AMLab | Amsterdam Machine Learning Lab

Jacobus Dijkman

PhD candidate (advised by Jan-Willem van de Meent, Max Welling, and Bernd Ensing)
AMLab
Institute of Informatics, Van ‘t Hoff Institute for Molecular Sciences
University of Amsterdam
Science Park Lab 42, L4.07

Google scholar Github Twitter

Final-year PhD student at the Amsterdam Machine Learning Lab (AMLab) in collaboration with the Computational Chemistry Group, supervised by Jan-Willem van de Meent, Max Welling and Bernd Ensing. I combine statistical physics with machine learning to describe molecular fluids and accelerate materials discovery. My current work develops neural free-energy functionals for classical density functional theory. These are trained on molecular simulation data to predict how fluids adsorb in porous materials such as metal-organic frameworks.

Selected Publications

PRE

Learned Free-Energy Functionals from Pair-Correlation Matching for Dynamical Density Functional Theory

Ram, Karnik, Dijkman, Jacobus, van Roij, René, van de Meent, Jan-Willem, Ensing, Bernd, Welling, Max, and Cremers, Daniel

Physical Review E Oct 2025

Abs HTML PDF

Classical density functional theory (cDFT) and dynamical density functional theory (DDFT) are modern statistical mechanical theories for modeling many-body colloidal systems at the one-body density level. The theories hinge on knowing the excess free-energy accurately, which is, however, not feasible for most practical applications. Dijkman et al. recently showed how a neural excess free-energy functional for cDFT can be learned from bulk simulations via pair-correlation matching. In this article, we demonstrate how this same functional can be applied to DDFT, without any retraining, to simulate nonequilibrium overdamped dynamics of inhomogeneous densities. We evaluate this on a three-dimensional Lennard-Jones system with planar geometry under various complex external potentials, and we observe good agreement of the dynamical densities with those from expensive Brownian dynamic simulations, up to the limit of the adiabatic approximation. We further develop and apply an extension of DDFT based on gradient flows to a grand-canonical system modeled after breakthrough gas adsorption studies, finding similarly good agreement. Our results demonstrate a practical route for leveraging learned free-energy functionals in DDFT, paving the way for accurate and efficient modeling of many-body nonequilibrium systems.
PRL

Learning Neural Free-Energy Functionals with Pair-Correlation Matching

Dijkman, Jacobus, Dijkstra, Marjolein, van Roij, René, Welling, Max, van de Meent, Jan-Willem, and Ensing, Bernd

Physical Review Letters Feb 2025

Abs HTML PDF

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 neural-network approximation of this functional by exclusively training on a dataset of radial distribution functions, circumventing the need to sample costly heterogeneous density profiles in a wide variety of external potentials. For a supercritical Lennard-Jones system with planar symmetry, we demonstrate that the learned neural free-energy functional accurately predicts inhomogeneous density profiles under various complex external potentials obtained from simulations.