Early drought stress detection in cereals: simplex volume maximisation for hyperspectral image analysis
Christoph Römer A F , Mirwaes Wahabzada B , Agim Ballvora C , Francisco Pinto D , Micol Rossini E , Cinzia Panigada E , Jan Behmann A , Jens Léon C , Christian Thurau B , Christian Bauckhage B , Kristian Kersting B , Uwe Rascher D and Lutz Plümer A
+ Author Affiliations
- Author Affiliations
A Institute of Geodesy and Geoinformation, Geoinformation, University of Bonn, Meckenheimer Allee 172, 53115 Bonn, Germany.
B Institute for Intelligent Analysis and Information Systems, Fraunhofer, Schloss Birlinghoven, 53754 Sankt Augustin, Germany.
C Institute of Crop Science and Resource Conservation, Plant Breeding and Biotechnology, University of Bonn, Katzenburgweg 5, 53115 Bonn, Germany.
D Institute of Bio- and Geosciences, IBG-2: Plant Sciences, Forschungszentrum Jülich, Leo-Brandt-Str., 52425 Jülich, Germany.
E Laboratorio di Telerilevamento delle Dinamiche Ambientali (LTDA), Dip. di Scienze dell’Ambiente e del Territorio (DISAT), Università degli Studi di Milano Bicocca (UNIMIB), Piazza della Scienza, 1, 20126 Milano, Italy.
F Corresponding author. Email: roemer@igg.uni-bonn.de
Functional Plant Biology 39(11) 878-890 https://doi.org/10.1071/FP12060
Submitted: 24 February 2012 Accepted: 8 July 2012 Published: 28 August 2012
Abstract
Early water stress recognition is of great relevance in precision plant breeding and production. Hyperspectral imaging sensors can be a valuable tool for early stress detection with high spatio-temporal resolution. They gather large, high dimensional data cubes posing a significant challenge to data analysis. Classical supervised learning algorithms often fail in applied plant sciences due to their need of labelled datasets, which are difficult to obtain. Therefore, new approaches for unsupervised learning of relevant patterns are needed. We apply for the first time a recent matrix factorisation technique, simplex volume maximisation (SiVM), to hyperspectral data. It is an unsupervised classification approach, optimised for fast computation of massive datasets. It allows calculation of how similar each spectrum is to observed typical spectra. This provides the means to express how likely it is that one plant is suffering from stress. The method was tested for drought stress, applied to potted barley plants in a controlled rain-out shelter experiment and to agricultural corn plots subjected to a two factorial field setup altering water and nutrient availability. Both experiments were conducted on the canopy level. SiVM was significantly better than using a combination of established vegetation indices. In the corn plots, SiVM clearly separated the different treatments, even though the effects on leaf and canopy traits were subtle.
Additional keywords: canopy, imaging spectroscopy, matrix factorisation, non-invasive, pattern recognition, plant phenotyping, unsupervised learning, water stress.
References
Aitichison J (1982) ‘The statistical analysis of compositional data.’ (Chapman & Hall: London)Aldakheel YY, Danson FM (1997) Spectral reflectance of dehydrating leaves: measurements and modelling. International Journal of Remote Sensing 18, 3683–3690.
| Spectral reflectance of dehydrating leaves: measurements and modelling.Crossref | GoogleScholarGoogle Scholar |
Bateson CA, Asner GP, Wessmann CA (2000) Endmember bundles: a new approach to incorporating endmember variability into spectral mixture analysis. IEEE Transactions on Geoscience and Remote Sensing 38, 1083–1094.
| Endmember bundles: a new approach to incorporating endmember variability into spectral mixture analysis.Crossref | GoogleScholarGoogle Scholar |
Bilger W, Björkman O (1990) Role of the xanthophylls cycle in photoprotection elucidated by measurements of light-induced absorbance changes, fluorescence and photosynthesis in leaves of Hedera canariensis. Photosynthesis Research 25, 173–185.
| Role of the xanthophylls cycle in photoprotection elucidated by measurements of light-induced absorbance changes, fluorescence and photosynthesis in leaves of Hedera canariensis.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DyaK3cXmtVymsbs%3D&md5=438bfb82476a83f01957e3366c76e84dCAS |
Bilger W, Schreiber U, Bock M (1995) Determination of the quantum efficiency of photosystem II and of non-photochemical quenching of the chlorophyll fluorescence in the field. Oecologia 102, 425–432.
