Current Projects
Image acquisition for quantifying agronomic traits to evaluate wheat cultivars in different agro-climatic conditions using UFPS (University of Saskatchewan Field Phenotyping System)
Working with UFPS phenocart will facilitate to characterize the differences in a large set of diverse wheat cultivars. This project will develop and advance methodologies to process and analyze high-resolution imagery. The data will be use to quantify phenometrics that will aid in crop breeding programs. To facilitate plant phenotyping, the establishment of UFPS system will require various phases of development
- Imaging with the proximal sensors mounted on a GPS-enabled phenocart to acquire multilocation datasets from diverse wheat cultivars.
- Explore and identify data management, integration and computing options to efficiently store, share, process and archive big volume of phenomics dataset.
- Develop multivariate regression algorithms for training and validation of data collected from different environment field trials within wheat breeding programs.
- Establish a data collection, processing and analysis pipeline that translate acquired images into phenometrics, to interpret for traits selection by wheat breeders.
Developing deep learning models for traits estimation using General Purpose Science Cluster (GPSC)
General Purpose Science Cluster (GPSC) is a High Performance Computing (HPC) cluster maintained by Shared Services Canada (SSC) to assist federal government researcers and scietists across the country in performing computationally intensive tasks.
30 heritage wheat cultivars have been sent to 6 different AAFC sites across the country (Saskatoon, Swift Current, Brandon, Modern, Ottawa, and Lethbridge). The phenocart shall be used for data collection at five different gorwth stages (emergence, tillering, booting, flowering, and ripening). The collected data from six centres shall be transfered to the GPSC for processing. Deep learning models shall be developed to estimate key agronomic traits such as height, biomass, days to flowering, days to maturity, yield, and protien content from data from the payloads (RGB, NIR, and LiDAR).