The FastPheno project is soliciting applications for a postdoctoral position at the University of Toronto.
The individual will be working as part of a larger team including researchers from the University of Toronto, Université Laval, Natural Resources Canada, and the Ministry of Forests, Fauna and Parcs of Quebec. Our team combines the next generation of high-throughput drone-based phenotyping platforms, plant ecophysiological and genomics approaches to better understand forest dynamics and tree resilience to climate change impacts. The successful candidate will be based in Toronto and work in an interdisciplinary team of researchers of the four participating organizations in a highly collaborative environment.
If you have a background or interest in one or several of the following areas, you should send us your application: High resolution image classification, remote sensing of vegetation, data sciences, computer sciences, bioinformatics, statistical modelling, environmental sciences, ecophysiology of plants, and ecology of trees.
The postdoc will take leads in the FastPheno project activities on drone-based collection and processing of hyperspectral and LiDAR data from multiple experimental field sites and forest stands located in Quebec and Southern Ontario. The focus will be on improving our existing data analysis pipeline, including the identification of trees, assessing health and fitness of individual trees, and estimating structural features of vegetation using deep learning approaches. Candidates must hold a PhD in remote sensing, geoinformatics, plant biology, forestry, or a related field. Strong background in image classification, big data analysis and experience with deep learning algorithms is required.
Preferred skills include:
• Proficiency in optical (hyperspectral and multispectral) and LiDAR remote sensing, photogrammetry.
• Experience in preprocessing and analysis of VHR optical and LiDAR remote sensing data.
• Good understanding of object-oriented programming in Python and C++, sell scripting, relational databases.
• Experience with GDAL Geospatial libraries, QGIS/ArcGIS and GRASS, point cloud processing tools such as LasTools or CloudCompare.
• Knowledge in cloud computing platforms such as Azure, cluster computing and job schedulers such as SLURM.
• Experience with retrieval of plant physiological and structural information using hyperspectral or LiDAR information is an advantage.
Postdoctoral candidates must have received their PhD after January 2019. Candidates must have excellent verbal and written communication skills, willingness to work independently and in a collaborative team environment, and a track record of timely completion of projects and publications.
Potential applicants should send their CV, a list with the names and contact information of 2-3 references and a max. one1 page motivation letter in a single PDF file to [email protected]. Use the words Application Postdoc High Resolution Imagery in the subject line of your email. The review of applications will commence immediately until the position is filled.
About the position
The ensmingerlab is highly collaborative, multi-disciplinary and inclusive. We affirm diversity, creativity, integrity and ambition. For questions, please email [email protected]. For further information on the lab or the FastPheno project please visit the lab website https://ensminger.csb.utoronto.ca/ or the FastPheno website https://www.fastpheno.com/.