University College London Featured PhD Programmes
Birkbeck, University of London Featured PhD Programmes
Imperial College London Featured PhD Programmes
University College London Featured PhD Programmes
Centre for Genomic Regulation (CRG) Featured PhD Programmes

Machine learning for nearshore wave prediction

  • Full or part time
  • Application Deadline
    Thursday, January 09, 2020
  • Competition Funded PhD Project (European/UK Students Only)
    Competition Funded PhD Project (European/UK Students Only)

Project Description

Co-Supervisor: Dr Rafael Bergillos, University of Cordoba
Co-Supervisor: Dr Ali Belmadani, Météo France Martinique


This project will investigate the prediction capabilities of nearshore wave conditions from offshore wave parameters and remotely sensed information, including satellite data and video imagery. Machine learning and numerical modelling techniques will be used for the development of this project.

Project background

At present, about 40% of the world’s population lives within 100 kilometres of the coast. Storm surge at present days, aggravated by predicted rise in the future are serious hazards for coastal communities and infrastructure. In order to plan, manage and mitigate current and future hazards for coastal populations, the characterisation of wave properties and sea level variations in the nearshore region is essential. Different techniques have been typically used for this purpose: in situ measurements of wave height and other variables (period, direction, etc.) using moored buoys, and local recording methods (e.g., video imagery). However, innovative methodologies have arisen in the past decades, such as remote sensing. The combination of in situ measurements, numerical models, remote sensing and machine learning provides a powerful mix that is useful to produce better estimations of nearshore variables that might be difficult to monitor and predict otherwise. Nearshore measurements are occasionally exposed to hazardous conditions with the risk of instrument and/or data stream loss during crises when they are most needed. In that sense, developing a capability to accurately estimate nearshore conditions from the available offshore observations (less prone to damage due to multiple offshore locations) combined with satellite and model data would contribute to improve the security of wave monitoring, while providing new insight on wave transformation processes from the ocean to the coast.

Research questions

• How well can nearshore wave parameters be quantified using satellite data? What is the best methodology to capture wave processes over time using satellite data?

• How can in situ offshore measurements, numerical models, satellite observations and artificial intelligence be combined to predict nearshore wave parameters and storm surge?

• In the presence of complex bathymetry, waves can be diffracted, refracted, reflected, scattered... and strongly modulate offshore wave spectra. Sandy beaches are very responsive to wave conditions and, as a result, are subject to morphodynamic changes. Changes in beach slope or sandbank morphology then induce modifications of the cross-shore wave spectrum evolution. How can such two-way wave-morphology coupling be taken into account by machine learning algorithms in order to provide meaningful nearshore wave predictions?

• In terms of storm surge and morphodynamical changes, one important aspect is the generation of highly energetic infragravity waves. Can machine learning algorithms forecast the generation of such waves and their impact on morphology?


The project will develop a methodology to estimate nearshore wave parameters from offshore variables, numerical models, satellite data and machine learning in Martinique, French West Indies. Local video imagery will be used to validate the methods and during algorithm training phases wherever is possible. Machine learning techniques, such as neural networks, will be used to link the available information and extract complex relationships. Initial work will use Sentinel satellites. The following distribution of work is proposed over a three-year period:

• Year 1.Research training – The researcher will be trained on with the use and interpretation of satellite data, data processing, numerical models, and machine learning techniques.
• Year 2. Development of a methodology to predict wave parameters using the machine learning algorithms learnt in Year 1.
• Year 3. Development of case studies for validation of the methodology.


A comprehensive training programme will be provided comprising both specialist scientific training and generic transferable and professional skills. Advanced training in programming will be arranged as required. There will be opportunities to attend training programmes in coastal processes, as well as international conferences. There is also potential for short summer placements to deepen in the student’s knowledge and expertise in wave modelling.


The ideal student will have good quantitative and communication skills and a very good understanding of coastal processes and ocean engineering. Examples of suitable backgrounds are Oceanography, Civil and Environmental Engineering, Geology, or Geophysics. Experience in some type of programming language is also very important (Python, R, Matlab, or JavaScript), and the ability to acquire new programming skills is essential.

Funding Notes

1. Application procedure described on View Website.

2. Eligibility:

2.a. Full funding: UK/EU citizens or settled overseas students only, who have worked and/or studied in the UK for at least three years before the programme starts.

2.b. Fees-only: UK/EU citizens who do not comply with the 3-year UK residency criteria. The award includes fees and research costs but not stipend. Students have to find match funding to cover their living costs for 3 years minimum.

2.c. Non Eligible: Overseas students who are currently on a Tier 4 Visa or would need a Visa to come to the UK.

How good is research at University of Edinburgh in General Engineering?
(joint submission with Heriot-Watt University)

FTE Category A staff submitted: 91.80

Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully

FindAPhD. Copyright 2005-2019
All rights reserved.