Top of page

Student/Staff Portal
Global Site Navigation

School of Science

Local Section Navigation
You are here: Main Content

Related Contents

3D Imaging and Machine learning approaches for Carbon Estimation in agroforestry and remnant vegetation areas of WA

Project Outline

Recent government regulations have promoted the need to measure carbon resilience on agricultural properties in WA. The development of this carbon credit scheme has highlighted the financial importance of measuring carbon stocks if the property is to be considered for carbon-credits.  There is a now a pressing need to find better approaches in the estimation of above ground carbon storage in agricultural and remnant vegetation.  The current approaches to measure carbon involve manual measurements of diameter of tree/plant and size of crop canopy. At present, the remote measurement of these environments is by satellite imagery which estimates this using NDVI/vegetative indexes.

This research aims to find the best approaches for estimating carbon capture in the agricultural landscape of Western Australia through novel approaches using 3D Imagery, ground truthing and machine learning techniques.  The use of 3D imagery is now being examined as a more accurate measurement of tree and crop carbon capture than the use of 2D satellite imagery.

This project aims to develop a protocol for 3D imagery (RGB, Lidar, Hyperspectral) for carbon capture for agricultural landscapes.  The research also incorporates AI techniques to further improve the accuracy carbon storage measurement by providing analytical tools for the estimation of the proportion of difference plant-types each which store different levels of carbon.

This research will examine novel 3D imaging approaches and application of remote sensing technologies, particularly LiDAR and multi-sensor satellite imagery, for monitoring forest characteristics such as Above Ground Biomass (AGB), wood volume, and canopy height and estimating carbon storage.

The research will explore various methodologies, data sources, evaluation metrics, and the importance of contextual information in improving these predictive models.

Essential skills

  • Skills in Database Programming, Artificial Intelligent systems and
  • Advanced Computer Programming
  • Skills in Image Processing techniques
  • Advanced programming skills in R, python or other languages
  • Good oral and report writing skills
  • Able to work in team environment
  • Good project management skills

Desired skills

  • Experience in Environmental or Geospatial sciences
  • Drivers License
  • Drone pilot license

Project Area: Computer Science / Biological and Environmental Science

Supervisor(s): Dr Leisa Armstrong , Professor Dean Diepeveen

Project level: Masters/PhD

Funding: Applicant should apply for ECU HDR or RTP Scholarship

Start date: Any

Skip to top of page