Functional unfold principal component analysis for automatic plant-based stress detection in grapevine
Annelies Baert A C , Kris Villez B and Kathy Steppe A
+ Author Affiliations
- Author Affiliations
A Department of Applied Ecology and Environmental Biology, Laboratory of Plant Ecology, Faculty of Bioscience Engineering, Ghent University, Coupure links 653, 9000 Gent, Belgium.
B Laboratory for Intelligent Process Systems, School of Chemical Engineering, Purdue University, West Lafayette, IN 47907, USA.
C Corresponding author. Email: aebaert.baert@ugent.be
Functional Plant Biology 39(6) 519-530 https://doi.org/10.1071/FP12007
Submitted: 10 January 2012 Accepted: 26 April 2012 Published: 22 May 2012
Abstract
Detection of drought stress is of great importance in grapevines because the plant’s water status strongly affects the quality of the grapes and hence, resulting wine. Measurements of stem diameter variations show promise for detecting drought stress, but they depend strongly on microclimatic changes. Tools for advanced data analysis might be helpful to distinguish drought from microclimate effects. To this end, we explored the possibilities of two data mining techniques: Unfold principal component analysis (UPCA) – an already established tool in several biotechnological domains – and functional unfold principal component analysis (FUPCA) – a newer technique combining functional data analysis with UPCA. With FUPCA, the original, multivariate time series of variables are first approximated by fitting the least-squares optimal linear combination of orthonomal basis functions. The resulting coefficients of these linear combinations are then subjected to UPCA. Both techniques were used to detect when the measured stem diameter variations in grapevine deviated from their normal conditions due to drought stress. Stress was detected with both UPCA and FUPCA days before visible symptoms appeared. However, FUPCA is less complex in the statistical sense and more robust than original UPCA modelling. Moreover, FUPCA can handle days with missing data, which is not possible with UPCA.
Additional keywords: drought stress, functional data analysis, statistical process control, stem diameter variations, Vitis vinifera.
References
Bacci L, De Vincenzi M, Rapi B, Arca B, Benincasa F (1998) Two methods for the analysis of colorimetric components applied to plant stress monitoring. Computers and Electronics in Agriculture 19, 167–186.| Two methods for the analysis of colorimetric components applied to plant stress monitoring.Crossref | GoogleScholarGoogle Scholar |
Baeza P, Sánchez-de-Miguel P, Centeno A, Junquera P, Linares R, Lissarrague JR (2007) Water relations between leaf water potential, photosynthesis and agronomic vine response as a tool for establishing thresholds in irrigation scheduling. Scientia Horticulturae 114, 151–158.
| Water relations between leaf water potential, photosynthesis and agronomic vine response as a tool for establishing thresholds in irrigation scheduling.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BD2sXhtFelsLfE&md5=690448ca9054b8579102ab791b714afdCAS |
Bicciato S, Bagno A, Soldà M, Manfredini R, Di Bello C (2002) Fermentation diagnosis by multivariate statistical analysis. Applied Biochemistry and Biotechnology 102–103, 49–62.
| Fermentation diagnosis by multivariate statistical analysis.Crossref | GoogleScholarGoogle Scholar |
Chen J, Liu J (2001) Derivation of function space analysis based PCA control charts for batch process monitoring. Chemical Engineering Science 56, 3289–3304.
| Derivation of function space analysis based PCA control charts for batch process monitoring.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BD3MXksVektL8%3D&md5=2056bb197238148278ff1cf478d6f5ebCAS |
Choné X, Van Leeuwen C, Dubourdieu D, Gaudillère J-P (2001) Stem water potential is a sensitive indicator of grapevine water status. Annals of Botany 87, 477–483.
| Stem water potential is a sensitive indicator of grapevine water status.Crossref | GoogleScholarGoogle Scholar |
Creasy GL, Creasy LL (2009) Grapes. In ‘Crop production science in horticulture 16’. (Eds J Atherton, A Rees) pp. 70–155. (CABI: Oxfordshire, UK)
Cruiziat P, Tyree MT (1990) La montée de la sève dans les arbres. La Recherche 21, 406–414.
Daudet F-A, Améglio T, Cochard H, Archilla O, Lacointe A (2005) Experimental analysis of the role of water and carbon in tree stem diameter variations. Journal of Experimental Botany 56, 135–144.
