Instantaneous and non-destructive relative water content estimation from deep learning applied to resonant ultrasonic spectra of plant leaves

BackgroundNon-contact resonant ultrasound spectroscopy (NC-RUS) has been proven as a reliable technique for the dynamic determination of leaf water status. It has been already tested in more than 50 plant species. In parallel, relative water content (RWC) is highly used in the ecophysiological field to describe the degree of water saturation in plant leaves. Obtaining RWC implies a cumbersome and destructive process that can introduce artefacts and cannot be determined instantaneously.ResultsHere, we present a method for the estimation of RWC in plant leaves from non-contact resonant ultrasound spectroscopy (NC-RUS) data. This technique enables to collect transmission coefficient in a [0.15–1.6] MHz frequency range from plant leaves in a non-invasive, non-destructive and rapid way. Two different approaches for the proposed method are evaluated: convolutional neural networks (CNN) and random forest (RF). While CNN takes the entire ultrasonic spectra acquired from the leaves, RF only uses four relevant parameters resulted from the transmission coefficient data. Both methods were tested successfully in Viburnum tinus leaf samples with Pearson’s correlations between 0.92 and 0.84.ConclusionsThis study showed that the combination of NC-RUS technique with deep learning algorithms is a robust tool for the instantaneous, accurate and non-destructive determination of RWC in plant leaves.

[1]  T. G. Gomez Alvarez-Arenas,et al.  Monitoring plant response to environmental stimuli by ultrasonic sensing of the leaves. , 2014, Ultrasound in medicine & biology.

[2]  H. Medrano,et al.  The Application of Leaf Ultrasonic Resonance to Vitis vinifera L. Suggests the Existence of a Diurnal Osmotic Adjustment Subjected to Photosynthesis , 2016, Front. Plant Sci..

[3]  Haibo He,et al.  Learning from Imbalanced Data , 2009, IEEE Transactions on Knowledge and Data Engineering.

[4]  J. Peguero-Pina,et al.  Non-contact ultrasonic resonant spectroscopy resolves the elastic properties of layered plant tissues , 2018, Applied Physics Letters.

[5]  Chak-Kuen Wong,et al.  An Efficient Method for Weighted Sampling Without Replacement , 1980, SIAM J. Comput..

[6]  J. Camarero,et al.  Functional groups in Quercus species derived from the analysis of pressure–volume curves , 2002, Trees.

[7]  J. Peguero-Pina,et al.  Shear waves in vegetal tissues at ultrasonic frequencies , 2013 .

[8]  Tomas Gómez Álvarez-Arenas,et al.  Air-Coupled Piezoelectric Transducers with Active Polypropylene Foam Matching Layers , 2013, Sensors.

[9]  Yogan Monnier,et al.  The Impact of Competition and Allelopathy on the Trade-Off between Plant Defense and Growth in Two Contrasting Tree Species , 2016, Front. Plant Sci..

[10]  Ismael Moya,et al.  Photochemistry, remotely sensed physiological reflectance index and de-epoxidation state of the xanthophyll cycle in Quercus coccifera under intense drought , 2008, Oecologia.

[11]  T. G. Gomez Alvarez-Arenas.  Simultaneous determination of the ultrasound velocity and the thickness of solid plates from the analysis of thickness resonances using air-coupled ultrasound. , 2010, Ultrasonics.

[12]  B. Slavík,et al.  Methods of Studying Plant Water Relations , 1974 .

[13]  J. Peguero-Pina,et al.  Determination of plant leaves water status using air-coupled ultrasounds , 2009, 2009 IEEE International Ultrasonics Symposium.

[14]  J. Peguero-Pina,et al.  Air-coupled broadband ultrasonic spectroscopy as a new non-invasive and non-contact method for the determination of leaf water status. , 2010, Journal of experimental botany.

[15]  John R. Miller,et al.  Imaging chlorophyll fluorescence with an airborne narrow-band multispectral camera for vegetation stress detection , 2009 .

[16]  Darko Stefanovic,et al.  Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification , 2016, Comput. Intell. Neurosci..

