The project is an NSF-funded position (up to 4 years of funding, starting at $51,000 with a cost-of-living increase annually) to improve how well we can detect tree health and mortality across spatial and temporal scales. We have a wealth of ground truth data, high resolution lidar and hyperspectral imagery, intermediate level lidar and hyperspectral, and ultimately satellite-based products to tease out the signals of forest/tree health. The position will be based at the University of Florida and supervised by Dr. Daniel Johnson, with close collaborations with Drs. Eben Broadbent, Carlos Silva, Krista Andersen-Teixeira, and Jim Lutz. The position will begin as soon as possible.
We are seeking a collaborative researcher to join our team. We are seeking someone who wants to combine a passion for forests, forest health, and remote sensing. Experience in AI/Machine Learning approaches to signal recovery from image spectroscopy, particularly hyperspectral remotely sensed data and lidar (ALS, UAV-lidar, and GEDI) are strongly desired qualifications.