NCSA staff who would like to submit an item for the calendar can email newsdesk@ncsa.illinois.edu.
We look forward to seeing you online on Tuesday, January 17th at 4:00pm. Join online at https://go.illinois.edu/AIFARMSSeminarSeries
Abstract: AI and machine learning concepts have transformed the way we now extract plant traits – both under laboratory as well as field conditions. Well-trained machine-learning models can significantly simplify and accelerate trait extraction as well as diversify the type of traits that one can extract. Training a ML model typically requires the availability of copious amounts of annotated data. Creating a (large) annotated dataset requires effort, patience, time, and resources. This has become a major bottleneck in deploying ML tools in practice. I will present ways we circumvent the need for large annotated datasets for plant phenotyping. The utility of domain adaption and self-supervised learning approaches is explored for difficult plant phenotyping problems. Next, I will present some ongoing work on building 3D mechanistic models of plants that integrate data with domain knowledge. These activities represent two themes within the AI Institute for Resilient Agriculture (AIIRA) vision of building goal-oriented digital twins for agriculture at various agronomically relevant scales.