Abstract
The plant photosynthetic capacity determines the photosynthetic rates of the terrestrial biosphere. Timely approaches to obtain the spatiotemporal variations of the photosynthetic parameters are urgently needed to grasp the gas exchange rhythms of the terrestrial biosphere. While partial least squares regression (PLSR) is a promising way to predict the photosynthetic parameters maximum carboxylation rate (Vcmax) and maximum electron transport rate (Jmax) rapidly and non-destructively from hyperspectral data, the approach, however, faces a high risk of overfitting and remains a high hurdle for applications. In this study, we propose to incorporate proper band selection techniques for PLSR analysis to refine the goodness-of-fit (GoF) in estimating Vcmax and Jmax. Different band selection procedures coupled with different hyperspectral forms (reflectance, apparent absorption, as well as derivatives) were examined. Our results demonstrate that the GoFs of PLSR models could be greatly improved by combining proper band selection methods (especially the iterative stepwise elimination approach) rather than using full bands as commonly done with PLSR. The results also show that the 1st order derivative spectra had a balance between accuracy (R2 = 0.80 for Vcmax, and 0.94 for Jmax) and denoising (when a Gaussian noise was added to each leaf reflectance spectrum at each wavelength with a standard deviation of 1%) on retrieving photosynthetic parameters from hyperspectral data. Our results clearly illustrate the advantage of using the band selection approach for PLSR dimensionality reduction and model optimization, highlighting the superiority of using derivative spectra for Vcmax and Jmax estimations, which should provide valuable insights for retrieving photosynthetic parameters from hyperspectral remotely sensed data.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Ainsworth EA, Serbin SP, Skoneczka JA, Townsend PA (2014) Using leaf optical properties to detect ozone effects on foliar biochemistry. Photosynth Res 119:65–76. https://doi.org/10.1007/s11120-013-9837-y
Akaike H (1974) A new look at the statistical model identification. IEEE Trans Automat Contr 19:716–723. https://doi.org/10.1109/TAC.1974.1100705
Andersen CM, Bro R (2010) Variable selection in regression-a tutorial. J Chemom 24:728–737. https://doi.org/10.1002/cem.1360
Barnes ML, Breshears DD, Law DJ et al (2017) Beyond greenness: detecting temporal changes in photosynthetic capacity with hyperspectral reflectance data. PLoS ONE 12:1–17. https://doi.org/10.1371/journal.pone.0189539
Cai W, Li Y, Shao X (2008) A variable selection method based on uninformative variable elimination for multivariate calibration of near-infrared spectra. Chemom Intell Lab Syst 90:188–194. https://doi.org/10.1016/j.chemolab.2007.10.001
Camino C, Gonzalez-Dugo V, Hernandez P, Zarco-Tejada PJ (2019) Radiative transfer Vcmax estimation from hyperspectral imagery and SIF retrievals to assess photosynthetic performance in rainfed and irrigated plant phenotyping trials. Remote Sens Environ 231:111186. https://doi.org/10.1016/j.rse.2019.05.005
Centner V, Massart DL, De Noord OE et al (1996) Elimination of uninformative variables for multivariate calibration. Anal Chem 68:3851–3858. https://doi.org/10.1021/ac960321m
Chapra SC, Canale RP (1988) Numerical methods for engineers. McGraw-Hill, New York
Chen H, Chen T, Zhang Z, Liu G (2017) Variable selection using adaptive band clustering and physarum network. Algorithms 10:1–16. https://doi.org/10.3390/a10030073
Cho MA, Sobhan I, Skidmore AK, et al (2008) Discriminating species using hyperspectral indices at leaf and canopy scales. In: ISPRS 2008 : Proceedings of the XXI congress : Silk road for information from imagery : the International Society for Photogrammetry and Remote Sensing, 3-11 July, Beijing, China. Comm. VII, WG VII/3. Beijing : ISPRS, 2008. pp. 369–376. http://www.isprs.org/proceedings/XXXVII/congress/7_pdf/3_WG-VII-3/28.pdf
