A best-practice guide to predicting plant traits from leaf-level hyperspectral data using partial least squares regression

Burnett, Angela C.; Anderson, Jeremiah; Davidson, Kenneth; Ely, Kim; Lamour, Julien; Li, Qianyu; Morrison, B. D.; Yang, Dedi; Rogers, Alistair; Serbin, Shawn P.

doi:10.1093/jxb/erab295

Cited by 112 publications

(88 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Considering the operation efficiency and prediction accuracy of the model, the method is effective for monitoring the disease. In contrast, the performance of the PLSR model was slightly worse, which might be because PLSR was better at addressing multicollinearity between parameters [ 72 ], and the parameters used in the present study were optimized by the SPA algorithm, which eliminated the influence of multicollinearity, resulting in an inability to maximize the performance of the PLSR model.…”

Section: Discussionmentioning

confidence: 99%

Monitoring Wheat Powdery Mildew Based on Hyperspectral, Thermal Infrared, and RGB Image Data Fusion

Feng

Song

Duan

et al. 2021

Sensors

View full text Add to dashboard Cite

Powdery mildew severely affects wheat growth and yield; therefore, its effective monitoring is essential for the prevention and control of the disease and global food security. In the present study, a spectroradiometer and thermal infrared cameras were used to obtain hyperspectral signature and thermal infrared images data, and thermal infrared temperature parameters (TP) and texture features (TF) were extracted from the thermal infrared images and RGB images of wheat with powdery mildew, during the wheat flowering and filling periods. Based on the ten vegetation indices from the hyperspectral data (VI), TF and TP were integrated, and partial least square regression, random forest regression (RFR), and support vector machine regression (SVR) algorithms were used to construct a prediction model for a wheat powdery mildew disease index. According to the results, the prediction accuracy of RFR was higher than in other models, under both single data source modeling and multi-source data modeling; among the three data sources, VI was the most suitable for powdery mildew monitoring, followed by TP, and finally TF. The RFR model had stable performance in multi-source data fusion modeling (VI&TP&TF), and had the optimal estimation performance with 0.872 and 0.862 of R2 for calibration and validation, respectively. The application of multi-source data collaborative modeling could improve the accuracy of remote sensing monitoring of wheat powdery mildew, and facilitate the achievement of high-precision remote sensing monitoring of crop disease status.

show abstract

Section: Discussionmentioning

confidence: 99%

Monitoring Wheat Powdery Mildew Based on Hyperspectral, Thermal Infrared, and RGB Image Data Fusion

Feng

Song

Duan

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…2 and 3, we selected seven traits that represent a range of patterns in VIP across the tissue types (cell = cellulose). The dashed horizontal line at 0.8 represents a heuristic threshold for importance suggested by Burnett et al (2021). VIP plots for remaining traits are in the Supplementary Materials.…”

Section: Resultsmentioning

confidence: 99%

“…Our methods for model calibration and validation largely follow Burnett et al (2021). First, we randomly divided the data into calibration (75%) and validation (25%) datasets, stratified by functional group.…”

Section: Methodsmentioning

confidence: 99%

“…We also report the RMSE as a percentage of the 2.5% trimmed range of measured values (%RMSE), which we used rather than the entire range (as in e.g. Burnett et al 2021) for robustness to outliers. For each trait, we also tested whether the magnitude of residuals (observed minus predicted) in the validation dataset varied among leaves with different discoloration scores.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Reflectance spectroscopy allows rapid, accurate, and non-destructive estimates of functional traits from pressed leaves

