[Post-doc] Maxime Ryckewaert : Detection of water stress of the vine by optical instrument

#DigitAg labelled post-doctorate

Detection of water  stress of the vine by optical instrument

  • Starting date: 1st November 2020
  • Field(s): Optics – Data analysis
  • Co-Supervisors: Ryad Bendoula, Itap, Inrae
  • Funding: InterregSudoe VINIoT
  • #DigitAg: Axis 3: Sensors and data acquisition/processing, Axis 5:Data Mining, Data Analysis and Knowledge Discovery, Challenge 3: ICT and crop protection, Challenge 5: ICT and new farm advisory services

Keywords: Phenotyping, Vine, Water stress, Drought, Hyperspectral Imaging, Internet of Things (IOT)

Abstract: The postdoctorate position is part of the VINIoT project of Interreg Sudoe. The objective of this project is to propose a new precision viticulture service based on an IoT (Internet Of Things) sensor network. This service will enable SMEs in the wine sector in the SUDOE area to monitor their vineyards in real time, remotely and at different precision scales (grape, plant, plot and vineyard). The aim is to accurately assess the state of the vine, from the maturity of the berries to the early detection of the appearance of diseases or water stress. The first year is dedicated to the study on the leaf scale with a precise monitoring of the potted vine. The other years are devoted to the application on the scale of the agricultural field.
The Research Team ‘optical sensors for complex media’ (COMIC) of the research unit UMR ITAP is in charge of proposing optical instrument solutions for vine monitoring in a water stress context. The objective of the COMIC team is to study the detection limits of optical instruments to monitor the state of the vine.
Experiments will be carried out during the three years of the project in partnership with other INRAE teams (UMR LEPSE, UE Pech-Rouge). The first step will consist of studying whether the detection of water stress in grapevines is possible with tools usually used in the laboratory, in particular hyperspectral imaging. The second step will then be to consider less expensive sensor solutions adapted to field constraints for the use of IoT objects. The COMIC team will also provide the necessary scientific support to the collaborators from a data analysis point of view and on the discussions of technological choices.
The post-doctoral student will coordinate the scientific aspects of the part of the project concerning the COMIC team.
The missions will be:
– To manage the experiments (organization, planning the needs of material and human resources).
– To conceive experimental designs and to establish protocols for hyperspectral image acquisition, NIR spectroscopy and other phenotyping tools
– To analyze data from different experiments.
– To valorize results through the writing of scientific articles.
– To participate in the meetings between the different collaborators of the project: AIMEN (Spain), Agacal (Spain), ADVID (Portugal), IFV (France), AGAMELARIOJA (Gobierno de la Rioja), FEUGA (Spain).

Contact:  maxime.ryckewaert [AT] inrae.fr

Social Networks: ResearchGate – LinkedIn – Twitter

Communications / Papers:


Ryckewaert, Maxime. 2016-2019. « Potentiel d’un couplage entre un capteur de haute résolution spectrale/faible résolution spatiale et un capteur à faible résolution spectrale/forte résolution spatiale pour la sélection variétale ». These soutenue, Montpellier, SupAgro.

Ryckewaert, Maxime, Nathalie Gorretta, Fabienne Henriot, Federico Marini, et Jean-Michel Roger. 2020. « Reduction of Repeatability Error for Analysis of Variance-Simultaneous Component Analysis (REP-ASCA): Application to NIR Spectroscopy on Coffee Sample ». Analytica Chimica Acta 1101:23‑31. doi: 10.1016/j.aca.2019.12.024.

Ryckewaert, Maxime, Daphné Héran, Emma Faur, Pierre George, Bruno Grèzes-Besset, Frédéric Chazallet, Yannick Abautret, Myriam Zerrad, Claude Amra, et Ryad Bendoula. 2020. « A New Optical Sensor Based on Laser Speckle and Chemometrics for Precision Agriculture: Application to Sunflower Plant-Breeding ». Sensors 20(16):4652. doi: 10.3390/s20164652

Héran, Daphné, Maxime Ryckewaert, Yannick Abautret, Myriam Zerrad, Claude Amra, et Ryad Bendoula. 2019. « Combining Light Polarization and Speckle Measurements with Multivariate Analysis to Predict Bulk Optical Properties of Turbid Media ». Applied Optics 58(30):8247. doi: 10.1364/AO.58.008247.

Taleb Bendiab, Anis, Maxime Ryckewaert, Daphné Heran, Raphaël Escalier, Raphaël K. Kribich, Caroline Vigreux, et Ryad Bendoula. 2019. « Coupling Waveguide-Based Micro-Sensors and Spectral Multivariate Analysis to Improve Spray Deposit Characterization in Agriculture ». Sensors 19(19):4168. doi: 10.3390/s19194168.

Valle, B., T. Simonneau, F. Sourd, P. Pechier, P. Hamard, T. Frisson, M. Ryckewaert, et A. Christophe. 2017. « Increasing the Total Productivity of a Land by Combining Mobile Photovoltaic Panels and Food Crops ». Applied Energy 206:1495‑1507. doi: 10.1016/j.apenergy.2017.09.113.

Valle, Benoît, Thierry Simonneau, Romain Boulord, Francis Sourd, Thibault Frisson, Maxime Ryckewaert, Philippe Hamard, Nicolas Brichet, Myriam Dauzat, et Angélique Christophe. 2017. « PYM: A New, Affordable, Image-Based Method Using a Raspberry Pi to Phenotype Plant Leaf Area in a Wide Diversity of Environments ». Plant Methods 13(1):98. doi: 10.1186/s13007-017-0248-5

Communications :

REP-ASCA: A method to reduce repeatability error for Analysis of variance-Simultaneous Component Analysis (ASCA) – January 2020 – Chimiométrie

Removing spatial effects of spectral dataset acquired into an experimental design by using multivariate analysis of variance – June 2019 – EFITA

Predicting maize yield of new varieties from known varieties with temporal- spectral data using multibloc-analysis – January 2019 – Chimiométrie

Multivariate analysis of variance of vegetation spectra dataset included into an experimental design by using ANOVA-SCA and ANOVA-Target Projection – May 2018 – SFPT

ANOVA-Simultaneous component analysis on vegetation spectra data acquired into an experimental design November 2017 – HelioSpir

The impact of the spatial resolution of highly resolved spectral data on pan- sharpening methods to reconstruct a hyperspectral image