Site navigation

Edinburgh Firm New Gradient Develops ML Tool to Accelerate Woodland Creation

Graham Turner

,

AI woodland monitoring
The solution, developed with UK Space Agency backing, will be integrated into the firm’s Calterra platform.

Edinburgh-based AI consultancy New Gradient has developed a machine learning tool to enhance woodland monitoring across the UK, supporting increased private investment in woodland creation and contributing to national net zero and nature recovery targets.

The tool has been backed by the UK Space Agency (UKSA) through its third Climate Services Call, which supports the development of UK-based Earth observation-enabled solutions to address climate challenges.

Woodland creation plays a key role in the UK’s net-zero ambitions, with forests already removing around 17.4 million tonnes of carbon dioxide equivalent (tCO2e) each year – around 4% of national greenhouse gas emissions. The UK government has targets to reach 16.5% tree and woodland cover by 2050 and plans to plant 30,000 hectares of new woodlands annually – estimated to save up to 12 million tCO2e in total.

Delivering this ambition will require substantial private investment to help bridge an estimated £1.8 billion funding gap. The Woodland Carbon Code, the UK’s government-backed framework, provides a critical mechanism for attracting this investment, enabling businesses to fund verified woodland projects in exchange for high-integrity carbon credits.

While more than 93,000 hectares of UK woodland are already registered under the framework, progress and scalability are constrained by outdated monitoring approaches. Infrequent, manual woodland surveys deliver imprecise measurements of carbon and biodiversity outcomes, delaying project verification and reducing investor confidence in the integrity and value of carbon credits generated.

New Gradient’s AI solution addresses this issue through automated digital Monitoring, Reporting and Verification (dMRV) – enhancing the speed, accuracy and scale of woodland data collection, while providing richer insights into tree health, carbon value and biodiversity gains.

Using advanced machine learning, the model can assess every individual tree – expanding woodland measurement coverage from under 1% to 100% and increasing the number of trees directly analysed for carbon sequestration and wider environmental impact by 100-fold.

According to the firm, early results show a crown segmentation accuracy of 72.3% – significantly higher than published academic benchmarks – alongside deeper insights into woodland characteristics such as species identification, biomass, height and carbon storage. Together, these capabilities offer a more complete and reliable picture of climate and nature benefits delivered by woodland creation and management.

Ewan McMillan, founder of New Gradient, said: “Our solution represents a breakthrough for Woodland Carbon Code verification. By replacing expensive, time-consuming manual field surveys with automated dMRV across a broader range of performance indicators, we are putting landowners in a far stronger position to attract investment into these critical woodland projects.

“The solution also facilitates continuous monitoring, shifting verification from decade-long cycles to annual reporting. This gives investors, verifiers, and land managers near real-time visibility of woodland carbon delivery, bolstering confidence in verified woodland carbon units.”

The funding from the UKSA’s Climate Services Call forms part of a £380,000 investment to accelerate the UK’s Earth observation and climate services sectors. The programme supports businesses in transforming innovative concepts into market-ready services that advance net-zero targets and drive economic growth.


Recommended reading


McMillan added:“The UK Space Agency grant enabled us to extend our existing peatland dMRV capability, currently deployed in our Calterra platform, into the woodland domain.

“The project has delivered a self-supervised foundation model pre-trained on 1.8 million multi-modal UK aerial image pairs, alongside four expert models for tree counting, crown segmentation, species classification and canopy height, as well as a biomass and carbon estimation pipeline. The results have been overwhelmingly positive, demonstrating a validated approach to automated woodland measurement, reporting and verification using Earth observation data.”

New Gradient is integrating the new solution into its Calterra platform, a joint venture with peatland restoration experts Caledonian Climate, for commercial use later this year.

Graham Turner

Sub Editor

Latest News

AI

Nvidia Launches Open Secure AI Alliance for AI Safety and Security

AI Business Recruitment

Nearly a Quarter of Orgs Reducing Entry-level Hiring Due to AI Automation

Business

Scottish Businesses Turn to Self-funding as Growth Confidence Dips in H2

Data Finance

Payment Leaders are Struggling to Get Real-time Data