Postdoctoral position OT-14802

Post-Doctoral position in Phenotyping/Close Range sensing/Artificial Intelligence

84000 Avignon

Back to jobs listing

INRAE presentation

The French National Research Institute for Agriculture, Food, and the Environment (INRAE) is a public research establishment. It is a community of 12,000 people with more than 200 research units and 42 experimental units located throughout France. The institute is among the world leaders in agricultural and food sciences, in plant and animal sciences, and is 11th in the world in ecology and environment. INRAE’s main goal is to be a key player in the transitions necessary to address major global challenges. In the face of the increase in population, climate change, scarcity of resources and decline in biodiversity, the institute develops solutions for multiperformance agriculture, high quality food and sustainable management of resources and ecosystems.

Work environment, missions and activities

High throughput phenotyping of wheat cultivars from in situ optical observations acquired by unmanned ground robot

Context

To meet the future demand of food, fiber and fuel, the agriculture in 2050 will need to increase production by 50%, and crop productivity must be one of the drivers of that increase. The significant advances in genomics during the last decades were expected to boost crop productivity and drive the adaptation required by the climate change. These advances have generated new opportunities to increase plant genetic variability, with an enormous potential for crop improvement. However, their success will depend on how far genotypic traits can be linked to the mechanisms that produce a distinguishable response of the genotype to the environment. That response is known as phenotype.

Plant phenomics –the observation of plant phenotypic traits– is the discipline that must fill the gap between genotype and phenotype. In the recent years, the development of field high-throughput phenotyping platforms and devices –capable of acquiring and processing efficiently massive volumes of in situ observations over field experiments– has opened a new era on plant phenomics. At both national and European levels, different projects like PHENOME-EMPHASIS (https://www.phenome-emphasis.fr/, France) have built networks of phenotyping facilities, including the development of new instruments and devices (Phenomobile, Unmaned Air Vehicles, field sensors…).

The project FFAST (Functioning from the assimilation of structural traits. Understanding wheat functioning from the assimilation of high throughput observations into plant simulation models) funded by ANR from 2022 onwards aims at developing a phenotyping approach for wheat based on crop process-based models. In such approach, high-throughput observations of multiple architectural traits (GAI, height, plant density, head density, head size, leaf inclination, etc.) acquired from different optical sensors will be assimilated into the SiriusQuality model to derive functional traits.

Activities

The candidate will join the CAPTE team (Capteurs et Télédétection) at the EMMAH Unit (INRAE Avignon) which is coordinating the FFAST project. He/she will be in charge of the development and validation of algorithms for the estimation of morphological traits for wheat varieties from optical data acquired by the Phenomobile. The Phenomobile is an unmanned ground robot designed for high-throughput phenotyping currently operated by the INRAE experimental units DiaScope (Mauguio), AgroPhen (Toulouse), and PHACC (Clermont). The Phenomobile incorporates different optical sensors: three LiDARs, three RGB cameras, two multispectral cameras and, in the near future, stereo pairs for the 3D reconstruction of canopy architecture.

More specifically, the foreseen activities are:

  • Development of algorithms based on artificial intelligence/computer vision for estimating wheat morphological traits like: leaf area inclination, leaf density at early stages, head density, head size/volume…
  • Validation of these morphological traits from destructive/manual measurements in field experiments conducted at the units equipped with the Phenomobile.
  • Production of 1 or 2 scientific papers.
  • Documenting the algorithms for their implementation in the Plant Phenotyping Processing Platform (4P) run by INRAE.

 

You will be required to make occasional trips to the experimental sites

Training and skills

PhD
  • PhD in agricultural, environment sciences, computer vision or similar domains with expertise on image/signal processing to estimate plant morphological traits. Familiarity with plant phenotyping will be an asset.
  • Experience in the use of computer vision and deep learning algorithms (convolutional neural networks)
  • Proficiency in the use of Python programming language
  • English reading and writing
  • Teamwork skills
  • Organizational skills to program and conduct field campaigns

INRAE's life quality

By joining our teams, you benefit from (depending on the type of contract and its duration):

- up to 30 days of annual leave + 15 days "Reduction of Working Time" (for a full time);
parenting support: CESU childcare, leisure services;
- skills development systems: trainingcareer advise;
social support: advice and listening, social assistance and loans;
holiday and leisure services: holiday vouchers, accommodation at preferential rates;
sports and cultural activities;
- collective catering.

How to apply

I send my CV and my motivation letter

Offer reference

  • Contract: Postdoctoral position
  • Duration: 24 months
  • Beginning: As soon as possible
  • Remuneration: INRAE salary grid, depending on experience
  • Reference: OT-14802
  • Dealine: 15/06/2022

Contact

Living in France and working at INRAE Our guide for international scientists

Learn more