This website uses cookies to store information on your computer. Some of these cookies are used for visitor analysis, others are essential to making our site function properly and improve the user experience. By using this site, you consent to the placement of these cookies. Click Accept to consent and dismiss this message or Deny to leave this website. Read our Privacy Statement for more.
Project Abstract: Microbial Community Modeling with Neural Networks
Faculty Sponsor: Geoffery Zahn
The changing global climate has disrupted habitats for many plant species, including mangroves in Southeast Asia. Reintroducing these plants into their natural environments is crucial for cultural and environmental reasons, but it has
been challenging. Recent studies have shown that beneficial microbes can help improve the success of these reintroduction efforts. However, understanding how these microbes interact and affect transplant success has been difficult.
This research aims to develop a method for predicting the success of transplanting these microbes, which could greatly improve habitat restoration efforts. To do this, we are using advanced computer models called Convolutional Neural
Networks (CNNs) to analyze simulated data that mimics microbial communities before and after transplantation. CNNs are particularly good at recognizing patterns in complex data, which makes them well-suited for this task. By training
these models to identify ecological processes in the simulated data, we hope to uncover the key factors that determine the success of microbiome transplantation. This approach could lead to more informed decisions and better outcomes
for habitat restoration projects, particularly in mangrove ecosystems. Ultimately, our research aims to advance our understanding of microbial interactions and improve our ability to restore habitats and support plant life in a changing
climate.
Print Page