Skip to the content

Understanding the subsurface is critical to the needs of the E&P industry for minimising drilling risk and maximising subsurface recovery

S-Cube is a spinout company from Imperial College formed in 2015 created to advance data-driven automated earth parameter learning from raw exploration seismic data. It was formed on the back of breakthroughs by Imperial College researchers made in the algorithm of full waveform inversion. This is a form of extreme machine learning for seeing into the earth using seismic field recordings and involving compute intensive wavefield simulations. S-Cube has taken the powerful technique to the next level through algorithmic developments and a cloud-native architecture which can consume data directly from the seismic survey and turn them into actionable subsurface volumes.

The first major anisotropic application of waveform inversion was conducted by founding members of S-Cube in this award-winning study. This was at a site in the North Sea with a known shallow gas accumulation in the clastic section situated above a chalk reservoir. The waveform inversion successfully defines the structure using a data feed from a ocean-bottom seismic survey as shown below.

The company grew on the basis of this work and a breakthrough to a long-standing limitation in localised optimisation methodology known as "cycle-skipping". The adaptive formulation of waveform inversion increased the learning accuracy and improved the steepest descent search direction. AWITM was patented, proven on field data and became the recipient of the EAGE Guido Bonarelli Award for 2015. It is now in mainstream use within Equinor, Woodside Energy and most recently in 2019 within Chevron.

Ocean-bottom survey receiver cables are positioned on the seafloor with 1440 individual hydrophone locations marked as dots shown on the horizontal slices below. The left column is the input model grid with a manually inserted low blob to approximate the gas accumulation whilst the right column shows the iterated model grid converting the low velocity feature into a defined structure.

Also displayed are the simulated and recorded traces from a shot firing into a cable of receivers over the anomaly. The details of the gas charged interbedded layers and faults get captured as low velocity features in the model grid as the data fitting feedback loop cause the simulations to increase their fit with the recordings.

Aerial view through input model at depth 1.2km

Aerial view through input model at depth 1.2km

Aerial view through iterated model at depth 1.2km

Aerial view through iterated model at depth 1.2km

Vertical slice through input model

Vertical slice through input model

Vertical slice through iterated model

Vertical slice through iterated model

What happens if we eliminate the low velocity zone from the starting model completely? The gas cloud is detected but the model iterates to a local minimum trap from which it cannot recover. This is due to a phenomenon known as cycle-skipping where the predicted data shifts in a direction which causes it to misalign with the observed data. 

Vertical view through model without any evidence of low-velocity zone

Vertical view through model without any evidence of low-velocity zone

Vertical slice through intermediate model without AWI

Vertical slice through intermediate model without AWI

Vertical slice through final model without AWI

Vertical slice through final model without AWI

Aerial view through model without any evidence of low-velocity zone

Aerial view through model without any evidence of low-velocity zone

Aerial view through intermediate model without AWI

Aerial view through intermediate model without AWI

Aerial view through final model without AWI

Aerial view through final model without AWI

As a result of cycle skipped mismatch, the wider applicability of the generic technique is limited given reliance on a-priori knowledge of the target, i.e. an accurate starting model. S-Cube formed to specifically tackle this through restructuring of the data fitting feedback loop optimisation cost function, making it sufficiently convex to be able to start further from the true answer without misconvergence.

S-Cube AWITM driven by an adaptive cost function reformulates generic waveform inversion to overcome cycle skipping

S-Cube formulates Adaptive Waveform Inversion (AWITMusing a mapping between the observed and predicted data and minimising the misfit to send the non zero lag filter coefficients to zero. This solves a long-standing theoretical problem in waveform inversion parameter learning succumbing to false local minima due to oscillatory seismic data.

Repeating the previous example with the adaptive cost function and changing nothing else gives the result below. It enables successful recovery of the gas cloud from a cycle-skipped initial position at which which point conventional waveform inversion with a least-squares norm cost function can be applied to return to the previously obtained global minimum result.

Vertical view through model without any evidence of low-velocity zone

Vertical view through model without any evidence of low-velocity zone

Vertical view through AWI intermediate model (1)

Vertical view through AWI intermediate model (1)

Vertical view through AWI intermediate model (2)

Vertical view through AWI intermediate model (2)

Vertical view through AWI intermediate model (3)

Vertical view through AWI intermediate model (3)

Vertical view through AWI intermediate model (4)

Vertical view through AWI intermediate model (4)

Aerial view through model without any evidence of low-velocity zone

Aerial view through model without any evidence of low-velocity zone

Aerial view through AWI intermediate model (1)

Aerial view through AWI intermediate model (1)

Aerial view through AWI intermediate model (2)

Aerial view through AWI intermediate model (2)

Aerial view through AWI intermediate model (3)

Aerial view through AWI intermediate model (3)

Aerial view through AWI intermediate model (4)

Aerial view through AWI intermediate model (4)

Vertical view through final model with AWI

Vertical view through final model with AWI

Vertical view through tomography model

Vertical view through tomography model

Aerial view through final model with AWI

Aerial view through final model with AWI

Aerial view through tomography model

Aerial view through tomography model

Pre-drill predictive power of AWITM shown in Woodside Energy exploration application offshore Myanmar 

The application of AWITM to narrow azimuth towed steamer data leads to pre-drill prediction of gas bearing formation offshore Myanmar. The low velocity interval prediction is confirmed by a subsequent well penetration of the zone. 

Vertical slice through featureless starting model

Vertical slice through featureless starting model

Vertical slice through XWI with AWI model

Vertical slice through XWI with AWI model

The XWITM toolbox enhances the ability of waveform inversion to extend the model update deeper with reflection energy

Reflection Waveform Inversion (RWI) specifically targeting the deepest penetrating energy in the survey is added to the XWITM toolkit.

Starting model

Starting model

Stage 1 - AWI

Stage 1 - AWI

Stage 2 - RWI

Stage 2 - RWI

Final XWI model

Final XWI model

FWI only model

FWI only model

On the left is the final result using XWITM toolkit which had the closest agreement with true answer out of all industry contestants. On the right is the equivalent result using generic waveform inversion with spurious velocity variations occurring below the diving wave zone.

Cloud-native XWITM launches on Amazon Web Services with pilot user Tullow Oil 

We ran our first major cloud project here at the end of 2018. Following that new users can now access the industry’s leading FWI algorithm on demand in a managed VPC environment hosted on the cloud with the benefit of multiple cases running concurrently to enhance convergence to the basin of the misfit global minimum.

S-Cube Cloud allows the user to take an existing (baseline) run and make modifications, such as add an adaptive cost function or modify seafloor-position/density-contrast, and beat existing scores. The cloud native architecture gives the ability to to set off multiple initialisations avoiding having to run blind and guess these hidden parameters which can have a large effect on the result.  

"By running multiple scenarios simultaneously, we were able to increase quality score from a baseline of 57% to 75% by narrowing uncertainty in the sea floor position and density ratio. This directly impacted the resolution we obtained deeper down at the target level. This is an example of gaining extra value through intelligent use of predictive analytics.” Gareth O'Brien Principal Geophysicist, Tullow Oil pilot user of XWI on AWS. Click here for the full quote.

 

S-Cube is on a journey ... it's not yet reached its destination but currently has an industry-leading product and with AWS it is positioned for accelerated growth.
S-Cube Cloud

Run XWI on the Cloud

Discover an unprecedented increase in the resolution of your velocity model.