model performance and uncertainty estimates. PLSR is attractive for its straightforward implementation and interpretation, but requires bootstrapping-based methods to estimate and map prediction uncertainties. On the other hand, GPR is more complex to implement and interpret, but provides explicit estimates of uncertainties. Our results indicated that foliar functional traits can be retrieved in these grasslands with moderate to high accuracies using either method. Highest validation accuracies were obtained for leaf mass per area (LMA), soluble cell contents, hemicellulose and cellulose (all with R2 > 0.8), and lower accuracies for lignin, nitrogen, and some pigments with both techniques. The estimations for the mass-based pigments were more accurate than the area-based pigments (at least 5% improvement in normalized RMSE). Overall, GPR and PLSR performed comparably with respect to both skill of predictions and the selection of most informative spectral regions. Maps of uncertainties corresponded well between the two models, with highest uncertainties related to low vegetation cover, high diversity levels, or under irrigation and nitrogen treatments (not represented in the field sampling). The maps showed that trait values in each plot were relatively stable across three years of managed species richness. Our results provide a template for mapping foliar traits and their uncertainties in grasslands, and point to the need for extensive ground data across time to properly evaluate performance of trait mapping algorithms.

Original languageEnglish (US)
Pages (from-to)405-416
Number of pages12
JournalRemote Sensing of Environment
Volume221
DOIs
StatePublished - Feb 1 2019

Fingerprint

uncertainty
grasslands
grassland
pigment
Pigments
least squares
experiment
Experiments
pigments
AVIRIS
Ecosystems
bootstrapping
ecosystem
nitrogen
prediction
vegetation cover
lignin
Nitrogen
cellulose
photosynthesis

Keywords

  • Gaussian processes regression
  • Grassland
  • Imaging spectroscopy
  • Trait map
  • Uncertainty

Cite this

Mapping foliar functional traits and their uncertainties across three years in a grassland experiment. / Wang, Zhihui; Townsend, Philip A.; Schweiger, Anna K; Couture, John J.; Singh, Aditya; Hobbie, Sarah E; Cavender-Bares, Jeannine M.

In: Remote Sensing of Environment, Vol. 221, 01.02.2019, p. 405-416.

Research output: Contribution to journalArticle

@article{bc1b8ab89907473192c524f290548282,
title = "Mapping foliar functional traits and their uncertainties across three years in a grassland experiment",
abstract = "Foliar functional traits refer to a range of biochemical and physiognomic characteristics of vegetation that control photosynthesis, nutrient and water cycling, and can be used to describe the functional diversity of ecosystems. In this study, we utilize NASA AVIRIS - Next Generation imaging spectroscopy data to map 15 foliar functional traits in a grassland experiment at the Cedar Creek Ecosystem Science Reserve, a Long-Term Ecological Research site in Central Minnesota, across three years. To estimate traits, we compared the widely used partial least squares regression (PLSR) with Gaussian processes regression (GPR) to assess differences in model performance and uncertainty estimates. PLSR is attractive for its straightforward implementation and interpretation, but requires bootstrapping-based methods to estimate and map prediction uncertainties. On the other hand, GPR is more complex to implement and interpret, but provides explicit estimates of uncertainties. Our results indicated that foliar functional traits can be retrieved in these grasslands with moderate to high accuracies using either method. Highest validation accuracies were obtained for leaf mass per area (LMA), soluble cell contents, hemicellulose and cellulose (all with R2 > 0.8), and lower accuracies for lignin, nitrogen, and some pigments with both techniques. The estimations for the mass-based pigments were more accurate than the area-based pigments (at least 5{\%} improvement in normalized RMSE). Overall, GPR and PLSR performed comparably with respect to both skill of predictions and the selection of most informative spectral regions. Maps of uncertainties corresponded well between the two models, with highest uncertainties related to low vegetation cover, high diversity levels, or under irrigation and nitrogen treatments (not represented in the field sampling). The maps showed that trait values in each plot were relatively stable across three years of managed species richness. Our results provide a template for mapping foliar traits and their uncertainties in grasslands, and point to the need for extensive ground data across time to properly evaluate performance of trait mapping algorithms.",
keywords = "Gaussian processes regression, Grassland, Imaging spectroscopy, Trait map, Uncertainty",
author = "Zhihui Wang and Townsend, {Philip A.} and Schweiger, {Anna K} and Couture, {John J.} and Aditya Singh and Hobbie, {Sarah E} and Cavender-Bares, {Jeannine M}",
year = "2019",
month = "2",
day = "1",
doi = "10.1016/j.rse.2018.11.016",
language = "English (US)",
volume = "221",
pages = "405--416",
journal = "Remote Sensing of Environment",
issn = "0034-4257",
publisher = "Elsevier",

}

TY - JOUR

T1 - Mapping foliar functional traits and their uncertainties across three years in a grassland experiment

AU - Wang, Zhihui

AU - Townsend, Philip A.

