CREW DelugeAI workshop: exploring the potential of AI in flood forecasting

Setting the scene
Gaining a greater understanding of how artificial intelligence (AI) and machine learning could support better prediction, communication, and management of flood risks across Scotland over the coming years is a key priority. Following a project request from SEPA, The Centre of Expertise for Waters (CREW) funded this project (DelugeAI) to conduct a rapid literature review, stakeholder engagement, and deliver a feasibility assessment and 5-year roadmap for future AI integration into flood forecasting. This workshop, which is a key milestone in the project, brings together area experts to share knowledge, identify opportunities and discuss challenges. The project is led by Chris White’s team from the University of Strathclyde.
From Continental Models to Local Insights: Advancing Hydrological Prediction in Europe with AI
The workshop kicked off with a keynote by Ilias Pechlivanidis, Lead Scientist at the Swedish Meteorological and Hydrological Institute and chair of the HEPEX initiative. Ilias discussed research on using AI to improve large-scale hydrological predictions across Europe. By combining traditional models with machine learning techniques, his team has developed hybrid approaches that better simulate river flows, including extreme events. Ilias shared his hope that in the future “no-one should be surprised by a flood”.
Understanding the use of AI for flood forecasting
Expert insights on AI applications – Lightning talks
After a short break, the second part of the workshop started with a series of three five-minute lightning talks. The first was given by Michael Butts, Lead Hydrologist at the Danish Meteorological Institute, who discussed how AI can support, but not replace, human decision making in flood warning systems. This was a sentiment echoed at multiple points throughout the workshop. By combining remote sensing, river data, and model outputs, AI could help experts interpret complex information.
Massimiliano Zappa, senior scientist at the Swiss Federal Institute for Forest, Snow and Landscape Research (WSL) discussed his team’s work applying AI to drought forecasting. Although he expressed that AI showed promise in improving forecasts, he also stressed the importance of cautious use, transparency, and linking predictions to real-world impacts.
The final lightning talk in this session was given by Jonathan Frame, Assistant Professor at The University of Alabama. Jonathan highlighted how AI, particularly convolutional networks, can be an amazing tool for things like large-scale flood forecasting. By combining physical models with AI, researchers can reconstruct flood events even when cloud cover obscures satellite images.
Initial findings from a systematic review of flood forecasting and AI
In this section of the workshop, Vicky Martí from the DelugeAI project team presented some preliminary findings from their literature review exploring how AI is being used in flood forecasting. Her work identified growing global interest, especially since 2018, in applying AI across different stages of flood forecasting, from monitoring to emergency response. Whilst most academic research is concentrated in countries like China, the US, India, the UK and Canada there are also many practical applications in existence. These range from Google's global Flood Hub to small-scale projects such as FloodCast, FloodAI in the UK and FloodWaive from Germany. Vicky explained that AI is most commonly used to complement traditional models and support decision-making, rather than to fully replace existing forecasting systems.
Open discussion: Expert insights on AI applications
The final activity in the second workshop session was an open discussion chaired by Robert Atkinson from the project team. The expert voices in the room agreed that AI is promising, especially for speeding up forecasts, supporting decision-making, and processing large volumes of data. However, there were also concerns about over reliance on AI, lack of transparency, and the ongoing need for human expertise. Speakers stressed the importance of keeping a “human in the loop” to interpret forecasts and make informed decisions. As such, it will be important to consider having clear best practices and sensitive integration to allow trust, accountability, and effective communication. This is especially important for high stakes scenarios such as flooding.
Looking forward
Expert insights on AI applications: Lightning talks
The third and final session of the day commenced with three more five-minute lightning talks. Maria Luisa Taccari, researcher at the European Centre for Medium-Range Weather Forecasts, discussed how deep learning offers faster, more flexible flood forecasting than traditional models, which can be expensive and find the physics too complex to simulate. Deep learning can learn from real-world data and performs well in challenging areas like Spain, which have seen extensive anthropogenic changes. Although results are promising, questions remain around predicting multiple variables, dealing with varying timescales, and applying models across different climates.
The second lightning talk was given by Steven Ramsdale, Chief Forecaster at the UK Met Office. Steven talked about using machine learning to improve severe weather warnings. By focusing on three key atmospheric parameters, their model can help identify when and where warnings may be needed. This approach keeps human expertise central to final decisions with support to highlight priority areas being provided by an AI tool.
Jan Verkade, Senior Hydrometeorologist at Deltares, gave the last lightning talk of the day and highlighted the growing pressure on flood agencies to adopt AI, but warned of a lack of clear best practices. His team is working with the forecasting community to define how AI can be responsibly integrated—considering ethics, costs, legal frameworks, and the need for human oversight.
Open discussion: Identifying realistic applications of AI in flood forecasting
Following the five-minute talks, Doug Bertram from the project team opened the floor up for another discussion session in which the expert attendees discussed the future role of AI in operational settings. Although AI offers promise in speeding up forecasts and handling large data volumes, workshop participants stressed the importance of maintaining human expertise, especially for decision-making and public trust. Key themes included the need for better data, ethical safeguards, explainability and workforce upskilling. The need for communication tools, interdisciplinary collaboration, and improved knowledge on the environmental costs of AI were also highlighted as areas for further focus. Ultimately, whilst AI can enhance forecasting, experts agreed it must complement, not replace, human judgement.
Closing Remarks
The workshop concluded with reflections from the DelugeAI team lead, Chris White, and SEPA requester, Michael Cranston (Lead Flood Forecaster). They expressed the value of bringing together experts from different fields to explore the role of AI in flood forecasting. Despite the rapid pace of AI development, participants agreed that there’s no single solution, highlighting the need for continued collaboration, shared learning, and practical experimentation. Key themes included the importance of keeping humans “in the loop” for decision-making, building trust in AI tools, and ensuring that any implementation is operationally relevant. There was strong support for focusing on low risk, quick win applications in the near future, whilst acknowledging that more strategic, long-term planning is a challenge. The need for skills development, ethical safeguards, and open communication with end users were also recurring points throughout the workshop. As the project moves forward, the team will compile insights into a report and roadmap.
CREW would like to thank the research team (University of Strathclyde) and the Project Steering Group (SEPA, Environment Agency and Scottish Government) for their dedication and support to the project and in addressing this important issue.
CREW Spring 2025 Newsletter

