Team
- Faculty: Ananth Kalyanaraman (WSU), Markus Keller (WSU), Alan Fern (OSU), Lav Khot (WSU), Bala Krishnamoorthy (WSU)
- Senior Collaborators: Paola Gabriela Pesantez-Cabrera (WSU, Data Scientist)
- Graduate students: Nathan Balcarcel (WSU, CS)
- Undergraduate students: Sejal Welankar (WSU, CS)
Objectives
- Define topological data analysis workflows to capture multi-cultivar divergence and conserved behavior in cold hardiness.
- Implement an open-source software for topological analysis, clustering, and visualization of spatiotemporal data.
- Investigate methods to incorporate topological information into multi-task learning to improve prediction efficacy on single and multi-cultivar data.
- Investigate approaches to use RNN model traces for mapping to crop phenological states.
Hypotheses
- Discovering higher-order structures from historic data sets can help improve our understanding of the variability of cold hardiness behavior across the population.
- Topological techniques can also potentially help with model interpretation.
Related Publications
2023
1.
Persistent Homology to Study Cold Hardiness of Grape Cultivars Workshop
2nd AAAI Workshop on AI for Agriculture and Food Systems (AIAFS), arXiv, 2023.
2022
2.
Extracting patterns in cold hardiness behavior using topological data analysis Workshop
arXiv, 2022.