De Groot PJ, Swierenga H, Postma GJ et al (2003) Effect on the partial least-squares prediction of yarn properties combining raman and infrared measurements and applying wavelength selection. Appl Spectrosc 57:642–648
Dechant B, Cuntz M, Vohland M et al (2017) Estimation of photosynthesis traits from leaf reflectance spectra: correlation to nitrogen content as the dominant mechanism. Remote Sens Environ 196:279–292. https://doi.org/10.1016/j.rse.2017.05.019
Dillen SY, de Beeck MO, Hufkens K et al (2012) Seasonal patterns of foliar reflectance in relation to photosynthetic capacity and color index in two co-occurring tree species, Quercus rubra and Betula papyrifera. Agric for Meteorol 160:60–68. https://doi.org/10.1016/j.agrformet.2012.03.001
Dorigo WA, Zurita-Milla R, de Wit AJW et al (2007) A review on reflective remote sensing and data assimilation techniques for enhanced agroecosystem modeling. Int J Appl Earth Obs Geoinf 9:165–193. https://doi.org/10.1016/j.jag.2006.05.003
Duursma RA (2015) Plantecophys—an R package for analysing and modelling leaf gas exchange data. PLoS ONE 10:1–13. https://doi.org/10.1371/journal.pone.0143346
Farquhar GD, von Caemmerer S, Berry JA (1980) A biochemical model of photosynthetic CO2 assimilation in leaves of C3 species. Planta 149:78–90. https://doi.org/10.1007/BF00386231
Foley S, Rivard B, Sanchez-Azofeifa GA, Calvo J (2006) Foliar spectral properties following leaf clipping and implications for handling techniques. Remote Sens Environ 103:265–275. https://doi.org/10.1016/j.rse.2005.06.014
Fu P, Meacham-Hensold K, Guan K, Bernacchi CJ (2019) Hyperspectral leaf reflectance as proxy for photosynthetic capacities: an ensemble approach based on multiple machine learning algorithms. Front Plant Sci 10:1–13. https://doi.org/10.3389/fpls.2019.00730
Fu P, Meacham-Hensold K, Guan K et al (2020) Estimating photosynthetic traits from reflectance spectra: a synthesis of spectral indices, numerical inversion, and partial least square regression. Plant Cell Environ. https://doi.org/10.1111/pce.13718
Fung T, Yan Ma HF, Siu WL (2003) Band selection using hyperspectral data of subtropical tree species. Geocarto Int 18:3–11. https://doi.org/10.1080/10106040308542284
Gamon JA, Filella A, Penuelas J (1993) The dynamic 531-nanometer delta reflectance signal: a survey of twenty angiosperm species. In: Yamamoto HY, Smith CM (eds) Photosynthetic responses to the environment. American Society of Plant Physiologists, Rockville
Gitelson AA, Gritz Y, Merzlyak MN (2003) Relationships between leaf chlorophyll content and spectral reflectance and algorithms for non-destructive chlorophyll assessment in higher plant leaves. J Plant Physiol 160:271–282. https://doi.org/10.1078/0176-1617-00887
Gowen A, Burger J, Esquerre C et al (2014) Near infrared hyperspectral image regression: on the use of prediction maps as a tool for detecting model overfitting. J near Infrared Spectrosc 22:261–270. https://doi.org/10.1255/jnirs.1114
Gowen AA, Downey G, Esquerre C, O’Donnell CP (2011) Preventing over-fitting in PLS calibration models of near-infrared (NIR) spectroscopy data using regression coefficients. J Chemom 25:375–381. https://doi.org/10.1002/cem.1349
Groenendijk M, Dolman AJ, van der Molen MK et al (2011a) Assessing parameter variability in a photosynthesis model within and between plant functional types using global Fluxnet eddy covariance data. Agric for Meteorol 151:22–38. https://doi.org/10.1016/j.agrformet.2010.08.013
Groenendijk M, Dolman AJ, Ammann C et al (2011b) Seasonal variation of photosynthetic model parameters and leaf area index from global Fluxnet eddy covariance data. J Geophys Res Biogeosciences 116:1–18. https://doi.org/10.1029/2011JG001742
Hasegawa K, Miyashita Y, Funatsu K (1997) GA strategy for variable selection in QSAR studies: GA-based PLS analysis of calcium channel antagonists. J Chem Inf Comput Sci 37:306–310. https://doi.org/10.1021/ci960047x
Huang X, Xu QS, Liang YZ (2012) PLS regression based on sure independence screening for multivariate calibration. Anal Methods 4:2815–2821. https://doi.org/10.1039/C2AY25032B
