Activity Number:
|
69
- Statistical Methods in Ecology
|
Type:
|
Contributed
|
Date/Time:
|
Sunday, August 7, 2022 : 4:00 PM to 5:50 PM
|
Sponsor:
|
Section on Statistics and the Environment
|
Abstract #323420
|
|
Title:
|
Machine Learning for Identifying Plant-Microbiome Interactions
|
Author(s):
|
Anastasiia Kim* and Eric Moore and Sanna Sevanto and Nicholas Lubbers
|
Companies:
|
Los Alamos National Laboratory and Los Alamos National Laboratory and Los Alamos National Laboratory and Los Alamos National Laboratory
|
Keywords:
|
microbiome;
plant-microbiome interaction;
topic modeling;
bayesian networks;
neural networks;
machine learning
|
Abstract:
|
Understanding how soil microbiomes influence plant growth and performance under water shortages may help to overcome many challenges in agriculture brought by changing climate and environment. Using data from our directed evolution experiment, we reveal groups of microbiomes in the soil and other environmental factors affecting plant drought tolerance. We uncover the compositions of microbiomes associated with drought via Latent Dirichlet Allocation topic modeling. We couple the LDA learned microbial community-topics with Bayesian networks to explain the complex interplay among microbiomes and plant traits. We are also exploring neural networks capabilities to further uncover complex associations between plant characteristics and soil microbiomes.
|
Authors who are presenting talks have a * after their name.