Bridging The Gap Between Remote Sensing And Tree Modelling With Data Science

Announced today, a group of international scientists from New Zealand and Singapore is collaborating on a three-year project, funded by MBIE, to use data science and remote sensing to automatically model and analyse tree species and their interactions with environment.

Singapore, the ‘City in a Garden’, embodies the ‘green city’ concept with over 7 million urban trees covering 700 km2. New Zealand, with 24% of its 270,000km2 land covered in forest, also actively supports and promotes urban re-greening in many of its cities.

Sustaining and enhancing biodiversity and healthy living environments are priorities for Singapore and New Zealand that require careful management of trees in urban areas and forests. Reliable information, models, and analysis of trees and their interaction with the surrounding environment are essential to inform management decisions. However, these are currently limited by the quality of available data, tools, and techniques.

Leveraging their joint expertise in data science, remote sensing, and 3D modelling, the researchers propose a proof-of-concept integrated methodology.

According to key researcher and Co-PI, University of Canterbury Computer Science and Software Engineering Professor Richard Green, they will develop novel data-science methods for extracting tree species information from petabytes of multiresolution remote-sensing data to model tree species and their interactions with the environment, and subsequently analyse their socio-economic impacts.

“This will include tree segmentation from remote sensing, with the objective to extract individual tree point cloud and tree information from both high- and low-resolution remote sensing data,” Professor Green says.

“We will also automate tree species recognition and species profiling based on learning from both high- and low-resolution remote sensing data. Among other things, this will give us automatic inference of species profiles and enable tree species classification.”

This work will form the basis for future research collaborations to enable further modelling, simulation, and analysis. In the long term, our work will empower and inform decision-makers on trees and environmental considerations for the greater benefit of both New Zealand and Singapore.

Under the Government-wide New Zealand-Singapore Enhanced Partnership, the Ministry of Business, Innovation & Employment (MBIE) has established a jointly-funded Data Science Research Programme with the Singapore Data Science Consortium (SDSC), on behalf of the National Research Foundation of Singapore. The successful projects will help lead to the creation of new and world-leading knowledge and contribute to the overarching objective of accelerating the development of data science and future foods capabilities in both Singapore and New Zealand.

Eight projects have been selected for New Zealand's 2 joint research programmes with Singapore on Data Science and Future Foods. MBIE's funding commitment for these projects totals almost $23 million (excluding GST) over 3 years, and represents New Zealand's largest ever single investment in a bilateral science programme.

Project team:

• Dr Jan Schindler (NZ Science Leader/PI) | Manaaki Whenua – Landcare Research, New Zealand)
• Professor Richard Green (Co-PI) | University of Canterbury, New Zealand
• Dr Alan Tan (Co-PI) | Scion, New Zealand
• Dr Kourosh Neshatian (Key Individual) | University of Canterbury, New Zealand
• Dr Oliver Batchelor (Key Individual) | University of Canterbury, New Zealand
• Professor Mengjie Zhang (Key Individual) | Victoria University of Wellington, New Zealand
• Dr Like Gobeawan (Singapore Principal Investigator (PI)) | Institute of High Performance Computing, A*STAR, Singapore
• Associate Professor Lee Bu Sung (Key Researcher) | Nanyang Technological University, Singapore

© Scoop Media