With demand and prices so high for crude oil, petroleum companies are searching for new reservoirs deep below the ocean floor, in areas of more geological complexity. But drilling under the ocean is very expensive, so oil companies need to have as complete an understanding of the geology where they’re drilling as possible.
Even armed with reams of seismic data about the Earth’s subterranean features, though, making accurate maps of the geology underlying the ocean is a challenge. Now Shell is working with computer scientists at MIT to design algorithms that will allow them to more quickly and more accurately create maps of these underground areas.
Generating maps of the deep and complex areas now under exploration by oil companies can take several people many months, says Richard Sears, a visiting scientist from Shell at MIT. Regions under study may be hundreds of kilometers in area and several kilometers deep. Those working to create 3-D maps of these areas must process huge amounts of data.
Shell turned to Alan Willsky, professor of electrical engineering at MIT, for a way to make sense of the vast amount of seismic data that the company gathers for map-making. Willsky’s group specializes in computational methods for extracting the shapes of objects from complex data.
For its first project with Shell, his group is tailoring algorithms to help the company’s geologists study salt deposits under the Gulf of Mexico. Shell hopes that these formations, which are difficult to map, have trapped large deposits of oil under the sea floor. Willsky and colleagues are helping Shell map the surfaces, shapes, and boundaries of these deposits.
Willsky says that determining the shape and size of salt deposits under the earth is a similar to another undertaking of his group: collaborating with radiologists to develop image analysis algorithms for mapping the prostate to determine where to insert a cancer-killing radioactive pellets. Their algorithms “could impact many fields,” he says, including biomedicine and oceanography.
The oil surveying process starts with ships sweeping over a large area around the clock for several weeks, while sending high-intensity vibrations into the Earth and measuring their echoes. About every 10 seconds, compressed air is shot into the water from many cylinders simultaneously. Vibrations from these blasts travel through the water and into the earth until they bump into something. Then they echo back to the water’s surface, where they’re registered by kilometers-long streamers of pressure-sensitive microphones trailing the ship. Although each echo is weak, multiple signals reinforce each other.
Then company geologists have to turn hundreds of millions of points of this vibrational or seismic data into a 3-D map for determining whether or not oil deposits lie below. Such map-making is an iterative process. First, a computer processes the raw data. Then, looking at vertical sections, the map maker picks out a few points where he or she sees something interesting – where it looks like the sound waves have echoed off a particular kind of geological structure, such as a salt deposit.
The new algorithms developed by Willsky’s group and in use by Shell can define statistical relationships between the data points selected by the map makers, and use these relationships to connect the dots and create a map. The algorithms also calculate the uncertainty of each data point.
“The computer can take days to generate a complex surface, and the interpreter takes days to go through the data,” says Sears.
“One hundred percent success is a rare circumstance,” says Ron Masters, a senior staff geophysicist at Shell. “You have to drill a lot of prospects,” some of which will not bear out map makers’ predictions.
Shell and Willsky hope that ever-more-sophisticated algorithms will help the map makers do their job more quickly and with greater accuracy, especially as the company continues to look for oil in more geologically complex areas, such as those around salt deposits.
According to Masters, salt deposits are a dominant characteristic of the deep waters of the Gulf of Mexico. But he says the mapping algorithms developed by Willsky should apply to other geologically complex deposits elsewhere in the world’s oceans.
The big new idea for making self-driving cars that can go anywhere
The mainstream approach to driverless cars is slow and difficult. These startups think going all-in on AI will get there faster.
Inside Charm Industrial’s big bet on corn stalks for carbon removal
The startup used plant matter and bio-oil to sequester thousands of tons of carbon. The question now is how reliable, scalable, and economical this approach will prove.
The dark secret behind those cute AI-generated animal images
Google Brain has revealed its own image-making AI, called Imagen. But don't expect to see anything that isn't wholesome.
The hype around DeepMind’s new AI model misses what’s actually cool about it
Some worry that the chatter about these tools is doing the whole field a disservice.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.