AU - Schweiger, Anna K

AU - Couture, John J.

AU - Singh, Aditya

AU - Hobbie, Sarah E

AU - Cavender-Bares, Jeannine M

PY - 2019/2/1

Y1 - 2019/2/1

N2 - Foliar functional traits refer to a range of biochemical and physiognomic characteristics of vegetation that control photosynthesis, nutrient and water cycling, and can be used to describe the functional diversity of ecosystems. In this study, we utilize NASA AVIRIS - Next Generation imaging spectroscopy data to map 15 foliar functional traits in a grassland experiment at the Cedar Creek Ecosystem Science Reserve, a Long-Term Ecological Research site in Central Minnesota, across three years. To estimate traits, we compared the widely used partial least squares regression (PLSR) with Gaussian processes regression (GPR) to assess differences in model performance and uncertainty estimates. PLSR is attractive for its straightforward implementation and interpretation, but requires bootstrapping-based methods to estimate and map prediction uncertainties. On the other hand, GPR is more complex to implement and interpret, but provides explicit estimates of uncertainties. Our results indicated that foliar functional traits can be retrieved in these grasslands with moderate to high accuracies using either method. Highest validation accuracies were obtained for leaf mass per area (LMA), soluble cell contents, hemicellulose and cellulose (all with R2 > 0.8), and lower accuracies for lignin, nitrogen, and some pigments with both techniques. The estimations for the mass-based pigments were more accurate than the area-based pigments (at least 5% improvement in normalized RMSE). Overall, GPR and PLSR performed comparably with respect to both skill of predictions and the selection of most informative spectral regions. Maps of uncertainties corresponded well between the two models, with highest uncertainties related to low vegetation cover, high diversity levels, or under irrigation and nitrogen treatments (not represented in the field sampling). The maps showed that trait values in each plot were relatively stable across three years of managed species richness. Our results provide a template for mapping foliar traits and their uncertainties in grasslands, and point to the need for extensive ground data across time to properly evaluate performance of trait mapping algorithms.

AB - Foliar functional traits refer to a range of biochemical and physiognomic characteristics of vegetation that control photosynthesis, nutrient and water cycling, and can be used to describe the functional diversity of ecosystems. In this study, we utilize NASA AVIRIS - Next Generation imaging spectroscopy data to map 15 foliar functional traits in a grassland experiment at the Cedar Creek Ecosystem Science Reserve, a Long-Term Ecological Research site in Central Minnesota, across three years. To estimate traits, we compared the widely used partial least squares regression (PLSR) with Gaussian processes regression (GPR) to assess differences in model performance and uncertainty estimates. PLSR is attractive for its straightforward implementation and interpretation, but requires bootstrapping-based methods to estimate and map prediction uncertainties. On the other hand, GPR is more complex to implement and interpret, but provides explicit estimates of uncertainties. Our results indicated that foliar functional traits can be retrieved in these grasslands with moderate to high accuracies using either method. Highest validation accuracies were obtained for leaf mass per area (LMA), soluble cell contents, hemicellulose and cellulose (all with R2 > 0.8), and lower accuracies for lignin, nitrogen, and some pigments with both techniques. The estimations for the mass-based pigments were more accurate than the area-based pigments (at least 5% improvement in normalized RMSE). Overall, GPR and PLSR performed comparably with respect to both skill of predictions and the selection of most informative spectral regions. Maps of uncertainties corresponded well between the two models, with highest uncertainties related to low vegetation cover, high diversity levels, or under irrigation and nitrogen treatments (not represented in the field sampling). The maps showed that trait values in each plot were relatively stable across three years of managed species richness. Our results provide a template for mapping foliar traits and their uncertainties in grasslands, and point to the need for extensive ground data across time to properly evaluate performance of trait mapping algorithms.

KW - Gaussian processes regression

KW - Grassland

KW - Imaging spectroscopy

KW - Trait map

KW - Uncertainty

UR - http://www.scopus.com/inward/record.url?scp=85057489543&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057489543&partnerID=8YFLogxK

U2 - 10.1016/j.rse.2018.11.016

DO - 10.1016/j.rse.2018.11.016

M3 - Article

AN - SCOPUS:85057489543

VL - 221

SP - 405

EP - 416

JO - Remote Sensing of Environment

JF - Remote Sensing of Environment

SN - 0034-4257

ER -