<?xml version="1.0" encoding="UTF-8"?><ns2:project xmlns:ns1="http://gtr.rcuk.ac.uk/gtr/api" xmlns:ns2="http://gtr.rcuk.ac.uk/gtr/api/project" xmlns:ns3="http://gtr.rcuk.ac.uk/gtr/api/fund" xmlns:ns4="http://gtr.rcuk.ac.uk/gtr/api/person" xmlns:ns5="http://gtr.rcuk.ac.uk/gtr/api/project/outcome" xmlns:ns6="http://gtr.rcuk.ac.uk/gtr/api/organisation" ns1:created="2026-06-03T15:52:43Z" ns1:href="http://gtr.ukri.org/gtr/api/projects/AACE78E0-5F5D-47BA-8CBA-CDE9DC6C56AB" ns1:id="AACE78E0-5F5D-47BA-8CBA-CDE9DC6C56AB"><ns1:links><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/persons/81C795ED-B198-4CE5-B781-3ECB9DD78E03" ns1:rel="PM_PER"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/55C8B78D-2E97-4AAA-BF4F-725434BE0BF0" ns1:rel="LEAD_ORG"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/55C8B78D-2E97-4AAA-BF4F-725434BE0BF0" ns1:rel="PARTICIPANT_ORG"/><ns1:link ns1:end="2025-07-30T23:00:00Z" ns1:href="http://gtr.ukri.org/gtr/api/funds/2656BBB4-089E-4C19-A035-BBA97E3F5BBB" ns1:rel="FUND" ns1:start="2024-08-31T23:00:00Z"/></ns1:links><ns2:identifiers><ns2:identifier ns2:type="RCUK">10123907</ns2:identifier></ns2:identifiers><ns2:title>A Historic Land Use Data from Historic Maps using Machine Vision &amp;amp; Machine Learning</ns2:title><ns2:status>Closed</ns2:status><ns2:grantCategory>Collaborative R&amp;D</ns2:grantCategory><ns2:leadFunder>Innovate UK</ns2:leadFunder><ns2:abstractText>MyNestBox t/a Martello (UK-based limited company) was founded in 2020 by CEO Dr Henry Crosby PhD and CTO Adam Rogers.

Our vision is to develop an automatic approach to conveyancing searches that will significantly reduce waiting times for home buyers with the aim of reducing the time taken for conveyancing searches from 12-weeks to 1-day. Our technology will allow house-buyers to identify and understand the risk involved in a purchase before they make an offer, and greatly reduce the current fall through rate in house purchases, which stands at 40% (property-reporter,2022).

We have developed a proof-of-concept demonstrator that uses digitised scans of historical OS maps, and leverages machine learning and computer vision technologies to identify historical features relating to environmental risk. These include potential areas of groundwater flooding and contaminated land, for example, where land has previously been used as a petrol station or as part of military land.

Our existing technology is based on our initial proof-of-concept demonstrator, which can identify and extract the text and symbols associated with potential features of interest. This proof-of-concept was created because of a previously successful Innovate UK grant (Project:60287). Additionally, we have secured &amp;pound;1.7m funding from Fuel Ventures, and property adn legal angels.

We have secured customers and partners with several conveyancing firms including Mischon de Reya, Thomas Legal, the Environment Bank, Lawlight and Sail Legal. This is alongside letters of intent worth in excess of &amp;pound;750,000 from prospective clients who are waiting on the outputs from this proposed project.

This project will develop and test our MVP which will be capable of identifying and extracting 128 features that contribute to potential environmental risks. This will be supported by the creation of novel computer vision and machine learning techniques, with expert input from environmental specialists, and lawyers.</ns2:abstractText></ns2:project>