[17]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[18]  T. G. Gomez Alvarez-Arenas,et al.  Acoustic impedance matching of piezoelectric transducers to the air. , 2004, IEEE transactions on ultrasonics, ferroelectrics, and frequency control.

[19]  V. Vallejo,et al.  Cavitation, stomatal conductance, and leaf dieback in seedlings of two co-occurring Mediterranean shrubs during an intense drought. , 2003, Journal of experimental botany.

[20]  H. Jones,et al.  The role of solute accumulation, osmotic adjustment and changes in cell wall elasticity in drought tolerance in Ziziphus mauritiana (Lamk.) , 1998 .

[21]  Tomas E. Gomez Alvarez-Arenas,et al.  Microwave l-band (1730MHz) accurately estimates the relative water content in poplar leaves. A comparison with a near infrared water index (R1300/R1450) , 2011 .

[22]  J. Peguero-Pina,et al.  Noncontact and noninvasive study of plant leaves using air-coupled ultrasounds , 2009 .

[23]  J. Peguero-Pina,et al.  Ultrasonic spectroscopy allows a rapid determination of the relative water content at the turgor loss point: a comparison with pressure-volume curves in 13 woody species. , 2013, Tree physiology.

[24]  Hilde van der Togt,et al.  Publisher's Note , 2003, J. Netw. Comput. Appl..

[25]  T. T. Kozlowski,et al.  Determination of water deficits in plant tissues. , 1968 .

[26]  T. Mcburney,et al.  The Relationship Between Leaf Thickness and Plant Water Potential , 1992 .

[27]  T.E.G. Alvarez-Arenas,et al.  Acoustic impedance matching of piezoelectric transducers to the air , 2004, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[28]  A. Búrquez.  Leaf Thickness and Water Deficit in Plants: A Tool for Field Studies , 1987 .

[29]  E. Bamberg,et al.  A novel, non-invasive, online-monitoring, versatile and easy plant-based probe for measuring leaf water status , 2008, Journal of experimental botany.

[30]  John O. Outwater,et al.  Ball Tonometry: A Rapid, Nondestructive Method for Measuring Cell Turgor Pressure in Thin-Walled Plant Cells , 2000, Journal of Plant Growth Regulation.

[31]  María Romero,et al.  Vineyard water status estimation using multispectral imagery from an UAV platform and machine learning algorithms for irrigation scheduling management , 2018, Comput. Electron. Agric..

[32]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[33]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[34]  Tomas E. Gomez Alvarez-Arenas,et al.  Simultaneous determination of the ultrasound velocity and the thickness of solid plates from the analysis of thickness resonances using air-coupled ultrasound , 2010 .

[35]  Pablo J. Zarco-Tejada,et al.  Monitoring yield and fruit quality parameters in open-canopy tree crops under water stress. Implications for ASTER , 2007 .

[36]  M. Gullo,et al.  Drought avoidance strategy in Ceratonia siliqua L., a mesomorphic-leaved tree in the xeric mediterranean area , 1986 .

[37]  Tomas Gómez Álvarez-Arenas,et al.  Ultrasonic Sensing of Plant Water Needs for Agriculture , 2016, Sensors.

[38]  Neil C. Turner,et al.  Techniques and experimental approaches for the measurement of plant water status , 1981, Plant and Soil.

[39]  H. Jones,et al.  Exploring thermal imaging variables for the detection of stress responses in grapevine under different irrigation regimes. , 2006, Journal of experimental botany.

[40]  P. Jarvis,et al.  Water in Tissues and Cells , 1982 .

[41]  M. D. Fariñas,et al.  Ultrasonic assessment of the elastic functional design of component tissues of Phormium tenax leaves. , 2014, Journal of the mechanical behavior of biomedical materials.

[42]  Marcel Salathé,et al.  Using Deep Learning for Image-Based Plant Disease Detection , 2016, Front. Plant Sci..

[43]  Ian Stavness,et al.  Deep Plant Phenomics: A Deep Learning Platform for Complex Plant Phenotyping Tasks , 2017, Front. Plant Sci..