📣 Help Shape the Future of UKRI's Gateway to Research (GtR)

We're improving UKRI's Gateway to Research and are seeking your input! If you would be interested in being interviewed about the improvements we're making and to have your say about how we can make GtR more user-friendly, impactful, and effective for the Research and Innovation community, please email gateway@ukri.org.

SPLASH: digital approaches to predict wave hazards

Lead Research Organisation: University of Plymouth
Department Name: Sch of Biological and Marine Sciences

Abstract

Abstracts are not currently available in GtR for all funded research. This is normally because the abstract was not required at the time of proposal submission, but may be because it included sensitive information such as personal details.

Publications

10 25 50
 
Description Most significant achievements include:
Wave overtopping prediction tool for Dawlish and Penzance applying AI in overtopping observations. The final digital twin will include daily updates with 5 day operational overtopping forecast and will include a user interface to explore uncertainty in inputs. This version of the digital twin will be hosted in the National Network of Regional Coastal Monitoring Programmes website.
EO processing tools transferable for coastal wave hazard analysis: (1) Wave-related indicators derived from satellite EO will provide statistics on and time sequences of coastal wave properties (localised sea surface roughness, breaking, propagation direction) across a region; (2) Understanding regular asymmetries (e.g., flood/ebb-dominance) in wave hazards will support our project partners and others (e.g., Local Authorities) managing coastal hazard through improved site-specific hazard understanding.
Documentation with lessons learned to build digital prototypes for coastal hazards.
There are significant opportunities for using machine and deep learning approaches to predict wave overtopping : good accuracy, potential for generalisation, and high speed and computational efficiency.
Machine learning random forests offer the highest predictive performance even when comparing against very developed operational forecasting systems using traditional approaches (process-based models and empirical overtopping prediction using EurOtop.
Wind related variables are significantly important variables influencing overtopping, that current empirical approaches disregard.
There are multiple opportunities to aim to generalise these AI approaches to multiple locations across the UK if overtopping observations are available. Future testing to measure overtopping in #gravelbeach project using LiDAR 2D.
Exploitation Route SPLASH provides a useful and inclusive tool that can be used by coastal practitioners, policy makers and regular public. Next steps should include generalisation of the model to other study sites. This tool has a great potential to be extended if new funding is secured.
Sectors Communities and Social Services/Policy

Environment

Transport

Other

 
Description While wave overtopping has received a lot of attention, almost all existing measurements were obtained from small scale lab experiments. Full-scale field data is extremely challenging to obtain using traditional methods ("overtopping buckets" where overtopping volumes are captured in a container), which require substantial infrastructure, cannot be done remotely and so must target rare overtopping events. If a remote method can be successfully developed, this will represent a significant advance which will lead to a greater understanding of the causes of coastal flooding and our ability to predict flooding hazards. Nieves Valiente has a PhD student working on 2D LiDAR sensors (i.e. remote sensing data) to measure overtopping. In the medium term, the new method, along with SPLASH findings should provide the foundation from which to apply for a major grant (e.g., EPSRC) which will investigate wave overtopping using multiple field deployments among other things. The experimental findings will be used to develop a real-time coastal flooding forecast tool for engineers and coastal managers which can be trained and updated based on continuous overtopping data at flooding hotspots.
Sector Communities and Social Services/Policy,Digital/Communication/Information Technologies (including Software),Education
Impact Types Policy & public services

 
Title Investigating Appropriate Artificial Intelligence Approaches to Reliably Predict Coastal Wave Overtopping and Identify Process Contributions 
Description Supplementary material for the study "Investigating Appropriate Artificial Intelligence Approaches to Reliably Predict Coastal Wave Overtopping and Identify Process Contributions", This includes the code for constructing the AI models, the datasets for training the models, and some additional tables computing the performance metrics and model specifications 
Type Of Material Computer model/algorithm 
Year Produced 2024 
Provided To Others? Yes  
Impact All members of the public including policy makers, coastal practitioners and the industry can use the models to predict overtopping at two specific study sites. Additionally, this can be used as a digital prototype for other study sites. 
URL https://zenodo.org/records/14330146
 
Description AI developed from in-situ wave overtopping observation, University of Bath Seminar 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Postgraduate students
Results and Impact Seminar given to the Centre for Climate Adaptation & Environment Research to promote the advances in wave overtopping predictive capability within the SPLASH research project. Questions were asked afterwards.
Year(s) Of Engagement Activity 2024
 
