Point-dendrometers for ecosystem growth and health

Point dendrometers are indispensable for monitoring tree growth and detecting stress in forest ecosystems, offering detailed insights into cambial activity and environmental responses. The project’s goal is to harness machine learning to address data gaps and enhance the precision of trend detection in dendrometer data. This
approach will also seek to identify signals of ecosystem health and stress, such as drought or disease impact, observable in tree growth patterns. By integrating these ground-level measurements with remote sensing data, the project aims to scale localized stress indicators to wider ecosystem monitoring, thus providing a more holistic
view of forest health. The synergy between detailed dendrometer data and expansive remote sensing imagery, analyzed through advanced algorithms, will offer unprecedented capabilities in assessing the resilience and vitality of forests on a macroscopic scale.

Faculty Supervisor:

Arturo Sanchez-Azofeifa

Student:

Partner:

Veritree

Discipline:

Earth science

Sector:

Professional, scientific and technical services

University:

University of Alberta

Program: