Potential of Visible and Near infrared spectroscopy aerial acquisition with high spectral/low spatial resolution for plant phenotyping
I'm Maxime Ryckewaert, recruited as a postdoctoral fellow at Inrae, and a member of the Itap unit and the Comic team. I'm in charge of the scientific part of the European VINIoT project as far as the Comic team is concerned. After completing my Master's degree in Physics and Computer Science, I was recruited as a design engineer at Sun'R and CIRAD to develop a simulation software package for agrivoltaic systems. It was on the basis of this experience that I decided to embark on a career in research. I did a Cifre thesis with the Limagrain company and the Irstea laboratory, where I learned about multivariate data analysis, experimental design and experimentation.
For this post-doctorate, I'm setting up measurement protocols for optical instruments, including hyperspectral imaging, on an experimental plan drawn up with UMR Lepse and U.E. Pech-Rouge. The first stage will be to study whether it is possible to detect water stress on vines using tools normally used in laboratories. The second step will then be to consider less costly sensor solutions adapted to constraints for use as IoT objects.
Research applied to agriculture is motivating, as it enables us to study the complex relationships between vegetation and the environment within very specific constraints (technology, cost, etc.). Digital agriculture is therefore one of the answers to environmental and societal challenges. This discipline is facing new challenges, as data is becoming increasingly voluminous and complex, with the need to automate crop monitoring and multi-criteria descriptions of vegetation functioning. It is in the context of this post-doctorate on the detection of water stress in vines that I hope to propose new methods and tools.
- Starting date: 1st November 2020
- Scientific field: Optics– Data analysis
- Funding: InterregSudoe VINIoT
- Post-doc supervisors: Ryad Bendoula, Itap, Inrae
- #DigitAg : Axe 3 : Capteurs, acquisition et gestion de données, Axe 5 : Fouille de données, analyse de données, extraction de connaissances, Challenge 3 : La protection des cultures, Challenge 5 : Les services de conseil agricole
Keywords: Phenotyping, Vine, Water stress, Drought, Hyperspectral imaging, Internet of things
Abstract: The operational objective of this thesis is to study the opportunities offered by the VIS/NIR spectrometry couple with an aerial acquisition system to address the needs of new tools for high-throughput phenotyping. The underlying application is to identify and describe new genotypes with better behavioural response under water-stress. From a technological point of view, it also represents a potential way to have access to the high spectral resolution of vegetal cover. However, the spectral information must be relevant and exploitable for phenotyping, and therefore, processing will be optimised by developing: • methods for extracting appropriate parameters for breeding genotype • methods that will improve in spectral/spatial resolution of signals Maintaining a high degree of spectral resolution is the key factor to produce models. In this context, it would provide answers to this following scientific question: How can a low spatial/high spectral resolution sensor be coupled with a mobile vector in order to produce high spatial /high spectral resolution information allowing to describe vegetal response under stress? Thus, the research objectives are: • To test the hypothesis that with a total spectral signature of vegetation, the crop monitoring or the extraction of phenotyping traits are more robustness and more sensitive with a small variation of genotype response under stress. • To define acquisition protocols and to develop processing methods of these spectral information to guarantee enough spectral and spatial resolution for phenotyping • To approve methodology for identification and precise characterisation of different corn cultivars under water stress.
Contact : alexia.gobrecht [AT] inrae.fr
Social networks: ResearchGate – LinkedIn – Twitter
Communications & Papers:
Aldrig Courand, Maxime Metz, Daphné Héran, Carole Feilhes, Fanny Prezman, Eric Serrano, Ryad Bendoula, Maxime Ryckewaert (2022) Evaluation of a robust regression method (RoBoost-PLSR) to predict biochemical variables for agronomic applications: Case study of grape berry maturity monitoring, Chemometrics and Intelligent Laboratory Systems
Maxime Metz, Maxime Ryckewaert, Sílvia Mas Garcia, Ryad Bendoula, Pierre Dardenne, Matthieu Lesnoff, Jean Michel Roger (2022) RoBoost-PLS2-R: An extension of RoBoost-PLSR method for multi-response, Chemometrics and Intelligent Laboratory Systems
Maxime Ryckewaert, Gilles Chaix, Daphné Héran, Abdallah Zgouz, Ryad Bendoula (2022) Evaluation of a combination of NIR micro-spectrometers to predict chemical properties of sugarcane forage using a multi-block approach, Biosystems Engineering
Maxime Ryckewaert, Daphné Héran, Thierry Simonneau, Florent Abdelghafour, Romain Boulord, Nicolas Saurin, Daniel Moura, Sílvia Mas Garcia, Ryad Bendoula (2022) Physiological variable predictions using VIS–NIR spectroscopy for water stress detection on grapevine: Interest in combining climate data using multiblock method, Computers and Electronics in Agriculture
Maxime Ryckewaert, Nathalie Gorretta, Fabienne Henriot, Alexia Gobrecht, Daphné Heran, Daniel Moura, Ryad Bendoula, Jean-Michel Roger (2021) Potential of high-spectral resolution for field phenotyping in plant breeding: Application to maize under water stress, Computers and Electronics in Agriculture
Sílvia Mas Garcia, Maxime Ryckewaert, Florent Abdelghafour, Maxime Metz, Daniel Moura, Carole Feilhes, Fanny Prezman, Ryad Bendoula (2021) Combination of multivariate curve resolution with factorial discriminant analysis for the detection of grapevine diseases using hyperspectral imaging. A case study: flavescence dorée, Analyst, Royal Society of Chemistry
Puneet Mishra, Roy Sadeh, Maxime Ryckewaert, Ehud Bino, Gerrit Polder, Martin P.Boer, Douglas N.Rutledge, Ittai Herrmann (2021) A generic workflow combining deep learning and chemometrics for processing close-range spectral images to detect drought stress in Arabidopsis thaliana to support digital phenotyping, Chemometrics and Intelligent Laboratory Systems
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.
Acts of conference:
Comparison between ParSketch-PLSDA and PLSDA in a context of large amounts of spectral data for sunflower genotype discrimination – October 2021 – NIR2021
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
