A 15TB collection of diverse physics simulations for machine learning. Explore 21 datasets spanning fluid dynamics, astrophysics, biological systems, and more — now with Agent R's normalization enhancements.
New third normalization strategy alongside ZScore and RMS. Normalizes data to [0, 1] using per-field min/max statistics. Guards against constant fields with a configurable min_denom.
WellDataset and WellDataModule had shared mutable default lists for include_filters/exclude_filters. Replaced with Optional[List[str]] = None — coerced inside the body.
Metric.eval had a spurious self parameter in its @staticmethod definition, silently shifting positional arguments. Removed self from the declaration.
Resize augmentation swallowed warnings with a bare print(). Replaced with warnings.warn(…, UserWarning, stacklevel=2) so callers can filter or catch it properly.
All three normalizers — ZScoreNormalization, RMSNormalization, and new MinMaxNormalization — are now importable directly from the_well.data.
New WellMetadata.total_trajectories computed property returns sum(n_trajectories_per_file), replacing scattered sum(meta.n_trajectories_per_file) call sites.
Centers data to zero mean with unit standard deviation. Best for Gaussian data. Formula: z = (x − μ) / σ
from the_well.data import ZScoreNormalization
norm = ZScoreNormalization(stats, fields, const_fields)
x_norm = norm.normalize(x, "field") # z-score
x_back = norm.denormalize_flattened(x_norm, "variable")
Loading…
Thermal convection driven by temperature gradients. A fluid heated from below becomes unstable and forms convective cells.
Magneto-hydrodynamic turbulence as seen in extra-galactic fluids. Magnetic field lines interact with plasma flows.
Turing-type pattern formation via two chemical species. Self-organizing spots and stripes emerge from random initial conditions.
Self-propelled particles exhibiting collective motion and flocking behavior — biological system dynamics.