Gamification of shallow geosteering (Sergey Alyaev, NORCE Norwegian Research Centre)


Sergey Alyaev from NORCE Norwegian Research Centre


Horizontal directional drilling (HDD) is a go-to method for installing subsurface pipelines, telecommunication cables, power lines, and sewers without digging trenches. The traditional methodology follows a pre-defined path to drill a horizontal well under surface obstacles such as rivers or inhabited areas. In the last few years, logging-while-drilling (LWD) measurements developed for oil and gas drilling have become more affordable and made their way to civil drilling. They enable geosteering of shallow wells: intensional real-time trajectory adjustment to adapt to the observed subsurface environment as the uncertainty gets reduced with new measurements.

On this poster, we present a recently created open source web simulation game that demonstrates shallow geosteering. As a player, you must avoid subsurface obstacles and reach the target across a river by only controlling the bit’s bias, either up or down, and hence the drilling direction. The “fog of uncertainty” hides subsurface obstacles: large boulders. However, in the pre-drill stage, the obstacle tops are detected by seismology and shown as dots. As you start drilling, the fog clears following the bit, simulating an LWD tool with a limited look around. If you hit a boulder, you can pull back on the pipe and try drilling in another direction. But the drill bit will get broken after three collisions. The final score accounts for the total length drilled, the final length of the well, and the number of stuck times. The prototype demonstrates the HDD and geosteering principles to a general audience and enables experimenting with AI training in the simulated environment.


Sergey Alyaev holds MSc and PhD degrees in applied and computational mathematics from the University of Bergen. He works as a senior researcher at NORCE, where he develops mathematical methods for problems in flow-modeling drilling and geosteering. His research interests include forward and inverse modeling, uncertainty quantification, data-driven methods, and decision theory; and their real-time applications.

Download poster