Accessible, asset-level dataset covering 183 countries harnesses satellite imagery and machine learning to support energy transition decision-making
Climate analytics non-profit TransitionZero today launched Solar Asset Mapper (TZ-SAM), an open-access global dataset of commercial- and utility-scale solar facilities utilising satellite imagery and machine learning. This is the first time that open-access, geo-located solar asset data has been made available at this level of granularity, and identifies small- and medium-sized solar assets at scale. Regularly updated, it can be integrated into system models for electricity grid operations and planning, supporting more effective forecasting by filling gaps in traditional methods of solar asset reporting.
Solar power is the fastest-growing power generation technology in history. In 2023 alone, the world added almost 400 gigawatts (GW) of solar capacity, equivalent to installing more than 192 football fields of solar panels every hour1. To effectively manage ongoing solar deployment, accurate and current facility-level data is essential. It enables the management of intermittency, facilitates grid planning, and allows for the assessment of trade-offs with biodiversity, conservation, and land protection priorities.
Up to now, datasets of solar generating capacity have not been able to fully meet the changing needs of grid planners. Datasets are country-level, don’t adequately differentiate between large- and small-scale facilities, and struggle to keep up with the rapid pace of solar expansion.
The TZ-SAM Q1 2024 dataset contains the location and shape of 63,616 assets, along with estimated capacities, an at least threefold increase in GW capacity for facilities under 5 MW compared to public and commercial alternatives. It estimates the construction date for over 80% of these assets. The dataset contains over 19,100 square kilometres of solar farms across 183 countries, with a total estimated capacity of 711 GW.
The dataset and methodology can be accessed now through Zenodo [DOI: 10.5281/zenodo.11368204] or through TransitionZero’s website.
TransitionZero developed algorithms using earth observation and machine learning to accurately identify the capacity, land area, and age of every large solar facility worldwide, in addition to a large number of small and medium-sized assets. TZ-SAM’s methodology builds on Kruitwagen, L., Story, K.T., Friedrich, J. et al. and uses the European Space Agency’s (ESA) Sentinel-2 dataset, combined with the community-driven and open-source OpenStreetMap (OSM) dataset for training labels.
TransitionZero will host a webinar on Monday, June 24 at 12:30 pm BST to discuss this work. Register to attend here.
Matt Gray, Co-founder and CEO of TransitionZero:
To prevent poor decision-making resulting from 'junk-in, junk-out' modelling, utilising accurate and current geospatial data is essential. We're excited to announce the availability of this innovative dataset and eagerly anticipate its integration into our software platform, Model Builder, later this year.
Diren Kocakuşak, Research Analyst, Global Energy Monitor:
Keeping tabs on the global solar build-out requires all hands on deck. At Global Energy Monitor, we compile a project-by-project, ground-up inventory of solar installations for scientists, policymakers and the public. But as progress quickens towards the global goal of tripling renewables, providing complete and accurate data on the growing number of smaller-scale projects across the globe is increasingly difficult. TransitionZero's Solar Asset Mapper addresses this challenge by rounding out the solar picture with geometries, locations, and capacity estimates.
