Abstract
Abstract
Conventional methods of acquiring log and core often exposes project owners to high cost and time-consuming operation. Other than that, massive data availability in different platforms are also persistent issue waiting to be resolved. Artificial Intelligent module of well log artificial intelligent prediction module named Enhanced Resource Monetization Artificial Intelligent (ERMAI) and physical core artificial intelligent prediction module named Core Artificial Intelligent (COREAI) are developed to eliminate expensive operation, factor out human biasness, enable prediction of core data and log data at any depth and all data are kept in structural corporate database.
Overall approach presents innovation and agile technologies that integrate data management, data quality assessment and predictive machine learning to maximize the company asset value using existing core and well log data. The development of machine learning algorithms identifies potential outliers, benchmark the valuable data against the current industry standards, increases the confidence in data quality and avoids augmented error in predicting reservoir properties. For core prediction using CatBoost algorithm machine learning methods by combining digital raw data with core photo. And for log prediction using random forest assemble learning methods which using certain training wells for massive prediction.
Reference5 articles.
1. Tao
Lin
, MokhlesMezghani, ChiichengXu, WeichangLi, "Machine Learning for Multiple Petrophysical Properties Regression Based on Core Images and Well Logs in a Heterogenous Reservoir." Paper presented at the SPE Annual Technical Conference and Exhibition, Dubai, UAE, September 2021.
2. Siti Najmi Farhan
Zulkipli
, PETRONAS Carigali; BenardRalphie and Jamari MShah, PETRONAS; TaufikNordin, "Bringing Huge Core Analysis Legacy Data Into Life Using Machine Learning." This paper was prepared for presentation at the Offshore Technology Conference Asia held in Kuala Lumpur, Malaysia, 22 - 25 March 2022.
3. Akkurt, R. C.
(2018). Accelerating and Enhancing Petrophysical Analysis With Machine Learning: A Case Study of an Automated System for Well Log Outlier Detection and Reconstruction. SPWLA 59th Annual Logging Symposium. London.
4. Akinnikawe, O. L.
(July2018). Synthetic Well Log Generation Using Machine Learning Techniques. SPE/AAPG/SEG Unconventional Resources Technology Conference. Houston, Texas, USA.
5. Machine Learning Brings Vast Core-Analysis Legacy Data to Life;Carpenter,2022