Artificial Intelligence and Machine Learning based mapping, derived from remotely sensed data, presents a significant opportunity within the environmental field. These technologies can replace manual digitising of features in imagery, and map larger areas to a finer granularity than is possible using traditional techniques such as Geospatial Information System (GIS) based analysis. As with any new technology however, there are reservations to its use 'on the ground'. This scepticism is to some degree warranted, due to the lack of standardised methods for comparing AI algorithms to ground results in a methodical manner. To address this challenge, a consortium, led by EOLAS Insight and partner organisation Scotland's Rural College (SRUC), will define a framework and candidate standard for direct comparison of AI / ML generated mapping algorithms. The consortium will define application-dependant standard classes for algorithms, and perform accurate ground-based mapping of baseline sites. Organisations with an active interest in the field can determine key performance metrics of their algorithms by analysing these baseline sites and comparing their results to pre-ground truthed data. This framework will be developed using nature markets as an initial use case due to the high requirement for trust in the outputs, emerging best practice, and its position as a high growth market suitable for SME involvement. The consortium, including Omanos Analytics, Agrimetrics, Highlands Rewilding and AECOM, and a working group of interested governmental departments, nature-based agencies and global investment managers, will overcome a key challenge for geospatial AI algorithm developers: user trust in the technology. This will be achieved through provision of educational resources around the use of AI generated mapping, and an established framework for measurement and comparison of algorithm quality. This will be openly published to allow developers to verify their results against pre- ground truthed data. This consortium will, through working groups, ensure a peer reviewed outcome which meets the needs of the market more widely. Through engagement and standard definition the group will mature the use of emerging AI technologies within the nature markets use case, serving as an example for wider adoption of these techniques within the environmental and geospatial sectors. By providing open and transparent methodologies for assessing the quality of AI / ML derived data products this project will increase overall trust in AI as a mechanism for mapping features in combination with remotely sensed data, benefitting the wider community.

Artificial Intelligence and Machine Learning based mapping based on remote sensing data presents a significant opportunity within the environmental field, removing the need for manually digitising features in imagery and for mapping larger areas to a finer granularity than is possible using traditional techniques such as Geospatial Information System (GIS) based analysis. As with any new technology however, there are reservations to its use 'on the ground'. This scepticism is to some degree warranted, due to the lack of standardised methods for comparing AI algorithms to ground results in a methodical manner. To address this challenge, EOLAS and partner organisation Scotland's Rural College's (SRUC's) Trustable Credit scheme will define a framework and candidate standard which allows for direct comparison of AI / ML generated mapping algorithms. This includes the definition of standard classes to be used by algorithms depending on the application, and baseline sites mapped to a high degree of accuracy. Using these organisations with an active interest in the field can run these trial sites through their algorithms to determine key performance metrics, comparing their results to pre-ground truthed data. The initial use case will be the carbon credit markets, selected due to the high requirement for trust in the outputs, emerging best practice, and its position as a high growth market suitable for SME involvement. The key approach to the project will be the definition of a consortium with interests in AI derived data products and wider engagement to ensure that a common methodology is defined and agreed. Here existing schemes such as Trusted Credit will be leveraged, due to their established networks of interested parties. A large part of this project will be engagement with the geospatial community more widely, ensuring a collaborative approach aimed at overcoming a challenge faced by all operators: user trust in the technology. This consortium will, through working groups, explore the issue and present solutions for standardised quality metrics. Through engagement and standard definition we will mature the use of emerging AI technologies within the carbon credit use case, serving as an example for techniques for wider adoption within the environmental and geospatial sectors. By providing open and transparent methodologies for assessing the quality of AI / ML derived data products this project will increase the overall levels of trust in AI as a mechanism for mapping features in combination with remote sensing data, benefitting the wider community.

In the face of climate change and biodiversity loss there is an ever increasing need for private sector participation in environmental management and monitoring. National and international efforts have supported the early developments of markets for carbon credits, allowing emitters to offset emissions by investment in projects which demonstrate the ability to sequester carbon. Additionally there is increasing pressure from investors for companies to consider the Environmental, Social and Governance (ESG) factors of decisions at board level. Where it is not possible to reduce emissions or environmental impacts organisations may look to voluntary offsetting to reduce their overall footprint. In the UK this generally includes improvement to natural assets such as peatlands, or creation of new woodland. There is however some ambiguity on what constitutes a sound investment, given the many trade-offs inherent in decision making, and current low levels of regulation. For example large plantations of non-indigenous tree species are a good way to sequester carbon, but can be terrible for biodiversity and indigenous ecological systems. EOLAS Insight are developing tools which support land managers in making decision to best optimise the revenue creating potential of their natural assets. By following Natural Capital approaches, which assign a monetary value to nature, we can better understand and make trade-offs around sustainable growth. Artificial Intelligence, satellite based imagery and ground based data collection are currently used to measure and classify natural assets, and to look for sites for restoration. By extending the current portfolio of tools at EOLAS this project will create a new and highly innovative service for organisations looking to reduce the emissions and impacts of their supply chain decisions. The tool will allow the user to geospatially assess changes to the environment based on decisions such as new facilities or resource extraction, and provide estimates on the carbon impacts. If required, the user will then be linked to existing projects which could offset some of the impacts of the decision such as peatland restoration, or new native woodland schemes. By providing more insight to decision makers the project will allow carbon to be considered fully during the planning phase of new projects. This will allow for environmental planning alongside early project financial planning, and environmental mitigation methods to be defined up front. As such the tool will support the decarbonisation of supply chains and facilitate organisational Net Zero transitions based on sound, standardised and transparent environmental principles.