An Edinburgh-based artificial intelligence consultancy has created a machine learning system to boost woodland monitoring across the UK, with support from the UK space agency. the technology is designed to reduce risk for forestry projects and attract private investment to support the UK’s nature and climate goals.
New Gradient, an AI firm based in Edinburgh, has developed a tool that uses satellite data and machine learning to assess tree health, carbon storage, and biodiversity gains. The project received backing from the UK Space Agency under its third Climate Services Call, a programme that funds British Earth observation technologies tackling climate-related issues.
Woodland expansion is central to the UK’s net zero strategy. Existing forests already absorb around 17.4 million tonnes of carbon dioxide equivalent annually. The government aims to increase tree cover to 16.5% by 2050, which would require planting 30,000 hectares of new woodland each year. Meeting this target would capture an estimated 12 million tonnes of CO2 equivalent in total.
However, a funding shortfall of approximately £1.8 billion means private investment will be essential. The Woodland Carbon Code, a government-backed standard, allows businesses to fund verified woodland projects in return for carbon credits. More than 93,000 hectares of UK woodland are already registered under the scheme.
Progress has been limited by outdated monitoring methods. Manual, infrequent surveys produce imprecise data on carbon and biodiversity, slowing project verification and undermining investor confidence. New Gradient’s AI tool offers an automated digital monitoring, reporting and verification (dMRV) system. It can assess every individual tree within a site, expanding measurement coverage from less than 1% to 100%.
Early results show crown segmentation accuracy of 72.3%, meaning that nearly three-quarters of the time, the AI correctly identified and outlined each individual tree’s canopy. This is significantly higher than published academic benchmarks, allowing the system to provides data on species, biomass, height and carbon storage, offering a more reliable picture of the environmental benefits delivered by woodland projects.
The tool will be integrated later this year into the Calterra platform, a joint venture with peatland restoration specialist Caledonian Climate, for commercial use.
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.’
Ewan 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.’
The Space Agency’s funding forms part of a £380,000 investment to accelerate the UK’s Earth observation and climate services sectors.