PIXELS to KNOWLEDGE extracting insights from energy data through - PowerPoint PPT Presentation

from PIXELS to KNOWLEDGE extracting insights from energy data through visualization kyle bradbury, phd

ENERGY DATA ANALYTICS LAB

milestones in energy through VISUALIZATION

Early Power Plants Technical Drawings 1869 Source: Babcock & Wilcox Company. Steam, its generation and use . Babcock & Wilcox., 1922.

Thermal Energy Efficiency, 1898 Sankey Diagrams Source: https://en.wikipedia.org/wiki/Sankey_diagram#/media/File:JIE_Sankey_V5_Fig1.png

U.S. Energy Use, 2014 Sankey Diagram

Electrification of the U.S., 1921 Cartogram Source: http://www.firstgreen.co/2013/08/graph- of-the-day-map-of-u-s-electricity-consumption-in- 1921/

Oil Trade 1969 flow diagram

Hubbert Curve 1956 line plot Source: Hubbert’s Peak, from M. King Hubbert , “Nuclear Energy and the Fossil Fuels,” presented at a meeting of the American Petroleum Institute, 1956.

Hubbert Curve 2000 line plot Actual Production Hubbert’s Predicton Source: https://en.wikipedia.org/wiki/Hubbert_peak_theory#/media/File:Hubbert_Upper-Bound_Peak_1956.png

Hubbert Curve 2014 line plot Actual Production Hubbert’s Predicton Source: https://en.wikipedia.org/wiki/Hubbert_peak_theory#/media/File:Hubbert_Upper-Bound_Peak_1956.png

Atmospheric CO 2 2006 line plot Source: NOAA. http://climate.nasa.gov/vital-signs/carbon-dioxide/

Atmospheric CO 2 , 2006 line plot Left: https://filmefuerdieerde.org/en/films/climate/an-inconvenient-truth Right: http://www.moviesteve.com/wp-content/uploads/2013/09/inconvenient_truth1.jpg

History of U.S. Energy Consumption, 2009 line plot Petroleum Natural Gas Coal Nuclear Hydroelectric Wood Source: U.S. Energy Information Administration – Annual Energy Review 2009

U.S. ELECTRICITY generation

Energy Information Administration (EIA) http://www.eia.gov/state/maps.cfm?src=home-f3

Capacity LINK

Generation

CO 2 Emissions

Generator Age

U.S. Generation LINK

energy resource assessment from REMOTE SENSING data Jordan Malof Kyle Bradbury Rui Hou Richard Newell Leslie Collins Energy Initiative SSPACISS Laboratory

Oahu, Hawaii New Solar Arrays after 2008 Kyle Bradbury & Mengyang Lin LINK

Oahu, Hawaii New Solar Arrays after 2008 Kyle Bradbury & Mengyang Lin

Oahu, Hawaii New Solar Arrays after 2008 Kyle Bradbury & Mengyang Lin

Oahu, Hawaii New Solar Arrays after 2008 Kyle Bradbury & Mengyang Lin

the problem Interest exists in quantifying U.S. Theoretical illustration of solar distributed solar power capacity panel capacity by region more Capacity estimates are difficult to obtain less – Large-scale audits are conducted with questionnaires Malof , J. M., R. Hou, L. M. Collins, K. Bradbury, and R. Newell, “Automatic solar photovoltaic panel detection in satellite imagery,” in 2015 International Conference on Renewable Energy Research and Applications (ICRERA), 2015, pp. 1428 – 1431.

machine learning solution Example e of of imag agery ery data ta High resolution satellite images are increasingly available Algorithms may automatically estimate power capacity from images Solar r arra ray Malof , J. M., R. Hou, L. M. Collins, K. Bradbury, and R. Newell, “Automatic solar photovoltaic panel detection in satellite imagery,” in 2015 International Conference on Renewable Energy Research and Applications (ICRERA), 2015, pp. 1428 – 1431.

detection algorithm development Our development dataset of 100 images were extracted 100 house images from US Geological Survey 50 with solar panels (red) satellite imagery (right) … ML algorithms were developed 50 without solar panels to automatically locate the … solar panels Malof , J. M., R. Hou, L. M. Collins, K. Bradbury, and R. Newell, “Automatic solar photovoltaic panel detection in satellite imagery,” in 2015 International Conference on Renewable Energy Research and Applications (ICRERA), 2015, pp. 1428 – 1431.

A snapshot of the algorithm Malof , J. M., R. Hou, L. M. Collins, K. Bradbury, and R. Newell, “Automatic solar photovoltaic panel detection in satellite imagery,” in 2015 International Conference on Renewable Energy Research and Applications (ICRERA), 2015, pp. 1428 – 1431.

solar array detection algorithm performance 92% of panels were curve identified, with 4 total false alarms Malof , J. M., R. Hou, L. M. Collins, K. Bradbury, and R. Newell, “Automatic solar photovoltaic panel detection in satellite imagery,” in 2015 International Conference on Renewable Energy Research and Applications (ICRERA), 2015, pp. 1428 – 1431.

visualizing results – houses with panels Black polygons are labeled solar arrays Yellow ellipses are detected regions Malof, J. M., R. Hou, L. M. Collins, K. Bradbury, and R. Newell, “Automatic solar photovoltaic panel detection in satellite imagery,” in 2015 International Conference on Renewable Energy Research and Applications (ICRERA), 2015, pp. 1428 – 1431.

visualizing results – houses without panels Black polygons are labeled solar arrays + Yellow ellipses are detected regions Malof, J. M., R. Hou, L. M. Collins, K. Bradbury, and R. Newell, “Automatic solar photovoltaic panel detection in satellite imagery,” in 2015 International Conference on Renewable Energy Research and Applications (ICRERA), 2015, pp. 1428 – 1431.

Data+ team created a ground truth data set of over 19,000 solar array locations

ENERGY data analytics lab