Background/Objectives

Loblolly Pine (Pinus taeda) is a highly beneficial species with a variety of economic and climatic benefits, including timber production, carbon sequestration, climate regulation, and support for biodiversity. Sustainable management practices are essential to ensure the continued provision of these benefits while addressing challenges such as pests, diseases, and the potential impacts of climate change.

Climate change is reshaping forest ecosystems, influencing the growth potential of tree species and altering the dynamics of associated insect pests. This study will employ machine learning statistical modeling and climate scenario analysis to investigate the potential impacts of climate change on habitats of the Southern Pine Beetle (Dendroctonus frontalis), one of the most destructive pests of Loblolly Pines in the southern United States.

Approach/Activities

MaxEnt is a common species distribution model that employs machines learning to estimate the probability distribution that is closest to uniform (maximum entropy) based on a species' known occurrences and environmental variables such as can be extracted from Global Climate Model (GCM) datasets.  Using MaxEnt and environmental fields representing multiple future climate scenarios, we will model the relationships between climate change and habitat expansion/contraction of the Southern Pine Beetle.  In doing so, we aim to understand the implications for timber production, carbon sequestration, and sustainable forest ecosystem management of Loblolly Pine in the Southeast United States.

Results/Lessons Learned

This study will result in habitat suitability heat maps for various climate scenarios for the Southern Pine Beetle with implications and recommendations offered for forest ecosystem management of Loblolly Pine in the southeastern United States.