Imanishi J, Sugimoto K, Morimoto Y (2004) Detecting drought status and LAI of two Quercus species canopies using derivative spectra. Comput Electron Agric 43:109–129. https://doi.org/10.1016/j.compag.2003.12.001
Jin J, Wang Q (2019a) Selection of informative spectral bands for PLS models to estimate foliar chlorophyll content using hyperspectral reflectance. IEEE Trans Geosci Remote Sens 57:3064–3072. https://doi.org/10.1109/TGRS.2018.2880193
Jin J, Wang Q (2019b) Evaluation of informative bands used in different PLS regressions for estimating leaf biochemical contents from hyperspectral reflectance. Remote Sens 11:11–15. https://doi.org/10.3390/rs11020197
Jin J, Pratama BA, Wang Q (2020) Tracing leaf photosynthetic parameters using hyperspectral indices in an Alpine deciduous forest. Remote Sens 12:1124. https://doi.org/10.3390/rs12071124
Jin P, Wang Q, Iio A, Tenhunen J (2012) Retrieval of seasonal variation in photosynthetic capacity from multi-source vegetation indices. Ecol Inform 7:7–18. https://doi.org/10.1016/j.ecoinf.2011.10.004
Kawamura K, Watanabe N, Sakanoue S et al (2010) Testing genetic algorithm as a tool to select relevant wavebands from field hyperspectral data for estimating pasture mass and quality in a mixed sown pasture using partial least squares regression. Grassl Sci 56:205–216. https://doi.org/10.1111/j.1744-697X.2010.00196.x
Kochubey SM, Kazantsev TA (2012) Derivative vegetation indices as a new approach in remote sensing of vegetation. Front Earth Sci 6:188–195. https://doi.org/10.1007/s11707-012-0325-z
Krutz D, Muller R, Knodt U et al (2019) The instrument design of the DLR earth sensing imaging spectrometer (DESIS). Sensors 19:1622. https://doi.org/10.3390/s19071622
le Maire G, François C, Dufrêne E (2004) Towards universal broad leaf chlorophyll indices using PROSPECT simulated database and hyperspectral reflectance measurements. Remote Sens Environ 89:1–28. https://doi.org/10.1016/j.rse.2003.09.004
le Maire G, François C, Soudani K et al (2008) Calibration and validation of hyperspectral indices for the estimation of broadleaved forest leaf chlorophyll content, leaf mass per area, leaf area index and leaf canopy biomass. Remote Sens Environ 112:3846–3864. https://doi.org/10.1016/j.rse.2008.06.005
Leardi R (2000) Application of genetic algorithm-PLS for feature selection in spectral data sets. J Chemom 14:643–655. https://doi.org/10.1002/1099-128X(200009/12)14:5/63.0.CO;2-E
Leardi R, Boggia R, Terrile M (1992) Genetic algorithms as a strategy for feature selection. J Chemom 6:267–281. https://doi.org/10.1002/cem.1180060506
Leardi R, Lupiáñez González A (1998) Genetic algorithms applied to feature selection in PLS regression: how and when to use them. Chemom Intell Lab Syst 41:195–207. https://doi.org/10.1016/S0169-7439(98)00051-3
Li B, Morris J, Martin EB (2002) Model selection for partial least squares regression. Chemom Intell Lab Syst 64:79–89. https://doi.org/10.1016/S0169-7439(02)00051-5
Long SP, Bernacchi CJ (2003) Gas exchange measurements, what can they tell us about the underlying limitations to photosynthesis? Procedures and sources of error. J Exp Bot 54:2393–2401. https://doi.org/10.1093/jxb/erg262
Lu DM, Song KS, Li L et al (2010) Training a GA-PLS model for Chl-a concentration estimation over inland Lake in Northeast China. Procedia Environ Sci 2:842–851. https://doi.org/10.1016/j.proenv.2010.10.095
Luo X, Croft H, Chen JM et al (2019) Improved estimates of global terrestrial photosynthesis using information on leaf chlorophyll content. Glob Chang Biol 25:2499–2514. https://doi.org/10.1111/gcb.14624
Marshall M, Thenkabail P (2014) Biomass modeling of four leading world crops using hyperspectral narrowbands in support of HyspIRI mission. Photogramm Eng Remote Sensing 80:757–772
Marshall M, Thenkabail P (2015) Developing in situ non-destructive estimates of crop biomass to address issues of scale in remote sensing. Remote Sens 7:808–835. https://doi.org/10.3390/rs70100808
