Generating Synthetic Well Logs by Artificial Neural Networks (ANN) Using MISO-ARMAX Model in Cupiagua Field.
- Guillermo Arturo Alzate (Universidad Nacional De Colombia) | Alejandra Arbelaez-Londono (Universidad Nacional De Colombia) | Abel de Jesus Naranjo Agudelo (Universidad Nacional De Colombia) | Richard Disney Zabala Romero (Ecopetrol) | Mario Alejandro Rosero Bolanos (Universidad Nacional De Colombia) | Diego Leonardo Rodriguez Escalante (Universidad Nacional De Colombia) | S. Gomez Quintero (Universidad Nacional De Colombia) | C. A. Benitez Pelaez (Universidad Nacional De Colombia)
- Document ID
- Society of Petroleum Engineers
- SPE Latin America and Caribbean Petroleum Engineering Conference, 21-23 May, Maracaibo, Venezuela
- Publication Date
- Document Type
- Conference Paper
- 2014. Society of Petroleum Engineers
- transit time curves, compressional waves, synthetic well logs, shear waves, artificial neural networks
- 1 in the last 30 days
- 229 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 5.00|
|SPE Non-Member Price:||USD 28.00|
Well logs acquired directly in field have turned out to be one of the most key engineering elements to evaluate hydrocarbon formations. Nevertheless, the lack of information, some technical troubles related to the unfolding of tools, the operational states of the well and many other reasons may sharply limit the carrying out of an optimal formation characterization methodology along the entire productive or injective lifespan of a reservoir. Nowadays, artificial neural networks (ANN) are one of the strongest tools to supply such missing information in order to generate synthetic logs.
In this paper, we explain the putting into practice of an ANN methodology with the aim of provide useful input information in geomechanical modeling for the hydraulic fracturing simulator GIGAFRAC. More explicitly, the purpose of the schemes presented here is to provide transit-time curves for primary or compressional waves (DtP) and secondary or shear waves (DtS), based on full information measurements of Gamma Ray, Neutron-Porosity, Density, DtP and DtS logs; for some wells in the Cupiagua field located in Colombian Foothills, which break through some geologic formations such as Mirador, Barco, Guadalupe, and Los Cuevos.
A noteworthy amount of considerations were taken into account to ensure the success of the ANN estimation phases. A strong focus is done regarding to filtration and quality control of the input information to the network, relating to the control mechanism of outliers, as well as the splitting-up of logs in zones by using a geological criteria and spreading of data information in computationally convenient vectorial and matricial arrangements. Finally, good adjustments were obtained throughout the validation phases and they all were considered as successful outcomes, together with training phase and subsequent use of the same for estimating DtP and DtS curves.
Synthetic well logs derived from several methodologies, like artificial neural networks (ANNs), are used when formation or well data are not available, due to factors like the tool timing, the non-inclusion of the variable of interest or the difficulties during the logging operation.
ANNs are a set of learning and analysis models based on the human nervous system. The pattern recognition capability of ANNs makes them ideal in applications involving limited or highly distorted data, as long as it is possible to assign an appropriate training level, ensuring a proper fit to the problem of interest.
The aim of the implemented methodology and the proposed procedures is the generation of transit time curves for wells without this information. The generated data are essential for the geomechanical properties estimation of geologic formations in surrounding wells, to select well candidates regarding their feasibility for hydraulic fracturing.
|File Size||4 MB||Number of Pages||14|