Postdoc: Forest LiDAR & AI for Inventory Tech

Adelaide University; Adelaide; On-site; AUD 104,000 - 111,000; Full time

Benefits offered by this job

17% superannuation

Job summary

Adelaide University invites applications for a highly motivated postdoctoral research associate to develop the next generation of operational forest inventory methods. The project combines unmanned aerial laser scanning, terrestrial and mobile laser scanning, calibration-transfer, and machine learning to improve forest attribute estimation across plantation environments.

The successful applicant will transfer detailed ground-based LiDAR data to landscape-scale aerial datasets, contributing to

Qualifications

• PhD (or near completion) in Remote Sensing, Computer Vision, Forestry, Geomatics, ML, Spatial Statistics or closely related.
• Experience in LiDAR processing, photogrammetry, ML and geospatial analysis.
• Ability to analyse large spatial datasets and communicate results clearly.

Responsibilities

• Develop next-generation calibration-transfer methods for multi-platform LiDAR.
• Machine learning and statistical modelling of forest structural attributes.
• Quantify uncertainty and propagate it in operational forest inventory.
• Develop transferable inventory models across species and regions.
• Automate tree detection, segmentation and structural reconstruction.
• Integrate aerial, terrestrial and mobile LiDAR with other sensing modalities.
• Publish high-impact journal papers and collaborate with forestry industry partners.

Skills

LiDAR processing

Photogrammetry

Machine learning

Geospatial analysis

Large spatial datasets

Programming Python

Programming R

Programming MATLAB

Written and oral communication

Quantitative skills

Education

PhD (or near completion) in Remote Sensing / Geomatics / ML / CV

Tools

Python

R

MATLAB

Job description

Adelaide University invites applications for a highly motivated postdoctoral research associate to develop the next generation of operational forest inventory methods. The project combines unmanned aerial laser scanning, terrestrial and mobile laser scanning, calibration-transfer, and machine learning to improve forest attribute estimation across plantation environments.

The successful applicant will transfer detailed ground-based LiDAR data to landscape-scale aerial datasets, contributing to