Meacham-Hensold K, Fu P, Wu J et al (2020) Plot-level rapid screening for photosynthetic parameters using proximal hyperspectral imaging. J Exp Bot 71:2312–2328. https://doi.org/10.1093/jxb/eraa068
Meacham-Hensold K, Montes CM, Wu J et al (2019) High-throughput field phenotyping using hyperspectral reflectance and partial least squares regression (PLSR) reveals genetic modifications to photosynthetic capacity. Remote Sens Environ 231:111176. https://doi.org/10.1016/j.rse.2019.04.029
Mehmood T, Liland KH, Snipen L, Sæbø S (2012) A review of variable selection methods in partial least squares regression. Chemom Intell Lab Syst 118:62–69. https://doi.org/10.1016/j.chemolab.2012.07.010
Norgaard L, Saudland A, Wagner J et al (2000) Interval partial least-squares regression (iPLS): a comparative chemometric study with an example from near-infrared spectroscopy. Appl Spectrosc 54:413–419. https://doi.org/10.1366/0003702001949500
Pacheco-Labrador J, El-Madany T, Martin MP et al (2020) Combining hyperspectral remote sensing and eddy covariance data streams for estimation of vegetation functional traits. Biogeosciences Discuss. https://doi.org/10.5194/bg-2019-501
Rady AM, Guyer DE, Kirk W, Donis-González IR (2014) The potential use of visible/near infrared spectroscopy and hyperspectral imaging to predict processing-related constituents of potatoes. J Food Eng 135:11–25. https://doi.org/10.1016/j.jfoodeng.2014.02.021
Richardson AD, Berlyn GP (2002) Changes in foliar spectral reflectance and chlorophyll fluorescence of four temperate species following branch cutting. Tree Physiol 22:499–506. https://doi.org/10.1093/treephys/22.7.499
Ryu Y, Berry JA, Baldocchi DD (2019) What is global photosynthesis? History, uncertainties and opportunities. Remote Sens Environ 223:95–114. https://doi.org/10.1016/j.rse.2019.01.016
Savitzky A, Golay MJE (1964) Smoothing and differentiation of data by simplified least squares procedures. Anal Chem 36:1627–1639. https://doi.org/10.1021/ac60214a048
Schmitt N, Ployhart RE (1999) Estimates of cross-validity for stepwise regression and with predictor selection. J Appl Psychol 84:50–57. https://doi.org/10.1037/0021-9010.84.1.50
Serbin SP, Dillaway DN, Kruger EL, Townsend PA (2012) Leaf optical properties reflect variation in photosynthetic metabolism and its sensitivity to temperature. J Exp Bot 63:489–502. https://doi.org/10.1093/jxb/err294
Serbin SP, Singh A, Desai AR et al (2015) Remotely estimating photosynthetic capacity, and its response to temperature, in vegetation canopies using imaging spectroscopy. Remote Sens Environ 167:78–87. https://doi.org/10.1016/j.rse.2015.05.024
Silva-Perez V, Molero G, Serbin SP et al (2018) Hyperspectral reflectance as a tool to measure biochemical and physiological traits in wheat. J Exp Bot 69:483–496. https://doi.org/10.1093/jxb/erx421
Singer RB, Geissler PE (1988) An independent assessment of derivative analysis of reflectance spectra. In: Abstracts of the Lunar and Planetary Science Conference 19:1087
Song G, Wang Q, Jin J (2020) Leaf photosynthetic capacity of sunlit and shaded mature leaves in a deciduous forest. Forests 11:1–14. https://doi.org/10.3390/f11030318
Tsai F, Philpot W (1998) Derivative analysis of hyperspectral data. Remote Sens Environ 66:41–51. https://doi.org/10.1016/S0034-4257(98)00032-7
Vilfan N, van der Tol C, Verhoef W (2019) Estimating photosynthetic capacity from leaf reflectance and Chl fluorescence by coupling radiative transfer to a model for photosynthesis. New Phytol 223:487–500. https://doi.org/10.1111/nph.15782
Wang S, Guan K, Wang Z et al (2020) Unique contributions of chlorophyll and nitrogen to predict crop photosynthetic capacity from leaf spectroscopy. J Exp Bot. https://doi.org/10.1093/jxb/eraa432
Wang ZX, He Q, Wang J (2014) Comparison of different variable selection methods for partial least squares soft sensor development. In: 2014 American Control Conference, 4–6 June 2014. Portland, OR, USA. https://doi.org/10.1109/ACC.2014.6859335
