Jacobus Dijkman
banner
jdijkman.bsky.social
Jacobus Dijkman
@jdijkman.bsky.social
Infusing statistical physics with machine learning to describe molecular fluids.

PhD Candidate at UvA with Max Welling, Jan-Willem van de Meent and Bernd Ensing.
Our efficient method could accelerate research into molecular systems for critical applications like hydrogen storage and direct air capture—enabling scientists to explore far more scenarios than traditional simulations allow. 🌎

Want to learn more? Read the full paper here: doi.org/10.1103/Phys...
February 13, 2025 at 9:21 AM
This approach lets us skip time-intensive simulations of complex systems, which could become prohibitively expensive for larger, real-world applications.
February 13, 2025 at 9:21 AM
The key insight: our model learns by observing molecular interactions in simple uniform bulk systems. Once it grasps these patterns, it can predict behavior in complex environments like pores—despite never encountering non-uniform conditions during training.
February 13, 2025 at 9:21 AM
We developed a novel ML approach that rapidly predicts molecular behavior—without running lengthy simulations. 🏎️
February 13, 2025 at 9:21 AM
Scientists traditionally rely on computer simulations to understand molecular-level behavior of liquids and gases. However, these simulations can be incredibly time-consuming. ⏳
February 13, 2025 at 9:21 AM
Our efficient method could accelerate research into molecular systems for critical applications like hydrogen storage and direct air capture—enabling scientists to explore far more scenarios than traditional simulations allow. 🌎

Want to learn more? Read the full paper here: doi.org/10.1103/Phys...
February 13, 2025 at 9:11 AM
This approach lets us skip time-intensive simulations of complex systems, which could become prohibitively expensive for larger, real-world applications.
February 13, 2025 at 9:11 AM
The key insight: our model learns by observing molecular interactions in simple uniform bulk systems. Once it grasps these patterns, it can predict behavior in complex environments like pores—despite never encountering non-uniform conditions during training.
February 13, 2025 at 9:11 AM
We developed a novel ML approach that rapidly predicts molecular behavior—without running lengthy simulations. 🏎️
February 13, 2025 at 9:11 AM
Scientists traditionally rely on computer simulations to understand molecular-level behavior of liquids and gases. However, these simulations can be incredibly time-consuming. ⏳
February 13, 2025 at 9:11 AM
🙋‍♂️
November 27, 2024 at 6:14 PM