Reservoir prediction modelling conventionally involves complex statistical models that aim to integrate feature on multiple scales. These features are sourced from various types of data and often have a significant impact on flow performance. Conventional geostatistical algorithms provide a framework to integrate data from different scales, such as: geological interpretation of depositional structure based on analogues (e.g. by using conceptual training images); spatial correlation of geological bodies, their variety and geometrical relations (e.g. with imbedded geometrical shapes or elicited relations from analogues); high resolution seismic can be a source of multi-scale model features that can be integrated into stochastic model by means of soft conditioning.
|Number of pages||2|
|Publication status||Published - Jun 2014|
|Event||76th EAGE Conference and Exhibition 2014 - Amsterdam, Netherlands|
Duration: 16 Jun 2014 → 19 Jun 2014
|Conference||76th EAGE Conference and Exhibition 2014|
|Period||16/06/14 → 19/06/14|
Demyanov, V. (2014). Machine learning methods for reservoir prediction modelling under uncertainty: Tackling multiples scales. 1-2. Paper presented at 76th EAGE Conference and Exhibition 2014, Amsterdam, Netherlands. https://doi.org/10.3997/2214-4609.20141707