Welcome to our new quarterly CREW newsletter, CREW NEWS!
In this spring edition we’re reminding you of our current calls for proposals, highlighting completed projects and feeding back from our project evaluation forms. As it’s our first edition we’ve also included a refresher on ‘who we are and what we do’ and there’s a letter from our comms officer detailing some favourite moments from her first year in post.
We’d love to hear what you’d be interested in reading in future issues of CREW NEWS.
CRW2024_04 Natural Capital and River Basin Management Planning: Protecting and Improving Scotland’s Water Environment

Title: Natural Capital and River Basin Management Planning: Protecting and Improving Scotland’s Water Environment
Type of project: Capacity Building Project
Overview: This c. 9-month capacity building project will conduct an evidence synthesis to assess the current state of knowledge of how investments in protecting and improving natural capital influence the state of the water environment. The synthesis will also explore the wider benefits these investments provide for nature, climate adaptation, public health, net zero targets and agriculture.
Project Status: Project in procurement. Call closed.
Review of psychoactive substances wastewater monitoring approaches and recommendations for the feasibility of applying different approaches in Scotland

Scotland faces a critical public health crisis with one of the highest drug-related death rates in the developed world. Polysubstance use further complicates this issue, creating unpredictable health risks for users. Efforts to address this crisis include the National Drugs Mission Plan (2022–2026), which emphasizes reducing drug-related deaths through improved data collection and harm reduction strategies. The RADAR system (Rapid Action Drug Alerts and Response) plays a pivotal role in providing early warnings about emerging drug trends, such as the rise of potent synthetic opioids like nitazenes, enabling timely policy responses. However, existing approaches to monitor psychoactive substance use are limited by their time-consuming nature and inability to provide real-time data on drug consumption dynamics. Wastewater-Based Epidemiology (WWBE) offers a promising solution by analysing psychoactive substance residues in wastewater to deliver robust, dynamic, and timely insights into drug use patterns. This project explored the feasibility of leveraging Scotland’s existing wastewater monitoring infrastructure to enhance early warning systems like RADAR and support public health initiatives.
Objectives and Approach
The objectives of the project were to address the following questions:
- Which specific target substances should be monitored to address the highest public health threats for Scotland? For which are there recognised analytical strategies internationally?
- What are the characteristics of (a) existing infrastructure and (b) different analytical approaches available internationally and in Scotland for supporting the monitoring of target psychoactive substances and their metabolites?
- What are the characteristics of existing early warning reporting systems on drug use – internationally and in Scotland – that the different monitoring activities feed into?
- What are the options for monitoring and reporting of target psychoactive substances and their metabolites that are currently a) feasible and b) infeasible to do in Scotland and why, based on: - existing infrastructure for influent sampling of wastewater and its capacities - speed of turnaround to fit in with current reporting times (e.g. in RADAR updates) - availability of licenced laboratories with the appropriate skillset and technology in Scotland and the UK - restricted funding environment - capacities in relation to laboratory analysis - existing reporting systems?
- What are the potential benefits afforded by such a recommended monitoring approach to support the existing systems of early warning surveillance data to inform Public Health Scotland action and international public health organisations?
- What is the most feasible recommended approach to implement post-project (through limited trials or nationwide use of all appropriate Scottish Water sampling sites)?
Objectives were addressed through systematic literature review, evidence mapping, engagement of key stakeholders (Scottish Water, Public Health Scotland, European Drugs Agency) and experts through informal discussion, and a formal focus group.
Project Outputs
CRW2023_10 Psychoactive substances wastewater monitoring approaches - Main report and appendices
CRW2023_10 Psychoactive substances wastewater monitoring approaches - Appendix 7
CRW2023_10 Psychoactive substances wastewater monitoring approaches - Policy Brief
CRW2023_10 Psychoactive substances wastewater monitoring approaches - Project Summary
Review of monitoring approaches to deliver healthy ecosystems for Scotland's protected fresh waters and wetlands

NatureScot is committed to reversing the decline in freshwater biodiversity by protecting and improving ecosystem health in protected areas. This effort aligns with Scotland’s goal to safeguard 30% of its land and sea by 2030. This project makes recommendations on a monitoring framework that would inform management decisions to deliver healthy ecosystems. To achieve this, monitoring efforts must shift toward a broader landscape or catchment-scale approach, providing a more comprehensive understanding of freshwater and wetland ecosystems.
The project recommends developing a multi-index ecosystem assessment framework that will:
- Use indicators of pressures, physicochemical state and biological impact to assess ecosystem health.
- Help decision-makers allocate monitoring resources appropriately to inform the delivery of healthy ecosystems.
- Facilitate data sharing and inter-organisational collaboration to create practical conservation strategies.
The project found that to support this transition, NatureScot can leverage existing tools while exploring new, innovative approaches. The key steps in this transition include:
- Working with monitoring partners to assess the availability, format, and accessibility of existing healthy ecosystem indicator data.
- Building the necessary skills to collate, interpret and apply a wider ecosystems dataset.
- Developing a data integration approach that will synthesis ecosystem data across a range of data types and scales.
- Evaluating the policy, resource, and legislative implications of a new monitoring approach.
Project outputs
CRW2024_07 Economic, societal and public health benefits of improving water quality at designated bathing waters to a good or excellent standard in Scotland: Literature review

Type of project: Capacity Building
Project status: Project in procurement. Call closed.
Overview: This project aims to provide information on the benefits to the economy, society and public health to improving bathing water quality in Scotland, and the approaches, investment levels, ambition, achievements in other parts of the UK. This information will support the development of a framework approach to understanding and calculating the benefits of improving bathing water quality in Scotland, with an indicative way of calculating these benefits which can be applied to individual sites.
The key questions to be addressed, via review of academic and grey literature, are:
- What factors should be considered when assessing the economic, societal and public health benefits of improving bathing water quality from sufficient to good or excellent?
- What approaches, investment levels, ambition and achievements have been set/achieved in other parts of the UK and EU of improving bathing water quality beyond the sufficient classification, with values where possible, and who set these (Government, Local Authorities Water Companies or other bodies)?
- What cost benefit analysis, or other method of assessing proportional cost, has been used for any decisions worldwide on water quality improvements to support recreational water use?
CRW2024_06 Transitioning surface water collection to surface water reuse systems

Type: Capacity Building
Project Status: Project in procurement. Call closed.
Overview: This Capacity Building project aims to explore the emerging area of interest in surface water reuse before the next regulatory planning period (April 2027-March 2033) and demonstrate clear policy/strategic alignment. The project will focus on non-potable uses, such as non-food agriculture, car washing, and cooling systems, which are less regulated, but may still require adherence to local planning and environmental legislation.
Careful consideration will therefore be given to:
- Where water is captured from, given that rainwater from roofs generally contains a lower pollutant load than surface water from roads, for example.
- What untreated surface water can be used for, within current legislation.
- Feasibility of minor treatment/settlement/screening of surface water to allow captured water to be reused more widely.
- Which legislations exist regarding the reuse of grey water for non-potable uses.
Water Scarcity in Scotland: Future Impact for Distilleries and Agriculture