Wang Q, Ho A, Tenhunen J, Kakubari Y (2008a) Annual and seasonal variations in photosynthetic capacity of Fagus crenata along an elevation gradient in the Naeba Mountains, Japan. Tree Physiol 28:277–285. https://doi.org/10.1093/treephys/28.2.277
Wang Q, Iio A, Kakubari Y (2008b) Broadband simple ratio closely traced seasonal trajectory of canopy photosynthetic capacity. Geophys Res Lett 35:1–5. https://doi.org/10.1029/2008GL033619
Wang Q, Jin J, Sonobe R, Chen J (2018) Derivative Hyperspectral Vegetation Indices in Characterizing Forest Biophysical and Biochemical Quantities. In: Thenkabail PS, Lyon JG, Huete A (eds) Hyperspectral Indices and image classifications for agriculture and vegetation. CRC Press, Boca Raton
Wang Z, Kawamura K, Sakuno Y et al (2017) Retrieval of chlorophyll-a and total suspended solids using iterative stepwise elimination partial least squares (ISE-PLS) regression based on field hyperspectral measurements in irrigation ponds in Higashihiroshima, Japan. Remote Sens 9:1–14. https://doi.org/10.3390/rs9030264
Watt MS, Buddenbaum H, Leonardo EMC et al (2020) Monitoring biochemical limitations to photosynthesis in N and P-limited radiata pine using plant functional traits quantified from hyperspectral imagery. Remote Sens Environ 248:112003. https://doi.org/10.1016/j.rse.2020.112003
Wold S, Sjöström M, Eriksson L (2001) PLS-regression: a basic tool of chemometrics. Chemom Intell Lab Syst 58:109–130. https://doi.org/10.1016/S0169-7439(01)00155-1
Wu Q, Wang J, Wang C, Xu T (2016) Study on the optimal algorithm prediction of corn leaf component information based on hyperspectral imaging. Infrared Phys Technol 78:66–71. https://doi.org/10.1016/j.infrared.2016.07.011
Yang X, Yu Y, Fan W (2015) Chlorophyll content retrieval from hyperspectral remote sensing imagery. Environ Monit Assess 187:456. https://doi.org/10.1007/s10661-015-4682-4
Yendrek CR, Tomaz T, Montes CM et al (2017) High-throughput phenotyping of maize leaf physiological and biochemical traits using hyperspectral reflectance. Plant Physiol 173:614–626. https://doi.org/10.1104/pp.16.01447
Yin X, Struik PC (2009) C3 and C4 photosynthesis models: An overview from the perspective of crop modelling. NJAS Wagening J Life Sci 57:27–38. https://doi.org/10.1016/j.njas.2009.07.001
Yu T, Yu G, Li PY, Wang L (2014) Citation impact prediction for scientific papers using stepwise regression analysis. Scientometrics 101:1233–1252. https://doi.org/10.1007/s11192-014-1279-6
Zhang Y, Migliavacca M, Penuelas J, Ju W (2021) Advances in hyperspectral remote sensing of vegetation traits and functions. Remote Sens Environ 252:1–5. https://doi.org/10.1016/j.rse.2020.112121
Zheng T, Chen JM (2017) Photochemical reflectance ratio for tracking light use efficiency for sunlit leaves in two forest types. ISPRS J Photogramm Remote Sens 123:47–61. https://doi.org/10.1016/j.isprsjprs.2016.11.005
Zhou Y, Ju W, Sun X et al (2014) Close relationship between spectral vegetation indices and Vcmax in deciduous and mixed forests. Tellus Ser B Chem Phys Meteorol. https://doi.org/10.3402/tellusb.v66.23279
Acknowledgements
We thank the members of the Laboratory of Macroecology and the Institute of Silviculture, Shizuoka University, for their support of both fieldwork and laboratory analyses.
Author information
Authors and Affiliations
Contributions
QW designed the research and involved in data collection; JJ, GS, and QW analyzed and interpreted the data. JJ wrote the first draft. All authors read and contributed to the manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declared that they have no conflict of interests to disclose.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Jin, J., Wang, Q. & Song, G. Selecting informative bands for partial least squares regressions improves their goodness-of-fits to estimate leaf photosynthetic parameters from hyperspectral data. Photosynth Res 151, 71–82 (2022). https://doi.org/10.1007/s11120-021-00873-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11120-021-00873-9