<?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="2026-06-22T07:57:45Z" ns1:href="http://gtr.ukri.org/gtr/api/projects/A85C427D-79C1-4680-B416-AF15757110F1" ns1:id="A85C427D-79C1-4680-B416-AF15757110F1"><ns1:links><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/persons/2266031B-7A4A-499A-8F75-DEA06C0D1F32" ns1:rel="PM_PER"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/0936A8F1-D96F-4AFC-B264-76D37AF2FCB2" ns1:rel="LEAD_ORG"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/0936A8F1-D96F-4AFC-B264-76D37AF2FCB2" ns1:rel="PARTICIPANT_ORG"/><ns1:link ns1:end="2024-03-31T00:00:00Z" ns1:href="http://gtr.ukri.org/gtr/api/funds/DCD91983-5E43-4E00-8F76-30902DC6DF70" ns1:rel="FUND" ns1:start="2023-01-01T00:00:00Z"/></ns1:links><ns2:identifiers><ns2:identifier ns2:type="RCUK">10045459</ns2:identifier></ns2:identifiers><ns2:title>StormHarvester’s ‘AIFloodPredict’: A unique AI engine and rainfall prediction system to accurately predict advanced flood warning in regions of high vulnerability</ns2:title><ns2:status>Closed</ns2:status><ns2:grantCategory>Collaborative R&amp;D</ns2:grantCategory><ns2:leadFunder>Innovate UK</ns2:leadFunder><ns2:abstractText>StormHarvester is a UK SME dedicated to producing leading predictive industrial-AI solutions for effective wastewater and sewer management. Pivoting on their success with their world-class AI engine to address problems in the wastewater space (IntelligentSewerSuite - now being used by 60% of UK Water Companies), StormHarvester is now looking to develop an advanced AI-powered hyperlocal Flood Early Warning System (FEWS) for rivers.

Floods are among the most common and destructive natural hazards and are predicted to increase, as climate change makes devastating events more likely. Environment Agencies, Lead Local Flood Authorities (LLFAs) and Coastal Protection Authorities (CPAs) rely on hydraulic flood modelling tools to produce forecasts as their main tool for warnings. Many LLFAs and CPAs also use sensors to ensure rising river waters can be observed in realtime to try and understand where flooding may be worst. However, these sensors do not have accompanying software with a predictive capability, preventing authorities and citizens from pinpointing precisely where and when river flooding will occur. This reduces optimal use of resources making emergency planning and flood preparation more difficult.

Building on StormHarvester's sound machine learning architectural building blocks, AIFloodPredict will tackle current flood forecasting limitations by providing a _predictive_ data extraction platform using river level sensors and hyperlocal rainfall forecasts. AIFloodPredict will help LLFAs and CPAs to precisely pinpoint where and when rising river flood waters will occur, using an advanced FEWS to accelerate emergency response.</ns2:abstractText></ns2:project>