AI Case Study
Orbital Insight identifies 4x more crude oil tanks in China than the official number by analysing satellite imagery
Orbital Insight has introduced its China Oil product, which estimates oil reserves in China based on oil storage tank floating roofs. This is done by using machine learning and computer vision to identify oil tankers from satellite images and then predict capacity.
Oil And Gas
According to Orbital Insights on Medium, they "saw a chance to help stabilize the price of oil by giving investors a real look at the volume stored in closed economies. The amount of oil in storage is the most important single quantity in the market because it reflects the ongoing difference between a varying supply against a varying demand.
Aboveground oil storage can be quantified by using advanced machine learning and computer vision to identify oil tanks and measure their capacity. The volume of the oil is visible because the tanks have floating roofs. Using our shadow detection techniques, we can gauge the size of the crescent-shaped shadow on the roof and calculate how full it is. To obtain an accurate estimate of global oil supply, we are analyzing high-resolution satellite images from DigitalGlobe and Airbus.
We found more than 1,500 crude oil storage tanks that were not cataloged in the industry standard database of tank farms. At first, we didn’t believe there would be so many “unknown” tanks, but as we started to check the tanks manually, we knew the algorithm had indeed found them. After that, we performed quality assurance for the China Oil product. Our quality control processes involve a mix of algorithms and manual verification."
Orbital Insights' estimated China's crude oil supply at 600M barrels in May 2016. The company's methodology proved accurate at estimating the US crude oil supply within 8% over 300 weeks.
From Orbital on Medium: "Oil prices have been unusually volatile over the last decade — in the most extreme case rising by nearly 25% in a single day. The price of oil is driven by many political, technological, and economic factors but much of this volatility is due to a lack of transparency in the market. The consequences of price swings are quick and widespread. In the US, Hummers and Priuses go in and out of style or the cost of residential heating changes. Effects in the developing world are much more dramatic as energy can account for a much larger share of a family’s income.
In China, nearly all of the information about oil supply comes directly from the Chinese government. Without other ways to check that data, we can’t be sure that it’s correct. Underestimating the amount of available crude oil artificially inflates prices, which is a way for oil producers to make higher margins."
According to Orbital on Medium, the company uses "high-resolution satellite images from DigitalGlobe and Airbus". For their China Oil product they used about 10,000 images.