Modeling & Predicting Tree Growth with Data Science

Stuart Ian Graham is a graduate student in the University of Washington’s Biology program who recently published a paper with Senior Data Science Fellow and eScience Institute Research Scientist Ariel Rokem, along with others from the University of Washington, Université de Montpellier, and University of California Los Angeles. The paper, published in the Forests journal and titled “Regularized Regression: A New Tool for Investigating and Predicting Tree Growth,” initially grew from a 2019 Winter Incubator project at eScience, which paired Graham and Rokem together to utilize data science to explore how neighboring tree species can influence one another’s growth rates in Mt. Rainier National Park in Washington State.

Old-growth conifer forests at Mt. Rainier National Park in Washington State

The research began with examining 40 years of tree growth data collected from 15 plots in the mature and old-growth conifer forests of Mt. Rainier National Park, each of which measured 100 x 100 meters. The tree locations were mapped within the plots, and the annual growth rates were extrapolated from the decades of existing measurements from the Pacific Northwest Permanent Sample Plot Program. Although 17 different tree species were identified in the dataset, the 6 most prolific were chosen as focal species for modeling: Pacific Silver Fir, Alaskan Yellow Cedar, Douglas Fir, Western Red Cedar, Western Hemlock, and Mountain Hemlock.

Read the full article here.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s