Back to search

FFL-JA-Forskningsmidlene for jordbruk og matindustri

Reliable and efficient high-throughput phenotyping to accelerate genetic gains in Norwegian plant breeding (virtual phenomics; vPheno)

Alternative title: Større avlingsframgang i norsk kornforedling gjennom pålitelig og high-throughput fenotyping (virtual phenomics; vPheno)

Awarded: NOK 2.2 mill.

This project has developed and tested new technologies in both image analysis and genomic prediction that can facilitate a more precise selection of new plant varieties. This will give the plant breeder access to more precise data on the growth and development of the plants. Field trials with 300 spring wheat lines were conducted every year both at Vollebekk research station in Ås and at Staur research station in Stange. In addition to evaluating agronomic traits and grain yield, drone images were taken repeatedly at about weekly intervals from emergence to maturity. Parameters from these images were compared with manual measurements. In the last four seasons, a validation panel of 300 new spring wheat breeding lines were also tested at both locations. The use of machine learning-based variable selection methods resulted in promising grain yield predictions from the multispectral drone images, which was published in 2021. In 2020 and 2021 we performed parallel testing of two different multispectral cameras at weekly intervals during the field seasons to compare their data quality for yield prediction. These results show that a much cheaper and user-friendly drone with an integrated multispectral camera provides comparable data to the more advanced and expensive camera we used at the start of the project. This was documented in a scientific publication that will contribute to make multispectral imaging more accessible to plant breeders with limited experience in drone flying. During the last year we worked to improve the trait estimation methodology for plant height and heading date from drone images, and in collaboration with Boston University tried out promising methods for handling shadow effects from clouds in the orthomosaics from drone images. In collaboration with CIMMYT in Mexico we have developed efficient and quite reliable statistical models for use in genomic selection that combines phenotypic data with marker data and multispectral information from drone images. Several models that incorporate correlated traits, genotype-by-environment interactions and weather data have been tested out and published. Testing of these models on field trial data from the project shows promising results of improving prediction accuracy by integrating multispectral vegetation data in the genomic prediction models. Recently, we have also compered these classical statistical models with models based on deep learning and artificial intelligence. Results so far show that these models require more data to achieve the same reliability and robustness as the simpler statistical models. In 2022 funding from the project was used to hold a training course at CIMMYT for four guest researchers from Norway during the project postdocs stay in Mexico. The research stay gave good insight into plant breeding methodology and how high-throughput phenotyping data from field trials are being analysed together with genetic marker data in the global wheat breeding programs at CIMMYT. We have in the project also conducted yield trials with 24 historical wheat cultivars to study the plant physiological basis of grain yield increase in Norwegian wheat breeding. At Vollebekk, the cultivars have been planted over seven years (2016 to 2022) at two nitrogen fertilization levels corresponding to today’s common practice (150 kg N per ha) and half of that (75 kg N per ha). In addition to grain yield and agronomic traits, yield components and plant physiological traits were also investigated in some of the trials. In addition, repeated drone imaging with multispectral camera and close-up imaging with the field robot was performed. These trials clearly document a steady progress in grain yield over the past five decades, with the number of grains per spike as a main driving factor for the yield increase. There is also a tendency with the modern cultivars showing a longer grain-filling period. A manuscript on this was published in 2022. The project has developed new ways to visualize data from field trials in “virtual reality”. A demo-version was completed by Making View in 2021 that combines the three-dimensional models from drone images with multispectral data and close-up images from the robot and other data that are being gathered in the field trials. This is a tool that enables the plant breeder to visit the field trials virtually after the end of the field season and select what type of images and information to be displayed. We have towards the end of the project focused our resources on systematization and automation of the processing of the massive amounts of data generated by the drone images and made solutions that enables pre-processing and quality check of the imaging data on the same day as they are being gathered. We also made further progress in developing deep learning models to automatically detect and count wheat heads based on close-up images from the field robot, a work that will be continued in the PhenoCrop project.

Direct outcomes achieved by the project: - an operable field phenotyping robot for close-up imaging in field trials - reliable drone imaging protocols with RGB and multispectral cameras in field trials under Norwegian growing conditions - reliable data processing-pipelines for drone imaging data - documentation of genetic yield gains by plant breeding in Norwegian spring wheat - insight into the genetics of grain yield and agronomic traits in Norwegian spring wheat - improved statistical models for predicting grain yield based on multispectral drone imaging data - improved statistical models for genomic prediction - new statistical models for combining genomic data with phenomics data in genomic prediction - a proof-of-concept prototype for displaying field trial data based on robot and drone images in virtual reality - buildup of national competence in high-throughput field phenotyping - expanded research portfolio in high-throughput field phenotyping for partners in the project Future impacts: - less costly and more precise trait estimation in field trials compared to manual measurements - faster genetic gains in plant breeding by use of high-throughput field phenotyping in combination with genomic selection - increased profitability of Norwegian plant breeding, leading to more high-yielding and better-adapted cultivars for the Norwegian market - more sustainable agriculture based on cultivars with higher yields and better resource use efficiency

New approaches are necessary to meet the goals of increased food production. Plant breeding can play a key role by developing cultivars with higher yield potential. New technologies like genomic selection and high-throughput phenotyping offer possibilities to increase genetic gains through more precise selection and shortening of the breeding cycle. However, considerable research is needed in terms of theoretical developments, statistical modeling and technical solutions to achieve this in practice. By bringing in world-leading expertise in statistical modeling and image analysis, we will develop novel statistical models to extract biologically relevant information from hyperspectral images. The work will consist of developing reliable methods for capturing high-resolution images of field plots, and utilizing novel computational solutions to integrate top view images from drones with close-up images from robots to build 3D models that retain the original resolution and hyperspectral information. Computational algorithms will then be used to extract important physical and physiological traits from these 3D models that can be used directly as selection tools in plant breeding. By coupling hyperspectral data with grain yield and other direct measurements, statistical prediction models will be developed that plant breeders can use in early-generation selection to increase yield gains. Considerable efforts will be spent on developing efficient computational solutions to manage the large amounts of data that will be generated, and finding intuitive ways of displaying relevant information to the plant breeder. User-friendly solutions will be developed through direct involvement of Graminor plant breeders in the project. By utilizing virtual reality technology, our ultimate goal is to "take the field to the breeder" and let the plant breeder observe the field plots and associated data through VR goggles.

Publications from Cristin

No publications found

Funding scheme:

FFL-JA-Forskningsmidlene for jordbruk og matindustri