Abstract:

This talk introduces an end-to-end in-house development of an AI-assisted subsurface workflow designed for compartmentalized gas fields in the Gulf of Thailand, which faces the challenge of small reservoirs requiring a large number of wells and swift subsurface analysis. The objective is to streamline and automate key subsurface processes—subsurface interpretation (fault, horizon, prospect), well targeting, and production forecasting—to reduce exhaustive effort, improve consistency, and suggest optimal decision-making across the full field development lifecycle.

The workflow starts by defining subsurface planning requirements and standardizing procedures to align with business objectives. Fit-for-purpose data analytics are then applied to automate and accelerate each stage. Automated subsurface interpretation uses trap-specific algorithms based on contour-fault geometry and probabilistic HCCH scenarios to generate consistent, bias-free prospect maps across closure, nose, and ramp trap types. This significantly reduces interpretation time, improves reproducibility, and ensures no viable hydrocarbon prospects are missed. Well targeting and platform optimization apply mixed-integer linear programming (MILP) to reduce the number of required wellhead platforms, shorten well paths, and maintain full resource coverage. This not only lowers development costs but also enhances operational efficiency by selecting better-targeted drilling plans under realistic constraints. Production forecasting & Optimization integrates decline curve analysis with constrained linear programming to maximize condensate production, minimize water output, and schedule drilling and interventions based on export and network limits.

Overall, the integrated workflow cut full-cycle planning time from months to weeks. It shifted engineering focus from repetitive manual work to strategic review and decision-making. The system produced high-quality, scalable outputs across complex, compartmentalized reservoirs and proved significantly more efficient and reliable than conventional methods. Powered by HPC and deployed via PETREL, DSG, and Excel, it supports fast, asset-level adoption.

This talk showcases a practical, AI-powered subsurface workflow successfully applied in the compartmentalized gas fields Gulf of Thailand. It blends domain expertise with advanced analytics, runs on HPC, and integrates with commercial software, offering a scalable solution for faster, smarter E&P decisions.

Biography:

Peerapong Ekkawong is a professional petroleum engineer with an M.S. in Petroleum Engineering from Texas A&M University. He specializes in integrating data science and AI/ML into practical subsurface engineering. His multidisciplinary expertise spans the full subsurface domain, including reservoir modeling, production optimization, automated interpretation, database management, and software development.

Currently serving as Head of Subsurface Data Analytics at PTTEP, Peerapong leads subsurface data research and drives digital transformation in the upstream sector. His mission is to embed data-driven technologies into core subsurface domain to enhance efficiency and maximize hydrocarbon recovery.