This Project Grant award from the National Science Foundation (NSF) Division of Polar Programs (CFDA 47.078) provides $193,194 to the Woods Hole Oceanographic Institution, a private non-profit research organization, to fund a postdoctoral fellowship focused on leveraging community structure data and machine learning techniques to improve microbial functional diversity modeling in the Arctic Ocean ecosystem.
The key products and services to be delivered under this award include:
- Statistical analysis of sequence-based observations of the current Arctic microbial community to transform understanding of cellular environmental responses into a scale relevant for ecosystem processes
- Updating a microbial-oriented, one-dimensional biogeochemical model to assess variable contributions of specific members of the polar bacterial community
- Applying machine learning modeling techniques to segment upper ocean community structure data into distinct bacterial ecotypes and identify critical physiological and functional differences
- Conducting a series of modeling experiments to compare skill between the machine learning-integrated and base model frameworks, with the goal of improving the fidelity of Arctic climate change predictions
- Making the adapted source codes of the produced model accessible through open-source archiving as a resource for the Arctic science community
This grant award is co-funded by NSF to support AI/ML advancement in the geosciences and aims to build computational capacity in Arctic research through undergraduate student training.
Generated 5/14/24, 5:52 AM