De Swaef T, Steppe K (2010) Linking stem diameter variations to sap flow, turgor and water potential in tomato. Functional Plant Biology 37, 429–438.
| Linking stem diameter variations to sap flow, turgor and water potential in tomato.Crossref | GoogleScholarGoogle Scholar |
De Swaef T, Steppe K, Lemeur R (2009) Determining reference values for stem water potential and maximum daily trunk shrinkage in young apple trees based on plant responses to water deficit. Agricultural Water Management 96, 541–550.
| Determining reference values for stem water potential and maximum daily trunk shrinkage in young apple trees based on plant responses to water deficit.Crossref | GoogleScholarGoogle Scholar |
De Swaef T, Verbist K, Cornelis W, Steppe K (2012) Tomato sap flow, stem and fruit growth in relation to water availability in rockwool growing medium. Plant and Soil 350, 237–252.
| Tomato sap flow, stem and fruit growth in relation to water availability in rockwool growing medium.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BC3MXhs1agsbbL&md5=381639d54654de4b56d355cd8a266db2CAS |
Dunia R, Qin J (1998) Subspace approach to multidimensional fault identification and reconstruction. AIChE Journal 44, 1813–1831.
Fereres E, Goldhamer DA (2003) Suitability of stem diameter variations and water potential as indicators for irrigation scheduling of almond trees. The Journal of Horticultural Science & Biotechnology 78, 139–144.
Fernández JE, Cuevas MV (2010) Irrigation scheduling from stem diameter variations: a review. Agricultural and Forest Meteorology 150, 135–151.
| Irrigation scheduling from stem diameter variations: a review.Crossref | GoogleScholarGoogle Scholar |
Gaudillère J-P, Van Leeuwen C, Ollat N (2002) Carbon isotope composition of sugars in grapevine, an integrated indicator of vineyard water status. Journal of Experimental Botany 53, 757–763.
| Carbon isotope composition of sugars in grapevine, an integrated indicator of vineyard water status.Crossref | GoogleScholarGoogle Scholar |
Génard M, Fishman S, Vercambre G, Huguet J-G, Bussi C, Besset J, Habib R (2001) A biophysical analysis of stem and root diameter variations in woody plants. Plant Physiology 126, 188–202.
| A biophysical analysis of stem and root diameter variations in woody plants.Crossref | GoogleScholarGoogle Scholar |
Goldhamer D, Fereres E (2001) Irrigation scheduling protocols using continuously recorded trunk diameter measurements. Irrigation Science 20, 115–125.
| Irrigation scheduling protocols using continuously recorded trunk diameter measurements.Crossref | GoogleScholarGoogle Scholar |
Gurden SP, Westerhuis JA, Bro R, Smilde AK (2001) A comparison of multiway regression and scaling methods. Chemometrics and Intelligent Laboratory Systems 59, 121–136.
| A comparison of multiway regression and scaling methods.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BD3MXoslSms7o%3D&md5=63b75a07ad18df862fbc4226a1173117CAS |
Hoefsloot HCJ, Verouden MPH, Westerhuis JA, Smilde AK (2006) Maximum likelihood scaling (MALS). Journal of Chemometrics 20, 120–127.
| Maximum likelihood scaling (MALS).Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BD2sXks1KqtL4%3D&md5=dd5021f95caefea30f468a7de0fb85c0CAS |
Hotelling H (1947) Multivariate quality control – illustrated by the testing of sample bombsights. In ‘Selected techniques of statistical analysis’. (Ed. O Eisenhart) pp. 113–184. (McGraw-Hill: New York, USA)
Intrigliolo DS, Castel JR (2007) Evaluation of grapevine water status from trunk diameter variations. Irrigation Science 26, 49–59.
| Evaluation of grapevine water status from trunk diameter variations.Crossref | GoogleScholarGoogle Scholar |
Jackson J (1991) ‘A user’s guide to principal components.’ (Wiley-Interscience: New York, USA)
Johnson RA, Wichern DW (2002) ‘Applied multivariate statistical analysis.’ 5th edn. (Prentice-Hall Inc.: New Jersey, USA)
Jones HG (1990) Plant water relations and implications for irrigation scheduling. Acta Horticulturae 278, 67–76.
Jones HG (1992) ‘Plants and microclimate. A quantitative approach to environmental plant physiology.’ 5th edn. (Cambridge University Press: Cambridge, UK)
Jones HG (2004) Irrigation scheduling: advantages and pitfalls of plant-based methods. Journal of Experimental Botany 55, 2427–2436.
| Irrigation scheduling: advantages and pitfalls of plant-based methods.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BD2cXovVOisr4%3D&md5=e0ce282d86b18c4085f25db86b2783a2CAS |
Keller M (2010) Managing grapevines to optimise fruit development in a challenging environment: a climate change primer for viticulturists. Australian Journal of Grape and Wine Research 16, 56–69.
| Managing grapevines to optimise fruit development in a challenging environment: a climate change primer for viticulturists.Crossref | GoogleScholarGoogle Scholar |
Kourti T (2002) Process analysis and abnormal situation detection: from theory to practice. IEEE Control Systems Magazine 22, 10–25.
| Process analysis and abnormal situation detection: from theory to practice.Crossref | GoogleScholarGoogle Scholar |
Lee DS, Vanrolleghem PA (2003) Monitoring of a sequencing batch reactor using adaptive multiblock principal component analysis. Biotechnology and Bioengineering 82, 489–497.
| Monitoring of a sequencing batch reactor using adaptive multiblock principal component analysis.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BD3sXjtFSlsL4%3D&md5=04ab2cf165edf8ce343b37fb31799beeCAS |
Lennox J, Rosén C (2002) Adaptive multiscale principal components analysis for online monitoring of wastewater treatment. Water Science and Technology 45, 227–235.