Kothari

Beauchamp‐Rioux

Laliberté

et al. 2021

Preprint

View full text Add to dashboard Cite

More than ever, ecologists seek to employ herbarium collections as tools to estimate plant functional traits from the past or from places that are hard to sample. However, many functional trait measurements are destructive, which may preclude their use on valuable herbarium specimens. Reflectance spectroscopy is increasingly used to estimate traits rapidly from fresh or dried, ground leaves, as well as to differentiate and identify taxa. Here, we extend this body of work to pressed, intact leaves such as those in herbarium collections. Using a dataset with 619 plant samples belonging to 70 woody and herbaceous species, we used partial least-squares regression to build validated models linking pressed-leaf reflectance spectra to a broad suite of traits, including leaf mass per area (LMA), leaf dry matter content (LDMC), carbon (Cmass) and nitrogen (Nmass) concentrations, and carbon fractions such as cellulose and lignin. We compared the accuracy of these trait estimates to those from fresh- or ground-leaf spectra of the same samples. Our pressed-leaf models predicted these traits with moderate-to-high accuracy (R2 = 0.586-0.924; %RMSE = 5.7-11.7%). For estimating chemical traits, pressed-leaf models performed better than fresh-leaf models but slightly worse than ground-leaf models. Pressed-leaf models did not perform as well as fresh-leaf models for estimating LMA and LDMC, but outperformed ground-leaf models for LMA. Accuracy was no worse for pressed leaves that underwent discoloration in storage. Finally, on a subset of common species in the dataset, we used partial least-squares discriminant analysis to classify specimens to species with near-perfect accuracy from pressed-(>97%), and ground-leaf (>96%) spectra and slightly lower accuracy from fresh-leaf spectra (>89%). The success of trait estimation and species classification from pressed-leaf spectra may owe to the fact that they combine advantages of fresh and ground leaves: like fresh leaves, they retain some of the spectral expression of internal leaf structure; like ground leaves, they reveal minor absorption features of chemical constituents that would otherwise be masked by water. These results show that applying spectroscopy to pressed leaves is a promising way to estimate leaf functional traits non-destructively. Our study has far-reaching implications for capturing the wide range of functional, phenotypic, and taxonomic information in the world’s preserved plant collections.

show abstract

“…Once the training and validation datasets were created, we used the guide and code from [ 53 ] to train and validate the PLSR models. In this guide, two steps are considered: 1) Statistically selecting the most parsimonious number of PLSR components which balances model performance.…”

Section: Methodsmentioning

confidence: 99%

Rapid estimation of photosynthetic leaf traits of tropical plants in diverse environmental conditions using reflectance spectroscopy

et al. 2021

Self Cite

View full text Add to dashboard Cite

Tropical forests are one of the main carbon sinks on Earth, but the magnitude of CO2 absorbed by tropical vegetation remains uncertain. Terrestrial biosphere models (TBMs) are commonly used to estimate the CO2 absorbed by forests, but their performance is highly sensitive to the parameterization of processes that control leaf-level CO2 exchange. Direct measurements of leaf respiratory and photosynthetic traits that determine vegetation CO2 fluxes are critical, but traditional approaches are time-consuming. Reflectance spectroscopy can be a viable alternative for the estimation of these traits and, because data collection is markedly quicker than traditional gas exchange, the approach can enable the rapid assembly of large datasets. However, the application of spectroscopy to estimate photosynthetic traits across a wide range of tropical species, leaf ages and light environments has not been extensively studied. Here, we used leaf reflectance spectroscopy together with partial least-squares regression (PLSR) modeling to estimate leaf respiration (Rdark25), the maximum rate of carboxylation by the enzyme Rubisco (Vcmax25), the maximum rate of electron transport (Jmax25), and the triose phosphate utilization rate (Tp25), all normalized to 25°C. We collected data from three tropical forest sites and included leaves from fifty-three species sampled at different leaf phenological stages and different leaf light environments. Our resulting spectra-trait models validated on randomly sampled data showed good predictive performance for Vcmax25, Jmax25, Tp25 and Rdark25 (RMSE of 13, 20, 1.5 and 0.3 μmol m-2 s-1, and R2 of 0.74, 0.73, 0.64 and 0.58, respectively). The models showed similar performance when applied to leaves of species not included in the training dataset, illustrating that the approach is robust for capturing the main axes of trait variation in tropical species. We discuss the utility of the spectra-trait and traditional gas exchange approaches for enhancing tropical plant trait studies and improving the parameterization of TBMs.

show abstract

A best-practice guide to predicting plant traits from leaf-level hyperspectral data using partial least squares regression

Cited by 112 publications

References 74 publications

Monitoring Wheat Powdery Mildew Based on Hyperspectral, Thermal Infrared, and RGB Image Data Fusion

Monitoring Wheat Powdery Mildew Based on Hyperspectral, Thermal Infrared, and RGB Image Data Fusion

Reflectance spectroscopy allows rapid, accurate, and non-destructive estimates of functional traits from pressed leaves

Rapid estimation of photosynthetic leaf traits of tropical plants in diverse environmental conditions using reflectance spectroscopy

Contact Info

Product

Resources

About