February 22, 2024
This is some text inside of a div block.

Case Study: Surveying Bird Species Using Geolocation

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse varius enim in eros elementum tristique. Duis cursus, mi quis viverra ornare, eros dolor interdum nulla, ut commodo diam libero vitae erat. Aenean faucibus nibh et justo cursus id rutrum lorem imperdiet. Nunc ut sem vitae risus tristique posuere.This is some text inside of a div block.

Working with Seascape Surveillance to develop machine learning models to identify bird species.

Data Scientists at the Hartree Centre North East Hub worked closely with Seascape Surveillance over 12 weeks to explore the use of geolocation and machine learning models to identify bird species to provide findings to aid the development of offshore renewable energy.

The Challenge

Seascape Surveillance was set up to develop new methodologies for the biodiversity surveys required for the development of offshore renewable energy. Current systems use electrooptical methods that are restricted to visible images in daylight. In order to conduct wide area surveys in conditions of cloud or at night, forms of radar must be utilised. However radar images can rarely provide sufficient details for species identification of marine birds. The Seascape hypothesis was that species identification might be possible from the spatial patterning of birds. So, the challenge was to use existing data sets to determine through machine learning, the species of birds marked only by their geolocation.

The Support

The Hartree Centre North East Hub team worked with Seascape to create multiple machine learning models for identifying bird species using limited data. The initial stages involved exploring and understanding the currently available data and assessing its suitability for modelling. Pre-processing methods were developed for turning raw data into suitable model inputs. Multiple types of model were then trained using the processed data and evaluated based on their accuracy at classifying bird species. The initial results are promising and show that the approaches considered have potential. Seascape will now look to acquire more data to further develop the method.

Benefits of the Support

The initial model results produced by Hartree Centre | North East Hub will enable Seascape to demonstrate the potential viability of their approach. The team now have a good understanding of the available datasets and what will be required for further validation and development. They have also gained valuable knowledge around data wrangling and modelling that will provide a good foundation for further learning. As a result of the project, a new part-time role was created to focus on data acquisition. Seascape are now a step closer towards realising their vision for lower cost, higher-quality surveys for the renewables industry.

“Our experience with the Hartree programme has been of immense value, not only in the excellence of their work for us, but in the important education in data science that we have received. The Hartree Centre North East Hub enabled us to move quickly in a space where we had very limited experience and only an outline hypothesis. We now have encouraging results which can be used to demonstrate the potential of our approach to investors.”

- Dave Baillie, Seascape Surveillance

Further Information

Our collaborative data projects are up to 12 weeks in duration and give you access to a wide range of expertise across our team of data scientists and data engineers. We will work alongside your team to scope your data science or engineering project, build a prototype solution, and explore options to deploy it within your organisation. You can learn more about them on our webpage here.

If you would like to learn more about the Hartree Centre North East Hub or our collaborative data projects, please get in touch with us at: