Remote sensing and computer vision: localising energy transitions

Learn more Add to Calendar 03/19/2020 11:00 AM 03/19/2020 01:00 PM Europe/London Remote sensing and computer vision: localising energy transitions Location of the event
Thursday 19 Mar 2020
Time: 11:00 - 13:00

Event type


Audience type



Watch a recording of the seminar. Please be advised seminar beings at 8m10s and is audio only until slides start at 47m03s.

About the event

Understanding the spatially-embedded energy system is necessary to manage generation intermittency, to mitigate climate risks and associated social impacts, and to target optimal policy interventions. Remote sensing and computer vision offers a novel method for localising energy infrastructure agnostic to company and country reporting. Using a longitudinal corpus of remote sensing imagery and machine learning we provide a globally-exhaustive inventory of utility-scale solar PV generating stations, complete with installation dates for facilities built after June 2016. We also present ongoing research in the development of a self-supervised sensor-fusion model for general-purpose semantic embedding of remote sensing imagery.