Description Centre for Science and Policy, University of Cambridge, blog: "Coastal resilience in the face of climate change" 
Form Of Engagement Activity Engagement focused website, blog or social media channel
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Public/other audiences
Results and Impact Contributed to a blog "Coastal resilience in the face of climate change" to raise awareness of new techniques of predicting future flood risk.
Year(s) Of Engagement Activity 2024
URL https://www.csap.cam.ac.uk/news/article-podcast-mini-series-coastal-resilience-face-climat/
 
Description Defra Flood Rescue Tactical Advisors continuous professional development (CPD) event 2024 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact A talk on new expertise on coastal flooding and its predictions was given to Defra's Flood Rescue Tactical Advisors as part of their annual professional development activities. Members may be called upon by Local Resilience Forums to assist with drawing up plans to assist in the rescue of people in a flood situation.
Year(s) Of Engagement Activity 2024
 
Description Into the Blue Podcast "The Growing Threat of Coastal Flooding". 
Form Of Engagement Activity Engagement focused website, blog or social media channel
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact A podcast was recorded to raise awareness of flood hazard.
Year(s) Of Engagement Activity 2024
URL https://youtu.be/aXiopSIpVwE
 
Description Met office seminar "From measuring to monitoring & forecasting wave overtopping" 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Policymakers/politicians
Results and Impact A seminar was given at the Met Office to demonstrate the capability of the WireWall dataset as training resource for Machine Learning techniques to forecast coastal hazard. Discussion followed around the ability to upscale for national capability and around data sharing to support new forecast services.
Year(s) Of Engagement Activity 2025
 
Description National Hazard Partnership. SPLASH: digital approaches to predict wave hazards 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact Talk as part of the National Hazard Partnership
Year(s) Of Engagement Activity 2024
 
Description Oral presentation at UK Coastal Research Conference 2025 - Nearshore wave breaking detection using satellite radar altimetry 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Other audiences
Results and Impact Oral presentation during conference
Year(s) Of Engagement Activity 2025
 
Description Presentation "Incorporating SW monitoring with research measurements to predict & understand wave overtopping" 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Professional Practitioners
Results and Impact A presentation was given at the SW coastal monitoring annual meeting, Plymouth. The aim was to showcase the new AI capability within the SPLASH project. Questions were asked afterwards.
Year(s) Of Engagement Activity 2024
 
Description Presentation at the Met Office - SPLASH: Digital Approaches to predict wave hazards 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Other audiences
Results and Impact Presentation of the project and demo of the Digital Twin at the Met Office during the Ocean Ice Tea meting. This actitivy reached more than 50 people most of them working on Ocean Forecasting and OCean climate and modelling
Year(s) Of Engagement Activity 2025
 
Description Presentation at the UK Coastal Research Conference 2025 - SPLASH: understanding wave overtopping using artificial intelligence 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Other audiences
Results and Impact Talk during the UK Coastal Research Conference 2025 on "SPLASH: understanding wave overtopping using artificial intelligence"
Year(s) Of Engagement Activity 2025
 
Description Skills Network Webinar "Wave overtopping hazard - from observation to prediction" 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact A webinar was given to the UK Collaboratorium for Research on Infrastructures & Cities (UKCRIC) doctoral skills training network and Infrastructure for Port cities And Coastal Towns (iPACT) network. Questions were asked afterwards.
Year(s) Of Engagement Activity 2024
 
Description Symposium Exploring Coastal Hazards Coastal (The Netherlands) presentation "Digital Twins and artificial intelligence: a novel approach to predict overtopping" 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Symposyum on Coastal Hazards in The Netherlands where we will be presenting "Digital Twins and artificial intelligence: a novel approach to predict overtopping "
Year(s) Of Engagement Activity 2024
 
Description Talk in the International Conference Coastal Dynamics Portugal 2025 - The Role Of Machine Learning, Incorporating Wind Da-ta, To Predict Coastal Wave Overtopping 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Other audiences
Results and Impact Talk during the International Conference Coastal Dynamics. this will also include a publication (not available just yet)
Year(s) Of Engagement Activity 2025
 
Description Talk to Hazards Forum "SPLASH: digital approaches to predict wave hazards" 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Industry/Business
Results and Impact Title SPLASH: digital approaches to predict wave hazards
Year(s) Of Engagement Activity 2024
 
Description Talk to the Centre for Climate Adaptation & Environment Research at University of Bath, "AI developed from in-situ wave overtopping observation" 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Postgraduate students
Results and Impact Presentation of SPLASH model outcomes to the Centre for Climate Adaptation & Environment Research
Year(s) Of Engagement Activity 2024