Neural network promoted to produce oil on Yamal

in technotec •  6 years ago 

At the Vyngapurovskoye field of Yamal oil which was discovered after digital processing of geological data by artificial intelligence was produced for the first time.

A special self-learning program for the search for new hydrocarbon formations was created by the Scientific and technical center of Gazprom Neft together with IBM Services.

The development has no analogues and helps to predict with high possibility the location of deposits that are difficult to identify by traditional methods.

From a technical point of view, the program is really amazing: hundreds of gigabytes of data from thousands of wells located in the field are processed. About 60 thousand results of geophysical studies are analyzed simultaneously, both historical and incoming new geological data.

The neural network created by the developers looks for patterns, determining where the layers may be located, which have not been detected earlier because of the small size or complex structure.

As reported by “Rossiyskaya Gazeta” with reference to the press service of “Gazprom Neft”: “the Program during the pilot project analyzed the data of more than three thousand wells in the field and predicted new promising areas. Industrial work confirmed that there are hydrocarbons in these formations. As a result of the tests, oil inflow was obtained without creating additional infrastructure».

140619.png

Authors get paid when people like you upvote their post.
If you enjoyed what you read here, create your account today and start earning FREE STEEM!
Sort Order:  

Warning! This user is on my black list, likely as a known plagiarist, spammer or ID thief. Please be cautious with this post!
If you believe this is an error, please chat with us in the #cheetah-appeals channel in our discord.