[Defended thesis] Paul Tresson: Quantification of pest regulation by generalist predators of the banana weevil with field-imagery analysis

Quantification of pest regulation by generalist predators of the banana weevil with field-imagery analysis

Hello, my name is Paul Tresson. I have an agricultural engineering degree in crop protection from ENSAIA, the Ecole Nationale Supérieure d'Agronomie et des Industries Alimentaires in Nancy, and a double degree in Forestry, Agronomy and Ecosystem Management. Always keen to deepen my knowledge and interested in research, I decided to continue my training with a thesis.
This particular subject combines a number of fields that are close to my heart: crop protection, entomology, ecosystem studies and information technology. The possibilities opened up by the use of deep learning are immense, and I think there's a lot to learn from these technologies.
Through my thesis, I hope to contribute to a better understanding of ecosystems and thus to more sustainable crop protection.

• Starting date: October 2018
• University: MUSE Montpellier Université D’Excellence / Institut Agro
• PhD school: GAIA
• Scientific field: Bioinformatics, Agroecology
• Thesis management: Philippe Tixier, Geco, Cirad  et William Puech, Lirmm, Université de Montpellier
• Thesis supervisors: Dominique Carval, Geco, Cirad et Wiliam Puech, Lirmm, Université de Montpellier
• Funding: #DigitAg – Cirad
•  #DigitAg : Cofunded PhD – Axes 3 et 5 – Challenges 1, 3 et 8

Keywords: Image analysis, Conservation-based biological control, Convolutional neural networks, Cosmopolites sordidus

Abstract: In the context of sustainable development in agriculture, it is crucial to define integrated pest management methods. Among these, pest regulation by natural enemies represents a promising way. However, to date, there is no method (i) to identify with certitude the generalist predators that are involved in the biocontrol of pests and (ii) to quantify the effect of this biocontrol on the population dynamics of the pests (i.e. the effectiveness of biocontrol in the field). These knowledges are crucial for the development and the transfer of effective agroecological management practices. We propose the use of in natura mesocosms coupled with a non-perturbing video measurement method of interaction networks to quantify regulation and predation. These mesocosms will correspond to existing banana production situations in Martinique, the study area of ​​the GECO unit, and will cover a large range of plant biodiversity (planned or not). In each of these mesocosms, the population dynamics of the banana weevil Cosmopolites sordidus will be followed by capture-mark-recapture method in order to determine the magnitude of the regulation by the natural enemies that occurs. In each selected situation, we will establish a control corresponding to a plot where natural enemies are excluded. The video method will allow to know the identity of the predators involved in the regulations and to quantify the links of trophic and non-trophic interactions existing in the animal community (frequency, duration and type of interactions). To this end, methods of automated digital image analysis will be developed (e.g. automatic recognition of a pest, count of individuals), including machine learning and in particular convolutional neural network methods that are developed by the ICAR team (LIRMM unit). These methods should revolutionize our understanding of the functioning of agrosystems and, because of their genericity, can be applied to the study of most cultivated systems.

Jury compound:

Rapporteurs:

• Emmanuelle Porcher, MNHN
• David Bohan, INRAE Dijon

Examiners:

• Elsa Canard, INRAE Rennes
• Vincent Charvillat, Univ. Toulouse

PhD school representative :

Marie-Stéphane Tixier, Montpellier SupAgro

Supervisors:

• Philippe Tixier, CIRAD (directeur)
• William Puech, LIRMM (co-directeur)
• Dominique Carval, CIRAD (encadrant)

Contact :  
dominique.carval [AT] cirad.fr
philippe.tixier [AT] cirad.fr

Communications & Papers

Publications in international peer-reviewed journals

• Paul Tresson, Philippe Tixier, William Puech, Bernard Abufera, Antoine Wyvekens, et al.. Caught on camera: Field imagery reveals the unexpected importance of vertebrates for biological control of the banana weevil (Cosmopolites sordidus Col. Curculionidae). PLoS ONE, 2022, 17 (9), pp.1-17/e0274223. DOI : 10.1371/journal.pone.0274223
• Paul Tresson, Philippe Tixier, William Puech, Dominique Carval. The challenge of biological control of Cosmopolites sordidus Germar (Col. Curculionidae): A review. Journal of Applied Entomology, 2021, 145 (3), pp.171-181. DOI : 10.1111/jen.12868
• Paul Tresson, Dominique Carval, Philippe Tixier, William Puech. Hierarchical Classification of Very Small Objects: Application to the Detection of Arthropod Species. IEEE Access, 2021, 9, pp.63925-63932. DOI : 10.1109/ACCESS.2021.3075293
• Paul Tresson, William Puech, Philippe Tixier, Leïla Bagny Beilhe, Sacha Roudine, et al.. CORIGAN: Assessing multiple species and interactions within images. Methods in Ecology and Evolution, 2019, 10 (11), pp.1888-1893. DOI : 10.1111/2041-210X.13281

Publications at international conferences

• Paul Tresson, Philippe Tixier, William Puech, Dominique Carval. Insect interaction analysis based on object detection and CNN. MMSP 2019 - IEEE 21st International Workshop on Multimedia Signal Processing, Sep 2019, Kuala Lumpur, Malaysia. DOI : 10.1109/MMSP.2019.8901798