Research led by The James Hutton Institute, in collaboration with Scotland’s Rural College, the University of Aberdeen, and the British Geological Survey, highlights the increasing threat of water scarcity in Scotland due to climate change. Recently published in The Geographer (Winter 2024 edition, Adaption: Are we ready? And how far is it possible to adapt?), the study examines the potential impact on agriculture and distilleries.
Scotland’s agriculture and whisky industries rely heavily on rainfall and surface water. However, projections up to 2049 indicate reduced summer and early autumn rainfall, especially in eastern Scotland. This will likely double the frequency of low river flow events by 2050. For example, low flows in the River Spey, important for Scotch whisky production, could increase from once every five years to every two.
The research outlines risks across sectors:
- Crop Production: Lower yields and income losses due to reduced rainfall during critical growth stages.
- Livestock Farming: Diminished grass growth, water access, and animal health risks.
- Distilleries: Potential production halts due to restrictions in water use.
Proposed measures include efficient irrigation, increased water storage during wetter winters, and improved soil and groundwater management. While the whisky industry is exploring water-saving technologies, stakeholders in agriculture face challenges such as financial constraints and infrastructure needs.
This research underscores the urgency for Scotland’s industries to adapt to water scarcity, advocating proactive planning, innovative solutions, and further study to ensure resilience against future droughts.
CREW would like to thank the research team (The James Hutton Institute, the University of Aberdeen, SRUC and BGS) and the Project Steering Groups (Consumer Scotland, NatureScot, SEPA, WICS and the Scottish Government) for their dedication and support to the project and in addressing this important issue.
See the full project outputs here.
Scotland’s Flood Resilience Conference Highlights Urgent Need for Action and Innovation

The 2025 Sniffer (now Verture ) Flood Resilience Conference brought together experts, policymakers, and communities at Dynamic Earth in Edinburgh to tackle the pressing challenges of flood resilience.
Dr Alasdair Allan, Acting Minister for Climate Action, launched Scotland’s National Flood Resilience Strategy, emphasising the importance of proactive flood management and how Scotland takes flooding seriously. One of CREWs recent science policy fellowships (Building Public Health Resilience to Fluvial Flooding in Scotland) features in the strategy and you can read more about that here.
The conference also amplified young voices from local schools, highlighting the next generation’s concerns and aspirations for climate resilience, and gave a platform to early career researchers from SEPA, AECOM, RPALtd, University of Dundee and Mott MacDonald.
Key sessions explored innovative flood solutions, sustainable drainage systems, and nature-based approaches. Please follow the links for more information about our recently published SuDS (sustainable drainage systems) project, ‘Increasing flood resilience: residential and community runoff retention solutions’ and our science-policy fellowship ‘Resilience to Fluvial Flooding: Knowns and Unknowns to Recommendations for Management’ which touched on the theme of natural flood management.
One of the most impactful talks came from members of the Glasgow Disability Alliance who spoke about involving disabled people in flood resilience, giving examples of how critical it is for disabled peoples voices to be included in emergency response planning. The CREW science-policy fellowship ‘Policy to Preparedness: Flood Policy and Community Engagement’ broaches inequalities in society. The research team finding that distribution of physical flood risk is not fair nor equal, nor are the social circumstances of many who live on low incomes with limited resources.
The event underscored the need for co-produced, community-led solutions. As Sniffer’s new CEO, Jo Kerr, noted, “We need to meaningfully and deeply co-produce solutions.” With Scotland facing increasing flood risks, these conversations will shape future strategies for resilience and adaptation.
On a final note, we would like to thank Diarmuid O'Neill, Director of Environment and Forestry for Scottish Government for mentioning the work done by CREW in his plenary address, and to also thank all of the people who came to talk to us at the CREW stand.
CSPF2025_01 Exploring the use of Artificial Intelligence for flood forecasting in Scotland

Type of project: Science Policy Fellowship
Overview: CREW invites proposals for a c.3-month Science Policy Fellowship to undertake a rapid evidence review of the current and emerging capabilities of AI to support and enhance flood forecasting capabilities.
Project Status: Project in progress
Pages
