Sign in

Jacobus Dijkman

@jdijkman.bsky.social
653 followers 212 following 12 posts

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.

PostsRepliesMedia
Reposted by Jacobus Dijkman
Max Zhdanov @maxxxzdn.bsky.social · 05/03/2025
🤹 Excited to share Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems joint work with @wellingmax.bsky.social and @jwvdm.bsky.social preprint: arxiv.org/abs/2502.17019 code: github.com/maxxxzdn/erwin
34114
Jacobus Dijkman @jdijkman.bsky.social · 13/02/2025
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...
000
Jacobus Dijkman @jdijkman.bsky.social · 13/02/2025
This approach lets us skip time-intensive simulations of complex systems, which could become prohibitively expensive for larger, real-world applications.
100
Jacobus Dijkman @jdijkman.bsky.social · 13/02/2025
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.
100
Jacobus Dijkman @jdijkman.bsky.social · 13/02/2025
We developed a novel ML approach that rapidly predicts molecular behavior—without running lengthy simulations. 🏎️
The neural free energy functional estimates the particle density much faster.
100
Jacobus Dijkman @jdijkman.bsky.social · 13/02/2025
Scientists traditionally rely on computer simulations to understand molecular-level behavior of liquids and gases. However, these simulations can be incredibly time-consuming. ⏳
Sampling the particle density from molecular simulation is expensive.
110
Jacobus Dijkman @jdijkman.bsky.social · 13/02/2025
🚨 Excited to share our work just published in Physical Review Letters with @wellingmax.bsky.social, @jwvdm.bsky.social, @berndensing.bsky.social, Marjolein Dijkstra and René van Roij: doi.org/10.1103/Phys.... Details below 👇
doi.org
Learning Neural Free-Energy Functionals with Pair-Correlation Matching
The intrinsic Helmholtz free-energy functional, the centerpiece of classical density functional theory, is at best only known approximately for 3D systems. Here we introduce a method for learning a ne...
1113
Jacobus Dijkman @jdijkman.bsky.social · 13/02/2025
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...
000
Jacobus Dijkman @jdijkman.bsky.social · 13/02/2025
This approach lets us skip time-intensive simulations of complex systems, which could become prohibitively expensive for larger, real-world applications.
100
Jacobus Dijkman @jdijkman.bsky.social · 13/02/2025
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.
100
Jacobus Dijkman @jdijkman.bsky.social · 13/02/2025
We developed a novel ML approach that rapidly predicts molecular behavior—without running lengthy simulations. 🏎️
100
Jacobus Dijkman @jdijkman.bsky.social · 13/02/2025
Scientists traditionally rely on computer simulations to understand molecular-level behavior of liquids and gases. However, these simulations can be incredibly time-consuming. ⏳
100
Jacobus Dijkman @jdijkman.bsky.social · 27/11/2024
🙋‍♂️
010