Webinar Series
Applying Deep Reinforcement Learning for Strategic Drilling in Subsurface Exploration
Webinar Overview
Date: Jun 24, 2026
Time: 11:00am CDT (4:00pm UTC)
Optimizing where to drill in a synthetic geological simulation to maximize hydrocarbon discovery, with no real seismic data to lean on. In this Expert Spotlight Series session, ThinkOnward Community Member, Roderick Perez, PhD, shows how he built a full pipeline to solve it: Markov-chain-driven geological sections to generate realistic subsurface structure, agent-based modeling to simulate hydrocarbon migration, Gassmann fluid substitution to produce synthetic seismic amplitudes, and a Deep Q-Network trained directly on the resulting seismic images to learn drilling strategy. The results showed that the agent's mindset matters as much as its inputs. Agents tuned for long-term thinking and a gradually narrowing search strategy consistently found stronger, more balanced drilling outcomes than agents that didn't. Roderick is candid about where the approach holds up and where it doesn't: it performs well on clear structural traps and struggles when the seismic signal gets noisy, a limitation worth understanding when considering how approaches like this might be evaluated in real-world settings. A technical, results-driven session for anyone curious where reinforcement learning is being explored in subsurface exploration today. The Expert Spotlight Series is ThinkOnward's recurring webinar program built around the expertise inside our community. Each session features a ThinkOnward Community Member presenting original work and hard-won knowledge across subsurface science, engineering, and AI.
Registration
Speaker
Dr. Roderick Pérez Altamar is a geophysical engineer with nearly twenty years of experience in the oil and gas industry. He has dedicated close to fifteen years to the intersection of Artificial Intelligence and the energy sector, cultivating extensive expertise in Machine Learning with a highly specialized focus on Reinforcement Learning applied to geoscience. His Data Science Master's thesis explored the application of Deep Reinforcement Learning for strategic drilling in subsurface exploration. In this research, he trained intelligent agents using Deep Q-Networks and Convolutional Neural Networks to optimize well site selection within dynamic, synthetically generated geological environments. Furthermore, he actively shares his AI knowledge as an instructor for the European Association of Geoscientists and Engineers, and the American Association of Petroleum Geologists.
His advanced computational capabilities are supported by a rigorous academic foundation. He holds a Master in Data Science from the University of Vienna, a Master of Business Administration from Universidad de los Andes, a Master in Geology from the University of Oklahoma, and a Bachelor in Geophysical Engineering from Universidad Simón Bolívar. Additionally, he earned his Ph.D. in Geophysics from the University of Oklahoma, where his doctoral dissertation focused on brittleness estimation from seismic measurements in unconventional reservoirs, specifically applied to the Barnett Shale.
Throughout his career, Dr. Pérez Altamar has held numerous technical and leadership roles worldwide. His professional journey began in the USA with internships at Anadarko Petroleum and Noble Energy. He then advanced to roles as an Oil and Gas Technology Expert and Technical Services Consultant at Enverus. In Colombia, he served as a Seismic Interpretation Specialist at Pacific Rubiales, and later as a Senior Development Geologist, Geophysicist, and Co-Founder at Scientia Energy. His international experience also includes working as a Geomodeller and Petroleum Geologist for other companies in Ecuador and Colombia. Currently, Dr. Pérez Altamar is a Senior Expert Geoscientist at OMV in Vienna, Austria, a position he has held since September 2023.