| Determination of the quantum efficiency of photosystem II and of non-photochemical quenching of the chlorophyll fluorescence in the field.Crossref | GoogleScholarGoogle Scholar |
Bishop CM (2006) ‘Pattern recognition and machine learning.’ (Springer: New York)
Chaves MM, Flexas J, Pinheiro C (2009) Photosynthesis under drought and salt stress: regulation mechanisms from whole plant to cell. Annals of Botany 103, 551–560.
| Photosynthesis under drought and salt stress: regulation mechanisms from whole plant to cell.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BD1MXktVGnu7s%3D&md5=5500739fc94ee3295b2dea488c3004b7CAS |
Çivril A, Magdon-Ismail M (2009) On selecting a maximum volume sub-matrix of a matrix and related problems. Theoretical Computer Science 410, 4801–4811.
| On selecting a maximum volume sub-matrix of a matrix and related problems.Crossref | GoogleScholarGoogle Scholar |
Cohen WB (1991) Temporal versus spatial variation in leaf reflectance under changing water stress conditions. International Journal of Remote Sensing 12, 1865–1876.
| Temporal versus spatial variation in leaf reflectance under changing water stress conditions.Crossref | GoogleScholarGoogle Scholar |
Colombo R, Meroni M, Marchesi A, Busetto L, Rossini M, Giardino C, Panigada C (2008) Remote sensing of leaf and canopy water content in poplar plantations by means of hyperspectral data. Remote Sensing of Environment 112, 1820–1834.
| Remote sensing of leaf and canopy water content in poplar plantations by means of hyperspectral data.Crossref | GoogleScholarGoogle Scholar |
Cox T, Cox M (1984) ‘Multidimensional scaling.’ (Chapman & Hall: London)
Cutler A, Breiman L (1994) Archetypal analysis. Technometrics 36, 338–347.
Damm A, Elbers J, Erler E, Giolo B, Hamdi K, Hutjes R, Kosyancoya M, Meroni M, Miglietta F, Moreno J, Schickling A, Sonnenschein R, Udelhoven T, van der Linden S, Hostert P, Rascher U (2010) Remote sensing of sun induced fluorescence to improve modeling of diurnal courses of gross primary production (GPP). Global Change Biology 16, 171–186.
| Remote sensing of sun induced fluorescence to improve modeling of diurnal courses of gross primary production (GPP).Crossref | GoogleScholarGoogle Scholar |
Danson FM, Steven MD, Malthus TJ, Clark JA (1992) High-spectral resolution data for determining leaf water content. International Journal of Remote Sensing 13, 461–470.
| High-spectral resolution data for determining leaf water content.Crossref | GoogleScholarGoogle Scholar |
Fiorani F, Rascher U, Jahnke S, Schurr U (2012) Imaging plants dynamics in heterogenic environments. Current Opinion in Biotechnology
| Imaging plants dynamics in heterogenic environments.Crossref | GoogleScholarGoogle Scholar |
Gamon JA, Penuelas J, Field CB (1992) A narrow waveband spectral index that tracks diurnal changes in photosynthetic efficiency. Remote Sensing of Environment 41, 35–44.
| A narrow waveband spectral index that tracks diurnal changes in photosynthetic efficiency.Crossref | GoogleScholarGoogle Scholar |
Gitelson AA, Keydan GP, Merzylak MN (2006) Three-band model for non-invasive estimation of chlorophyll, carotenoids, and anthocyanin contents in higher plant leaves. Geophysical Research Letters 33, L11402
| Three-band model for non-invasive estimation of chlorophyll, carotenoids, and anthocyanin contents in higher plant leaves.Crossref | GoogleScholarGoogle Scholar |
Haboudane D, Tremblay N, Miller JR, Vigneault P (2008) Remote estimation of crop chlorophyll content using spectral indices derived from hyperspectral data. IEEE Transactions on Geoscience and Remote Sensing 46, 423–437.
| Remote estimation of crop chlorophyll content using spectral indices derived from hyperspectral data.Crossref | GoogleScholarGoogle Scholar |
Hunt ER, Rock BN (1989) Detection of changes in leaf water content using near- and middle-infrared reflectances. Remote Sensing of Environment 30, 43–54.
| Detection of changes in leaf water content using near- and middle-infrared reflectances.Crossref | GoogleScholarGoogle Scholar |
Jackson RD, Huete AR (1991) Interpreting vegetation indices. Preventive Veterinary Medicine 11, 185–200.
| Interpreting vegetation indices.Crossref | GoogleScholarGoogle Scholar |
Kimes DS, Newcomb WW, Shutt JB, Pinter PJ, Jackson RD (1984) Directional reflectance factor distributions of a cotton row crop. International Journal of Remote Sensing 5, 263–277.
| Directional reflectance factor distributions of a cotton row crop.Crossref | GoogleScholarGoogle Scholar |
Knipling EB (1970) Physical and physiological basis for the reflectance of visible and near-infrared radiation from vegetation. Remote Sensing of Environment 1, 155–159.
| Physical and physiological basis for the reflectance of visible and near-infrared radiation from vegetation.Crossref | GoogleScholarGoogle Scholar |
Mahlein AK, Oerke E-C, Steiner U, Dehne H-W (2012) Recent advances in sensing plant diseases for precision crop protection. European Journal of Plant Pathology 133, 197–209.
| Recent advances in sensing plant diseases for precision crop protection.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BC38XkvVCrsbk%3D&md5=9909017b82d6e53fedbadaa08461f964CAS |
Malenovský Z, Mishra KB, Zemek F, Rascher U, Nedbal L (2009) Scientific and technical challenges in remote sensing of plant canopy reflectance and fluorescence. Journal of Experimental Botany 60, 2987–3004.
| Scientific and technical challenges in remote sensing of plant canopy reflectance and fluorescence.Crossref | GoogleScholarGoogle Scholar |
Meroni M, Rossini M, Picchi V, Panigada C, Cogliati S, Nali C, Colombo R (2008) Assessing steady-state fluorescence and PRI from hyperspectral proximal sensing as early indicators of plant stress: the case of ozone exposure. Sensors 8, 1740–1754.
| Assessing steady-state fluorescence and PRI from hyperspectral proximal sensing as early indicators of plant stress: the case of ozone exposure.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BD1cXkvVCrtb4%3D&md5=f9f3f90e3fe2b05803c2d8ca8b6116b7CAS |
Meroni M, Panigada C, Rossini M, Picchi V, Cogliati S, Colombo R (2009a) Using optical remote sensing techniques to track the development of ozone-induced stress. Environmental Pollution 157, 1413–1420.
| Using optical remote sensing techniques to track the development of ozone-induced stress.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BD1MXktF2lurg%3D&md5=129fec8ee57cc255050eab753604331fCAS |
Meroni M, Rossini M, Guanter L, Alonso L, Rascher U, Colombo R, Moreno J (2009b) Remote sensing of solar induced chlorophyll fluorescence: review of methods and applications. Remote Sensing of Environment 113, 2037–2051.
| Remote sensing of solar induced chlorophyll fluorescence: review of methods and applications.Crossref | GoogleScholarGoogle Scholar |
Niinemets U (2007) Photosynthesis and resource distribution through plant canopies. Plant, Cell & Environment 30, 1052–1071.
| Photosynthesis and resource distribution through plant canopies.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BD2sXhtVeiurrN&md5=f2cbcb4d65b56899813d9e58680bf147CAS |
Peñuelas J, Filella L (1998) Technical focus: visible and near-infrared reflectance techniques for diagnostic plant physiological status. Trends in Plant Science 3, 151–156.
| Technical focus: visible and near-infrared reflectance techniques for diagnostic plant physiological status.Crossref | GoogleScholarGoogle Scholar |
Penuelas J, Filella I, Gamon JA (1995) Assessment of photosynthetic radiation-use efficiency with spectral reflectance. New Phytologist 131, 291–296.
| Assessment of photosynthetic radiation-use efficiency with spectral reflectance.Crossref | GoogleScholarGoogle Scholar |
Penuelas J, Pinol J, Ogaya R, Filella I (1997) Photochemical reflectance index and leaf photosynthetic radiation-use-efficiency assessment in Mediterranean trees. International Journal of Remote Sensing 18, 2869–2875.
| Photochemical reflectance index and leaf photosynthetic radiation-use-efficiency assessment in Mediterranean trees.Crossref | GoogleScholarGoogle Scholar |
Rascher U, Nichol CJ, Small C, Hendricks L (2007) Monitoring spatio-temporal dynamics of photosynthesis with a portable hyperspectral imaging system. Photogrammetric Engineering and Remote Sensing 73, 45–56.
