Close

We use cookies to improve your experience of our website. Privacy Policy

Skip to main content

Institute of Applied Data Science

Search
Menu

News

Harmonised, high-coverage, open dataset of solar photovoltaic installations in the UK

13 November 2020

Dr Dan Stowell
Dr Dan Stowell

The work on new solar panel geographic data for the UK, led by Dr Dan Stowell, Senior Research Fellow at the Centre for Digital Music (C4DM) at the School of Electronic Engineering and Computer Science, Queen Mary University of London and Queen Mary Turing Fellow, has been published today in Nature Scientific Data.

Solar photovoltaic (PV) is an increasingly significant fraction of electricity generation. Efficient management, and innovations such as short-term forecasting and machine vision, demand high-resolution geographic datasets of PV installations. However, official and public sources have notable deficiencies: spatial imprecision, gaps in coverage and lack of crucial meta data, especially for small-scale solar panel installations. The work, led by Dan and colleagues from the Alan Turing Institute, present the results of a major crowd-sourcing campaign to create open geographic data for over 260,000 solar PV installations across the UK, covering an estimated 86% of the capacity in the country. The focus is in particular on capturing small-scale domestic solar PV, which accounts for a significant fraction of generation but was until now very poorly documented. The free open dataset suggests nameplate capacities in the UK (as of September 2020) amount to a total of 10.66 GW explicitly mapped, or 13.93 GW when missing capacities are inferred. The method is applied to the UK but applicable worldwide, and compatible with continual updating to track the rapid growth in PV deployment.

This research project "Solar nowcasting with machine learning" to create a harmonised, high-coverage, open dataset of solar photovoltaic installations in the UK was a two-year collaboration between Queen Mary University of London's School of Electronic Engineering and Computer Science (lead: Dr Dan Stowell) and colleagues from the Alan Turing Institute, Open Climate Fix, OpenStreetMap United Kingdom community, the University of Sheffield and hundreds of volunteers all around the UK.

The published data will enable decarbonisation at national scales, through forecasting and management of generation, and also serves as a training dataset for machine vision detection of new PV.

Read the full Nature article here: A harmonised, high-coverage, open dataset of solar photovoltaic installations in the UK

Dataset is available here: Solar panels and solar farms in the UK - geographic open data (UKPVGeo).

Contact: Dr Dan Stowell
Link: https://www.nature.com/articles/s41597-020-00739-0

Updated by: Michal Filus