971721Intelligent Environmental Estate Phase 2ClosedSmall Business Research InitiativeInnovate UKHighways England aspires to operate an intelligent, self-maintaining network of assets with a positive environmental footprint. How will automated systems deploy the right resources, to the right location at the right time? How will environmental value be quantified, improvement areas identified, prioritised and monitored? Understanding location and context is the foundation of intelligent operations. The overall vision for this project is to revolutionise how Highways England manages its environmental estate by automatically calculating network wide environmental metrics and remotely monitoring assets. Phase 1 of this project demonstrated the feasibility of automatically interpreting satellite imagery and vehicle-collected imagery data to create input data for such intelligent applications. This brought together Ramboll technical expertise, our deep understanding of Highways England's environmental obligations, and key stakeholders from Highways England. Outcomes from phase 1 included the identification of several related but distinct applications that are of significant value to Highways England. These applications relate to: 1.Habitat identification and classification including habitat connectivity; 2.Invasive species; and 3.Object detection including assets such as noise barriers. The work proposed in Phase 2 will further refine and develop the approaches tested in Phase 1 and produce a prototype in anticipation of commercialising the product. The work in Phase 2 falls into the following categories: 1.Automating the data pipeline used for habitat classification from satellite imagery; 2.Extend the geographic footprint of the training dataset; 3.Tune the machine learning algorithms to improve accuracy and generalizability; 4.Prototype development, including applications serving results from various machine learning tasks; and 5.Business model development and commercialisation / exploitation.