Lennox B, Montague GA, Hiden HG, Kornfeld G, Goulding PR (2001) Process monitoring of an industrial fed-batch fermentation. Biotechnology and Bioengineering 74, 125–135.
| Process monitoring of an industrial fed-batch fermentation.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BD3MXkvVejsrY%3D&md5=459d9f7185c40893d7bf0114b4dc41e6CAS |
MacGregor JF, Jaeckle C (1994) Process monitoring and diagnosis by multiblock PLS methods. AIChE Journal. American Institute of Chemical Engineers 40, 826–838.
| Process monitoring and diagnosis by multiblock PLS methods.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DyaK2cXjt1Kktr4%3D&md5=3ae07f0e863348f91b5324225901778dCAS |
MacGregor JF, Kourti T (1995) Statistical process control of multivariate processes. Control Engineering Practice 3, 403–414.
| Statistical process control of multivariate processes.Crossref | GoogleScholarGoogle Scholar |
Matthews MA, Ishii R, Anderson MM, O’Mahony M (1990) Dependence of wine sensory attributes on vine water status. Journal of the Science of Food and Agriculture 51, 321–335.
| Dependence of wine sensory attributes on vine water status.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DyaK3cXktlyrsL0%3D&md5=733b0bb3767f0b69971d463f2a89086bCAS |
Möller M, Alchanatis V, Cohen Y, Meron M, Tsipris J, Naor A, Ostrovsky V, Sprintsin M, Cohen S (2007) Use of thermal and visible imagery for estimating crop water status of irrigated grapevine. Journal of Experimental Botany 58, 827–838.
| Use of thermal and visible imagery for estimating crop water status of irrigated grapevine.Crossref | GoogleScholarGoogle Scholar |
Nomikos P, MacGregor J (1994) Monitoring batch process using multiway principal component analysis. AIChE Journal. American Institute of Chemical Engineers 40, 1361–1375.
| Monitoring batch process using multiway principal component analysis.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DyaK2cXlvVWmu7Y%3D&md5=9f82ab5ec0856ad8d0bc7925ed2f894bCAS |
Ortuño MF, Conejero W, Moreno F, Moriana A, Intrigliolo DS, Biel C, Mellisho CD, Pérez-Pastor A, Domingo R, Ruiz-Sanchez MC, Casadesus J, Bonany J, Torrecillas A (2010) Could trunk diameter sensors be used in woody crops for irrigation scheduling? A review of current knowledge and future perspectives. Agricultural Water Management 97, 1–11.
| Could trunk diameter sensors be used in woody crops for irrigation scheduling? A review of current knowledge and future perspectives.Crossref | GoogleScholarGoogle Scholar |
Patakas A, Noitsakis B, Chouzouri A (2005) Optimization of irrigation water use in grapevines using the relationship between transpiration and plant water status. Agriculture Ecosystems & Environment 106, 253–259.
| Optimization of irrigation water use in grapevines using the relationship between transpiration and plant water status.Crossref | GoogleScholarGoogle Scholar |
Ramsay JO, Silverman BW (2005) ‘Functional data analysis.’ 2nd edn. (Springer: New York, USA)
Ramsay JO, Hooker G, Graves S (2009) ‘Functional data analysis with R and MATLAB.’ (Springer: New York, USA)
Rosén C, Lennox JA (2001) Multivariate and multiscale monitoring of wastewater treatment operation. Water Research 35, 3402–3410.
| Multivariate and multiscale monitoring of wastewater treatment operation.Crossref | GoogleScholarGoogle Scholar |
Schultz HR (2000) Climate change and viticulture: a European perspective on climatology, carbon dioxide and UV-B effects. Australian Journal of Grape and Wine Research 6, 2–12.
| Climate change and viticulture: a European perspective on climatology, carbon dioxide and UV-B effects.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BD3cXjt1Sls70%3D&md5=0b2ed83b48f226a3144a3cb4db292ec1CAS |
Schultz HR, Stoll M (2010) Some critical issues in environmental physiology of grapevines: future challenges and current limitations. Australian Journal of Grape and Wine Research 16, 4–24.
| Some critical issues in environmental physiology of grapevines: future challenges and current limitations.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BC3cXislartrc%3D&md5=ae2b9a48ea95ba5218188404d030b2ceCAS |
Smart RE, Robinson M (1991) ‘Sunlight into wine: handbook for wine grape canopy management.’ (Winetitles: Adelaide, Australia)
Smart RE, Dick JK, Gravett IM, Fisher BM (1990) Canopy management to improve grape yield and wine quality – principles and practices. South African Journal of Enology & Viticulture 11, 3–17.