Rascher U, Damm A, van der Linden S, Okujeni A, Pieruschka R, Schickling A, Hostert P (2010) Sensing of photosynthetic activity of crops. In ‘Precision crop protection – the challenge and use of heterogeneity’. (Ed. E-C Oerke) pp. 878–99. (Springer Science & Business Media: Dordrecht, The Netherlands)
Richards RA, Rebetzke GJ, Watt M, Condon AG, Spielmeyer W, Dolferus R (2010) Breeding for improved water productivity in temperate cereals: phenotyping, quantitative trait loci, markers and the selection environment. Functional Plant Biology 37, 85–97.
| Breeding for improved water productivity in temperate cereals: phenotyping, quantitative trait loci, markers and the selection environment.Crossref | GoogleScholarGoogle Scholar |
Römer C, Bürling K, Rumpf T, Hunsche M, Noga G, Plümer L (2011) Robust fitting of fluorescence spectra for presymptomatic wheat leaf rust detection with support vector machines. Computers and Electronics in Agriculture 79, 180–188.
| Robust fitting of fluorescence spectra for presymptomatic wheat leaf rust detection with support vector machines.Crossref | GoogleScholarGoogle Scholar |
Rouse JW, Haas RH, Schell JA, Deering DW, Harlan JC (1974) Monitoring the vernal advancement of retrogradation of natural vegetation, NASA/GSFC, Type III, Final Report, Greenbelt, MD.
Scholander P, Bradstreet E, Hemmingsen E, Hammel H (1965) Sap pressure in vascular plants: negative hydrostatic pressure can be measured in plants. Science 148, 339–346.
| Sap pressure in vascular plants: negative hydrostatic pressure can be measured in plants.Crossref | GoogleScholarGoogle Scholar | 1:STN:280:DC%2BC3cvlsVKquw%3D%3D&md5=7a95ab02c16d02693138b3c00d255211CAS |
Schreiber U, Bilger W (1993) Progress in chlorophyll fluorescence research: major development during the past years in retrospect. Progress in Botany 53, 151–173.
Schulte D, Close TJ, Graner A, Langridge P, Matsumoto T, Muehlbauer G, Sato K, Schulman AH, Waugh R, Wise RP, Stein N (2009) The international barley sequencing consortium – at the threshold of efficient access to the barley genome. Plant Physiology 149, 142–147.
| The international barley sequencing consortium – at the threshold of efficient access to the barley genome.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BD1MXjt1Wqsb0%3D&md5=98a7dbf8144a7411805e517a30b2eb82CAS |
Somers B, Asner GP, Tits L, Coppin P (2011) Endmember variability in spectral mixture analysis: a review. Remote Sensing of Environment 115, 1603–1616.
| Endmember variability in spectral mixture analysis: a review.Crossref | GoogleScholarGoogle Scholar |
Tenenbaum JB, De Silva V, Langford JC (2000) A global geometrix framework for nonlinear dimensionality reduction. Science 290, 2319–2323.
| A global geometrix framework for nonlinear dimensionality reduction.Crossref | GoogleScholarGoogle Scholar | 1:STN:280:DC%2BD3M%2Fnt1yitQ%3D%3D&md5=8c415061e1b41e9c18899a15b6f51c9fCAS |
Thenkabail PS, Smith RB, De Pauw E (2000) Hyperspectral vegetation indices and their relationships with agricultural crop characteristics. Remote Sensing of Environment 71, 158–182.
| Hyperspectral vegetation indices and their relationships with agricultural crop characteristics.Crossref | GoogleScholarGoogle Scholar |
Thurau C, Kersting K, Bauckhage C (2010) Yes we can – simplex volume maximization for descriptive web-scale matrix factorization. In ‘Proceedings of the conference on information and knowledge management’. pp. 1785–1788.
Tilling AK, O’Leary GJ, Ferwerda JG, Jones SD, Fitzgerald GJ, Rodriguez D, Belford R (2007) Remote sensing of nitrogen and water stress in wheat. Field Crops Research 104, 77–85.
| Remote sensing of nitrogen and water stress in wheat.Crossref | GoogleScholarGoogle Scholar |
Ustin S, Gamon JA (2010) Remote sensing of plant functional types. New Phytologist 186, 795–816.
| Remote sensing of plant functional types.Crossref | GoogleScholarGoogle Scholar |
Yilmaz MT, Hunt ER, Jackson TJ (2008) Remote sensing of vegetation water content from equivalent water thickness using satellite imagery. Remote Sensing of Environment 112, 2514–2522.
| Remote sensing of vegetation water content from equivalent water thickness using satellite imagery.Crossref | GoogleScholarGoogle Scholar |
