Fields

Pick a domain and keep going deeper: field, subfield, topic. Every step lists the papers at that point or below it. The counts are papers that are accepted or in review; papers that were not accepted are in the full library.

Machine learning for physics (statistical, quantum many-body, particle, nonlinear dynamics, cosmology) 0

Statistical physics, lattice models and phase transitions with ML 0
Quantum many-body physics and variational neural wave functions 0
Particle physics ML (jet tagging, collider event classification, fast simulation) 0
Dynamical systems and chaos forecasting 0
Astrophysics and cosmology ML (simulation-based inference, emulators, survey data) 0

Machine learning for chemistry and materials science 0

Molecular property prediction (quantum-chemical and physico-chemical) 0
Machine-learned interatomic potentials and universal force fields 0
Materials property prediction, discovery, catalysis and crystal generation 0
Reaction prediction, retrosynthesis and synthesis planning 0
Molecular generation and goal-directed design 0

Machine learning for weather and climate 0

Medium-range global weather forecasting 0
Climate model emulation and learned parameterisations 0
Statistical downscaling and super-resolution of climate and weather fields 0
Extreme events and precipitation nowcasting 0

Scientific machine learning (neural PDE solvers, operator learning, equation discovery) 0

Neural operators and learned PDE surrogates 0
Physics-informed neural networks and physics-based losses 0
Differentiable simulation and hybrid solver-in-the-loop learning 0
Symbolic regression and equation discovery 0

Domain

Physical sciences

Machine learning for physics, chemistry, materials, weather and climate, and learned solvers for the equations behind them.

Fields

Physical sciences

No papers here yet