Scion says Forest Insights could become a "window into the heart of commercial forests". Photo / Georgina Campbell
Scion says Forest Insights could become a "window into the heart of commercial forests". Photo / Georgina Campbell
A prototype for a new interactive tool will provide the forestry industry with inventory information to make management, harvesting and wood processing decisions easier, says Scion.
It’s called Forest Insights and was developed by the Crown Research Institute in collaboration with Indufor Asia Pacific Ltd.
Scion scientists outlined the tool’s capabilities and applications for the industry at ForestTECH 2023 in Rotorua last week - a forestry technology event for forest managers, remote sensing specialists and tree crop managers.
The interactive Forest Insights tool, powered by machine learning and deep learning models, would provide forest owners, managers and wood processors with an overview of the changing availability and growth of planted radiata pine over time, Scion said.
The prototype is currently focused on the modelling of East Coast pine forests but Scion said it had plans to provide the same data and for a wider range of trees for other regions, with Bay of Plenty next cab off the rank.
Scion’s Grant Evans said the prototype would support forestry and wood processing companies to make more informed management decisions.
“Long term, it will help anyone with trees planted know their precise location and ultimately, what they can do with the trees in the future,” said Evans, who is Scion’s portfolio leader for new value from digital forests and wood sector.
Scion said Forest Insights was more than just a mapping tool and was set to become “a window into the heart of commercial forests”.
Built using AI technologies, as well as LiDAR, Forest Insights detected and identified stands of trees to quantify their volume and maturity over time.
It also outlined the boundaries for each stand of trees and provided essential details, such as age class, area in production, and the number of stems per hectare, Scion said.
Forest Insights also tracked the history of planting and harvesting, which provided insights into changing inventory levels.
Scion said this inventory data was more than statistics - it was the key to unlocking investments and strategic decisions for stakeholders across the timber supply chain.
The dashboard view for Forest Insights. Photo / Scion
Automatically detecting commercial radiata pine forests using trained Deep Learning Convolutional Neural Networks by their boundaries could be a game changer for forestry companies.
What used to be a laborious task of drawing polygons was now replaced with the click of a button.
Evans said Forest Insights could also level the playing field for smaller forest owners.
“These individuals, who own smaller woodlots or stands, can use the tool to see where other small lots in their region are maturing at a similar time and potentially co-operate to negotiate better pricing from mills.”
Therefore, the benefits of Forest Insights extended to all players in the industry, he said.
As a prototype, Forest Insights offered a glimpse into the future, with researchers already planning features that would provide additional value.
Scion was already working with the University of Canterbury to identify tree species beyond radiata pine, aligning with the Government’s goal of having 20 per cent non-radiata pine forests by 2030.
Currently, such measurements relied on people voluntarily reporting their data, making it difficult to track progress, Scion said.
Forest Insights would change that by using satellite imagery and LiDAR data from Toitū Te Whenua Land Information New Zealand to detect different tree species accurately and utilise Indufor’s dashboarding expertise.
Harvest tracking
Beyond tree species identification, the prototype automatically tracked forest activities.
Each orange segment on the map represented an area where harvesting had occurred.
This functionality not only helped in tracking inventory but it was hoped, with further training, it would provide a means to assess forest damage following natural disasters.
“For the East Coast, it could also be used as a tool to reveal where planted forests are being abandoned or are no longer being harvested due to concerns relating to planting on erosion-prone land,” Evans said.
The Forest Insights prototype can also reveal areas where harvest activity has occurred. Photo / Scion
“For forestry and wood processing companies, this data offers them a holistic view of their assets and a basis for well-informed decisions.”
Dr Pete Watt, from Indufor’s Resource Monitoring Team, said the highly detailed information available from Forest Insights offered benefits to industry and investors alike.
“Such information provides the cornerstone for developing wood availability forecasts that underpin investment decisions and support infrastructure planning and policy settings.”
Forest Insights started in 2022 and was a collaborative effort. Scion said its data scientists had supplied all the models and data, working with Indufor Asia Pacific Ltd to create the online tool and dashboard interactivity.
Testing with a handful of industry users had yielded positive feedback, with at least one forestry company expressing interest in using Forest Insights to validate their commercial forestry decisions.
Other collaborators had expressed interest in joining the Forest Insights project, and with their support, Scion aimed to expand its reach across New Zealand.
Another aim was to expand its functionality and develop layers of complexity over time.
Scion researchers had a grand vision for the prototype to serve as the foundation for a digital twin of New Zealand’s entire forestry estate, Evans said.
“Imagine having access to information on eucalyptus trees’ age, harvest readiness, and potential markets, including its suitability for pulp and paper, or feedstock for biorefineries, all neatly presented on a map.
Users can view by patch information about age class and query estimates of productivity, harvest information and transport distances. Photo / Scion
“By continuing to work collaboratively with industry and our key partners, we’re committed to expanding the capabilities of Forest Insights to meet everyone’s needs and add value to the forestry and wood processing sectors.”
Claire Stewart, programme manager for the FGR-led Precision Silviculture Programme, said inventory management tools were critical to being able to see the national forest scape more holistically and to support foresters manage at a finer level of detail.
“There are simple tasks that machine learning models can assist us with like boundary mapping, cutover mapping and post-plant survival assessment,” she said.
“By having a platform that pools data to create robust models we can move a lot quicker.
“On a national level, a tool such as this provides insights on a bigger scale that can inform our wood flows, logistics and national carbon accounting.”
