Cloud-Based Deep Learning for Tree Species Estimation from Airborne Laser Scanning (ALS)

Deep learning offers significant potential to extract more and different types of information from 3D point clouds, than traditional classification techniques. Point-based deep learning estimation of tree species proportions in forest stands is one key application, which can be limited by computing resources. Cloud based advanced computing offers significant potential to optimise these deep learning networks thus ensuring more accurate and transferable predictions.

The PDF will lead the implementation of 3D point-based deep learning approaches to species estimation onto advanced computing resources to optimise computation efficiently. The PDF will work with forest inventory datasets from a variety of sources to train both existing and new models using a variety of airborne laser scanning datasets. The PDF will work with PhD students working on related projects to implement, test, and validate their code on these advanced computing solutions. 

The PDF will lead the project, optimise and develop new point-based deep learning models, and test and validate the estimates on a cloud computing environment. The PDF will work within an active deep learning forestry team to advance the use of these tools in an advanced computing environment. The PDF will also be expected to produce publications and presentations in national and international workshops/conferences.

Successful applicants should:

  • Hold a relevant PhD (e.g., remote sensing, computer programming, deep learning, forest inventory, or forestry with a strong technical and statistical background).
  • Experience with deep learning approaches, particularly convolutional neural networks, generative adversarial networks, and graph neural networks.
  • Strong programming skills in Python.
  • Knowledge and experience with deep learning packages such as TensorFlow or PyTorch.
  • Experience in cloud computing and working in an advanced computing environment.
  • Documented track-record in publishing high-quality scientific papers within the field of the position.
  • Have excellent oral and written communication skills with a strong publication record


The candidate will be based at the University of British Columbia (UBC) in Vancouver, Canada, under the supervision of Professor Nicholas Coops. Applicants should send a letter explaining their motivation and relevant skill set, a CV and the names of three references to

The deadline for sending in applications is November 30th but we will consider applications until the position is filled. The expected start date would be in Jan 1st 2024. The position is for a fixed length of 24 months.

Equity and diversity are essential to academic excellence. An open and diverse community fosters the inclusion of voices that have been underrepresented or discouraged. We encourage applications from members of groups that have been marginalized on any grounds enumerated under the B.C. Human Rights Code, including sex, sexual orientation, gender identity or expression, racialization, disability, political belief, religion, marital or family status, age, and/or status as a First Nation, Metis, Inuit, or Indigenous person.

Reference Number

Please mention reference number GPS-57615 in all your correspondence about this Postdoctoral Fellow position.

This position will be supervised by

Sign up for an information session to connect with students, advisors and faculty from across UBC and gain application advice and insight.