Steppe K, Lemeur R (2004) An experimental system for analysis of the dynamic sap-flow characteristics in young trees: results of a beech tree. Functional Plant Biology 31, 83–92.
| An experimental system for analysis of the dynamic sap-flow characteristics in young trees: results of a beech tree.Crossref | GoogleScholarGoogle Scholar |
Steppe K, De Pauw DJW, Lemeur R, Vanrolleghem PA (2006) A mathematical model linking tree sap flow dynamics to daily stem diameter fluctuations and radial stem growth. Tree Physiology 26, 257–273.
| A mathematical model linking tree sap flow dynamics to daily stem diameter fluctuations and radial stem growth.Crossref | GoogleScholarGoogle Scholar |
Steppe K, De Pauw DJW, Lemeur R (2008) A step towards new irrigation scheduling strategies using plant-based measurements and mathematical modelling. Irrigation Science 26, 505–517.
| A step towards new irrigation scheduling strategies using plant-based measurements and mathematical modelling.Crossref | GoogleScholarGoogle Scholar |
Steppe K, Cochard H, Lacointe A, Améglio T (2012) Could rapid diameter changes be facilitated by a variable hydraulic conductance? Plant, Cell & Environment 35, 150–157.
| Could rapid diameter changes be facilitated by a variable hydraulic conductance?Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BC38XjvVWht7c%3D&md5=3017d4f2c649b02c79f9b2f0e80f1813CAS |
Turlach BA (2005) Shape constrained smoothing using smoothing splines. Computational Statistics 20, 81–104.
| Shape constrained smoothing using smoothing splines.Crossref | GoogleScholarGoogle Scholar |
Tyree MT, Zimmermann MH (2002) ‘Xylem structure and the ascent of sap.’ 2nd edn. (Springer-Verlag: Berlin, Germany)
Venkatasubramanian V, Rengaswamy R, Kavuri SN (2003) A review of process fault detection and diagnosis. Part III: process history based methods. Computers & Chemical Engineering 27, 327–346.
| A review of process fault detection and diagnosis. Part III: process history based methods.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DC%2BD3sXhtlGqsLk%3D&md5=e5f45c9fe7ebe8b36226b89b72a81dbeCAS |
Villez K, Ruiz M, Sin G, Colomer J, Rosén C, Vanrolleghem PA (2008) Combining multiway principal component analysis and clustering for efficient data mining of historical data sets of SBR processes. Water Science and Technology 57, 1659–1666.
| Combining multiway principal component analysis and clustering for efficient data mining of historical data sets of SBR processes.Crossref | GoogleScholarGoogle Scholar |
Villez K, Steppe K, De Pauw DJW (2009) Use of Unfold PCA for on-line plant stress monitoring and sensor failure detection. Biosystems Engineering 103, 23–34.
| Use of Unfold PCA for on-line plant stress monitoring and sensor failure detection.Crossref | GoogleScholarGoogle Scholar |
Wentzell PD, Lohnes MT (1999) Maximum likelihood principal component analysis with correlated measurement errors: theoretical and practical considerations. Chemometrics and Intelligent Laboratory Systems 45, 65–85.
| Maximum likelihood principal component analysis with correlated measurement errors: theoretical and practical considerations.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DyaK1MXkslOlsA%3D%3D&md5=7f8b464943b2c3029741b7b6684824d2CAS |
Williams LE (2000) Grapevine water relations. In ‘Raisin production manual’. (Ed. LP Christensen) pp. 121–126. (University of California, Agricultural and Natural Resources Publications: Oakland, CA, USA)
Williams LE, Matthews MA (1990) Grapevine. In ‘Irrigation of agricultural crops. Agronomy Monograph no. 30’. (Eds BA Stewart, DR Nielsen) pp. 1019–1055. (American Society of Agronomy: Madison, WI, USA)
Wold S, Geladi P, Esbensen K, Öhman J (1987) Multi-way principal components and PLS-analysis. Journal of Chemometrics 1, 41–56.
| Multi-way principal components and PLS-analysis.Crossref | GoogleScholarGoogle Scholar | 1:CAS:528:DyaL2sXit1Kns7c%3D&md5=c40456e26a3cb7f7260173d55cf1bdd0CAS |
