The first presentation continues the spring topic of evaluating Dutch geothermal reservoirs, while the second one returns to oil and gas and is on NMR assessment of wettability
Dear DPS Member, The next DPS meeting, featuring two presenters, is on Thursday June 4th 2026. We meet at our usual venue at KIVI Den Haag (Prinsessegracht 23, 2514 AP Den Haag) on the first floor. Pre-meeting coffee is served at 15:30h and talks commence at 16:00h. Social hour will follow at KIVI . Attendance is free of charge.
Talk 1
Title:
Deep-learning-assisted borehole image analysis for enhanced geothermal reservoir evaluation: A case study in the West Netherlands Basin
Speaker: Attilio Molossi, PhD, R&D and Data Engineer, GEOLOG International
Abstract: Evaluating the geothermal reservoir potential often requires fracture analysis, as fractures serve as key pathways for fluid flow in subsurface formations. Borehole images (BHIs) are essential for this analysis, providing 2D representations of boreholes with millimetre-scale resolution. However, their interpretation is highly subjective, leading to uncertainties in the results and the subsequent quantitative assessment of the fracture networks. In the West Netherlands Basin (WNB), accurate fracture characterization is critical for assessing the geothermal viability. However, the traditional manual interpretation of BHIs has shown inconsistencies. This study introduces a supervised deep learning (DL) approach to support fracture analysis using high-resolution formation micro-imager (FMI) data from the Naaldwijk well (NLW-GT-01). The proposed DL-based system integrates a U-Net model (PickNet) for segmentation and a fully connected convolutional network (FitNet) for automated feature extraction. Initially trained on synthetic low-resolution BHIs, the model has been adapted for FMI data using two approaches: (1) transfer learning and (2) a simplified adaptation method that involves resizing the FMI input, leading to some resolution loss. A comparison of these approaches has revealed that the simplified adaptation produces better results, closely aligning with conservative manual interpretations calibrated with core samples while enabling more detailed fracture detection. To enhance reliability, we propose a semi-automated human–machine collaboration framework, where experts validate or refine the automatically detected features. This approach leverages human expertise to improve interpretation accuracy while addr
Bio
Attilio Molossi is a geoscientist working at the intersection of geoscience and artificial intelligence, with a
focus on applying machine learning and deep learning to subsurface and drilling data. After
completing a PhD at the University of Trieste (Italy) on deep learning applications to borehole
imagery, he joined GEOLOG International as an R&D and Data Engineer, supporting drilling
operations worldwide and developing data-driven solutions for complex operational
environments.
Attilio believes the future of geoscience lies in the collaboration between human expertise and
intelligent systems. While AI is increasingly capable of matching expert-level interpretation in
many geoscience tasks, its greatest value comes from augmenting—not replacing—human
decision-making. His goal is to contribute to human-centric AI workflows that reduce
subjectivity and uncertainty while enhancing the quality and consistency of subsurface
interpretation.
Talk 2
Title: NMR wettability assessment during lab experiments
Speaker: Wim Looyestijn, NMR Consultant
Abstract: The results of laboratory experiments with oil/water systems are known to depend on the wettability of the samples. Consequently, one tries to preserve, or to restore the original wettability. Whether that is successful or not, another complication arises when the lab experiment involves flooding large quantities of water and oil, crude and/or refined, through the sample. By lack of anything better, it is then assumed that the wettability remains constant. Hand waving arguments include that refined oil is neutral and can thus (sic!) not alter the wettability. But is that true?
Like a surgeon can nowadays look into your head without having to use saws and scissels, we can monitor what’s happening at the interface of fluids and rock surface without disturbing the experiment. Both disciplines use NMR.
In this presentation I give a short recap of the technique used, and then follow the wettability during a USBM experiment. Whereas this experiment yields a single wettability index, and requires a large number of flooding stages, NMR can determine a wettability index at each of these stages. The result: come and see!
Bio:
Wim Looyestijn is currently a consultant on NMR interpretation. Before this he worked as a principal research petrophysicist at Shell International E&P in Rijswijk, The Netherlands. He joined Shell in 1979 to work in petrophysical research on a variety of subjects ranging from core analysis to interpretation of well-logging tools, with a strong focus on NMR log interpretation. He has served as a Technical Editor for SPE and SPWLA. He holds MSc and PhD degrees in physics from Leiden University, The Netherlands.
Privileged to have joined Shell around the time that interest in NMR logging was developing, Wim regards the quantitative assessment of wettability that can be done in many instances, both on core experiments and on NMR logs, and which forms the subject of today’s presentation, as his most enduring achievement.
Looking forward to seeing you there!
DPS Board