Global Photovoltaic Power Generation Directory (2016-2018)
Photovoltaic (PV) solar power generation capacity has grown by 41% annually since 2009. The authors point out that projections of energy systems that mitigate climate change and help universal access to energy show a nearly 10-fold increase in photovoltaic solar generation capacity by 2040. The authors further identified and verified 68,661 facilities, a 432% increase (number of facilities) over previously available asset-level data. With the help of a hand-labeled test set, we estimate the installed global power generation capacity at the end of 2018 to be 423 GW (-75/+77 GW). Preface – Bed Length Artificial Intelligence Tutorial
For installations over 10,000 m2 (approximately 600 kW), the achieved precision is 98.6% relative to our test set, with a slight loss in recall, dropping to 90% (Supplementary Fig. 6). For installations larger than 10,000 square meters, the final dataset has an IoU of 90%—sufficient for broad usage based on user reports. A global inventory of photovoltaic solar energy generating units |
Citation:¶
Kruitwagen, L., Story, K.T., Friedrich, J. et al. A global inventory of photovoltaic solar energy generating units.
Nature 598, 604–610 (2021). https://doi.org/10.1038/s41586-021-03957-7
Dataset Citation¶
Kruitwagen, Lucas, Story, Kyle, Friedrich, Johannes, Byers, Logan, Skillman, Sam, & Hepburn, Cameron. (2021). A global
inventory of solar photovoltaic generating units - dataset (1.0.0) [Data set].
Zenodo. https://doi.org/10.5281/zenodo.5005868
Earth Engine Snippet¶
var predicted_set = ee.FeatureCollection("projects/sat-io/open-datasets/global_photovoltaic/predicted_set");
var cv_polygons = ee.FeatureCollection("projects/sat-io/open-datasets/global_photovoltaic/cv_polygons");
var cv_tiles = ee.FeatureCollection("projects/sat-io/open-datasets/global_photovoltaic/cv_tiles");
var test_polygons = ee.FeatureCollection("projects/sat-io/open-datasets/global_photovoltaic/test_polygons");
var test_tiles = ee.FeatureCollection("projects/sat-io/open-datasets/global_photovoltaic/test_tiles");
var trn_tiles = ee.FeatureCollection("projects/sat-io/open-datasets/global_photovoltaic/trn_tiles");
var trn_polygons = ee.FeatureCollection("projects/sat-io/open-datasets/global_photovoltaic/trn_polygons");
Layer name and description table¶
File Name | Description |
---|---|
trn_tiles | 18,570 rectangular areas-of-interest used for sampling training patch data. |
trn_polygons | 36,882 polygons obtained from OSM in 2017 used to label training patches |
cv_tiles | 560 rectangular areas-of-interest used for sampling cross-validation data seeded from WRI GPPDB |
cv_polygons | 6,281 polygons corresponding to all PV solar generating units present in cv_tiles at the end of 2018. |
test_tiles | 122 rectangular regions-of-interest used for building the test set. |
test_polygons | 7,263 polygons corresponding to all utility-scale (>10kW) solar generating units present in test_tiles at the end of 2018. |
predicted_set | 68,661 polygons corresponding to predicted polygons in global deployment, capturing the status of deployed photovoltaic solar energy generating capacity at the end of 2018. |
License¶
Creative Commons Attribution 4.0 International License
Created by: Kruitwagen et al
Curated by: Samapriya Roy
Keywords: photovoltaic solar remote sensing geospatial data computer vision
Last updated: 2021-10-28