I am currently a Research Officer (Computational Biology) at the National Research Council of Canada. As a member of the Aquatic and Crop Resource Development (ACRD) Research Centre, my research interests involve advanced machine learning methods for improving crop plants. This includes genomic prediction, as well as efficient cross selection and other predictive breeding technologies.
Publications and Presentations ▾
Ubbens, J. R. (2024). Genomic prior-data fitted networks: a new approach for genomic prediction. Invited talk presented at the National Association of Plant Breeders. January 2024.
Ubbens, J. R. (2023). AI in plant breeding and genetics: the good, the bad, and the ugly. Invited talk presented at Canola Innovation Day, Calgary, AB. December 2023.
Previously, I was a Research Associate at the Global Institute for Food Security in the Plant Improvement group. My research at GIFS focused primarily on novel machine learning methods in quantitative genetics.
Publications and Presentations ▾
Ubbens, J. R., Stavness, I. & Sharpe, A. G. (2023). GPFN: Prior-Data Fitted Networks for Genomic Prediction. bioRxiv 2023.09.20.558648; doi:10.1101/2023.09.20.558648
Ubbens, J. R., Stavness, I. & Sharpe, A. G. (2023). The Instrinsic Dimensionality of Genotype Data and its Implications. PAG 30 (poster). San Diego, CA. February 2023.
Ubbens, J. R., Feldmann, M. J., Stavness, I. & Sharpe, A. G. (2022). Quantitative evaluation of nonlinear methods for population structure visualization and inference. G3 Genes|Genomes|Genetics, Volume 12, Issue 9, September 2022, jkac191, doi:10.1093/g3journal/jkac191
Ubbens, J. R., Parkin, I., Eynck, C., Stavness, I. & Sharpe, A. G. (2021). Deep Neural Networks for Genomic Prediction Do Not Estimate Maker Effects. Plant Genome, 2021;e20147. doi:10.1002/tpg2.20147
Feldmann, M. J., Gage, J. L., Turner-Hissong, S. D. & Ubbens, J. R. (2021). Images carried before the fire: The power, promise, and responsibility of latent phenotyping in plants. Plant Phenome J, 2021; 4:e20023. doi:10.1002/ppj2.20023
I did my Ph.D. in computer science at the Plant Phenotyping and Imaging Research Center at the University of Saskatchewan with Dr. Ian Stavness. I was interested in the application of computer vision and deep learning to the problem of image-based plant phenotyping, and my dissertation was about performing plant stress phenotyping in the latent space. During the summer of 2017, I was a visiting Ph.D. student at the Biological Modeling and Visualization lab at the University of Calgary.
Publications and Presentations ▾
Ubbens, J. R., Ayalew, T. W., Shirtliffe, S. J., Josuttes, A., Pozniak, C. J. & Stavness, I. (2020). AutoCount: Unsupervised Segmentation and Counting of Plant Organs in Field Images. European Conference on Computer Vision (ECCV) Workshops, 2020. August 2020.
Ayalew, T. W., Ubbens, J. R. & Stavness, I. (2020). Unsupervised Domain Adaptation for Counting Plant Organs. European Conference on Computer Vision (ECCV) Workshops, 2020. August 2020.
Ubbens, J. R. (2020). Counting Sorghum Heads with Density Estimation. Invited workshop presented at Phenome 2020, Tucson, AZ. February 2020.
Ubbens, J. R., Cieslak, M., Prusinkiewicz, P., Parkin, I., Ebersbach, J., & Stavness, I. (2020). Latent Space Phenotyping: Automatic Image-Based Phenotyping for Treatment Studies. Plant Phenomics, vol. 2020, 13 pages. doi:10.34133/2020/5801869
Higgs, N., Leyeza, B., Ubbens, J. R., Kocur, J., van der Kamp, W., Cory, T., Eynch, C. Vail, S., Eramian, M. & Stavness, I. (2019). ProTractor: a lightweight ground imaging and analysis system for early-season field phenotyping. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019. Long Beach, CA. June 2019.
Ubbens, J. R. & Stavness, I. Latent space association analysis: towards GWAS directly from images. Presented at Phenome 2019, Tucson, AZ. February 2019.
Ubbens, J. R. & Stavness, I. An introduction to deep learning in plant phenotyping without the agonizing pain. Presented at Phenome 2018, Tucson, AZ. February 2018.
Ubbens, J. R., Cieslak, M., Prusinkiewicz, P. & Stavness, I. (2018). The use of plant models in deep learning: an application to leaf counting in rosette plants. Plant Methods, 14(1), 6. doi:10.1186/s13007-018-0273-z
Ubbens, J. R. & Stavness, I. (2017). Deep Plant Phenomics: A Deep Learning Platform for Complex Plant Phenotyping Tasks. Front. Plant Sci. 8:1190. doi:10.3389/fpls.2017.01190